Two-dimensional ultrasound (2D US) is commonly used in clinical settings for its cost-effectiveness and non-invasiveness, but it is limited by spatial orientation and operator dependency. Three-dimensional ultrasound (3D US) overcomes these limitations by adding a third dimension and enhancing integration with other imaging modalities. Advances in deep learning (DL) have further propelled the viability of freehand image-based 3D reconstruction, broadening clinical applications in intraoperative and point-of-care (POC) settings. This review evaluates state-of-the-art freehand 3D US reconstruction methods that eliminate the need for external tracking devices, focusing on experimental setups, data acquisition strategies, and reconstruction methodologies. PubMed, Scopus, and IEEE Xplore were searched for studies since 2014 following PRISMA guidelines, excluding those using additional imaging or tracking systems other than inertial measurement units (IMUs). Fourteen eligible studies were analyzed, showing a shift from traditional speckle decorrelation towards DL-based methods, particularly Convolutional Neural Networks (CNNs). Variability in datasets and evaluation methods hindered a comprehensive quantitative comparison, but notable accuracy improvements were observed with IMUs and integration of contextual and temporal information within CNNs. These advancements enhance freehand 3D US reconstruction feasibility, though variability limits definitive conclusions about the most effective methods. Future research should focus on improving precision in complex trajectories and adaptability across clinical scenarios.

An improved anti-noise morphology vision navigation algorithm is proposed for intelligent tractor tillage in a complex agricultural field environment. At first the two key steps, Guided Filtering and improved anti-noise morphology navigation line extraction were addressed in detail. Then the experiments were carried out in order to verify the effectiveness and advancement of the presented algorithm. Finally, the optimal template and it’s application condition were studied for improving the image processing speed. The comparison experiment results show that the YCbCr color space has minimum time consumption of 0.094 s in comparison with HSV, HIS and 2R-G-B color spaces. The Guided Filtering method can effectively distinguish the boundary between the new and old soil than other competing vanilla methods such as Tarel, Multi-scale Retinex, Wavelet-based Retinex and Homomorphic Filtering inspite of having the fastest processing speed of 0.113 s. The extracted soil boundary line of the improved anti-noise morphology algorithm has best precision and speed compared with other operators such as Sobel, Roberts, Prewitt and Log. After comparing different size of image template, the optimal template with the size of 140×260 pixels can meet high precision vision navigation while the course deviation angle is not more than 7.5°. The maximum tractor speed of the optimal template and global template are 51.41 km/h and 27.47 km/h respectively which can meet real-time vision navigation requirement of the smart tractor tillage operation in the field. The experimental vision navigation results demonstrated the feasibility of the autonomous vision navigation for tractor tillage operation in the field using the new and old soil boundary line extracted by the proposed improved anti-noise morphology algorithm which has broad application prospect.

This review provides an overview of eXplainable AI (XAI) methods for oncological ultrasound image analysis and compares their performance evaluations. A systematic search of Medline Embase and Scopus between March 25 and April 14 2024 identified 17 studies describing 14 XAI methods, including visualization, semantics, example-based, and hybrid functions. These methods primarily provided specific, local, and post-hoc explanations. Performance evaluations focused on AI model performance, with limited assessment of explainability impact. Standardized evaluations incorporating clinical end-users are generally lacking. Enhanced XAI transparency may facilitate AI integration into clinical workflows. Future research should develop real-time methodologies and standardized quantitative evaluative metrics.

The foot-mounted inertial navigation system is an important application of pedestrian navigation as it in principle does not rely any external assistance. A real-time range decomposition constraint method is proposed in this paper to combine the information of dual foot-mounted inertial navigation systems. It is well known that low-cost inertial sensors with ZUPT (zero-velocity update) and range decomposition constraint perform better than in either single way. This paper recommends that the distance of separation between the position estimates of feet-mounted inertial navigation systems be restricted in the ellipsoidal constraint which relates to the maximum step and leg height. The performance of the proposed method is studied utilizing experimental data. The results indicate that the method can effectively correct the dual navigation systems’ position over the existing spherical constraint.

The popularity of handheld devices for point-of-care ultrasound (POCUS) has increased in recent years due to their portability and cost-effectiveness. However, POCUS has the drawback of lower imaging quality compared to conventional ultrasound, because of hardware limitations. Improving the quality of POCUS through post-image processing would therefore be beneficial, with deep learning approaches showing promise in this regard. This review investigates the state-of-the-art progress of image enhancement using deep learning suitable for POCUS applications. A systematic search was conducted from January 2024 to February 2024 on PubMed and Scopus. From the 457 articles that were found, the full text was retrieved for 69 articles. From this selection, 15 articles were identified addressing multiple quality enhancement aspects. A disparity in the baseline performance of the low-quality input images was seen across these studies, ranging between 8.65–29.24 dB for the Peak Signal-to-Noise Ratio (PSNR) and 0.03-0.71 for the Structural Similarity Index Measure (SSIM). In six studies, where both PSNR and the SSIM metrics were reported for the baseline and the generated images a mean difference of 6.60 (SD ± 2.99) and 0.28 (SD ± 0.15) was observed for the PSNR and SSIM, respectively. The reported performances demonstrate the potential of deep-learning-based image enhancement for POCUS. However, variability in the extent of performance gain across datasets and articles was notable, and the heterogeneity across articles makes quantifying the exact improvements challenging.

The increasing complexity and volume of job listings in the digital era necessitate advanced recommendation systems to match job seekers with suitable opportunities. This paper presents a hybrid job recommendation system that integrates Collaborative Filtering (CF) and Content-Based Filtering (CBF) to enhance recommendation accuracy and user satisfaction. The CF component leverages historical user interactions and similarities between users to suggest jobs, while the CBF component analyzes job descriptions and user profiles to provide personalized recommendations based on individual preferences and qualifications. By combining these two approaches, the proposed system mitigates the limitations of each method and offers a more comprehensive and effective solution. Experimental results on a real-world dataset demonstrate the system's improved performance in terms of precision, recall, and F1-score compared to traditional recommendation models. This study contributes to the field of job recommendation systems by providing a robust framework that effectively bridges the gap between user needs and job market opportunities.

Gene therapy is a medical approach capable of correcting genetic and epigenetic alterations in pathological conditions, including cancer. Different strategies have been pursued for cancer gene therapy, aiming to restore the function of tumor suppressor genes or inhibit oncogenes. These comprise the use of CRISPR/Cas9 gene editing technology and therapeutic oligonucleotides, such as microRNAs, anti-microRNAs, small interfering RNAs, DNAzymes, and epigenetic modifiers. However, despite great potential, their broad clinical use is hindered due to the lack of safe and efficient systems for targeted delivery to cancer cells. To this purpose, aptamers could represent an ideal tool. They are short single-stranded oligonucleotides that bind receptors selectively present or overexpressed on cancer cell membranes, often undergoing cell-specific internalization. Thanks to this last feature, numerous internalizing aptamers have been investigated as targeting moiety to deliver therapeutic oligonucleotides, viral vectors, and nanoparticle-based systems in preclinical studies. Here, we summarize the state-of-the-art of aptamer applications in cancer gene therapy, providing key examples and discussing their advantages, limitations, and clinical perspectives.

