Measuring pulmonary nodules accurately can help with early diagnosis of lung cancer, which can improve a patient’s chances of survival. Many methods for segmenting nodules have been developed, but they all rely on input from radiologists in the form of a 3D volume of interest (VOI) or use a constant region of interest (ROI) and only consider the presence of nodule within the given VOI. These approaches limit the networks’ ability to detect nodules outside the given VOI and can also include unnecessary structures in the VOI, leading to potentially inaccurate segmentation. In this work, we propose a novel approach for 3D lung nodule segmentation by using 2D region of interest (ROI) inputted from radiologist or computer-aided detection (CADe) system. Particularly, we design a dual-encoder-based hard attention network (DEHA-Net) which incorporates the full slice of thoracic computed tomography scan along with the ROI mask to produce an accurate segmentation mask of lung nodule in the given slice. The proposed architecture exploits the adaptive region of interest (A-ROI) algorithm to automatically investigates the penetration of lung nodule into surrounding slices while eliminating the need to drawing separate ROIs in each slice. Further, the framework performs the multi-view analysis, i.e., in sagittal and coronal views, to improve the segmentation performance. The proposed scheme has been rigorously evaluated on the lung image database consortium and image database resource initiative (LIDC/IDRI) dataset and an extensive analysis of results have been performed. The quantitative analysis shows that the proposed method not only improves the existing state-of-the-art in term of dice score but also, significantly robust against the different types, shape and dimensions of lung nodules.

Malignant growth is the most widely recognized repulsive infections winning around the world, and the patients with disease are saved just when the malignant growth is distinguished at the beginning phase. Each kind of disease is interesting, with its own arrangement of development properties and hereditary changes. This paper presents the lung knob division and disease characterization by proposing an enhancement calculation. The general technique of the created approach includes four stages, such as pre-processing, division, highlight extraction, and the order. From the outset, the CT picture of the lung is taken care of to the division. When the division is done, the highlights are extricated through morphological and measurable and surface highlights like LOOP and LGP. At long last, the extricated highlights are given to the order step. Here, the characterization is done dependent on the Deep Belief Network (DBN) which is prepared by utilizing the proposed Chicken-Sine Cosine Algorithm (CSCA) which distinguish the lung tumor, giving two classes in particular, knob or non-knob. The presentation assessment of lung knob division and malignant growth grouping dependent on CSCA is figured utilizing three measurements to be specific, precision, affectability, and the explicitness.

Lung cancer is a deadly disease if not diagnosed in its early stages. However, early detection of lung cancer is a challenging task due to the shape and size of its nodules. Radiologists need support from automated tools for precise opinion. Automated detection of the affected lungs nodule is difficult because of the shape similarity among healthy tissues. Over the years, several expert systems have been developed that help radiologists to diagnose lung cancer. In this article, we propose a framework to precisely detect lungs cancer by classifying it between benign and malignant nodules. The framework is tested using the subset of the publicly available at the Lung Image Database Consortium image collection (LIDC-IDRI). Multiple techniques including filtering and noise removing are applied for pre-processing. Subsequently, the OTSU and the semantic segmentation are used to accurately detect the unhealthy lungs nodules. In total, 13 nodules features were extracted using Principal Components Analysis (PCA) algorithm. Four optimal features are selected based on the classification performance. In the classification phase, 9 different classifiers are used along with two types of validation schemes i.e. train test holdout validation with 70-30 data split and 10 fold cross-validation. Our experiments show that the proposed system provides 99.23\% accuracy using logic boost classifier.

Renal Cell Carcinoma (RCC) is generally represented by low-FDG avidity, and [18F]FDG-PET/CT is not recommended to stage the primary tumor. However, its role to assess metastases is still unclear. The aim of this study was to evaluate the diagnostic accuracy of [18F]FDG-PET/CT to correctly identify RCC lung metastases using histology as standard of truth. Records of 350 patients affected by RCC and with CT evidence of at least one lung nodule, were retrospectively analyzed. Inclusion criteria were: a) histologically proven RCC; b) [18F]FDG-PET/CT performed prior to lung surgery; c) lung surgery with histological analysis of surgical specimens; d) complete follow-up available. A per-lesion analysis was performed, and diagnostic accuracy was reported as sensitivity and specificity, using histology as standard of truth. [18F]FDG-PET/CT semiquantitative parameters (Standardized Uptake Value [SUVmax], Metabolic Tumor Volume [MTV] and Total Lesion Glycolysis [TLG]) were collected for each lesion. Sixty-seven (n=67) patients with a total of 107 lesions were included: lung metastases from RCC were detected in 57/107 of cases, while 50/107 lesions were related to others lung malignancies. Applying a cut-off of SUVmax ≥2, the sensitivity and the specificity of [18F]FDG-PET/CT for detect RCC lung metastases were 33.3% (95% CI: 21.4% - 47.1%) and 26% (95%CI: 14.6% - 40.3%), respectively. The analysis demonstrated sub-optimal diagnostic accuracy of [18F]FDG-PET/CT to discriminate between RCC lung metastases versus other malignancies. However, semiquantitative analysis including also volumetric parameters (MTV and TLG) can support [18F]FDG-PET/CT image interpretation.

Asthma is a complex syndrome with multiple phenotypes and endotypes, and current diagnostic tools often fail to address this, therefore there is an increasing need for new predicting biomarkers for asthma which can enable personalized treatment strategies. Biomarkers can facilitate earlier diagnosis of asthma, potentially identifying the disease before clinical symptoms appear. This allows for early intervention, which can prevent asthma progression and complications and improve long-term outcomes. Reliable biomarkers can help in monitoring disease activity and treatment efficacy in real-time and can also lead to better disease management, reducing hospitalizations, emergency visits, and overall healthcare costs associated with poorly controlled asthma. Severe asthma patients often do not respond well to standard treatments. New biomarkers can help identify these patients and guide the development of novel therapeutic approaches specifically for severe asthma. In this review we summarize different candidate biomarkers on several levels of investigation: Genetic, subclinical inflammatory, allergen-specific immune response, and trained immunity, which could be promising for the early detection of asthma and better management of exacerbation and severity of symptoms in children.

Our study aimed to identify predictors for the effectiveness of tumor regression in lung cancer patients undergoing neoadjuvant treatment and cancer resections. Patients admitted between 2016 and 2022 were included in the study. Based on the histology of the tumor, patients were categorized into lung adenocarcinoma group (LUAD), and squamous cell carcinoma group (SQCA). Ninety-five patients with non-small cell lung cancer were included in the study. Fifty-eight (61.1%) and 37 (38.9%) patients were included in the LUAD and SQCA groups, respectively. Nine (9.5%), 56 (58.9%), and 30 (31.6%) patients were categorized with a tumor regression score of I, II, and III respectively. In multivariable analyses, histology of the primary tumor (SQCA), lymph node size in the preoperative CT scan (>1.7cm) and absolute tumor size reduction after neoadjuvant treatment (>2.6 cm) independently predict effectiveness of tumor regression (OR, [95% Confidence interval, p-value] of 6.88 [2.40-19.77, p70 years, extended resection >one lobe, and tumor recurrence or metastasis were identified as significant independent predictors of reduced overall survival. Assessment of tumor size before and after neoadjuvant treatment might help to identify high-risk patients with decreased survival and to improve patient management and care.

Lung nodule segmentation in CT images and its subsequent volume analysis can help determinethe malignancy status of a lung nodule. While several efficient segmentation schemes have beenproposed, only a few studies evaluated the segmentation’s performance for large nodules. In thisresearch, we contribute a semi-automatic system which is capable of performing robust 3-D segmen-tations on both small and large nodules with good accuracy. The target CT volume is de-noisedwith an anisotropic diffusion filter and a region of interest is selected around the target nodule ona reference slice. The proposed model performs nodule segmentation by incorporating a mean in-tensity based threshold in Geodesic Active Contour model in level sets. We also devise an adaptivetechnique using image intensity histogram to estimate the desired mean intensity of the nodule.The proposed system is validated on both lung nodules and phantoms collected from publicly avail-able diverse databases. Quantitative and visual comparative analysis of the proposed work withthe Chan-Vese algorithm and statistic active contour model of 3D Slicer platform is also presented.The resulting mean spatial overlap between segmented nodules and reference nodules is 0.855, themean volume bias is 0.10±0.2 ml and the algorithm repeatability is 0.060 ml. The achieved resultssuggest that the proposed method can be used for volume estimations of small as well as large-sizednodules.

As the use of AI in medical imaging has increased, so has the need to explain a model’s results. Segmentation models are one technique used to produce explainable results. Due to larger size and sophistication, segmentation models which operate on 2D data can often produce better results than models operating on 3D data. In the real world, imaging is combined with clinical factors for diagnosis. To replicate this, multimodal models are used which combine image and text modalities. I propose a multimodal arrangement that converts 3D scans to 2D and uses a 2D segmentation model (DeepLabV3) to analyze the images. This is combined with clinical biomarkers to achieve a complete confidence score. Using the Medical Segmentation Decathlon Lung (MSDL) dataset and the LUng CAncer Screening dataset (LUCAS), I achieved a testing Dice coefficient of 0.91 on segmentation with a receiver operating characteristic (ROC), average precision (AP), and F-Score of 0.89, 0.91, and 0.85 respectively on the final multimodal results. This approach raises the F-score from the previously achieved value of 0.508 to 0.85, creating a new baseline of what is achievable with multimodal lung cancer diagnostics and possible methods to achieve these accuracies.

Aiming at the problems of inaccurate segmentation of long object and information loss of small object in real-time semantic segmentation algorithm, this paper proposes a lightweight multi-branch real-time semantic segmentation network based on BiseNetV2. The new auxiliary branch makes full use of spatial details and context information to cover the long object in the field of view. Meanwhile, in order to ensure the inference speed of the model, the asymmetric convolution is used in each stage of the auxiliary branch to design a structure with low computational complexity. In the multi-branch fusion stage, the alignment and fusion module is designed to provide guidance information for deep and shallow feature mapping, so as to make up for the problem of feature misalignment in the fusion of information at different scales, and thus reduce the loss of small target information. In order to further improve the model’s awareness of key information, a global context module is designed to capture the most important features in the input data. The proposed network uses NVIDIA GeForce RTX 3080 Laptop GPU experiment, on the road street view data set Cityscapes and CamVid average occurring simultaneously ratio reached 77.1% and 78.4% respectively, with running speed of 127 frames/s respectively and 112 frames/s. The experimental results show that the proposed algorithm can achieve real-time segmentation and improve the accuracy significantly, showing good semantic segmentation performance

The NCO functional group of 3-isocyanatoproply triethoxysilane (IPTS) and the OH functional group of DOPO-BQ were used to conduct an addition reaction. Following completion of the reaction, triglycidyl isocyanurate (TGIC) was introduced to conduct a ring-opening reaction. Subsequently, a sol-gel method was used to take place a hydrolysis- condensation reaction on TGIC-IPTS-DOPO-BQ to form a hyperbranched nitrogen–phosphorous–silicon (HBNPSi) flame retardant. This flame retardant was incorporated into a polyurethane (PU) matrix to prepare a hybrid material. Fourier-transform infrared spectroscopy (FT-IR), thermogravimetric analysis (TGA), limiting oxygen index (LOI), UV-VIS spectrophotometry, and Raman analysis were conducted to structure characterization and analyzed transparency, thermal stability, flame retardancy, and residual char to understand the flame retardant mechanism of prepared hybrid materials. After the flame retardant was added, the maximum degradation rate decreased from −36 wt%/min to −17 wt%/min, the integral procedure decomposition temperature (IPDT) increased from 348 ℃ to 488 ℃, and the char yield increased from 0.7 to 8.1 wt%. The aforementioned results verified that thermal stability of PU can be improved after adding HBNPSi. The LOI analysis indicated that the pristine PU was flammable because the LOI of pristine PU was only 19. When the content of added HBNPSi was 40%, the LOI value was 26; thus the PU hybrid became nonflammable.

Open-vocabulary learning has recently gained prominence as a means to enable image segmentation for arbitrary categories based on textual descriptions. This advancement has extended the applicability of segmentation systems to a broader range of generally purpose scenarios. However, current methods often revolve around specialized architectures and parameters tailored to specific segmentation tasks, resulting in a fragmented landscape of segmentation models. In response to these challenges, we introduce OVAMTSeg, a versatile framework designed for Open-Vocabulary and Multitask Image Segmentation. OVAMTSeg harnesses adaptive prompt learning to empower the model to capture category-sensitive concepts, enhancing its robustness across diverse multi-task and scenario contexts. Text prompts are employed to effectively capture semantic and contextual features of the text, while cross-attention and cross-modal interactions enable the fusion of image and text features. Furthermore, a transformer-based decoder is incorporated for dense prediction. Extensive experimental results underscore the effectiveness of OVAMTSeg, showcasing its state-of-the-art performance and superior generalization capabilities across three segmentation tasks. Notable achievements include a 47.5 mIoU in referring expression segmentation, 51.6 mIoU on Pascal-VOC with four unseen classes, 46.6 mIoU on Pascal-Context in zero-shot segmentation, 65.9 mIoU on Pascal-5i, and 35.7 mIoU on COCO-20i datasets for one-shot segmentation.

Severe inherited alpha-1 antitrypsin deficiency (AATD) is an autosomal genetic condition linked to chronic obstructive pulmonary disease (COPD). The significance of heterozygous, milder deficiency variants (Pi*M, Pi*S, Pi*Z) is less clear. We studied AATD genotypes in 145 children (up to 72 months old) with assessed wheezing severity using the Pediatric Respiratory Assessment Measure (BCCH PRAM score). A control group of 74 children without airway obstruction was included. AAT concentration and Pi phenotype were determined from dry blood spot samples using nephelometry and real-time PCR; PiS and PiZ alleles were identified by isoelectrofocusing. Among the wheezers, the Pi*S allele incidence was 2.07% (3 cases) and Pi*Z allele was 6.9% (10 cases). The Pi*Z allele frequency was higher in wheezers compared to controls (44.8% vs. 20.27%) and the general Lithuanian population (44.8% vs. 13.6%) and was similar to adult COPD patients in Lithuania: Pi*S 10.3% vs. 15.8% and Pi*Z 44.8% vs. 46.1%. No association was found between AAT genotypes and wheezing severity. Finding that wheezer children exhibit a frequency of Z* and S* alleles like that found in adults with COPD suggests a potential genetic predisposition that links early wheezing in children to the development of COPD in adulthood. Larger cohort studies are needed to confirm this finding.