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

Due to constraints in launch platform and cost, the maneuverability of gliding-guided projectiles is limited, necessitating a rational design of their trajectory schemes. To reduce the sensitivity of trajectory schemes to uncertainties while ensuring compatibility between flight schemes and guidance control systems, and fully exploiting the control capability of the projectile, a closed-loop robust trajectory planning method is proposed. Models of major uncertain factors and states deviation at the control-start point are established. Based on the NIPCE method, the stochastic dynamic model is transformed into a high-dimensional deterministic model with PCE coefficients as state variables, and the uncertainty propagation law is obtained. A PID algorithm is employed to design a tracking guidance law based on position error feedback, and open-loop and closed-loop robust trajectory planning models are established accordingly. The optimal control problem is solved by transforming it into a nonlinear programming problem using the direct shooting method. Simulation results indicate that the NIPCE method can significantly improve the computational efficiency of uncertainty propagation while ensuring accuracy. Open-loop robust planning can effectively mitigate the sensitivity of gliding trajectories to uncertainties but cannot completely eliminate terminal dispersion. Closed-loop robust planning effectively improves control effort consumption on the basis of open-loop planning.

In modern warfare, the diversified tasks can sometimes be challenging to fulfill with a single projectile, necessitating the incorporation of cooperation constraints in trajectory planning. Limited by the stringent requirements of the launch platform and lower costs, the maneuverability and ability to adjust the flight time range of projectiles are weak. Therefore, the rationality of performance indicators and flight time coordination strategies is especially critical. To fully exploit the control capabilities of projectiles, a battlefield area segmentation method is proposed, differentiated performance indicators and a cooperative trajectory planning model that considers the entire range of projectiles are established. Considering the limitations of existing flight time coordination strategies in applications, targeted improvements have been made in different cooperation scenarios, and a bi-level adaptive cooperation strategy(BACS) with both optimality and flexibility is proposed. To rapidly determine feasible conditions, a simple and universal method for obtaining the capability ranges of cooperation is introduced. The multi-phase optimal control problems are transformed into nonlinear programming problems using the Radau pseudo-spectral method, and simulation results show that the proposed methods are capable of handling trajectory planning tasks in different cooperation scenarios. The improved strategies effectively enhance the planning success rate under relatively harsh conditions and BACS demonstrates good compatibility with the problems studied.

This paper presents a compact wideband circularly polarized cross dipole antenna with low-pass filter response. It consists of two pairs of folded crossed dipole arms printed separately on both sides of the top substrate, and the two dipole arms on the same surface are connected by an annular phase-shifting delay line to generate circular polarization. A bent metal square ring and four small metal square rings around the cross dipoles are employed to introduce new resonant frequencies, effectively extending the impedance and axial ratio bandwidth. Four square patches printed on the middle substrate are connected to the ground plane by the vertical metal plates, in order to reduce the antenna height. Thus, a compact wideband circularly polarized antenna is realized. In addition, a transmission zero can be introduced at the upper frequency stopband by the bent metal square rings, without using extra filter circuits. For verification, the proposed model is implemented and tested. The overall size of the model is 90mm×90mm×33mm(0.37λ0×0.37λ0×0.14λ0, λ0 denotes the center operating frequency). The measured impedance bandwidth and 3 dB axial ratio bandwidth are 53.3% and 41%, respectively. More than 15 dB upper-band radiation suppression level is realized, indicating a good low-pass filter response.

For many engineering applications it is sufficient to use the concept of simple materials. However, higher gradients of the kinematic variables are taken into account to model materials with internal length scales as well as to describe localization effects using gradient theories in finite plasticity or fluid mechanics. In many approaches length scale parameter have been introduced that are related to a specific micro structure. An alternative approach is possible, if a thermodynamically consistent framework is used for material modelling as shown in the present contribution. However, even if sophisticated and thermodynamically consistent material models can be established there are still not yet standard experiments to determine higher order material constants. In order to contribute to this ongoing discussion system identification based on the method of self-adaptive filtering is proposed in this paper. To evaluate the effectiveness of this approach it has been applied to second-order gradient materials considering longitudinal vibrations. Based on thermodynamically consistent models that have been solved numerically it has been possible to prove that system identification based on self-adaptive filtering can be used effectively for both narrow-band and broadband signals in the field of second-order gradient materials. It has also been found that the differences identified for simple materials and gradient materials allow for condition monitoring and detection of gradient effects in the material behavior.

We explored the statistics of filtering of simple patterns on a number of deterministic and random graphs as a tractable simple example of information processing in complex systems. In this problem, multiple inputs map to the same output, and the statistics of filtering is represented by the distribution of this degeneracy. For a few simple filter patterns on a ring we obtained an exact solution of the problem and described numerically more difficult filter setups. For each of the filter patterns and networks we found a few numbers essentially describing the statistics of filtering and compared them for different networks. Our results for networks with diverse architectures appear to be essentially determined by two factors: whether the graphs structure is deterministic or random, and the vertex degree. We find that filtering in random graphs produces a much richer statistics than in deterministic graphs. This statistical richness is reduced by increasing the graph’s degree.

An easy to implement and cost-effective Fiber Bragg Grating (FBG) sensor interrogation technique based on a ring Erbium-Doped Fiber Laser (EDFL) topology is proposed and experimentally assessed. The FBG sensor is part of the EDFL cavity and must have a central wavelength located within the linear region of the EDF’s amplified spontaneous emission (ASE) spectrum which occurs between 1530 and 1540nm. In this manner, the wavelength-encoded response of the FBG under strain is converted to a linear variation of the laser output power, removing the need for spectrum analysis as well as any limitations from the use of external edge-filtering components. In addition, the laser linewidth is significantly reduced with respect to the FBG bandwidth thus improving the resolution of the system, whereas its sensitivity can be controlled through the pumping power. The performance of the system has been characterized by modeling and experiments for EDF's with different lengths, doping concentrations and pumping power levels. The influence of mode-hopping in the laser cavity on the resolution and accuracy of the system has also been investigated.

Owing to the nondiffracting, self-accelerating, and self-healing properties, Airy beams of different nature have become a subject of immense interest in the past decade. Their interesting properties have opened doors to many diverse applications. Consequently, the questions of how to properly design spatial manipulation of Airy beams or how to implement them in different setups have become important and timely in the development of various optical devices. Here, based on our previous work, we present a short review on the spatial control of Airy beams, including the interactions of Airy beams in nonlinear media, beam propagation in harmonic potential, and the dynamics of abruptly autofocusing Airy beams in the presence of a dynamic linear potential. We demonstrate that under the guidance of nonlinearity and external potential, the trajectory, acceleration, structure, and even the basic properties of Airy beams can be adjusted to suit specific needs. We describe other fascinating phenomena observed with Airy beams, such as self-Fourier transformation, periodic inversion of Airy beams, and the appearance of spatial solitons in the presence of nonlinearity. These results have promoted the development of Airy beams, and have been utilized in various applications, including particle manipulation, self-trapping, and electronic matter waves.

Digital filtering is a fundamental technique in digital signal processing, which operates on a digital sequence without any information on how the sequence was generated. This paper proposes a methodology for designing the equivalent of digital filtering for neuromorphic samples, which are a low power alternative to conventional digital samples. In the literature, filtering using neuromorphic samples is done by filtering the reconstructed analog signal, which is required to belong to a predefined input space. We show that this requirement is not necessary, and introduce a new method for computing the neuromorphic samples of the filter output directly from the input samples, backed by theoretical guarantees. We show numerically we can achieve a similar accuracy compared to the conventional method. However, given that we bypass the analog signal reconstruction step, our results show significantly reduced computation time for the proposed method and good performance even when signal recovery is not possible.

In the ground-based infrared optical remote sensing system, the target signal is very weak due to the dynamic strong light background and the movement of small and small targets. In order to improve the limit detection capability, the background suppression and target enhancement methods are required to be more suitable for this scene. To solve this problem, we first analyze the image features in the current scene, and propose a more perfect point target and noise model. Then, we propose a new WY distribution function based on the Fermi Dirac distribution function, and propose an anisotropic filtering method based on this function, and further suppress the back-ground through the difference results of two steps. Then, based on the distribution function, we further designed an energy concentration accumulation strategy in 9 scale directions, through which the SNR of the target is effectively improved and the suppression ability of the background is enhanced. Through quantitative and qualitative experimental analysis, compared with the same type of algorithms, the proposed method has better robustness against extremely weak targets and dynamic backgrounds.

Several bio-actors are involved in the occurrence of leishmaniasis, which is made too complex for prevention and control options. Currently, all forms of leishmaniasis are being treated with chemical drugs, which have limitations and adverse effects on patients. Searching the bioactive molecules from plant sources allows the development of a novel drug. The essential oil and solvent extract of the roots of E. kebericho showed antileishmanial activity. But looking for biological activities of the isolated active ingredient from tubers of E. kebericho was scant. Thus, the isolation of the leishmanicidal compound from the roots of E. kebericho through a bioassay-guided technique was an aim of this work. Dehydrocostus lactone showed doubled potent than the standard drug miltefosine on leishmanicidal activities against L. major and L. tropica. Besides, the broad-spectrum biological activities of dehydrocostus lactone could be a potential drug candidate for co-infected patients caused by an association of leishmania and another pathogen.

Accurate prostate volume estimation is crucial for effective prostate disease management. Ultrasound (US) imaging, particularly transrectal ultrasound, offers a cost-effective and rapid assessment. However, US images often suffer from artifacts and poor contrast, making prostate volume estimation challenging. This review explores recent advancements in deep learning (DL) techniques for automatic prostate segmentation in US images as a primary step for prostate volume estimation. We examine various DL architectures, including traditional U-Net modifications and innovative designs incorporating residual connections, multi-directional image data, and attention mechanisms. Additionally, we discuss pre-processing methods to enhance image quality, the integration of shape information, and strategies to improve the consistency and robustness of DL models. The effectiveness of these techniques is evaluated through metrics such as Dice Similarity Coefficient, Jaccard Index, and Hausdorff Distance. The review highlights the potential of DL in improving prostate volume estimation accuracy and reducing clinical workload, while also identifying areas for future research to enhance model performance and generalizability.

Chylothorax is a rare complication occurring after cardio-thoracic surgical procedures. This condition presents challenges about diagnosis and treatment. Operative ductal ligation is the method of choice for relapsing or refractory cases, and it can be performed through the aid of IGC injection for the identification of chylous leakage. Our report presents the use of ICG fluorescence during VATS to successfully identify and treat a left-sided post-surgical chylothorax. The patient underwent a pulmonary wedge resection for a suspect malignant lesion and developed chylous leakage in the early postoperative period. On postoperative day 7 the patient underwent a revision thoracoscopy for hemostasis and thoracic duct ligation. ICG injections have been performed through bilateral inguinal lymph nodes and approximately 15 minutes after we performed the re-thoracoscopy with effective identification and ligation of the chyle leakage. ICG fluorescence-guided VATS is a valuable and effective method for managing postoperative chylothorax, especially for left-sided leaks. The video of the procedure can be found at: https://zenodo.org/records/13786288

In this paper, the filtering method of biomedical image denoising is described comprehensively. Firstly, it introduces the biomedical image denoising, describes the relationship between biomedical image denoising and medical care, introduces the filtering methods, the filtering methods of biomedical image denoising, the challenges encountered by the current filtering methods, and other application fields of filtering methods. Firstly, the background of biomedical image denoising is introduced. Biomedical image denoising is a challenge. Different imaging modes have different noise characteristics, and noise levels can vary greatly depending on the specific application. Secondly, it describes that biomedical image denoising plays an important role in medical care, and the biomedical image directly affects the patient's diagnosis, treatment plan and the overall quality of medical care service. Then the filtering method is introduced in detail, describing the core concepts and related features of linear filtering, nonlinear filtering and frequency domain filtering, and then focusing on the adaptive filtering method, describing the characteristics, conditions of use, common algorithms and advantages of adaptive filtering method. Then the filter methods of biomedical image denoising are introduced, and the core concepts of Gaussian filter, median filter, total variation denoising and Wiener filter are introduced respectively. Then, the challenges encountered by filtering methods are described, such as the accurate selection of filters, the balance between noise reduction and image detail preservation are introduced. Finally, the application of filtering method in other fields is mentioned, such as audio processing, speech recognition and so on. In summary, this paper comprehensively expounds the denoising and filtering methods of biomedical images, the filtering methods of medical image denoising, the relationship between medical image denoising and medical care, and the challenges encountered by filtering methods.

Oritavancin is a novel long-acting lipoglycopeptide with in vitro activity against methicillin-resistant (MR) Gram-positive pathogens and a good bactericidal activity even in presence of biofilm forming bacteria. It has been approved for acute bacterial skin and skin structure infections (ABSSSI), but recent reports have demonstrated possible off-label uses, as for prosthetic joint infections (PJI), which, in more than half of cases, are caused by MR Gram positive organisms. We reported a case of a man in his eighties with a late shoulder PJI caused by methicillin resistant Staphyloccus epidermidis (MRSE) with contraindications for surgical replacement and few oral therapeutic options for a long term suppressive antibiotic therapy. The prosthesis was retained, and the patient received ten outpatient sequential doses of 1200 mg of oritavancin during 28 weeks, based on therapeutic drug monitoring (TDM) as a guide for correct timing of administration of each dose. During oritavancin administration, the patient achieved clinical cure, with disappearance of the pain and regaining pre-infection joint mobility, with no side effects reported and no further surgery or hospitalization needed. The treatment is ongoing as a long-lasting suppressive antimicrobial therapy. Oritavancin could represent an excellent solution for treating PJI caused by MR organism, especially in patients who need a long-term suppressive therapy.