Based on the major, trace element, and isotope data of the Cenozoic basalts in the study area, it is indicated that the basalts in this region can be classified into three distinct magma systems: alka-li basalts, tholeiite basalts, and Nushan alkali basalts. The geochemical characteristics observed in the studied basalts indicate that the mantle source in this region might have experienced met-asomatic processes prior to partial melting, which could be linked to an ancient subduction pro-cess. Combining the geochemical characteristics in the studied basalts with previous research, we propose that the underlying mantle source in Anhui province may have undergone metaso-matism due to the carbonatitic melts. These melts are believed to have originated from car-bonated eclogite, derived from subducted Pacific slab materials present in the deeper mantle. According to the Sr-Nd isotope data, it is suggested that the mantle source in the Nushan region could be derived from a depleted asthenospheric mantle, while the basaltic composition in the Niugang area may be representative of the mantle's end components associated with the EM-I enriched mantle source present in this study area. Therefore, we propose that the Anhui basalts may have originated from the partial melting of a mantle source representing a mixing of two end-members: DMM (Depleted MORB Mantle) and EM-Ⅰ (Enriched Mantle 1). The Anhui basal-tic magmas may have originated from the partial melting of EM-Ⅰ, potentially influenced by upwelling asthenospheric mantle or asthenospheric diapirism processes. The mantle source in the study area experiences partial melting at 1-5%, 15%, and 1-10%, resulting in the formation of parent magmas for alkali basalt, tholeiitic basalt, and Nushan alkali basalt. Subsequently, the parent magmas experienced fractional crystallization processes, which included minerals like olivine, pyroxene, and plagioclase. This led to the formation of various types of basalt in the study area.

Pulmonary Embolism (PE) is the obstruction of blood arteries in the lungs by a blood clot. The mortality risk for PE is approximately 30%. Detecting pulmonary embolism in the segmental arteries of the lung is more challenging than in the main arteries and is very prone to being missed. A computer-based approach was created in this work to automatically identify pulmonary embolism in the segmental arteries using computed tomography images. The system's infrastructure includes an enhanced Mask R-CNN deep neural network that has been trained with images containing PE. The network accurately identifies the location of the pulmonary embolism on the computed tomography picture and successfully extracts its borders. The investigation was conducted by generating a local dataset. The study's performance was evaluated using pulmonary embolisms identified manually by the expert radiologist. The sensitivity, specificity, accuracy, dice coefficient, and Jaccard index values for 2130 pictures were 96.4%, 93.5%, 96.1%, 0.96, and 0.90, respectively. The improved Mask R-CNN model has demonstrated superior performance when compared to the traditional Mask R-CNN and U-Net models. This high-performance technology is designed to identify pulmonary embolism and will aid professionals in assessing the size of the embolism.

We propose a novel unsupervised semantic segmentation method for fast and accurate flood area detection utilizing color images acquired from Unmanned Aerial Vehicles (UAVs). To the best of our knowledge, this is the first fully unsupervised method for flood area segmentation in color images captured by UAVs, without the need of pre-disaster images. The proposed framework addresses the problem of flood segmentation based on parameter-free calculated masks and unsupervised image analysis techniques. First, a fully unsupervised algorithm gradually excludes areas classified as non-flood utilizing calculated masks over each component of the LAB colorspace, as well an RGB vegetation index and the detected edges of the original image. Unsupervised image analysis techniques, such as distance transform, are then applied, producing a probability map for the location of flooded areas. Finally, flood detection is obtained by applying the hysteresis thresholding segmentation. The proposed method is tested and compared with variations, and other supervised methods in two public datasets, consisting of 953 color images in total, yielding high-performance results, with 87.4% and 80.9% overall accuracy and F1-Score, respectively. The results and computational efficiency of the proposed method show that it is suitable for on board data execution and decision-making during UAVs flight.

The segmentation of abnormal regions is vital in smart manufacturing. However, the existing segmentation system for detecting sauce-packet leakage on intelligent sensors encounters an issue of imaging blurring caused by uneven illumination. This issue adversely affects segmentation performance, thereby impeding the rapid production of industrial assembly lines. To alleviate this issue, we propose the two-stage Illumination-aware Sauce-packet Leakage Segmentation (ISLS) method for intelligent sensors. The ISLS comprises two main stages: Illumination-aware region enhancement and leakage region segmentation. In the first stage, YOLO-Fastestv2 is employed to capture the Region of Interest (ROI), which reduces redundancy computations. Additionally, we propose an image enhancement to relieve the impact of uneven illumination, enhancing the texture details of ROI. In the second stage, we propose a novel feature extraction network. Specifically, we propose the Multi-scale Feature Fusion Module (MFFM) and the Sequential Self-Attention Mechanism (SSAM) to capture discriminative representations of leakage. The multi-level features are fused by MFFM with a small number of parameters, which capture leakage semantics at different scales. The SSAM realizes the enhancement of valid features and the suppression of invalid features by adaptive weighting of spatial and channel dimensions. Furthermore, we generated a self-built dataset of sauce-packets, including 606 images with various leakage areas. Comprehensive experiments demonstrate that our ISLS method shows better results than several state-of-the-art methods, with additional performance analyses deployed on intelligent sensors to affirm the effectiveness of our proposed method. Our code is available at https://github.com/LSJ5106/SauceDetect.

Lung cancer remains one of the leading causes of cancer-related mortality worldwide. There is evidence of a complex interplay between lung cancer and interstitial lung disease (ILD), affecting disease progression, management strategies, and patient outcomes. Both conditions develop as the result of common risk factors such as smoking, environmental exposures, and genetic predispositions. The presence of ILD poses diagnostic and therapeutic challenges in lung cancer management, including difficulties in interpreting radiological findings, increased susceptibility to treatment-related toxicities, such as acute exacerbation of ILD after surgery and pneumonitis after radiation therapy and immunotherapy. Moreover, due to the lack of large, phase III randomized controlled trials in patients with lung cancer and ILDs, the evidence-based therapeutic options remain limited. The role of antifibrotic treatment in the prevention of lung-cancer-related treatment toxicities remains to be elucidated. Emerging diagnostic modalities and biomarkers, and optimizing personalized treatment strategies are essential to improve outcomes in this patient population.

This paper proposes a compact planar Wi-Fi antenna with optimized radiation patterns for small uncrewed aerial vehicle (UAV) applications in both urban and open areas. It is suitable for mounting on the outermost side of the non-metallic wing of small UAVs. It has small dimensions of 16.5 mm (L) by 30.3 mm (W) by 1.6 mm (h), and the measured results of its prototype are in agreement with simulated data. Its impedance bandwidths over the two frequency ranges are 2.11 to 2.58 GHz and 5.06 to 7.5 GHz ( ). At 5.8 GHz, it has stronger radiation below the small UAV to reduce interference from rare-use directions. Its maximum radiations, the directions of the maximum radiation in each elevation plane, are below the UAV and between 14° and 29° from the horizontal plane. At 2.4 GHz, it has quasi-omnidirectional radiation to ensure a stable link in all directions, and its maximum radiations are near the horizontal plane. The optimized radiation patterns at 5.8 and 2.4 GHz can provide more antenna gain when the small UAV flies farther in urban and open areas, respectively. In addition, it has good vertically polarized radiation for long-distance applications.

Candida glabrata is a yeast of increasing medical relevance, particularly in critically ill patients. It is the second most isolated Candida species associated with invasive candidiasis (IC) behind C. albicans. The attributed higher incidence is primarily due to an increase in the acquired immunodeficiency syndrome (AIDS) population, cancer, and diabetes patients. The elderly population and the frequent use of indwelling medical devices are also predisposing factors. The work aimed to review various virulence factors that facilitate the survival of pathogenic C. glabrata in IC. The available published research articles related to the pathogenicity of C. glabrata were retrieved and reviewed from four credible databases, mainly Google Scholar, ScienceDirect, PubMed, and Scopus. The articles highlighted many virulence factors associated with pathogenicity in C. glabrata, including adherence to a susceptible host surface, evading host defences, and producing hydrolytic enzymes (e.g., phospholipases, proteases, and haemolysins). The factors facilitate infection initiation. Other virulent factors include iron regulation and genetic mutations. Accordingly, biofilm production, tolerance to high-stress environments, and development of resistance to the antifungal drug, notably to fluconazole and other azole derivatives, were reported. The review provided evident pathogenic mechanisms and antifungal resistance associated with C. glabrata in ensuring its sustenance and survival.

The task of weakly supervised point cloud semantic segmentation has received widespread attention and also has been widely used in autonomous driving, robotics, and modern industries. Due to the high dimensionality and large volume of point cloud data, many technical difficulties appeal to weakly supervised semantic processing, especially segmentation. However, weakly-supervised schemes usually provide only partial labelling information of the underlying point cloud data and thus need to effectively extract local features, geometric information, and contextual relationships only using these limited labelled data for supervised learning. To improve weakly-supervised semantic segmentation, we propose a novel segmentation network through the boundary-based feature aggregation based on a K-NN algorithm with down-sampling operation, and also introduce the smoothness loss and Siamese loss for effective segmentation. The experiments on public datasets demonstrate that our presented segmentation method exceeds most of the existing fully supervised and weakly-supervised methods in terms of mIoU. Specifically, our network has high segmentation accuracy on the labels of objects with similar geometrical structures, such as ceiling, wall, floor, chair and table, reaching 91.2%, 98.8%, 83.3%, 75.3% and 80.2%, respectively. Extensive experiments also illustrate its robustness, effectiveness, and generalization of the proposed weakly supervised segmentation network.

Recently, the medical image processing is extensively used in several areas. In earlier detection and treatment of these diseases is very helpful to find out the abnormality issues in that image. Here there are number of methods available for segmentation to detect the lung nodule of computer tomography (CT) image. The main result of this paper, the earlier detection of lung nodules using Pre-processing techniques of top-hat transform, median and adaptive bilateral filter was compared both filtering methods and proved the adaptive bilateral filter is suitable method for CT images. The proposed segmentation technique uses novel strip method and the image is split into number of strips 3, 4, 5 and 6. A marker- watershed method based on PSO and Fuzzy C-mean Clustering method was proposed method. Firstly, the input image was reduced noise reduction and smoothing and the filter image is using strips method and then the image is segmented by marker watershed method. Secondly, the enhanced PSO technique was used to locate the better accurate value of the clustering centers of Fuzzy C-mean Clustering. Final stage, with the accurate value of centers and the enhanced target function and the small region of the segmented object was clustered by Fuzzy C-mean. In segmentation algorithm presented in this paper gives 95% of accuracy rate to detect lung nodules when strip count is 5.

Image segmentation and classification still represent an active area of research since no universal solution can be identified. Established segmentation algorithms like thresholding are problem specific, treat well the easy cases and mostly relied on single parameter i.e intensity. Machine learning approaches offer alternatives where predefined features are combined into different classifiers. On the other hand, the outcome of machine learning is only as good as the underlying feature space. Differential geometry can substantially improve the outcome of machine learning since it can enrich the underlying feature space with new geometrical objects, called invariants. In this way, the geometrical features form a high-dimensional feature space for each pixel, where original objects can be resolved. Alternatives based on the geometry of the image scale-invariant interest points have been exploited successfully in the field of computer vision. Here, we integrate geometrical feature extraction based on signal processing, machine learning, and input relying on domain knowledge. The approach is exemplified on the ISBI 2012 image segmentation challenge data set. As a second application, we demonstrate powerful image classification functionality based on the same principles, which was applied to the HeLa and HEp-2 data sets. Obtained results demonstrate that feature space enrichment properly balanced with feature selection functionality can achieve performance comparable to deep learning approaches.

(1) Background: Ulcerative colitis (UC) is characterized by immune system dysregulation with frequent extraintestinal manifestations, including airways involvement. Reduction in CO diffusing capacity and functional alterations in small airways have been described. The extended analysis of Fractional Exhaled Nitric Oxide (FeNO), may distinguish the sites of production and the presence of small airways inflammation being a useful, non-invasive marker for these patient’s follow up. The aim of our study was to compare PFTs, FeNO and CANO values of UC patients with different clinical disease activity and healthy subjects to reveal lung function abnormalities and the presence of subclinical airway inflammation. (2) Methods: We enrolled 42 adult outpatients with different clinical activity stages of UC (mean age 39±13 years) and a healthy control group of 41 subjects (mean age 29±3 years). C-reactive protein (CRP) and FeNO values at different flows (50,100 and 200 ml/sec) were collected. All patients performed pulmonary function tests (PFT’s) with static volumes and diffusing capacity (DLCO). (3) Results: FENO, CANO and CRP values were significantly increased in UC patients when compared with controls (p=0.02 and p<0.0001, respectively) and proportionally to the disease activity (FeNO class 3: 27.1 ppb vs class 1-2: 6.2 ppb; CANO values class 3: 8.1 ppb vs class 1-2: 2.0 ppb (p < 0.0001). TLC and DLCO were significantly reduced in UC patients compared to controls (p=0.011 and p<0.0001, respectively). (4) The results of this study show significant lung functional abnormalities in UC patients and suggest the presence of airway inflammation directly correlated with the disease activity suggesting an integrated approach in routine assessment.

Medical image segmentation is a critical step in various healthcare applications, aiding in diagnosis, treatment planning, and disease monitoring. In this study, we investigate the efficacy of a segmentation approach based on the 2D wavelet transform. Leveraging a dataset comprising 10 diverse medical images, we evaluate the performance of our segmentation method using three key metrics: accuracy, precision, and recall. Our findings demonstrate that the proposed approach enhances segmentation accuracy, offering promising results compared to existing methods. By harnessing the multi-resolution feature extraction capabilities of the 2D wavelet transform, our method achieves improved delineation of medical image structures, paving the way for more accurate and efficient healthcare interventions.

Depth-sensing technology has led to broad applications of inexpensive depth cameras that can capture human motion and scenes in 3D space. Background subtraction algorithms can be improved by fusing color and depth cues, thereby allowing many issues encountered in classical color segmentation to be solved. In this paper, we propose a new fusion method that combines depth and color information for foreground segmentation based on an advanced color-based algorithm. First, a background model and a depth model are developed. Then, based on these models, we propose a new updating strategy that can eliminate ghosting and black shadows almost completely. Extensive experiments have been performed to compare the proposed algorithm with other, conventional RGB-D algorithms. The experimental results suggest that our method extracts foregrounds with higher effectiveness and efficiency.