Scaffold guided breast tissue regeneration (SGBTR) can both transform reconstructive and cosmetic breast surgery. Implant-based surgery is the most common method. However, there are inherent limitations as there is replacement of tissue rather than regeneration. Regenerating autologous soft tissue has the potential to provide a more like-for-like reconstruction with minimal morbidity. Our SGBTR approach regenerates soft tissue by implanting additively manufactured bioresorbable scaffolds filled with autologous fat graft. A pre-clinical large animal study was conducted implanting 100 ml breast scaffolds (n=55) made from medical-grade polycaprolactone in 11 minipigs for 12 months. Various treatment groups were investigated where immediate or delayed autologous fat graft, as well as platelet rich plasma were added to scaffolds. Computed Tomography and Magnetic Resonance Imaging was performed on explanted scaffolds to determine volume and distribution of regenerated tissue. Histological analysis was performed to confirm tissue type. At 12 months we were able to regenerate and sustain a mean soft tissue volume of 60.9 4.5 ml (95% CI) across all treatment groups. There was no evidence of capsule formation. There were no immediate or long-term post-operative complications. In conclusion, we were able to regenerate clinically relevant soft tissue volumes utilizing SGBTR in a pre-clinical large animal model.

Several stochastic H∞ filters for estimating the attitude of a rigid body from line-of-sight measurements and rate gyro readings are developed. The measurements are corrupted by white noise with unknown variances. Our approach consists of estimating the quaternion while attenuating the transmission gain from the unknown variances and initial errors to the current estimation error. The time-varying H∞ gains are computed through differential and algebraic linear matrix inequalities whose parameters are independent of the state. The case of a gyro drift is addressed, too. Extensive Monte Carlo simulations show that the proposed stochastic H∞ quaternion filters perform well for a wide range of noise variances. The actual attenuation, which improves with the noise level and is worst in the noise-free case, is better than the guaranteed attenuation by one order of magnitude. The proposed stochastic H∞ filter produces smaller biases than a standard quaternion Kalman filter and similar standard deviations at large noise levels. An essential advantage of this H∞ filter is that the gains are independent of the quaternion, which makes it insensitive to modeling errors. This desired feature is illustrated by comparing its performances against those of unmatched Kalman filters. When provided with too high or too low noise variances the Kalman filter is outperformed by the $H_\infty$ filter, which essentially delivers identical error magnitudes.

Autoencoders are neural networks that have applications in denoising processes. Their use is widely reported in imaging (2D), though 1D series can also benefit from this function. Here, three canonical waveforms are used to train a neural network and achieve a signal-to-noise reduction with curves whose noise energy was above that of the signals. A real-world test is carried out with the same autoencoder subjected to a set of time series corrupted by noise generated by a zener diode, biased on the avalanche region. Results showed that, observed some guidelines, the autoencoder can indeed denoise 1D waveforms usually observed in electronics, particularly square waves found in digital circuits.

: In this paper we present an optimization of the planar manufacturing scheme for stretch-free, shape induced metal interconnects to simplify the fabrication with the aim of maximizing the flexibility in the structure regarding to stress and strain. The Formation of trenches between silicon islands are actively used in the lithographic process to create arc shape structures by spin coating resist into the trenches. The resulting resist form is used as a template for the metal lines, which are structured on top. Because this arc shape is beneficial for the flexibility of these bridges. The trench depth as a key parameter for the stress distribution is investigated by applying numerical simulations. The simulated results show that the increase in penetration depth of the metal bridge into the trench increases the tensile load which is converted into a shear Force Q(x), that usually leads to increased strains the structure can generate. For the fabrication the filling of the trenches with resist is optimized by varying the spin speed. Compared to the theoretical resistance, the current-voltage measurements of the metal bridges show a similar behavior and almost every structural variation is capable of functioning as a flexible electrical interconnect in a complete island-bridge array.

Background: Glioma surgery was remarkably renewed in the past 2 decades, with improved safety and limited but yet improved life expectations. Fluorescence-guided resection of high-grade gliomas (HGG) plays a central role in this sense, by allowing higher degrees of extent of resection (EOR). The introduction of the exoscopic guided surgery may be considered an implementation for fluorescence techniques over the traditional microscopes. We present the application and the advantages of the exoscopic guided surgery compared to the microscopic surgery in tumor resection guided by 5-ALA fluorescence in patients with HGG. Methods: ten consecutive patients underwent a surgery for HGG resection. The surgery was performed via an exoscopic-guided procedure (Olympus Orbeye) and after oral administration of Gliolan 5 hours before the procedure. During surgery, the procedure was shifted to microscope (Kinevo 900, Zeiss) view. The intensity of the fluorescence under the two different was subjectively measured in different picture samples during the surgery in a 1 to 5 (from minimum to maximum) scale. The brightness of the surgical field and the detailing of the anatomy were also analyzed comparatively. Results: among the ten patients the histopathological diagnosis was an high grade glioma in all cases. In 9 cases was possible to achieve the gross total resection. There was no perioperative mortality. The median fluorescence intensity, on a scale of 1–5, was 4.5 in the exoscope group and 3.5 in the microscope group (p<0.01). Conclusions: The exoscopic guided surgery adds advantages to the traditional fluorescence- guided surgery with 5-aminolevulinic acid. Beyond the important advantage of low cost and the possibility to perform collaborative surgeries, it adds a plain and continuous visualization of the tumor and the surgical field in the fluorescence guided glioma surgery compared to the microscopic guided one.

Ultrasound imaging is a vital imaging tool in musculoskeletal medicine, with the number of publications on ultrasound-guided surgery increasing in recent years. However, ultrasound imaging has drawbacks, such as operator dependency and image obscurity. Artificial Intelligence (AI) and Deep Learning (DL), a subset of AI, can address these issues. DL methods, including segmentation, detection, and localization of target tissues and medical instruments, potentially allow physicians and surgeons to perform ultrasound-guided procedures more accurately and efficiently. This review summarizes recent advances in ultrasound-guided procedures for musculoskeletal diseases and provides a comprehensive overview of the utilization of AI/DL in ultrasound for musculoskeletal medicine, particularly focusing on ultrasound-guided surgery.

This paper presents an efficient topology optimization approach considering fail-safe requirements in the framework of the solid isotropic material with penalization method. Existing methods either are computationally extremely expensive or do not consider fail-safe requirements in the optimization. The current approach not only obtains the fail-safe optimization structure, but also significantly improves the computational efficiency of fail-safe topology optimization. In this method, the worst-case compliance is considered to minimize as the optimization objective, using the Kreisselmeier–Steinhauser function to approximate the non-differentiable max-operator. The sensitivity is derived by the adjoint method, and a general fail-safe optimality criteria method is developed to update design variables. The damage scenarios greatly reduces in the process of failsafe strategy optimization by employing the density-based filter method. Finally, the effectiveness and computational efficiency of this method for fail-safe optimization is verified by several numerical examples.

In this paper, we continue the research cycle on the properties of convolutional neural network-based image recognition systems and ways to improve noise immunity and robustness [1]. Currently, a popular research area related to artificial neural networks is adversarial attacks. The effect of adversarial attacks on the image is not highly perceptible to the human eye, also it drastically reduces the neural network accuracy. Image perception by a machine is highly dependent on the propagation of high frequency distortions throughout the network. At the same time, a human efficiently ignores high-frequency distortions, perceiving the shape of objects as a whole. The approach proposed in this paper can improve the image recognition accuracy in the presence of high-frequency distortions, in particular, caused by adversarial attacks. The proposed technique makes it possible to measure up the logic of artificial neural network to that of a human, for whom high-frequency distortions are not decisive in object recognition.

Coastal cliffs erode in response to short- and long-term environmental changes but predicting these changes continues to be a challenge. In addition to a chronic lack of data on the cliff face, vegetation presence and growth can bias our erosion measurements and limit our ability to detect geomorphic erosion by obscuring the cliff face. This paper builds on past research segmenting vegetation in 3-band red, green, blue (RGB) imagery and presents two approaches to segmenting and filtering vegetation from the bare cliff face in dense point clouds constructed from RGB images and structure-from-motion (SfM) software. Vegetation indices were computed from previously published research and their utility in segmenting vegetation from bare cliff face were compared against machine learning (ML) models for point cloud segmentation. Results demonstrate that, while existing vegetation indices and ML models are both capable of segmenting vegetation and bare cliff face sediments, ML models can be more efficient and robust across different growing seasons. ML model accuracy quickly reached an asymptote with only two layers and RGB images only (i.e., no vegetation indices), suggesting that these more parsimonious models may be more robust to a range of environmental conditions than existing vegetation indices which vary substantially from one growing season to another with changes in vegetation phenology.

Organised hiking and trekking tours are promoted by many providers in adventure travel. Such guided tours shall be engaging for the tourists and evoke positive attitudes towards enjoying nature. We present the Trekking Engagement Profile as a tool to evaluate engagement factors of such guided tours, based on engagement research performed in a different domain, namely evaluating engagement in museums and science centres. This tool shall strengthen guides’ soft skills and enable them to increase engagement during an ongoing arrangement. For instance, the Trekking Engagement Profile can be applied when tourists indicate that the quality of a guided tour is not entirely to their liking. We show the viability of using the Trekking Engagement Profile in a small study with guides and participants of trekking tours offered by the Norwegian Trekking Association. Further, we offer guidance and charts to promote its practical use.

The trigeminal nerve is responsible for innervating the periorbita. Ultrasound-guided trigeminal block is employed in humans for trigeminal neuralgia or periorbital surgery. There are no studies evaluating this block in dogs. This study aims to evaluate and compare two approaches (coronoid and temporal) of the trigeminal nerve block. We hypothesized superior staining with the coronoid approach. Thirteen dog heads were used. After a preliminary anatomical study, two ultrasound-guided injections per head (right and left, coronoid and temporal approach, randomly assigned), with an injectate volume of 0.15 mL cm-1 of cranial length were performed (iodate contrast and tissue dye mixture). The ultrasound probe was placed over the temporal region, visualizing the pterygopalatine fossa. For the temporal approach, the needle was advanced from the medial aspect of the temporal region in a dorsoventral direction. For the coronoid approach, it was advanced ventral to the zygomatic arch in a lateromedial direction. CT scans and dissections were conducted to assess and compare the position of the needle, spread of injectate, and nerve staining. No significant differences were found. Both approaches demonstrated effective interfascial distribution of injectate, with some minimal intracranial spread. Although the coronoid approach did not yield superior staining as hypothesized, it presents a viable alternative to the temporal approach. Studies in live animals are warranted to evaluate clinical efficacy and safety.

Topology optimization has become a very popular design tool when an optimum design with a concrete objective and subjected to several restrictions is searched. However, the resultant shape of the optimization process isn’t usually easy to manufacture with a typical manufacturing method as machining, being necessary an interpretation and validation of the result; besides, some parameters can be chosen, and the final shape is directly dependent on them. In this paper, a sensitivity analysis of the main parameters involved in 3D topology optimization, the penalization and the filter radius, is carried out for the concrete case of the density-based method, analyzing how manufacturable the results are for 3 axis machining. Also, a new filter and method is proposed for obtaining highly manufacturable and low interpretable parts. The main aim of the study is to help designers to choose the more appropriate parameters and showing what they must have into account for obtaining the desired optimized shapes. Note that the density-based topology optimization method has been chosen due to its popularity in commercial packages, so the conclusions may have direct applications in designers’ work. Finally, the results of the study are verified through different cases for checking the validity of the conclusions.

As various services have been generating large scale graphs to represent multiple relationships between objects, studies have been conducted to obtain subgraphs with particular patterns. In this paper, we propose a distributed query processing method to efficiently search a subgraph for a large graph on Spark. To reduce unnecessary processing costs, the search order is determined by filtering scores using the probability distribution. The partitioned queries are searched in parallel in the distributed graph of each slave node according to the search order, and the local search results obtained from each slave node are combined and returned. The query is partitioned in triplets based on the determined search order. The performance of the proposed method is compared with the performance of existing methods to demonstrate its superiority.

Guided image filter implicitly balances noise and details based on local variance, achieving noise suppression while preserving prominent edges. However, we have observed limitations in using variance to distinguish between noise and image details, resulting in the suppression of fine structures alongside noise. Furthermore, the goal of enhancing image details, which is crucial in image filtering, has not been adequately addressed in edge-preserving filter design. In this paper, we approach image filtering as a problem of spectral energy reconfiguration, where the gain of each spectral band is adaptively regulated to achieve simultaneous noise suppression and detail enhancement. Instead of relying on variance, we employ a linear noise estimator to obtain the Signal-to-Noise Ratio (SNR) measurement necessary for dynamic gain regulation. Similar to the guided image filter, we determine the filter coefficients by solving the closed-form solution of the optimizer. We demonstrate that the proposed extended guided filter effectively integrates information from multiple spectral bands locally, allowing for the joint enhancement of meaningful details while simultaneously smoothing noise.

Image synthesis poses a challenging problem that researchers in computer vision and machine learning have been grappling with for several decades. Numerous machine learning techniques have emerged and proven effective in generating high-fidelity artificial images. This study breaks new ground by exploring image synthesis through generative learning using the D-Wave 2000Q quantum annealer, marking the first attempt to address the issue of generative image synthesis on a Quantum Processing Unit (QPU). Alongside executing image synthesis on the quantum annealer, this research also compares its performance with existing classical models and delves into resolving the Generative Learning Trilemma.