Glaucoma, a global leading cause of blindness, necessitates accurate segmentation of the optic disc (OD) and optic cup (OC) for effective screening. However, existing segmentation methods based on convolutional neural networks (CNNs) suffer from high computational complexity and long inference times. In this paper, we propose an end-to-end segmentation method for the OD and OC using a lightweight MobileNetv3 as the feature extraction network. Our approach incorporates boundary branches and an adversarial learning network to achieve multi-label segmentation of the OD and OC. We evaluate the proposed method on three publicly available datasets: Drishti-GS, RIM-ONE-r3, and REFUGE. The experimental results demonstrate segmentation accuracies of 0.974/0.900, 0.966/0.875, and 0.962/0.880 for the OD and OC on the respective datasets, while significantly reducing inference time.

Tsallis entropy has been widely used in image thresholding because of its non-extensive properties. The non-extensive parameter q contained in this entropy plays an important role in various adaptive algorithms and has been successfully applied in bi-level image thresholding. In this paper, the relationships between parameter q and pixels’ long-range correlations have been further studied within multi-threshold image segmentation. It is found that the pixels’ correlations are remarkable and stable for images generated by a known physical principle, such as infrared images and medical CT images. And the corresponding non-extensive parameter q can be evaluated by using self-adaptive Tsallis entropy algorithm. The results of this algorithm are compared with those of Shannon entropy algorithm and the original Tsallis entropy algorithm, in terms of quantitative image quality evaluation metrics PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity). Furthermore, we observed that for image series with the same background, the q values determined by the adaptive algorithm are consistently kept in a narrow range. Therefore, similar or identical scenes during imaging would produce similar strength of long-range correlations, which provides potential applications for unsupervised image processing.

A single paragraph of about 200 words maximum. For research articles, abstracts should give a pertinent overview of the work. We strongly encourage authors to use the following style of structured abstracts, but without headings: (1) Background: Place the question addressed in a broad context and highlight the purpose of the study; (2) Methods: briefly describe the main methods or treatments applied; (3) Results: summarize the article’s main findings; (4) Conclusions: indicate the main conclusions or interpretations. The abstract should be an objective representation of the article and it must not contain results that are not presented and substantiated in the main text and should not exaggerate the main conclusions.

Large datasets play a crucial role in the progression of surgical robotics, facilitating advancements in the fields of surgical task recognition and automation. Moreover, public datasets enable the comparative analysis of various algorithms and methodologies, thereby assessing their effectiveness and performance. The ROSMA (Robotics Surgical Maneuvers) dataset provides 206 trials of common surgical training tasks performed with the da Vinci Research Kit (dVRK). In this work, we extend ROSMA dataset with two annotated subsets: ROSMAT24, which contains bounding box annotations for instrument detection, and ROSMAG40, which contains high and low level gesture annotations. We propose an annotation method that provides independent labels for the right-handed tool and the left-handed tool. For instrument identification, we validate our proposal with a YOLOv4 model in two experimental scenarios. We demonstrate the generalization capabilities of the network to detect instruments in unseen scenarios. For gesture segmentation, we propose two label categories: high-level annotations that describe gestures at a maneuvers level, and low-level annotations that describe gestures at a fine-grain level. To validate this proposal, we have designed a recurrent neural network based on a bidirectional long-short term memory layer. We present results for four cross-validation experimental setups, reaching up to a 77.35% mAP.

With the rapid developments that have been made in computer vision and computer technology, semantic segmentation of high-resolution images has emerged as a mainstream and challenging task. The, segmentation of water areas remains a complex task due to the similar features between water areas or between water areas and other land objects. Meanwhile, since coastlines and riverbanks are typically presented in irregular shapes, it is difficult to obtain the categories of pixels at boundaries. This paper proposed the use of a Water-Land Boundary Attention Network (WLBANet) to improve the accuracy of pixels at boundaries between water and land. This network also reinforced the performance of contextual information extraction into distinguishing between water areas and other land objects. To prove the validity of this proposed network, WLBANet was performed on the Water Land Dataset (WLD), which is also by this paper, and which contains water areas and other land objects categories. The results demonstrates that the proposed method has significant effectiveness.

A primary challenge facing conservationists is reconciling the human needs of forest adjacent communities with the needs of conserving forest biodiversity, especially in tropical regions with growing populations of rural poor. Agroforestry has the potential to simultaneously provide for human needs and enhance forest biodiversity, but the complex interactions and feedbacks between the social and natural dimensions are relatively undescribed and thus systematic implementation is rare. The attributes of trees on farms required for human needs and conservation value may conflict. For example, exotic species in monoculture may provide the most economic value for farmers, while relic or planted indigenous tree mixtures may be more valuable for biological conservation. The objective of this study was to explore whether agroforestry practices in a moist tropical forest ecosystem in Kenya can simultaneously provide timber and fuelwood value to small-holder farmers while extending forest tree biodiversity. We described the agroforestry attributes on farms around a tropical forest, assessed the relationship between number and biomass of timber/fuelwood trees and tree biodiversity, and explored the relationships between forest tree diversity attributes and farm tree diversity attributes on a landscape scale using spatial analysis. We found that the diversity and number of trees on farms in this area are extensive yet variable, but that no significant relationship exists between the number of timber/fuelwood trees and tree diversity. This suggests that the two values of agroforestry may not be in conflict, due mainly to the high diversity of trees used for fuelwood. We also found that trees on farms in the larger landscape add to the conservation value of forest tree biodiversity and could be important components in conservation management. If agroforestry is to play an increasingly active role in conserving biodiversity in human-dominated landscapes, particularly in areas of dense subsistence farmer populations, increase recognition needs to be given to farmer’s perception of the value of trees and their selection of what trees to plant or maintain.

This research develops the Osteoporosis Knowledge, Attitude, and Behaviors Questionnaire (OKABQ) with the intent to evaluate levels of osteoporosis knowledge, attitude and behavior change. The aims of the study were to develop and validate the OKABQ; and to establish a mediation model of the research. A quantitative, descriptive, and instrumental study was conducted in two phases: Phase I—development of the scale through Delphi Method by osteoporosis experts; Phase II—evaluation of the validity and reliability of the scale and construction of a mediation model using SmartPLS. In Phase I, the content validity index (CVI) of the questionnaire was higher than 0.96 and the inter-rater reliability (IRR) kappa was 1.00. In Phase II, exploratory factor analysis showed that two predominating factors of attitude as a mediation were addressed by the 26-item OKABQ. The indirect effect results from the estimated model indicates that attitude mediates the relationship between knowledge and behaviors (β = 0.114, t = 2.627, p < 0.001), which is positive and statistically significant. We concluded that the OKABQ is a valid measure of osteoporosis knowledge, attitude and behaviors for women with osteoporosis. These assessment results could assist healthcare providers in mitigating insufficiency on health education.

Many corporations have now revised their value statements to showcase their commitment to sustainable development and green business due to the pressing issues of climate and environmental damage. Despite the importance of value statements that can direct companies to achieve sustainable goals, what kind of values can be perceived as organizational orientations to sustainability remains unknown. This study explores how the general public views the inclusion of sustainable components in value statements from the listed companies in Hong Kong by using Q-sort methodology (n = 30). Analyzing the final sample of 40 value statements extracted from 27 listed companies, we identified three factors related to sustainability, namely, Empowering business process management, Empowering customer-centric excellence, and Empowering sustainable progress. This study provides an additional component to the traditional triple bottom line by suggesting that internal operation of a company is an emerging idea to understand corporate sustainability.

Plant phenotype plays an important role in crop breeding and planting. Leaf phenotype is an important part of plant phenotype. In order to analyze the leaf phenotype, the target leaf is required to be segmented from the complex background image. In this paper, an automatic soybean leaf segmentation method based on object detection and interactive segmentation models is proposed. Firstly, the Libra R-CNN object detection algorithm is used to detect all soybean leaves in the image. Then, based on the idea that the target soybean leaf is located in the center of the image and the area is large, the detection bounding box of the target leaf is selected. In order not to destroy the segmentation result, the bounding box is optimized to completely enclose the whole leaf. Finally, according to the optimized bounding box, the prior channels of foreground and background are constructed using Gaussian model. The two channels together with the original image are as the input of the interactive object segmentation with inside-outside guidance model to segment the target soybean leaf. A large number of qualitative and quantitative experimental results show that the method has high segmentation accuracy and strong generalization capacity.

Interstitial lung disease (ILD) is one of the most serious extra-articular complications of rheu-matoid arthritis (RA), which increases the mortality of RA. Because the pathogenesis of RA-ILD remains poorly understood, appropriate therapeutic strategies and biomarkers have not yet been identified. Thus, the goal of this review was to summarize and analyze the reported data on the etiology and pathogenesis of RA-ILD. The incidence of RA-ILD increases with age, and is also generally higher in men than in women and in patients with specific genetic variations and eth-nicity. Lifestyle factors associated with an increased risk of RA-ILD include smoking and exposure to pollutants. The presence of an anti-cyclic citrullinated peptide antibody, high RA disease activity, and rheumatoid factor positivity also increase the risk of RA-ILD. We also explored the roles of biological processes (e.g., fibroblast–myofibroblast transition, epithelial–mesenchymal transition, and immunological processes), signaling pathways (e.g., JAK/STAT and PI3K/Akt), and the his-topathology of RA involved in RA-ILD pathogenesis based on published preclinical and clinical models of RA-ILD in animal and human studies.

This research introduces a pioneering solution to the challenges posed by gastrointestinal tract (GI) cancer in radiation therapy, focusing on the imperative task of precise organ segmentation for minimizing radiation-induced damage. GI imaging has historically used manual demarcation, which is laborious and uncomfortable for patients. We address this by introducing the ResECA-U-Net deep learning model, a novel combination of the UNet and ResNet34 architectures. Furthermore, we further augment its functionality by incorporating the Efficient Channel Attention (ECA-Net) methodology. By utilizing data from the UW-Madison Carbone Cancer Centre, we carefully investigate several image processing techniques designed to capture critical local characteristics. With its foundation in computer vision concepts, the ResECA-U-Net model is excellent at extracting fine details from GI images. Sophisticated metrics such as intersection over union (IoU) and the dice coefficient are used to evaluate performance. Our study's outcomes demonstrate the effectiveness of the suggested method, yielding an impressive 96.27% Dice coefficient and 91.48% IoU. These results highlight the significant contribution that our strategy has made to the advancement of cancer therapy. Beyond its scientific merits, this work has the potential to significantly enhance cancer patients' quality of life and provide better long-term outcomes. Our work is a significant step towards automating and optimizing the segmentation process, which can potentially change how GI cancer is treated completely.

The process of preparing anti-glare thin films by spray-coating silica sol-gel to soda-lime glass was exclusively and statistically studied in this paper. The effects of sol-gel deliver pressure, air transport pressure, and spray gun displacement speed on the gloss, haze, arithmetic mean surface roughness, and total transmittance light were analyzed. The experimental results indicate that the factors of sol-gel deliver pressure, air transport pressure, and displacement speed exhibit significant effect on the haze, gloss, and Ra. In contrast, the variation of total transmittance light with these three factors are insignificant. Because the anti-glare property is predominantly determined by low gloss and high haze, therefore, we aim to minimize gloss and maximize haze to achieve high anti-glare. Central composite design and response rurface methodology are employed to analyze the main and interaction effects of the three factors through quadratic polynomial equations, which are confirmed by the analysis of variance and R². The response surface methodology predict the lowest gloss and highest haze are 9.2 GU and 57.0%, corresponding to the sol-gel deliver pressure, air-transport pressure, and displacement speed of 250 kPa, 560 kPa, and 140 mm/s, and 340 kPa, 620 kPa, and 20 mm/s, respectively. Comparing the predicted optimal data with the real experimental results validates the applicability of the mathematical model. This study provides an important basis for the subsequent production of anti-glare glass with different specifications to satisfy the market demand.

This article presents a succinct overview of the progress, obstacles, and uses of semantic segmentation and instance segmentation within the forestry domain. The objective of this review is to conduct a critical analysis of the current literature pertaining to segmentation techniques and provide a methodical summary of their impact on forestry-related activities, including but not limited to tree species classification, forest inventory, and ecological monitoring such as retrieval of dominant tree species. Through the process of synthesizing pivotal discoveries from multiple studies, this comprehensive analysis provides valuable perspectives on the present status of research and highlights prospective areas for further exploration. The primary topics addressed encompass the approach employed for executing the examination, the fundamental discoveries associated with semantic segmentation and instance segmentation in the domain of forestry, and the ramifications of these discoveries for the discipline. The results indicate that the utilization of semantic segmentation methods has been efficacious in the field of forestry for the precise identification of tree species. Such methods also aid in tracking of deforested regions over the course of time by separating other land-use classes from forested regions. Additionally, the employment of instance segmentation techniques exhibits potential in the demarcation of individual trees. Instance segmentation offers promising results due to deep learning models based on forest point clouds. However, several challenges persist in the successful implementation of semantic segmentation methods such as the presence of occlusions, overlapping branches, and intricate structures hampers the accurate segmentation of trees. Additionally, instance segmentation approaches that utilize models are mostly trained by using laser scanning data based on forest types which are typically trained on specific laser scanning data and forest types that create limitations in generalization from high to low resolution point clouds. Due to this reason, the existing approaches often struggle with handling these complex structures, leading to the need for manual methods for extracting measurements from forest point clouds. The review culminates by underscoring the necessity for additional research to tackle current obstacles and augment the precision and relevance of segmentation methodologies in the field of forestry. In general, the present article provides a significant reference for scholars and professionals who are interested in utilizing segmentation techniques in the field of forestry.