In recent years, with the rapid development of technology, artificial intelligence(AI) security issues represented by adversarial sample attack have aroused widespread concern in society. Adversarial samples are often generated by surrogate models and then transfer to attack the target model, and most AI models in real-world scenarios belong to black boxes, thus transferability becomes a key factor to measure the quality of adversarial samples. The traditional method relies on the decision boundary of the classifier and takes the boundary crossing as the only judgment metric without considering the probability distribution of the sample itself, which results in an irregular way of adding perturbations to the adversarial sample, an unclear path of generation, and a lack of transferability and interpretability. In the probabilistic generative model, after learning the probability distribution of the samples, a random term can be added to the sampling to gradually transform the noise into a new independent and identically distributed sample. Inspired by this idea, we believe that by removing the random term, the adversarial sample generation process can be regarded as static sampling of the probabilistic generative model, which guides the adversarial samples out of the original probability distribution and into the target probability distribution, and helps to improve transferability and interpretability. Therefore, we propose a Score Matching-Based Attack(SMBA) method to perform the adversarial sample attacks by manipulating the probability distribution of the samples, which can show good transferability in the face of different datasets and models, and give reasonable explanations from the perspective of mathematical theory and feature space. In conclusion, our research establishes a bridge between probabilistic generative models and adversarial samples, provides a new entry angle for the study of adversarial samples, and brings new thinking to AI security.

The task of determining the distance from one object to another is one of the important tasks solved in robotics systems. Conventional algorithms rely on an iterative process of predicting distance estimates, which results in an increased computational burden. Algorithms used in robotic systems should require minimal time costs, as well as be resistant to the presence of noise. To solve these problems, the paper proposes an algorithm for Kalman combination filtering with a Goldschmidt divisor and a median filter. Software simulation showed an increase in the accuracy of predicting the estimate of the developed algorithm in comparison with the traditional filtering algorithm, as well as an increase in the speed of the algorithm. The results obtained can be effectively applied in various computer vision systems.

Wearable technology will become available and allow prolonged electroencephalography (EEG) monitoring in the home environment of patients with epilepsy. Neurologists analyse the EEG visually and annotate all seizures, which patients often under report. Visual analysis of a 24 hour EEG recording typically takes one to two hours. Reliable automated seizure detection algorithms will be crucial to reduce this analysis. We study a dataset of behind-the-ear EEG measurements. Our first aim was to develop a methodology to reduce the EEG dataset by classifying part of the data automatically, while retaining 100% detection sensitivity (DS). Prediction confidences are determined by temperature scaling of the classification model outputs and trust scores. A DS of approximately 90% (99%) can be achieved when automatically classifying around 90% (60%) of the data. Perfect DS can be achieved when automatically classifying 50% of the data. Our second contribution demonstrates that a common modelling strategy, where predictions from several short EEG segments are used to obtain a final prediction, can be improved by filtering out untrustworthy segments with low trust scores. The false detection rate shows a relative decrease between 21% and 43%, and the DS shows a small increase or decrease.

In this paper, at first, a color image of a car is taken. Then the image is transformed into a grayscale image. After that, the motion blurring effect is applied to that image according to the image degradation model described in equation 3. The blurring effect can be controlled by a and b components of the model. Then random noise is added in the image via Matlab programming. Many methods can restore the noisy and motion blurred image; particularly in this paper Inverse filtering as well as Wiener filtering are implemented for the restoration purpose. Consequently, both motion blurred and noisy motion blurred images are restored via Inverse filtering as well as Wiener filtering techniques and the comparison is made among them.

Purpose: To compare the efficacy and safety of trabeculectomy with a collagen matrix implant (Ologen®) versus trabeculectomy with mitomycin C (MMC) versus trabeculectomy with both Ologen® and MMC (OLO+MMC). Methods: This non-randomized study included 119 eyes of 101 patients with uncontrolled open-angle glaucoma who underwent trabeculectomy, either alone or combined with phacoemulsification. Data were initially registered following a standard surgical protocol and using an electronic database with structured fields. Patients were divided into three groups: 44 received trabeculectomy with adjunctive MMC (MMC group), 34 with Ologen® (OLO group), and 41 with both Ologen® and MMC (OLO+MMC group). The main outcome measures were the change in intraocular pressure (IOP), change in number of medications needed, complete success rate (defined as IOP≤20 mmHg and at least 20% IOP reduction without hypotensive medications), rate of complications, and rate of postoperative interventions. The follow-up period was 36 months.
 Results: IOP significantly decreased (p=0,01) in all groups across all study visits, decreasing from 19.8 ± 4.6 mmHg to 12.7 ± 4.2 mmHg in the MMC group, from 20.5 ± 4.7 mmHg to 13.9 ± 3.5 mmHg in the OLO group, and from 23.5 ± 6.1 mmHg to 13.1 ± 3.5 mmHg in the OLO+MMC group. After correcting for baseline IOP, only the first two postoperative visits (first week and first month) showed significantly greater IOP reduction in the OLO+MMC group. The number of hypotensive medications was significantly reduced from 3.1±0.6 to 0.56±1.1 in the MMC group, from 2.9±0.4 to 0.83±1.1 in the OLO group, and from 3.0±0.6 to 0.45±0.95 in OLO + MMC group, with no statistically significant differences among the groups (p=0,57). Complete success rates were 63,6% in the MMC group, 67,6% in the OLO group, and 80,5% in the OLO +MMC group, with no statistically significant differences among the groups (p=0,21). Suture release was significantly more frequent in the MMC group (86,1%) than in the OLO group (62,1%) and in the OLO + MMC group (45,9%; p=0,02). Bleb needling, with (33.3%; p=0.005) or without (66.7%; p=0.0001) 5-Fluorouracil injection (5-FU), was significantly more common in the MMC group. The highest complete-success rate (61%) was offered by the OLO+MMC group. Conclusion: The use of Ologen® and Mitomycin C provided similar surgical IOP reduction in glaucoma surgery compared with MMC or Ologen® either alone but significantly reduced the need for postoperative interventions.

Real-time tracking is one of the most challenging problems in computer vision. Most Transformer-based trackers usually require expensive computational and storage power, which leads to the inability of these robust trackers to achieve real-time performance in resource-constrained devices. In this work, we propose a lightweight tracker, AnteaTrack. To localize the target more precisely, we develop a scaling-invariant max-filtering operator employing a sliding window combined with local max-pooling, which filters out the suspected target from the feature and performs an augmented representation while suppressing the background. For a more tight bounding box, we employ Pixel-Shuffle to increase the resolution of the feature map and get a more fine-grained representation of the target. In addition, AnteaTrack can run in real-time at 47 frames per second(FPS) on the CPU. We tested AnteaTrack on 5 datasets, and a large number of experiments have shown that AnteaTrack provides the most efficient solution compared to the same type of CPU real-time trackers. The code will be available at https://github.com/cnchange/AnteaTrack.

The most common source of transformer failure is in the insulation, and the most prevalent warning signal for insulation weakness is partial discharge (PD). Locating positons of these partial discharges would help repair the transformer to prevent failures. This work investigates algorithms that could be deployed to locate the position of a PD event using data from ultra-high frequency (UHF) sensors inside the transformer. These algorithms typically proceed in two steps: first determine the signal arrival time and then locate the position based on time differences. This paper reviews available methods for each task and then propose new algorithms: a convolutional iterative filter with thresholding (CIFT) to determine the signal arrival time and a reference table of travel times to resolve the source location. The effectiveness of these algorithms are tested with a set of laboratory-triggered PD events and two sets of simulated PD events inside transfers in production use. Tests show the new approach provides more accurate locations than the best-known data analysis algorithms, and the difference is particularly large, 3.7X, when the signal sources are far from sensors.

Clustered regularly interspaced short palindromic repeats (CRISPR) based gene-editing has begun to transform the treatment landscape of genetic diseases. The history of the discovery of CRISPR/CRISPR-associated (Cas) proteins/single guide RNA (sgRNA)-based gene-editing since the first report of repetitive sequences of unknown significance in 1987 is fascinating, instructive, and inspiring for future advances. The recent approval of CRISPR-Cas9-based gene therapy to treat patients with severe sickle cell anemia and transfusion-dependent beta thalassemia has renewed hope for treating other hematologic diseases, including patients with germline predisposition to hematologic malignancies, who would benefit greatly from the development of CRISPR-based gene therapies. The purpose of this manuscript is three-fold: first, a chronological description of the history of CRISPR-Cas9-sgRNA-based gene editing; second, a brief description of the current state of clinical research in hematologic diseases, including selected applications in treating hematologic diseases with CRISPR-based gene therapy; and third, the current progress in gene therapies in inherited hematologic diseases and bone marrow failure syndromes, to hopefully stimulate efforts towards developing these therapies for patients with inherited bone marrow failure syndromes and other inherited conditions with germline predisposition to hematologic malignancies.

Abstract Background: Occipital neuralgia is a debilitating condition and traditional treatments often provide limited or temporary relief. Recently, ultrasound-guided hydrodissection of the greater occipital nerve (GON) has emerged as a promising minimally invasive approach. Objectives: To describe two novel ultrasound-guided hydrodissection with 5% dextrose for GON and discuss their advantages, disadvantages, and considerations. Methods: Two case reports are presented. Case 1 describes a lateral decubitus approach for hydrodissecting the GON between the semispinalis capitis (SSC) and obliquus capitis inferior (OCI) muscles. Case 2 details a cranial-to-caudal approach for hydrodissecting the GON within the SSC and upper trapezius (UT) muscles when the GON pass through these two muscles. Results: Both patients experienced significant and sustained pain relief with improvements in function and quality of life. Conclusions: Ultrasound-guided GON hydrodissection using 5% dextrose is a promising treatment for occipital neuralgia. The lateral decubitus and cranial to caudal approaches provide additional options to address patient-specific anatomical considerations and preferences.

Tinnitus is an auditory phantom perception in the ears or head in the absence of a corresponding external stimulus. There is currently no effective treatment available that reliably reduces tinnitus. Educative counseling is a treatment approach that aims to educate patients and inform them about possible coping strategies. For this feasability study, we implemented educational material and self-help advice in a smartphone app. Participants used the educational smartphone unsupervised during their daily routine over a period of 4 months. Comparing the tinnitus outcome measures before and after smartphone-guided treatment, we measured changes in the tinnitus-related distress, but not in tinnitus loudness. Improvements on the Tinnitus Severity numeric rating scale reached an effect size of .408, while the improvements on the THI were much smaller with an effect size of .168. Analysis on the user behavior showed that frequent and intensive use of the app is a crucial factor for treatment success: participants that used the app more often and interacted with the app intensively, reported a stronger improvement of the tinnitus. Between study allocation and final assessment, 26 of 52 participants dropped out of the study. Reasons for the dropouts and lessons for future studies are discussed in this paper.

Endoscopic ultrasound-guided gallbladder drainage (EUS-GBD) is an alternative to surgery for acute cholecystitis (AC) in poor operative candidates. However, the role of EUS-GBD in non-cholecystitis (NC) indications has not been well studied. We compared clinical outcomes of EUS-GBD for AC and NC indications. Consecutive patients undergoing EUS-GBD for all indications at a single center were retrospectively analyzed. Fifty-one patients underwent EUS-GBD during the study period. Thirty-nine (76%) patients had AC while 12 (24%) had NC indications. NC indications included malignant biliary obstruction (n = 8), symptomatic cholelithiasis (n = 1), gallstone pancreatitis (n = 1), choledocholithiasis (n = 1), and Mirizzi’s syndrome (n = 1). Technical success was noted in 92% (36/39) for AC and 92% (11/12) for NC (p &gt; 0.99). Clinical success rate was 94% and 100%, respectively (p &gt; 0.99). There were 4 adverse events in the AC group and 3 in the NC group (p = 0.62). Procedure duration (median 43 vs 45 minutes, p = 0.37), post-procedure length of stay (median 3 vs 3 days, p = 0.97), and total gallbladder related procedures (median 2 vs 2, p = 0.59) were similar. EUS-GBD for NC indications is similarly safe and effective as EUS-GBD in AC.

The objective of this study is to preliminarily evaluate a new CT-biopsy guidance device, an origami needle guide. The device is created by laser cutting the structure from a sheet of cardboard, 3D printing two radiocontrast agent grids on to the surface and folding the structure into a rectangular prism with a viewing window. An abdominal imaging phantom was used to evaluate the device through CT imaging and the targeting of lesions for needle insertion. The lesion targeting trials resulted in a mean targeting error of 1.88 mm with a standard deviation of 0.73 mm. The device attaches to the patient and is rigid enough to adequately support standard biopsy needles, reducing the effect of gravity and the risk of laceration by the needles, making it potentially advantageous for biopsy of superficial lesions and lesions approached from a horizontal orientation. The device supports insertion of multiple needles at once, making it particularly suitable for composite ablation using multiple needles. Another advantage of the device is that it can guide off-axial needle insertion. The low-cost and disposability of the device make it well-suited for the minimally invasive image guided therapy environment.

In recent years, different deep learning frameworks were introduced for hyperspectral image (HSI) classification. However, the proposed network models have a higher model complexity and do not provide high classification accuracy if few-shot learning is used. This paper pre-sents an HSI classification method that combines random patches network (RPNet) and re-cursive filtering (RF) to obtain informative deep features. The proposed method first convolves image bands with random patches to extract multi-level deep RPNet features. Thereafter, the RPNet feature set is subjected to dimension reduction through principal component analysis (PCA) and the extracted components are filtered using the RF procedure. Finally, HSI spectral features and the obtained RPNet-RF features are combined to classify the HSI using a support vector machine (SVM) classifier. In order to test the performance of the proposed RPNet-RF method, some experiments were performed on three widely known datasets using a few training samples for each class and classification results were compared with those obtained by other advanced HSI classification methods adopted for small training samples. The comparison showed that the RPNet-RF classification is characterized by higher values of such evaluation metrics as overall accuracy and Kappa coefficient (https://github.com/UchaevD/RPNet-RF).