Laser-targeted weeding methods further enhance the sustainable development of green agriculture, with one key technology being the improvement of weed localization accuracy. Here, we propose an improved YOLOv8 instance segmentation based on bidirectional feature fusion and deformable convolution (BFFDC-YOLOv8-seg) to address the challenges of insufficient weed localization accuracy in complex environments with resource-limited laser weeding devices. Initially, by training on extensive datasets of plant images, the most appropriate model scale and training weights are determined, facilitating the development of a lightweight network. Subsequently, the introduction of the Bidirectional Feature Pyramid Network (BiFPN) during feature fusion effectively prevents the omission of weeds. Lastly, the use of Dynamic Snake Convolution (DSConv) to replace some convolutional kernels enhances flexibility, benefiting the segmentation of weeds with elongated stems and irregular edges. Experimental results indicate that the BFFDC-YOLOv8-seg model achieves a 4.9% increase in precision, an 8.1% increase in recall rate, and a 2.8% increase in mAP50 value to 98.8% on a vegetable weed dataset compared to the original model. It also shows improved mAP50 over other typical segmentation models such as Mask R-CNN, YOLOv5-seg, and YOLOv7-seg by 10.8%, 13.4%, and 1.8%, respectively. Furthermore, the model achieves a detection speed of 24.8 FPS on the Jetson Orin nano standalone device, with a model size of 6.8MB that balances between size and accuracy. The model meets the requirements for real-time precise weed segmentation, suitable for complex vegetable field environments and resource-limited laser weeding devices.

Abstract. This paper proposes a Second Order Terminal Sliding Mode (2TSM) approach to the trajectory tracking of Differential Drive Mobile Robot (DDMR). Within this cascaded control scheme, the 2TSM dynamic controller, at the inner most loop, tracks the robot’s velocity quantities; while a kinematic controller, at the outer most loop, regulates the robot’s positions. In this manner, chattering is greatly attenuated and finite time convergence is guaranteed by the second order TSM manifold which involves higher order derivatives of the state variables, resulting in inherently robust as well as fast and better tracking precision. The simulation results demonstrate the merit of the proposed control methods.

In this study, a composite flame retardant was created by combining fish scale (FS), fishery waste, and ammonium polyphosphate (APP), a commercially available flame retardant. The composite flame retardant was added to epoxy resin (EP) to form an EP/APP/FS composite that prevents burns and is environmentally friendly. The use of FS conforms to the concept of circular economy and lowers costs by reducing the consumption of APP. Thermogravimetric analysis (TGA), integral procedural decomposition temperature (IPDT), pyrolysis kinetics, limiting oxygen index (LOI), the Underwriters Laboratories 94 (UL94) flammability test, scanning election microscopy, Raman spectroscopy, and energy-dispersive X-ray spectroscopy were used to determine the thermal properties, flame retardant properties, flame retardant mechanism, char morphology, and composition of the composites. The TGA results indicated that the addition of 40% flame retardant raised the char residue from 16.45 wt% (pure EP) to 36.07 wt%, IPDT from 685.6 °C (pure EP) to 1143.1°C, LOI from 21% (pure EP) to 30%, and UL94 classification from fail (pure EP) to V-0. These results suggest an increase in char residue, which indicates better protection of the polymer matrix material. The improvements in IPDT, LOI, and UL94 classification, which indicate greater thermal stability, lower flammability (from flammable to fireproof), and higher flammability rating (from fail to V-0), respectively, suggest that the composite material has favorable thermal properties and is less inflammable.

Simple summary This reassessment of the findings from our Phase I/II study seeks to evaluate the effectiveness of SBRT for treating local intermediate-high risk prostate cancer in the absence of androgen-deprivation therapy due to patient’s refusal, with a median follow-up of 6.5 years. Our primary focus is on analysing the treated areas compared to recurrence patterns in the seven patients who experienced local relapse. Additionally, we provide updated data on late toxicities of grade 2 or higher, both genitourinary and gastrointestinal. Abstract Objectives: We investigated spatial patterns between primary and recurrent tumor sites and assessed long-term toxicity after dose escalation stereotactic body radiation therapy (SBRT) to the dominant intraprostatic nodule (DIN). Materials and methods: In 33 patients with intermediate-high risk prostate cancer (PCa), doses up to 50 Gy were administered to the DIN. Recurrence sites were determined and compared to the original tumor development sites through multiparametric MRI and 68Ga-labelled prostate-specific membrane antigen (PSMA) positron emission tomography/computed tomography (68Ga-PSMA-PET/CT) images. Overlap rates, categorized as 75% or higher for full overlap, and 25-74% for partial overlap, were assessed. Long-term toxicity is reported. Results: All patients completed treatment, with only one receiving concomitant androgen deprivation therapy (ADT). Recurrences were diagnosed after a median of 33 months (range: 17-76 months), affecting 13 out of 33 patients (39.4%). Intraprostatic recurrences occurred in 7 patients (21%), with ≥ 75% overlap in two, a partial overlap in another two, and no overlap in the remaining three patient. Notably, 5 patients with intra-prostatic recurrences had synchronous bone and/or lymph node metastases, while six patients had isolated bone or lymph node metastasis without intraprostatic recurrences. Extended follow-up revealed grade 2 or higher late GU and GI toxicity in 18% (n=6) and 6% (n=2) of the patients. Conclusions: Among patients with intermediate-high risk PCa undergoing focal dose-escalated SBRT without ADT, DIN recurrences were infrequent. When present, these recurrences were typically located at the original site or adjacent to the initial tumor. Conversely, relapses beyond the DIN and in extra-prostatic (metastatic) sites were prevalent, underscoring the significance of systemic ADT in managing this patient population. Advances in knowledge: focal dose escalated prostate SBRT prevented recurrences in the dominant nodule, however extra-prostatic recurrence sites were frequent.

Background: The Advanced Lung Cancer Inflammation Index (ALI) is a novel, comprehensive index that integrates inflammation and nutritional status, incorporating parameters such as albumin, body mass index (BMI), and the neutrophil-to-lymphocyte ratio (NLR). Unlike traditional inflammation biomarkers, this study aims to evaluate the prognosis of IPF patients by considering both inflammation and nutritional status. Method: A total of 102 patients with IPF were included in the study. Clinical data were obtained from the patients' medical records. NLR and ALI score were calculated based on data collected at the initiation of antifibrotic treatment using the following formula: Neut/Lym and albumin × BMI / NLR. Results: IPF subject subgroups in terms of ALI based on gender–age–physiology (GAP) stages (1,2,3), FVC (median split,

In addition to absorbing nitrogen from the soil, legumes have the ability to use atmospheric N2 through symbiotic nitrogen fixation. Therefore, legumes have developed mechanisms regulating nodulation in response to the amount of nitrate in the soil; in the presence of high nitrate concentrations, nodulation is inhibited while low nitrate concentrations stimulate nodulation and nitrogen fixation. This allows the legumes to switch from soil nitrogen acquisition to symbiotic nitrogen fixation. Recently, a particular interest has been given to the nitrate transporters, such as NPF or NRT2, having a role in the functioning of nodules. Nitrate transporters of the two model plants, Lotus japonicus and Medicago truncatula, shown to have a positive and/or a negative role in nodule functioning, depending on nitrate concentration, are presented in this review. Also, by exploiting available genomic and transcriptomic data in the literature we have identified the complete PsNPF family in Pisum sativum (69 sequences previously described and 21 new that we have annotated) and putative nitrate transporters candidate for playing a role in nodule functioning in P. sativum.

Bacterial communities in rhizosphere and root nodules have significant contributions to the growth and productivity of the soybean (Glycine max L.). In this report, we analyzed the physiological properties and dynamics of bacterial community structure in rhizosphere and root nodules at different growth stages using BioLog EcoPlate and high-throughput sequencing technology, respectively. The BioLog assay found that the metabolic capability of rhizosphere is in increasing trend in the growth of soybeans as compared to the bulk soil. As a result of the Illumina sequencing analysis, the microbial community structure of rhizosphere and root nodules was found to be influenced by the variety and growth stage of the soybean. At the phylum level, Actinobacteria were the most abundant in rhizosphere at all growth stages, followed by Alphaproteobacteria and Acidobacteria and the phylum Bacteroidetes showed the greatest change. But, in the root nodules Alphaproteobacteria were dominant. The results of the OTU analysis exhibited the dominance of Bradyrhizobium during the entire stage of growth, but the ratio of non-rhizobial bacteria showed an increasing trend as the soybean growth progressed. These findings revealed that bacterial community in the rhizosphere and root nodules changed according to both the variety and growth stages of soybean in the field.

Chronic obstructive pulmonary disease (COPD) is a progressive lung disease that is commonly considered to be a potent driver of non-small cell lung cancer (NSCLC) development and related mortality. A growing body of evidence supports the role of the immune system, mainly played by alveolar macrophages (AMs), as key axes regulating the development of COPD or NSCLC phenotypes in response to harmful agents. MicroRNAs (miRNAs) are small non-coding RNAs that influence most biological processes and interfere with several regulatory pathways. The purpose of this study was to assess miRNA expression patterns in patients with COPD, NSCLC, and ever- or never-smoker controls to explore theirinvolvment in smoking-related diseases. Bronchoalveolar lavage (BAL) specimens were collected from a prospective cohort of 43 sex-matched subjects to determine expression of hsa-miR-223-5p, 16-5p, 20a-5p, -17-5p, 34a-5p and 106a-5p by RT-PCR. In addition, bioinformatic analysis of miRNA target genes linked to cancer was performed. Distinct and common miRNA expression levels were identified in each pathological group suggesting their possible role as an index of NSCLC or COPD microenvironment. Moreover, we identified miRNA targets linked to carcinogenesis using in silico analysis. In conclusion, this study identified miRNA signatures in AMs, allowing us to understand the molecular mechanisms underlying smoking-related conditions and potentially providing new insight for diagnosis or pharmacological treatment.

Conventional cancer clinical trials can be time-consuming and expensive, often yielding results with limited applicability to real-world scenarios and presenting challenges for patient participation. Real-world data (RWD) studies offer a promising solution to address evidence gaps and provide essential information about the effects of cancer treatments in real-world settings. Defining RWD based on its original intent, which is the collection of data at the point of care for clinical purposes, can distinguish it from conventional clinical trial data. RWD can be generated using experimental designs that resemble those used in conventional clinical trials, but with several advantages, such as improved efficiency and a better balance between internal and external validity. RWD can support pharmacovigilance, insights into disease progression, and the development of external control groups. Prospective RWD collection enables evidence generation based on pragmatic clinical trials (PCTs) that support randomized study designs and expand clinical research to the point of care. To ensure the quality of real-world studies, it is crucial to implement auditable data abstraction methods and develop new incentives to capture clinically relevant data electronically at the point of care. The treatment landscape is constantly evolving, with the integration of front-line immune checkpoint inhibitors (ICIs), either alone or in combination with chemotherapy, affecting subsequent treatment lines. Real-world effectiveness and safety in underrepresented populations, such as the elderly, patients with poor performance status (PS), hepatitis, or human immunodeficiency virus-infected patients, are still largely unexplored. Similarly, the cost-effectiveness and sustainability of these innovative agents are important considerations in the real world.

The standard treatment for early-stage lung cancer is complete tumor excision by limited resection of the lung. Pre-operative localization is used before video-assisted thoracoscopic surgery (VATS) to improve the accuracy of pulmonary nodule excision. However, lung atelectasis and hypoxia resulting from controlling apnea during the localization procedure may affect the localization accuracy. Pre-procedural pulmonary recruitment may improve respiratory mechanics and oxygenation during localization. In this study, we investigated the potential benefits of pre-localization pulmonary recruitment prior to pulmonary ground-glass nodule localization in a hybrid operating room. We hypothesized that pre-localization pulmonary recruitment would increase localization accuracy, improve oxygenation, and prevent the need for re-inflation during the localization procedure. We retrospectively enrolled patients with multiple pulmonary nodule localizations before surgical intervention in our hybrid operating room. We compared localization accuracies between patients who had undergone pre-procedure pulmonary recruitment and patients who had not. Saturation, re-inflation rate, apnea time, procedure-related pneumothorax, and procedure time were also recorded as secondary outcomes. Patients who had undergone pre-procedure recruitment had better saturation, shorter procedure time, and higher localization accuracy. The pre-procedure pulmonary recruitment maneuver was effective in increasing regional lung ventilation, leading to improved oxygenation and localization accuracy.

Blood vessels are essential for maintaining tumor growth, progression, and metastasis, yet the tumor vasculature is under a constant state of remodeling. Since the tumor vasculature is an attractive therapeutic target, there is a need to predict the dynamic changes in intratumoral fluid pressure and velocity which occur across the tumor microenvironment (TME). The goal of this study is to get insight into perfusion anisotropy within lung tumors. To achieve this goal, we used the perfusion marker Hoechst 33342 and vascular endothelial marker CD31 to stain tumor sections from C57BL/6 mice harboring Lewis Lung Carcinoma tumors on their flank. Vasculature, capillary diameter, and permeability distribution were extracted at different time points along the tumor growth curve. A computational model was generated applying a unique modeling approach based on the smeared physical fields (Kojic Transport Model, KTM). KTM predicts spatial and temporal changes in intratumoral pressure and fluid velocity within the growing tumor. Anisotropic perfusion occurs within two domains - capillary and extracellular space. Anisotropy in tumor structure causes nonuniform distribution of pressure and fluid velocity. These results provide insights regarding local vascular distribution for optimal drug dosing and delivery to better predict distribution and duration of retention within the TME.

Small interfering RNA (siRNA) holds significant therapeutic potential by silencing target genes through RNA interference. Current clinical applications of siRNA have been primarily limited to liver diseases, while achievements in delivery methods are expanding its applications to various organs, including the lungs. Cholesterol-conjugated siRNA emerges as a promising delivery approach due to its low toxicity and high efficiency. This study focuses on developing a cholesterol-conjugated anti-Il6 siRNA and the evaluation of its potency for the potential treatment of inflammatory diseases using the example of acute lung injury (ALI). The biological activities of different Il6-targeted siRNAs containing chemical modifications were evaluated in J774 cells in vitro. The lead cholesterol-conjugated anti-Il6 siRNA after intranasal instillation demonstrated dose-dependent therapeutic effects in a mouse model of ALI induced by lipopolysaccharide (LPS). The treatment significantly reduced Il6 mRNA levels, inflammatory cell infiltration, and the severity of lung inflammation. IL6 silencing by cholesterol-conjugated siRNA proves to be a promising strategy for treating inflammatory diseases, with potential applications beyond the lungs.

Abstract This study delved into the application of various machine learning (ML) models for the classification of lung cancer levels. Through meticulous monitoring of parameters such as minimum child weight and learning rate, efforts were made to mitigate overfitting while optimizing model performance. The Deep Neural Network (DNN) emerged as a standout performer, showcasing robust performance across training, validation, and testing stages. Ensemble methods like voting and bagging also demonstrated promising results. However, Support Vector Machine (SVM) models with the Sigmoid kernel faced challenges in achieving satisfactory performance. Overall, the investigation sheds light on the efficacy of different ML models in lung cancer level classification and underscores the importance of parameter tuning to address overfitting concerns.

Semantic segmentation of high-resolution remote sensing images provides detailed and precise feature information, playing a pivotal role in decision-making and analysis in sectors such as water management, agriculture, military, and environmental protection. However, most methods merely combine features from various branches directly, without a mechanism for spatial location feature screening, and treat all extracted features as equally important. To overcome these limitations, we introduce a novel spatially adaptive interaction network (SAINet) for dynamic interaction across different features in remote sensing semantic segmentation task. Specifically, we propose a spatial refined module that leverages local context information to filter spatial locations and extract salient regions. Following this, we introduce an innovative spatial interaction module that uses a spatial adaptive modulation mechanism to dynamically select and allocate spatial position weights. This facilitates interaction between local salient areas and global information, allowing the network to focus more on relevant regions. This flexible approach enables the network to capture more informative features, thereby enhancing segmentation accuracy. Experiments conducted on the DeepGlobe, Vaihingen, and Potsdam public datasets confirm the effectiveness and capability of SAINet. Our code and models will be publicly available

In the contemporary era, youthful and healthy skin is a pivotal determinant of beauty. Choices pertaining to one's dietary and lifestyle practices wield substantial influence over skin health. Currently, the focal point of attention lies in strategies to delay skin aging and maintain skin quality. Remarkably, the skin, the body's largest organ, serves as the primary defense barrier against external elements. Skin aging encompasses intrinsic and extrinsic categories, both susceptible to genetic, lifestyle, and environmental factors. Given the strides in science and technology, the pursuit of effective and safe interventions for skin aging assumes paramount importance. Thus, this review delves into the intricate relationship between diet, lifestyle, and skin aging, culminating in an exploration of the crucial role played by excess iron in this intricate nexus. Understanding these dynamics holds promise for advancing our knowledge of skincare and the quest for timeless vitality.

Lung cancer (LC) continues to be an important public health problem being the most common form of cancer and a major cause of cancer deaths worldwide. Despite the great bulk of research to identify genetic susceptibility genes by genome-wide association studies, only few loci associated to nicotine dependence have been consistently replicated. Our previously published study in few phenotypically discordant sib-pairs identified a combination of germline truncating mutations in known cancer susceptibility genes in never smoker early-onset LC patient does not present in their healthy sib. These results firstly demonstrated the presence of an oligogenic combination of disrupted cancer predisposing genes in non-smokers patients, giving experimental support to a model of a “private genetic epidemiology”. Here, we used a combination of whole-exome and RNA sequencing coupled with a discordant sib’s model in a novel cohort of pairs of never-smokers early-onset LC patients and in their healthy sibs used as controls. We selected rare germline variants predicted as deleterious by CADD and SVM bio-informatics tools and absent in the healthy sib. Overall, we identified an average of 200 variants per patient, about 10 of which in cancer predisposing genes. In most of them, RNA sequencing data reinforced the pathogenic role of the identified variants showing: i) downregulation in LC tissue (indicating “second hit” in tumor suppressor genes); ii) upregulation in cancer tissue (likely oncogene); iii) downregulation in both normal and cancer tissue (indicating transcript instability). The combination of the two techniques demonstrates that each patient has an average of six (with a range from four to eight) private mutations with functional effect in tumor predisposing genes. The presence of a unique combination of disrupting events in the affected subjects may explain the absence of familial clustering of non-small cell lung cancer. In conclusion, these findings indicate that each patient has his/her own “predisposing signature” to cancer development and suggest the use of personalized therapeutic strategies in lung cancer.

Titanium dioxide nanoparticles (TiO2NPs) are used in products that are applied to the human body, such as cosmetics and food, but their biocompatibility remains controversial. Pycnogenol (PYC), a natural extract of pine bark, exerts anti-inflammatory and antioxidant effects. In this study, we investigated whether PYC effectively alleviates pulmonary toxicity induced by airway exposure to TiO2NPs, and the beneficial effects of PYC were explained through the analysis of changes to the mechanism of cytotoxicity. TiO2NPs induced pulmonary inflammation and mucus production, increased the levels of malondialdehyde, and upregulated thioredoxin-interacting protein (TXNIP) and cleaved-caspase 3 (Cas3) in the lungs of mice. However, PYC treatment reduced the levels of all toxicity markers of TiO2NPs and restored glutathione levels. These antioxidant and anti-inflammatory effects of PYC were also demonstrated in TiO2NP-exposed human airway epithelial cells by increasing the mRNA levels of antioxidant enzymes and decreasing the expression of TXNIP, cleaved-Cas3, and inflammatory mediators. Taken together, our results showed that PYC attenuated TiO2NP-induced lung injury via TXNIP downregulation. Therefore, our results suggest the potential of PYC as an effective anti-inflammatory and antioxidant agent against TiO2NP-induced pulmonary toxicity.

In our previous study, a novel barrier processing on a porous low-dielectric constant (low-k) film was developed: an ultrathin Mn oxide on a nitrogen-stuffed porous carbon-doped organosilica film (p-SiOCH(N)) as a barrier of the Cu film was fabricated. To form a better barrier Mn₂O_3-xN film, an additional annealing at 450°C was implemented. In this study, the electrical characteristics and reliability of this integrated Cu/Mn₂O_3-xN/p-SiOCH(N)/Si structure is investigated. The proposed Cu/Mn₂O_3-xN/p-SiOCH(N)/Si capacitors exhibited poor dielectric breakdown characteristics in the as-fabricted stage, although, less degradation was found after thermal stress. Moreover, its time-dependence-dielectric-breakdown electric-field acceleration factor slightly increased after thermal stress, leading to a larger dielectric lifetime in a low electric-field as compared to other MIS capacitors. Furthermore, its Cu barrier ability under electrical or thermal stress was improved. As a consequent, the proposed Cu/Mn₂O_3-xN/p-SiCOH(N) scheme is a promising integrity for back-end-of-line interconnects.

This study introduces a sophisticated neural network structure for segmenting breast tumors. It achieves this by combining a pretrained Vision Transformer (ViT) model with a U-Net framework. The U-Net architecture, commonly employed for biomedical image segmentation, is further enhanced with Depthwise Separable Convolutional Blocks to decrease computational complexity and parameter count, resulting in better efficiency and less overfitting. The Vision Transformer, renowned for its robust feature extraction capabilities utilizing self-attention processes, efficiently captures the overall context within images, surpassing the performance of conventional convolutional networks. By using a pretrained ViT as the encoder in our U-Net model, we take advantage of its extensive feature representations acquired from extensive datasets, resulting in a major enhancement in the model’s ability to generalize and train efficiently. The suggested model has exceptional performance in segmenting breast cancers from medical images, highlighting the advantages of integrating transformer-based encoders with efficient U-Net topologies. This hybrid methodology emphasizes the capabilities of transformers in the field of medical image processing and establishes a new standard for accuracy and efficiency in activities related to tumor segmentation.

This study used the sol–gel method to synthesize a non-halogenated hyperbranched flame retardant containing nitrogen, phosphorus and silicon, HBNPSi, which was then added to a polyurethane (PU) matrix to form an organic–inorganic hybrid material. Using 29Si nuclear magnetic resonance, energy-dispersive X-ray spectroscopy of P- and Si-mapping, scanning electron microscopy, and X-ray photoelectron spectroscopy, this study determined the organic and inorganic dispersity, morphology, and flame retardance mechanism of the hybrid material. The condensation density of the hybrid material PU/HBNPSi was found to be 74.4%. High condensation density indicates a dense network structure of the material. The P- and Si-mapping showed that adding inorganic additives in quantities of either 20% or 40% results in homogeneous dispersion of the inorganic fillers in the polymer matrix without agglomeration, indicating that the organic and inorganic phases had excellent compatibility. In the burning test, adding HBNPSi to PU resulted in the material passing the UL-94 standard at the V2 level, unlike the pristine PU, which did not meet the standard. The results demonstrated that after non-halogenated flame retardant was added to PU, the material’s flammability and dripping were lower, thereby proving that flame retardants containing elements such as nitrogen, phosphorus, and silicon exert an excellent flame retardant synergistic effect.

Dravet syndrome (DS), also known as severe myoclonic epilepsy of infancy, is a rare and drug-resistant form of developmental and epileptic encephalopathies, which is both debilitating and challenging to manage, typically arising during the first year of life, with seizures often triggered by fever, infections, or vaccinations. It is characterized by frequent and prolonged seizures, developmental delays, and various other neurological and behavioral impairments. Most cases result from pathogenic mutations in the sodium voltage-gated channel alpha subunit 1 (SCN1A) gene, which encodes a critical voltage-gated sodium channel subunit involved in neuronal excitability. Precision medicine offers significant potential for improving DS diagnosis and treatment. Early genetic testing enables timely and accurate diagnosis. Advances in our understanding of DS's underlying genetic mechanisms and neurobiology have enabled the development of targeted therapies, such as gene therapy, offering more effective and less invasive treatment options for patients with DS. Targeted and gene therapies provide hope for more effective and personalized treatments. However, research into novel approaches remains in its early stages, and their clinical application remains to be seen. This review addresses the current understanding of clinical DS features, genetic involvement in DS development, and outcomes of novel DS therapies.

The domestic ducks (Anas platyrhynchos domesticus) are resistant to most of the highly pathogenic avian influenza virus (HPAIV) infections. In this study, we characterized the lung proteome and phosphoproteome of ducks infected with HPAI H5N1 virus (A/duck/India/02CA10/2011/Agartala) at 12 hr, 48 hr and 5 days post infection condition. Total 2082 proteins were differentially expressed and 320 phosphorylation sites mapping to 199 phosphopeptides corresponding to 129 proteins were identified. Functional annotation of proteome data analysis reveals activation of RIG-I-like receptor and Jak-STAT signaling pathways, that lead to induction of interferon stimulated genes (ISGs) expression. The pathway analysis of phosphoproteome datasets also confirms the activation of RIG I, Jak-STAT signaling, NF-kappa B signaling and MAPK signaling pathways in the lung tissues. The induction of ISGs proteins (STAT1, STAT3, STAT5B, STAT6, IFIT5 and PKR) establishes protective antiviral immune response in duck lung tissue. Further, the protein-protein interaction network analysis identified proteins like AKT1, STAT3, JAK2, RAC1, STAT1, PTPN11, RPS27A, NFKB1 and MAPK1 as main hub proteins that might play important roles in disease progression in ducks. Together, functional annotation of proteome and phosphoproteome datasets reveals the molecular basis of the disease progression and disease resistance mechanism in ducks infected with HPAI H5N1 virus.

Vascular endothelial growth factor (VEGF) is a important biomarker with significant clinical importance. It plays a key role in angiogenesis, would healing, tumor growth, lung development, and in retinal diseases. Hence, detecting and quantifying VEGF is crucial in clinical diagnosis and prognosis of various diseases. In this work, a simple but highly cost-effective platform is developed for VEGF protein detection by using commercially available interdigitated sensors that are modified through surface chemistry tagged with DNA aptamer grafting. The dielectric characteristics between the fingers of sensor is modulated by the negatively charged aptamer-VEGF capture and the impedance is estimated using impedance analyzer. Impedance spectra tests was compared between pristine unmodified, functionalized monolayer surfaces and aptamer-grafted surfaces in order to evaluate the efficacy of VEGF detection. In our results, the sensitivity experiments as conducted had shown the ability of the interdigitated sensor to detect VEGF at a low concentration of 5 pM. The specificity of the functionalized sensor in detecting VEGF is further studied by comparing the impedance to platelet-derived growth factor (PDGF), and the results confirm the specificity of the sensor. Finally, an alternative illustration of impedance spectra is also proposed to improve the data visualization, and such presentation may be potential for intelligent VEGF detection.

The application of artificial intelligence to point-of-care testing (POCT) disease detection has become a hot research field, in which breath detection which detects the patient's exhaled VOCs combined with sensor arrays of Convolutional Neural Network (CNN) algorithms as a new lung cancer detection is attracting more researchers' attention. However, due to low accuracy, high complexity computation and large number of parameters make the CNN algorithms difficult transplant to the embedded system of POCT devices. A lightweight neural network (LTNet) in this work is proposed to deal with this problem, and meanwhile, achieve high-precision classification of acetone and ethanol gases, which are respiratory markers for lung cancer patients. Compared to currently popular lightweight CNN models such as EfficientNet, LTNet has fewer parameters (32K) and its training weight size is only 0.155 MB. LTNet achieved an overall classification accuracy of 99.06% and 99.14% in the own mixed gas dataset and the University of California (UCI) dataset, which are both higher than that of the five existing models’, and it also offers the shortest training (844.38s and 584.67s) and inference time (23s and 14s) in the same validation set. Compared to the existing CNN models, LTNet is more suitable for resource-limited POCT devices.

Lung cancer remains a pervasive global health challenge, necessitating precise and efficient classification methods to inform optimal treatment strategies. In this study, we investigate the potential of machine learning algorithms in developing a computer-aided diagnostic tool for early and accurate lung cancer classification, leveraging essential protein biomarkers as predictive features. Our investigation reveals the superiority of Deep Neural Networks (DNNs) in lung cancer classification, achieving an impressive accuracy of 96.91%. This highlights the transformative potential of DNNs in facilitating real-world clinical applications, offering clinicians a powerful tool for accurate diagnosis and prognosis. Additionally, we analyze the performance of Ensemble Methods, including Voting (91.75%) and Bagging (93.81%), as viable alternatives to DNNs. These ensemble techniques demonstrate robust performance, further underlining their utility in lung cancer classification tasks. Furthermore, our study underscores the critical role of hyperparameter tuning, particularly in adjusting parameters such as min child weights and learning rates, in mitigating overfitting and enhancing the generalizability of diverse machine learning models. For instance, Support Vector Machines (SVM) exhibit varying accuracies ranging from 74.23% to 95.88% across different hyperparameter configurations, emphasizing the importance of hyperparameter optimization in maximizing model performance. In summary, our comprehensive comparative analysis sheds light on the efficacy of different machine learning approaches in lung cancer classification. By leveraging advanced algorithms and optimizing model parameters, researchers and clinicians can harness the power of machine learning to advance early detection and personalized treatment strategies for lung cancer patients.

Lung neuroendocrine tumors (LNETs) and gastroenteropancreatic neuroendocrine tumors (GEPNETs) are two distinct types of neuroendocrine tumors (NETs) that have traditionally been treated as a single entity despite originating from different sources. Although they share certain phenotypic characteristics and the expression of neuroendocrine markers, they exhibit differences in their microenvironment, molecular mutations, and responses to various therapeutic regimens. Recent research has explored the genetic alterations in these tumors, revealing dissimilarities in the frequently mutated genes, role of EGFR in carcinogenesis, presence of transcription factors, and immunogenicity of the tumor and its microenvironment. Spread Through Air Spaces (STAS), a phenomenon unique to lung carcinomas, appears to play a crucial role in LNET prognosis. These distinctions are also evident in the cascade response of lung and GI tract neuroendocrine tumors to somatostatin analogs, Peptide Receptor Radionuclide Therapy (PRRT), chemotherapy, and immunotherapy. Identifying similarities and differences between the two groups may im-prove our understanding of the underlying mechanisms and facilitate the development of more effective treatment strategies.

Lung cancer, including both non-small cell lung cancer and small cell lung cancer, remains the leading cause of cancer-related mortality worldwide representing 18% of the total cancer deaths in 2020. Many patients are identified already at an advanced stage with metastatic disease and have a worsening prognosis. Recent advances in the genetic understanding of lung cancer have opened new avenues for personalized treatments and targeted therapies. This review examines the latest discoveries in the genetics of lung cancer, discusses key biomarkers, and analyzes current clinical therapies based on this genetic information. It will conclude with a discussion of future prospects and potential research directions.

Medication non-adherence remains a substantial obstacle in asthma care, prompting the exploration of novel therapeutic modalities that prioritize rapid symptom relief, anti-inflammatory activity and facilitate patients’ compliance. This task is well served by a new form of therapy - inhaled triple-combination medications ICS/LABA/LAMA (inhaled glucocorticosteroid/long-acting beta2-agonist/long-acting muscarinic antagonist). The integration of three medications within a singular inhalation device culminates in the reduction of the effective dose of the principal therapeutic agent for asthma management, namely, ICS. This consolidation yields a dual benefit of minimizing the likelihood of adverse effects typically linked with ICS while concurrently optimizing bronchodilator efficacy. The accumulated evidence suggests that adding LAMA to a medium- or high-dose ICS/LABA results in a decrease of asthma exacerbations compared to medium- or high-dose ICS/LABA alone, accompanied by sustained enhancements in lung function parameters. We propose in adult patients experiencing suboptimal asthma control despite medium/high-dose ICS/LABA treatment - regardless of adherence to GINA-recommended strategies, such as MART therapy as a first-line approach or alternative second-line strategies - the preferred course for intensifying asthma therapy involves the addition of a LAMA, ideally in the form of SITT.

Recent advancements in deep learning have spurred the development of numerous novel semantic segmentation models for land cover mapping, showcasing exceptional performance in delineating precise boundaries and producing highly accurate land cover maps. However, to date, no systematic literature review has comprehensively examined semantic segmentation models in the context of land cover mapping. This paper addresses this gap by synthesizing recent advancements in semantic segmentation models for land cover mapping from 2017 to 2023, drawing insights on trends, data sources, model structures, and performance metrics based on a review of 106 extracted articles. Our analysis identifies top journals in the field, including MDPI Remote Sensing, IEEE Journal of Selected Topics in Earth Science, and IEEE Transactions on Geoscience and Remote Sensing, IEEE Geoscience and Remote Sensing Letters, ISPRS Journal Of Photogrammetry And Remote Sensing as the leading journals. We find that research predominantly focuses on land cover, urban areas, precision agriculture, environment, coastal areas, and forests. Geographically, 35.29% of the study areas are located in China, followed by USA (11.76%), France (5.88 %), Spain (4%) and others. Sentinel-2, Sentinel-1, and Landsat satellites emerge as the most commonly used data sources. Benchmark datasets such as ISPRS Vaihingen &amp; Potsdam, LandCover.ai, DeepGlobe, and GID datasets are frequently employed. Model architectures predominantly utilize encoder-decoder, and hybrid convolutional neural network-based structures because of their impressive performances, with limited adoption of transformer-based architectures due to its computational complexity issue, and slow convergence speed. Lastly, this paper highlights existing key research gaps in the field to guide future research directions.

Breast cancer (BC) is a prevalent malignancy with various subtypes, each presenting unique diagnostic and therapeutic challenges. Triple-negative breast cancer (TNBC), which comprises 12-17% of breast cancers, is particularly aggressive due to its lack of estrogen receptor (ER), progesterone receptor (PR), and HER2 expression. This case report details the management of a 64-year-old woman with TNBC. Initially presenting with a left breast nodule, she underwent a biopsy that confirmed triple-negative infiltrating ductal carcinoma. Despite negative BRCA genetic testing, her significant family history of cancer and a newly detected right breast lesion led to a bilateral mastectomy. Post-surgery imaging revealed multiple hypodense nodules and a spiculated pulmonary nodule, prompting further investigation. An endoscopic lung biopsy identified a primary pulmonary carcinoma with histological features similar to the breast cancer, indicating the lung as the primary source. This case underscores the complexity of TNBC, the importance of comprehensive diagnostic evaluations, and the need for considering extramammary origins in metastatic cases. The findings emphasize the role of multidisciplinary teams in managing such rare and challenging cases and highlight the necessity for thorough and repeated evaluations in atypical BC presentations.

The enhancement of early diagnosis of lung cancer is mandatory to improve prognosis. We observed the increase cancer stem cells (CSC) and circulating tumor cells (CTC) in blood of mice on d3 after Lewis lung carcinoma (LLC) cell implantation before disease symptom. Besides we have developed an approach to reprogramming immune cells by inhibiting the MAPK/ERK pathway through MEKi and the PD-1/PD-L1 immune checkpoint signaling pathway. We hypothesized that reprogramming of spleen CD8+ T-cells could also create a population of immune cells with high antitumor activity. We reprogrammed CD8+ T-cells derived from the spleen of C57BL/6 mice (rsCD8+T-cells). The rsCD8+T-cells were able to migrate to lung and were more resistant after the exhaustion in vitro in comparison with naïve sCD8+T-cells. In the orthotopic LLC model, the rsCD8+T-cells therapy increased the amount of proliferating CD8+ and CD4+ T-cells in blood and lung from mice. The amount of CSC decreased in the blood and lung of mice treated with rsCD8+ T-cells. A morphological study revealed a decrease in the number of metastases in lung tissue. The antitumor effects of rsCD8+T-cells are based on the activation of the host immune response by increasing the populations of CD8+ and CD4+ T-cells and apoptosis of CSCs.

Uncontrolled and fast cell proliferation is the cause of brain tumors. Early cancer detection is vitally important in order to save many lives. Brain tumors can be divided into several categories depending on the kind, place of origin, pace of development, and stage of progression; as a result, tumor classification is crucial for targeted therapy. The aim of brain tumor segmentation is to accurately delineate the areas of the brain. A specialist with a thorough understanding of brain illnesses must manually identify the proper type of brain tumor. Additionally, processing a lot of images takes time and is tiresome. Therefore, automatic segmentation and classification techniques are required to speed up and enhance the diagnosis of brain tumors. Tumors can be quickly and safely detected by brain scans using imaging modalities, including computed tomography (CT), magnetic resonance imaging (MRI), and others. Machine learning (ML) and artificial intelligence (AI) have shown promise in the development of algorithms that aid in automatic classification and segmentation utilizing various imaging modalities. This review discussed various types of brain tumors, publicly accessible datasets, enhancement methods, segmentation, feature extraction, classification, machine learning techniques, and deep learning, learning through transfer, for the study of brain tumors.

Foraminifera are single-celled marine organisms that construct shells that remain as fossils in the marine sediments. Classifying and counting these fossils are important in e.g. paleo-oceanographic and -climatological research. However, the identification and counting process has been performed manually since the 1800s and is laborious and time-consuming. In this work, we present a deep learning-based instance segmentation model for classifying, detecting, and segmenting microscopic foraminifera. Our model is based on the Mask R-CNN architecture, using model weight parameters that have learned on the COCO detection dataset. We use a fine-tuning approach to adapt the parameters on a novel object detection dataset of more than 7000 microscopic foraminifera and sediment grains. The model achieves a (COCO-style) average precision of 0.78±0.00 on the classification and detection task, and 0.80±0.00 on the segmentation task. When the model is evaluated without challenging sediment grain images, the average precision for both tasks increases to 0.84±0.00 and 0.86±0.00, respectively. Prediction results are analyzed both quantitatively and qualitatively and discussed. Based on our findings we propose several directions for future work, and conclude that our proposed model is an important step towards automating the identification and counting of microscopic foraminifera.

With the rapid development of smart phones, tablets and their operative systems, many positioning enabled sensors have been built into these devices. Users can now accurately fix their location according to the function of GPS receivers. For indoor environments, as in the case we are studying, WiFi based positioning is preferred to GPS due to the attenuation or obstruction of signals. This paper deals with the automatic classification of customers in a Sports Shop Center on the basis of their movements around the shop's premises. To achieve this goal, we start by collecting (x,y) coordinates from customers while they visit the store. Consequently, any costumer's path through the shop is formed by a list of coordinates, obtained with a frequency of one measurement per minute. Then, a guess about the full trajectory is constructed and a number of parameters about these trajectories is calculated before performing an Unsupervised Learning Clustering Process. As a result, we can identify several types of customers, and the dynamics of their behavior inside the shop. This information is of great value to the company, to be used both in the long term and also in short periods of time, monitoring the current state of the shop at any moment, identifying different types of situation appearing during restricted periods, or predicting customer flow conditions

Despite the recent availability of immune checkpoint inhibitors, not all patients affected by Non-Small Cell Lung Cancer (NSCLC) benefit from immunotherapy. The reason for this variability relies to a variety of factors which may allow the identification of novel biomarkers. Presently, a variety of biomarkers are under investigation, including the PD1/PDL1 axis, the tumor mutational burden, and the Microbiota. This latter is made by all bacteria and other microorganisms hosted in our body. The gut microbiota is the most represented and has been involved in different physiological and pathological events, including cancer. In this light, it appears that all conditions modifying gut microbiota can influence cancer, its treatment, and its treatment-related toxicities. The aim of this review is to analyze all conditions influencing the gut microbiota and, therefore, affecting response to immunotherapy, iRAEs and their management in NSCLC patients. The investigation of the landscape of these biological events can allow novel insights for optimal management of NSCLC immunotherapy.

This purpose of the study presented in this article is to comparing different service quality measurements between Kano and TRIZ that plays the critical roles in the catering industrial. Data collected from a DINESERV questionnaire comprises service-quality standards to increase customer satisfaction of mobile dining car. Finally, the TRIZ is standardized measure designed to improve the idealization of strategy for selecting the most appropriate service quality model. In addition, the preferences of more than one decision maker are internally aggregated into the TOPSIS procedure. All these things provide several important theoretical and practical implications for developing a successful mobile catering app.

Several Lung diseases can result in lung damage structural changes, with lung transplantation as a only therapeutic option when the disease reaches an advanced progression, unfortunately, the success of lung transplantation is limited. In this context, lung bioengineering is considered a potential therapeutic alternative and the current approach is based on the use of the natural extracellular matrix (ECM) of the decellularized lung. The use of undifferentiated cells to seed an ECM can be a more practical strategy for lung bioengineering but the sterilization of the organ for this recellularization process is still a challenge. In this sense, Low-Level Laser Therapy (LLLT) can emerge as a potential treatment alternative. Therefore, the objective of this study was to verify if LLLT, can optimize lung recelularization with mesenchymal stem cells by cytokine modulation. For this, we decellularized lungs from C57BL/6 mice perfusing SDS 1% via pulmonary artery, sterilized with LLL (660nm, 100mW, 30s). Whole lung scaffolds were recellularized: (1) Recellularized Lung (2) Recellularized Lung + LLLT. Mesenchymal stem cells derived from human tooth pulp (DPSc) were seeded into lungs and incubated for 24 hours at 37ºC, 5% CO₂, in a bioreactor-like conditions, maintaining CPAP at 20cmH2O, 90% O2, and LLL at wavelength of 808nm, 100mW, 30s. Culture medium were analyzed at 24 hours. H&amp;E, immunostaining, SEM and ELISA assay were performed. We produced viable biological scaffolds absent of DNA content, preserving glycosaminoglycans and collagen I, III and IV, fibronectin, laminin and elastin and lung structure (SEM). The levels of IL-6 and IL-8 were stable during the 24 hours of culture. IFN-γ levels showed significant difference in the DPSc and DPSc+LLLT group in the 24-hour evaluation. The levels of IL-10 decreased after LLLT. These findings highlight LLLT's role in cytokine regulation and contamination prevention during lung recellularization with mesenchymal stem cells. Overall, these results demonstrated that LLLT's modulated cytokine levels and could prevent contamination during the lung recellularization process with mesenchymal stem cells, offering promise for enhanced therapeutic strategies in lung bioengineering.

Despite the development of targeted therapeutics, immunotherapy, and strategies for early detection, lung cancer carries a high mortality. Further, significant racial disparities in outcomes exist for which the molecular drivers have yet to be fully elucidated. The growing field of Epitranscriptomics has introduced a new layer of complexity to the molecular pathogenesis of cancer. RNA modifications can occur in coding and non-coding RNAs, such as miRNAs, possibly altering their gene regulatory function. The potential role for such modifications as clinically informative biomarkers remains largely unknown. Here, we concurrently profiled canonical miRNAs, shifted isomiRs (templated and non-templated), miRNAs with single-point modification events (RNA and DNA) in White American (W) and Black or African American (B/AA) lung adenocarcinoma (LUAD) patients. We found that while most deregulated miRNA isoforms were similar in W and B/AA LUAD tissues compared to normal adjacent tissues, there was a subgroup of isoforms with deregulation according to race. We specifically investigated an edited miRNA, miR-151a-3p with an A-to-I editing event at position 3, to determine how its altered expression may be associated with activation of divergent biological pathways between W and B/AA LUAD patients. Finally, we identified distinct race-specific miRNA isoforms that correlated with prognosis for both Ws and B/AAs. Our results suggest that concurrently profiling canonical and non-canonical miRNAs may have potential as a strategy for identifying additional distinct biological pathways and biomarkers in lung cancer.

Lung cancer is the leading cause of cancer related mortality worldwide. In order to improve its overall survival, early diagnosis is required. Since current screening methods still face some pitfalls, such as high false positive rates for low-dose computed tomography, researchers are still looking for early biomarkers to complement existing screening techniques in order to provide a safe, faster and more accurate diagnosis. Biomarkers are biological molecules found in body fluids, such as plasma, that can be used to diagnose a condition or disease. Metabolomics has already shown to be a powerful tool in the search for cancer biomarkers since cancer cells are characterised by impaired metabolism, resulting in an adapted plasma metabolite profile. The metabolite profile can be determined using nuclear magnetic resonance, or NMR. Although metabolomics and NMR metabolite profiling of blood plasma are still under investigation, there is already evidence for its potential for early-stage lung cancer diagnosis, therapy response, and follow-up monitoring. This review highlights some key breakthroughs in this research field, where the most significant biomarkers will be discussed in relation with their metabolic pathways and in light of the altered cancer metabolism.

To understand lung damage caused by COVID-19, we deduced two-phase lung damage mechanisms. After the lungs are infected with SARS-CoV-2 virus, the affected lung tissue swells and surface properties of pulmonary capillaries change, resulting in an increased flow resistance of affected capillaries. If a sufficient number of capillaries are affected by the infection, the swelling and increased cell wall adhesion collectively raise pulmonary vascular resistance. The increased vascular resistance further increases the dwell times of WBCs in affected capillaries and nearly capillaries. When pulmonary pressure is sufficiently higher, WBCs are forced to squeeze into interstitial spaces or alveolar spaces when local pressures are higher than what the capillaries can withstand. When more and more WBCs are dynamically retained, the flow resistance of more capillaries rises, pulmonary vascular resistance rises, and pulmonary pressure rises. The rise in the pulmonary pressure in turn results in elevated capillary pressures. When capillary pressures around the alveoli are sufficiently high, they cause interstitial pressures to change from normally negative values to positive values. The positive pressures cause fluid leakage to the alveolar space and thus degrade lung function. Tissue swelling, and occupation of WBCs in interstitial spaces and alveolar spaces further reduce compressible volume, and thus cause further rise in the pulmonary vascular resistance and pulmonary pressure. When the pulmonary pressure has reached a critical point as in the second phase, the blood breaks capillary walls and squeezes through interstitial spaces to reach alveolar spaces, resulting in irreversible lung damages. The available free volume in the thorax cage, organ usable capacities, temperature and humid are expected to have great impacts on degree of lung damages. The free volume in the thorax cage, lung usable surplus capacity, and other organ usable capacities determine the arrival time of last-phase irreversible damage. The mechanisms imply that the top priority for protecting lungs is maintaining pulmonary micro-circulation and preserving organ functions in the entire disease course while controlling viral reproduction should be stressed in the earliest time possible. The mechanisms also explain leukecytes are recruited and migrated into inflamed tissues by increasing their dwell times caused by increased local flow resistance.

Iron plays a critical role in lung infections due to its function in the inflammatory immune response but also as an important factor for bacterial growth. Iron chelation represents a potential therapeutic approach to inhibit bacterial growth and pathologically increased pro-inflammatory mediator production. The present study was designed to investigate the impact of the iron chelator, DIBI, in murine lung infection induced by intratracheal Pseudomonas aeruginosa (strain PA14) administration. DIBI (80mg/kg) was given by intraperitoneal injection either as a single dose immediately after PA14 administration or a double dose (second dose 4 h after PA14 administration). The results showed that lung NF-κBp65 levels, as well as levels of various inflammatory cytokines (TNFα, IL-1β, IL-6) both in lung tissue and bronchoalveolar lavage fluid (BALF), were significantly increased 24h after PA14 administration. Single-dose DIBI did not affect the bacterial load or inflammatory response in the lungs or BALF. However, two doses of DIBI significantly decreased bacterial load, attenuated NF-κBp65 upregulation, reduced inflammatory cytokines production, and relieved lung tissue damage. Our findings support the conclusion that the iron chelator, DIBI, can reduce lung injury induced by P. aeruginosa, via its anti-bacterial and anti-inflammatory effects.

Pepper leaf segmentation plays a crucial role in monitoring pepper leaf diseases in various backgrounds and ensuring the healthy growth of peppers. However, existing transformer-based segmentation methods suffer from computational inefficiency, excessive parameterization, and limited utilization of edge information. To tackle these challenges, we propose an adaptive multi-scale MLP framework, named AMS-MLP, which combines the multi-path aggregation module (MPAM) and the multi-scale context relation mask module (MCRD) to refine the object boundaries in pepper leaf segmentation. AMS-MLP consists of an encoder-based network, an adaptive multi-scale MLP (AM-MLP) module, and a decoder network. In the encoder network, the MPAM module effectively fuses five-scale features to generate a single-channel mask, improving the accuracy of pepper leaf boundary extraction. The AM-MLP module divides the input features into two branches: the global multi-scale MLP branch captures long-range dependencies between image information, while the local multi-scale MLP branch focuses on extracting local feature maps. Adaptive attention mechanism is designed to dynamically adjust the weights of global and local features. The decoder network incorporates the MCRD module into the convolutional layer, enhancing the extraction of boundary features. To verify the performance of the proposed method, we conducted extensive experiments on three pepper leaf datasets with different backgrounds. The results demonstrate mIoU scores of 97.39%, 96.91%, and 97.91%, as well as F1 scores of 98.29%, 97.86%, and 98.51%, respectively. Comparative analysis with U-Net and state-of-the-art models reveals that the proposed method dramatically improves the accuracy and efficiency of pepper leaf image segmentation.

Purpose Radiotherapy is integral in the management of hematological malignancies (HM). Standard radiotherapy dose fractionation regimens range between 20-50 Gy in 10-25 fractions over 2-5 weeks. This study presents the outcomes of patients with HM treated with hypofractionation radiotherapy (HFRT) during the COVID-19 pandemic. Methods Patients (N=36) were treated with HFRT between January 2020 and September 2022. The outcomes measured were the overall response rate (ORR), freedom from local progression (FFLP), and overall survival (OS). Results Median follow-up was 13.2 months. Thirty-three patients (92%) had non-Hodgkin (NHL) or Hodgkin lymphoma (HL). Eighteen patients (50%) had aggressive and 9 (25%) had indolent NHL. Nineteen patients (53%) presented with stage I/II and 15(42%) with stage III/IV disease. Twenty-five (69.4%) and eleven (30%) received consolidative and definitive RT, respectively. Twenty patients (56%) received treatment to the neck and/or thorax, and 9 (25%) to the abdomen or pelvis. Total dose ranged from 18 to 42.5 Gy in 6-17 fractions/ 2.67-5 Gy per fraction. Median dose in 2 Gy fractions for an alpha/beta (α/β) ratio of 10 amounted to 39 Gy (SD ± 13.86), and 43.6 Gy (SD ± 12) for an α/β of 3. The most commonly used fractionation scheme was 39 Gy in 13 fractions. ORR was 94.4% for the entire cohort, and 100, 94.4, and 83.3% for indolent NHL, aggressive NHL, and HL patients. Two-year FFLP was 76% (95% CI: 34-93%) for the entire cohort, and 100, 87 (95%CI: 56.4-96.5%) and 42% (95% CI: 1.1-84.3%) for the indolent NHL, aggressive NHL, and HL patients. Two-year OS for the entire cohort was 80% (95% CI:59.9-90.5%), and 100, 66.1 (95% CI: 36.4-84.4%) and 100% for the indolent NHL, aggressive NHL, and HL patients. Only one patient presented with grade two pulmonary toxicity. Conclusion HFRT in HM provides excellent local control without any increase in toxicity.

A single paragraph of about 200 words maximum. For research articles, abstracts should give a pertinent overview of the work. We strongly encourage authors to use the following style of structured abstracts, but without headings: (1) Background: place the question addressed in a broad context and highlight the purpose of the study; (2) Methods: describe briefly the main methods or treatments applied; (3) Results: summarize the article’s main findings; (4) Conclusions: indicate the main conclusions or interpretations. The abstract should be an objective representation of the article, it must not contain results which are not presented and substantiated in the main text and should not exaggerate the main conclusions.

Anomaly detection and segmentation aim at distinguishing abnormal images from normal images and further localizing the anomalous regions. Feature reconstruction based method has become one of the mainstream methods for this task. This kind of method has two assumptions: (1) The features extracted by neural network is a good representation of the image. (2) The autoencoder solely trained on the features of normal images cannot reconstruct the features of anomalous regions well. But these two assumptions are hard to meet. In this paper, we propose a new anomaly segmentation method based on feature reconstruction. Our approach mainly consists of two parts: (1) We use a pretrained vision transformer (ViT) to extract the features of the input image. (2) We design a self-attention autoencoder to reconstruct the features. We regard that the self-attention operation which has a global receptive field is beneficial to the methods based on feature reconstruction both in feature extraction and reconstruction. The experiments show that our method outperforms the state-of-the-art approaches for anomaly segmentation on the MVTec dataset. It is both effective and time-efficient.

The problem of event detection in general noisy signals arises in many applications; usually, either a functional form for the event is available, or a previous annotated sample with instances of the event that can be used to train a classification algorithm. There are situations, however, where neither functional forms nor annotated samples are available; then it is necessary to apply other strategies to separate and characterize events. In this work, we analyze 15 minute-long samples of an acoustic signal, and are interested in separating sections, or segments, of the signal which are likely to contain significative events. For that, we apply a sequential algorithm with the only assumption that an event alters the energy of the signal. The algorithm is entirely based on Bayesian methods.

Abstract: Lung cancer, characterized by its heterogeneity, presents a significant challenge in ther-apeutic management, primarily due to the development of resistance to conventional drugs. This resistance is often compounded by the tumour’s ability to reprogram its metabolic pathways, a survival strategy that enables cancer cells to thrive in adverse conditions. This review article ex-plores the complex link between drug resistance and metabolic reprogramming in lung cancer, offering a detailed analysis of the molecular mechanisms and treatment strategies. It emphasizes the interplay between drug resistance and changes in metabolic pathways, crucial for developing effective lung cancer therapies. The review examines the impact of current treatments on metabolic pathways and the significance of considering metabolic factors to combat drug resistance. It highlights the different challenges and metabolic alterations in non-small cell lung cancer and small cell lung cancer, underlining the need for subtype-specific treatments. Key signalling pathways, including PI3K/AKT/mTOR, MAPK, and AMPK, have been discussed for their roles in promoting drug resistance and metabolic changes, alongside the complex regulatory networks involved. The article evaluates emerging treatments targeting metabolism, such as metabolic inhibitors, dietary management, and combination therapies, assessing their potential and challenges. It concludes with insights into the role of precision medicine and metabolic biomarkers in crafting personalized lung cancer treatments, advocating for metabolic targeting as a promising approach to enhance treatment efficacy and overcome drug resistance. The review underscores ongoing advancements and hurdles in integrating metabolic considerations into lung cancer therapy strategies.

Land cover mapping, essential for understanding global land use patterns, relies on satellite imagery for monitoring changes, assessing ecosystem health, and supporting conservation ef- forts. However, significant challenges remain in managing large, complex satellite imagery datasets, acquiring specialized datasets due to high costs and labor intensity, and a lack of comparative studies for optimal deep learning model selection. Additionally, a scarcity of aerial datasets specifically tailored for agricultural areas exists. This study addresses these gaps by presenting a method for semantic segmentations of land covers in agricultural areas using satellite images and deep learning models with pre-trained backbones. We introduce an efficient methodology for preparing semantic segmentation datasets and contribute the "Land Cover Aerial Imagery" (LICAID) dataset for semantic segmentation. The study focuses on the Franciacorta area, Lombardy Region, leveraging the rich diversity of the dataset to effectively train and evaluate the models. We conduct a comparative study, employing cutting-edge deep learning-based segmentation models (U-Net, SegNet, DeepLabV3) with various pre-trained backbones (ResNet, Inception, DenseNet, EfficientNet) on our dataset acquired from Google Earth Pro. Through meticulous data acquisition, preprocessing, model selection, and evaluation, we demonstrate the effectiveness of these techniques in accurately delineating land cover classes. Integrating pre-trained feature extraction networks significantly improves performance across various metrics. Additionally, addressing challenges such as data availability, computational resources, and model interpret-ability is essential for advancing the field of remote sensing and supporting sustainable environmental stewardship worldwide.

White matter hyperintensity (WMH) has been considered the primary biomarker from small-vessel cerebrovascular disease to Alzheimer’s disease (AD) and has been reported for its correlation of brain structural changes. To perform WMH related analysis with brain structure, both T1-weighted (T1w) and (Fluid Attenuated Inversion Recovery(FLAIR) are required. However, in a clinical situation, it is limited to obtain 3D T1w and FLAIR images simultaneously. Also, the most of brain segmentation technique supports 3D T1w only. Therefore, we introduced the semi-supervised learning method that can perform brain segmentation using FLAIR image only. Our method achieved a dice overlap score of 0.86 for brain tissue segmentation on FLAIR, with the relative volume difference between T1w and FLAIR segmentation under 4.8%, which is just as reliable as the segmentation done by its paired T1w image. We believe our semi-supervised learning method has a great potential to be used to other MRI sequences and provide encouragement to people who seek brain tissue segmentation from a non-T1w image.

Driven by the importance of early detection for improving patient outcomes, this study investigates the effectiveness of various machine learning algorithms in predicting lung cancer based on clinical data. Lung cancer remains a significant global health concern, and this research seeks to contribute to advancements in early diagnosis through the application of machine learning techniques. The dataset consists of 385 training and 97 test samples, with a k-fold cross-validation approach (k=5) utilized to mitigate overfitting. Additionally, the ADASYN oversampling technique is employed to address class imbalance. Our analysis includes traditional algorithms such as Logistic Regression and Decision Trees, as well as ensemble methods like XGBoost, LGBM, and AdaBoost. Furthermore, we explore the effectiveness of deep learning models, particularly Deep Neural Networks (DNN). Results demonstrate promising accuracy rates across all models, with some outperforming others in terms of precision, recall, and F1-score. Our findings reveal that LGBM achieves the highest accuracy among all models, with an accuracy rate of 96.91%. It also exhibits superior performance in terms of precision, recall, and F1-score, particularly in classifying both positive and negative instances of lung cancer.

Purpose: Carotid intraplaque hemorrhage (IPH) increases risk of territorial cerebral ischemic events, but different sequences or criteria have been used to diagnose or quantify carotid IPH. The purpose of this study was to compare manual segmentation and semi-automatic segmentation for quantification of carotid IPH on magnetization-prepared rapid acquisition with gradient-echo (MPRAGE) sequences. Methods: Forty patients with 16–79% carotid stenosis and IPH on MPRAGE sequences were reviewed by two trained radiologists with more than five years of specialized experience in carotid plaque characterization with carotid plaque MRI. Initially, the radiologists manually viewed the IPH based on the MPRAGE sequence. IPH volume was then measured by three different semi-automatic methods, with high signal intensity 150%, 175%, and 200%, respectively, above that of adjacent muscle on the MPRAGE sequence. Agreement on measurements between manual segmentation and semi-automatic segmentation was assessed using the intraclass correlation coefficient (ICC). Results: There was near-perfect agreement between manual segmentation and the 150% and 175% criteria for semi-automatic segmentation in quantification of IPH volume. The ICC of each semi-automatic segmentation were as follows: 150% criteria: 0.861, 175% criteria: 0.809, 200% criteria: 0.491. The ICC value of manual vs. 150% criteria and manual vs. 175% criteria were significantly better than the manual vs. 200% criteria (p < 0.001). Conclusions: The ICC of 150% and 175% criteria for semi-automatic segmentation are more reliable for quantification of IPH volume. Semi-automatic classification tools may be beneficial in large-scale multicenter studies by reducing image analysis time and avoiding bias between human reviewers.

Lung cancer remains the main cause of global cancer-related deaths. Currently low-dose computed tomography (LD-CT) shows a 20% reduction of mortality. However, its clinical suitability is hindered by cost, radiation, and some false positives. Thus, the discovery non-invasive and less-expensive biomarker is urgent needed. In this scenario, proteins released in biological fluids could be considered interesting biomarkers for their role in cancer development. We conducted a pioneering case-control pilot study aimed at assessing the usefulness of Raf Kinase Inhibitory Protein (RKIP) and its phosphorylated form (pRKIP) as potential early-stage lung cancer biomarkers. Urine and Blood samples of two consecutive and independent cohorts of lung cancer patients and healthy controls were screened by means of a novel experimental ELISA assay designed to evaluate both forms of the biomarker. Although urinary levels of RKIP were not statistically different between the lung cancer group and high-risk healthy group, serum ones instead increased significantly in early stage LC patients and permitted to discriminate LC patients from both low-risk (HS) and high-risk healthy subjects (HR-HS) with an overall 93% accuracy (AUC 0.93) when LC was compared to HS and 74% (AUC 0.73) when it was compared to high-risk group. Of note, the analysis of RKIP/pRKIP ratio also showed a high accuracy (90% - AUC 0.95) in discriminating LC patients from HS and more importantly, it allowed to identify LC patients compared to HR-HS, with a higher accuracy (79% - AUC 0.79) than RKIP alone. We hypothesize that serum RKIP levels may be correlated to the activation of the immune systems against the tumor during the first phases of its development. Our study identified a preliminary, non-invasive, RKIP and pRKIP profile able to discriminate with high specificity and sensitivity the early-stage lung cancer patients from high-risk Healthy Subjects. These results, although preliminary, suggest the utility of measuring RKIP/pRKIP as potential new screening test for lung cancer and provide the basis for future validation studies.

Mechanical ventilation (MV), used in patients with acute lung injury (ALI), induces diaphragmatic myofiber atrophy and contractile inactivity, termed ventilator-induced diaphragm dysfunction. Phosphoinositide 3-kinase- (PI3K-) is crucial in modulating fibrogenesis during the reparative phase of ALI; however, the mechanisms regulating the interactions among MV, myofiber fibrosis, and PI3K- remain unclear. We hypothesized MV with or without bleomycin treatment would increase diaphragm muscle fibrosis through the PI3K- pathway. Five days after receiving a single bolus of 0.075 units bleomycin intratracheally, C57BL/6 mice were exposed to 6 or 10 mL/kg MV for 8 h after receiving 5 mg/kg of AS605240 intraperitoneally. In wild-type mice, bleomycin exposure followed by MV 10 mL/kg prompted significant increases in disruptions of diaphragmatic myofibrillar organization, transforming growth factor-1, oxidative loads, Masson’s trichrome staining, extracellular collagen levels, positive staining of -smooth muscle actin, PI3K- expression, and myonuclear apoptosis (P &lt; 0.05). Decreased diaphragm contractility and peroxisome proliferator activated receptor- coactivator-1 levels were also observed (P &lt; 0.05). MV-augmented bleomycin-induced diaphragm fibrosis and myonuclear apoptosis were attenuated in PI3K-γ-deficient mice and through AS605240-induced inhibition of PI3K- activity (P &lt; 0.05). MV-augmented diaphragm fibrosis after bleomycin-induced ALI is partially mediated through PI3K-γ. Therapy targeting PI3K-γ may ameliorate MV-associated diaphragm fibrosis.

Interaction between multiple phases especially liquid-gas is one of the most common phenomena in industrial systems. Computer Vision enables modern systems to derive an automated and robust image-processing technique to address this issue. However, diverse experimental conditions still make it a challenging task to overcome. In Deep Learning, instance segmentation has created a niche in various computer vision applications as it aims to provide different instance IDs to objects belonging to the same class. In this paper, we propose a novel approach employing the YOLO (You Look Only Once) an end-to-end deep learning architecture for the detection and segmentation of bubbles in fluid flows. YOLOv5 offers significant improvements in both speed and accuracy compared to its predecessors like YOLOv3. Therefore, we train the YOLOv5 network on a dataset consisting of annotated images representing instances of bubbles across varied fluid flow environments. This paper provides both qualitative and quantitative evaluation of three YOLOv5 networks (small, medium, and extra-large) in detecting and segmenting bubbles with high accuracy and efficiency. Based on the metrics all three YOLOv5 models achieved high precision above 0.98 for bounding box detection and 0.97 for segmentation mask, and high recall value greater than 0.97 for box and 0.96 for mask quality was achieved. The achieved results indicate that the models accurately localize bubbles within the image frame, and distinguish bubble pixels from the background. Also, mean average precision (mAP50-95) consistently exceeds 0.84 across all models for the bounding box and 0.73 for the segmentation mask. The ascertained results emphasize the potential of YOLOv5 architecture as a powerful tool for automated bubble analysis in real-world applications. Our research contributes to advancing the field of deep neural networks in fluid systems and provides a fresh approach for future developments in automated bubble analysis.

One of the most leading causes of death worldwide is Colorectal cancer(CRC). Polyp segmentation is the most important detected measure for preventing CRC. However, there is still a missing rate for diminutive polyps and multiple ones. In order to solve the phenomenon, we propose to introduce auxiliary attention module(AAM) that can enhance the learning of features related to multiple and diminutive polyps by focusing more on the located and detailed information. Meanwhile, we design to decrease missed rate of multiple and diminutive polyps by implementing an area adaptive loss(AAL) which adapts the weight according to the area and the number of polyps. Our proposed novel AAM and AAL concentrates on training with hard examples and localized information. To evaluate the effectiveness and generalization ability of our proposed model, We utilize three different datasets of variable sizes and a cross dataset. Our proposed method achieves the best results on the Kvasir-SEG dataset, the CVC-ClinicDB dataset and the cross dataset, particularly for the Kvasir-Sessile dataset consisting of small,flat and diminutive polyps. Extensive experimental results show that our proposed DoubleAANet surpass the performance of all existing state-of-the-art segmentation methods.

In the realm of computer vision, semantic segmentation is the task of recognizing objects in images at the pixel level. This is done by performing a classification of each pixel. The task is complex and requires sophisticated skills and knowledge about the context to identify objects’ boundaries. The importance of semantic segmentation in many domains is undisputed. In medical diagnostics, it simplifies the early detection of pathologies, thus mitigating the possible consequences. In this work, we provide a review of the literature on deep ensemble learning models for polyp segmentation and we develop new ensembles based on convolutional neural networks and transformers. The development of an effective ensemble entails ensuring diversity between its components. To this end, we combine different models (HarDNet-MSEG, Polyp-PVT, and HSNet) trained with different data augmentation techniques, optimization methods, and learning rates, which we experimentally demonstrate to be useful to form a better ensemble. Most importantly, we introduce a new method to obtain the segmentation mask which is more suitable for combining transformers in an ensemble. In our extensive experimental evaluation, the proposed ensembles exhibit state-of-the-art performance.

Current bridge inspection practices rely on paper-based data acquisition, digitization, and multiple conversions in between incompatible formats to facilitate data exchange. This practice is time-consuming, error-prone, cumbersome, and leads to information loss. One aim for future inspection procedures is to have a fully digitized workflow that achieves loss-free data exchange, which lowers costs and offers higher efficiency. On the one hand, existing studies proposed methods to automatize data acquisition and visualization for inspections. These studies lack an open standard to make the gathered data available for other processes. On the other hand, several studies discuss data structures for exchanging damage information through out different stakeholders. However, those studies do not cover the process of automatic data acquisition and transfer. This study focused on a framework that incorporates automatic damage data acquisition, transfer, and a damage information model for data exchange. This enables inspectors to use damage data for subsequent analyses and simulations. The proposed framework shows the potentials for a comprehensive damage information model and related (semi-)automatic data acquisition and processing.

The artificial intelligence (AI) is a machine or computing platform that is capable of making intelligent decision similarly to the human mind. The AI could improve diagnosis, treatment prognosis, and clinical workflow, particularly in the field of radiology. Concerning acute respiratory distress syndrome (ARDS) is a rather heterogeneous syndrome characterized by an inflammatory lung edema leading to an increased lung weight, decreased lung aeration with the presence of alveolar collapse and interstitial opacities mainly in the dependent area. Thus, lung imaging is an essential tool to assess not only the morphology but also the mechanical characteristics of ARDS patients. Chest computed tomography (CT) and ultrasound have a higher sensitivity and specificity than conventional chest radiography. This narrative review summarizes the state of art of AI in the field of lung imaging, focusing on CT and ultrasound technique in ARDS patients. A total number of 18 articles were retrieved. The application of AI in lung imaging was mainly devoted to assess the prediction of ARDS, the quantification of alveolar recruitment, the possible alternative diagnosis and the outcome. Although the presence of a physician is still essential to ensure a high quality of examinations the AI could assist the clinical team to provide the best possible care.

Diseases of the lung account for more than 5 million deaths worldwide and are a burden to healthcare. Improving clinical outcomes including mortality and quality of life involves a holistic understanding the etiopathogenesis, which can be provided by multi-omics integration of lung data. An enhanced understanding of large comprehensive datasets provides opportunities to mine those datasets for features that contribute to prevention and amelioration of disease. In this review, we evaluate lung disease models including animal models, organoids and single cell lines as mechanisms to study multiomics in lung health and disease. We provide examples of lung diseases where multi-omics investigations have provided a deeper insight into pathogenesis that has resulted in improved preventive and therapeutic interventions.

Heat dissipation from Li-ion batteries is a potential safety issue for large-scale energy storage applications. Maintaining low and uniform temperature distribution, and low energy consumption of the battery storage is very important. We studied the fluid dynamics and heat transfer phenomena of a single cell, 16-cell modules, battery packs, and cabinet through computer simulations and experimental measurements. The results show that the temperature distribution of single cell is relatively uniform when the cell is facing the air flow. In a module, very high air flow rate and large gap between the cells can reduce the cell temperature. A pack with a good thermally conductive case is very important to ensure good heat dissipation of the battery module. Due to limited space in the cabinet, additional air inlets and outlets can be opened outside of the cabinet to slightly lower the pack temperature. Installing fins outside the cabinet can also slightly reduce the temperature inside the cabinet. Liquid cooling medium, such as water, is much better than the air-cooling medium.

Identification and segmentation of rock particles is very important in geology, mining, engineering construction, and environmental monitoring. Traditional methods for recognizing the rock particle characteristics are time-consuming, labor-intensive, and limited by the geographical scope of the sampling sites, which makes it more difficult to represent the spatial distribution of the rock particles accurately. Recent advancements in deep learning techniques offer promising solutions to automate this process. This study aims at utilizing state-of-the-art (SOTA) Mask R-CNN deep learning algorithm from the Detectron2 framework, to capture global features of rocks that will enable the recognition of rock particles more efficiently, just from having the rock images. These images are subject to image processing techniques such as a Gaussian filter, to denoise and smoothen the image, and an Illumination Adaptive Transformer (IAT) framework, to adjust the lighting exposure; all of which add to improve the quality of the image dataset. Afterward, the Mask R-CNN and Detectron2 models are utilized in training the images using transfer learning. Experimental results from evaluating the performance of the proposed algorithms showcase the effectiveness of the approach, thereby highlighting its potential to revolutionize rock particle segmentation across various domains.

Nowadays, semantic segmentation is increasingly used in exploration by underwater robots, for example in autonomous navigation, so that the robot can recognise the nature and elements of its environment during the mission and act according to this classification to avoid collisions. Other applications can be found in the search for archaeological artefacts, in the inspection of underwater structures or in species monitoring. Therefore, it is necessary to try to improve the performance in these tasks as much as possible. To this end, we compare some methods for improving image quality and for data augmentation and test whether higher performance metrics can be achieved with both strategies. The experiments are performed with the SegNet implementations and the SUIM dataset with 8 common underwater classes to compare the obtained results with the already known ones. The results obtained with both strategies show that they are beneficial and lead to better performance results by achieving a mean IoU of 56% and an increased overall accuracy of 81.8%. The single result shows that there are 5 classes with an IoU value above 60% and only one class with an IoU value below 30%, which is a more reliable result and easier to use in real contexts.