A plant’s health and productivity is influenced by its associated microbes. Although the common microbiome is often thought to be the most influential, significant numbers of rare or uncommon microbes (eg. specialized endosymbionts) may also play an important role in the health and productivity of certain plants in certain environments. To help identify rare/specialized bacteria and fungi in the most important angiosperm plants, we contrasted microbiomes of the shoots, roots and rhizospheres of Arabidopsis, Brachypodium, maize, wheat, sugarcane, rice, tomato, coffee, common bean, cassava, soybean, switchgrass, sunflower, Brachiaria, barley, sorghum, and pea. Plants were grown inside sealed jars on sterile sand or field soil. About 95% and 86% of fungal and bacterial diversity inside plants was uncommon, however judging by read abundance, up to half of the mycobiome consists of uncommon fungal cells, while less than 11% of bacterial endophytes are rare. Uncommon seed transmitted microbiomes consisted mostly of Proteobacteria, Firmicutes, Bacteriodetes, Ascomycetes and Basidiomycetes that most heavily colonized shoots, to a lesser extent roots and least of all rhizospheres. Soil served as a more diverse source of rare microbes than seeds, replacing or excluding the majority of the uncommon seed transmitted microbiome. With the rarest microbes, their colonization pattern could either be the result of stringent biotic filtering by most plants, or uneven/stochastic inoculum distribution in seeds or soil. Several strong plant-microbe associations were observed such as seed transmission to shoots, roots and/or rhizospheres of Sarocladium zeae (maize), Penicillium (pea and Phaseolus), and Curvularia (sugarcane), while robust bacterial colonization from cassava field soil occurred with the cyanobacteria Leptolyngbya into Arabidopsis and Panicum roots, and Streptomyces into cassava roots. Some abundant microbes such as Sakaguchia in rice shoots or Vermispora in Arabidopsis roots appeared in no other samples, suggesting they were infrequent, stochastically deposited propagules from either soil or seed (impossible to know based on the available data). Future experiments with culturing and cross inoculation of these microbes between plants may help us better understand host preferences and their role in plant productivity, perhaps leading to their use in crop microbiome engineering and enhancement of agricultural production.

Modern Monte-Carlo-based rendering systems still suffer from the computational complexity involved in the generation of noise-free images, making it challenging to synthesize interactive previews. We present a framework suited for rendering such previews of static scenes using a caching technique that builds upon a linkless octree. Our approach allows for memory-efficient storage and constant-time lookup to cache diffuse illumination at multiple hitpoints along the traced paths. Non-diffuse surfaces are dealt with in a hybrid way in order to reconstruct view-dependent illumination while maintaining interactive frame rates. By evaluating the visual fidelity against ground truth sequences and by benchmarking, we show that our approach compares well to low-noise path traced results, but with a greatly reduced computational complexity allowing for interactive frame rates. This way, our caching technique provides a useful tool for global illumination previews and multi-view rendering.

Growing interest surrounds the assessment of perivascular spaces (PVS) on magnetic resonance imaging (MRI) and their validation as a clinical biomarker of adverse brain health. Nonetheless, the limits of validity of current state-of-the-art segmentation methods are still unclear. Here, we propose an open-source three-dimensional computational framework comprising 3D digital reference objects and evaluate the performance of three PVS filtering methods under various spatiotemporal imaging considerations (including sampling, motion artefacts, and Rician noise). Specifically, we study the performance of the Frangi, Jerman and RORPO filters in enhancing PVS-like structures to facilitate segmentation. Our findings were three-fold. First, as long as voxels are isotropic, RORPO outperforms the other two filters, regardless of imaging quality. Unlike the Frangi and Jerman filters, RORPO’s performance does not deteriorate as PVS volume increases. Second, the performance of all “vesselness” filters is heavily influenced by imaging quality, with sampling and motion artefacts being the most damaging for these types of analyses. Third, none of the filters can distinguish PVS from other hyperintense structures (e.g. white matter hyperintensities, stroke lesions, or lacunes) effectively, the area under precision-recall curve dropped substantially (Frangi: from 94.21 [IQR 91.60, 96.16] to 43.76 [IQR 25.19, 63.38]; Jerman: from 94.51 [IQR 91.90, 95.37] to 58.00 [IQR 35.68, 64.87]; RORPO: from 98.72 [IQR 95.37, 98.96] to 71.87 [IQR 57.21, 76.63] without and with other hyperintense structures, respectively). The use of our computational model enables comparing segmentation methods and identifying their advantages and disadvantages, thereby providing means for testing and optimising pipelines for ongoing and future studies.

Recently deep cross-modal hashing networks have received increasing interests due to its superior query efficiency and low storage cost. However, most of existing methods concentrate less on hash representations learning part, which means the semantic information of data cannot be fully used. Furthermore, they may neglect the high-ranking relevance and consistency of hash codes. To solve these problems, we propose a Self-Attention and Adversary Guided Hashing Network (SAAGHN). Specifically, it employs self-attention mechanism in hash representations learning part to extract rich semantic relevance information. Meanwhile, in order to keep invariability of hash codes, adversarial learning is adopted in the hash codes learning part. In addition, to generate higher-ranking hash codes and avoid local minima early, a new batch semi-hard cosine triplet loss and a cosine quantization loss are proposed. Extensive experiments on two benchmark datasets have shown that SAAGHN outperforms other baselines and achieves the state-of-the-art performance.

Purpose: Expanded carrier screening (ECS) informs couples of their risk of having offspring affected by certain genetic conditions. Limited data exists assessing the actions and reproductive outcomes of at-risk couples (ARCs). We describe the impact of ECS on planned and actual pregnancy management in the largest sample of ARCs studied to date. Methods: Couples who elected ECS and were found to be at high risk of having a pregnancy affected by at least one of 176 genetic conditions were invited to complete a survey about their actions and pregnancy management. Results: Three hundred ninety-one ARCs completed the survey. Among those screened before becoming pregnant, 77% planned or pursued actions to avoid having affected offspring. Among those screened during pregnancy, 37% elected prenatal diagnostic testing (PNDx) for that pregnancy. In subsequent pregnancies that occurred in both the preconception and prenatal screening groups, PNDx was pursued in 29%. The decision to decline PNDx was most frequently based on the fear of procedure-related miscarriage, as well as the belief that termination would not be pursued in the event of a positive diagnosis. Conclusions: ECS results impacted couples’ reproductive decision-making and led to altered pregnancy management that effectively eliminates the risk of having affected offspring.

This study introduces a robust methodology utilizing Multi-Criteria Decision Analysis (MCDA) combined with the Analytic Hierarchy Process (AHP) to repurpose abandoned hydrocarbon fields for energy storage, supporting the transition to renewable energy sources. We use a geostatistical approach integrated with Python scripting to analyze reservoir parameters—including porosity, permeability, thickness, lithology, temperature, heat capacity, and thermal conductivity—from a decommissioned hydrocarbon field in Southeast Hungary. Our workflow leverages stochastic simulation data to identify potential zones for energy storage, categorizing them into high, moderate, and low suitability scenarios. This innovative approach provides rapid and precise analysis, enabling effective decision-making for energy storage implementation in depleted fields.

Audio recording in classrooms is a common practice in educational research, with applications ranging from detecting classroom activities to analysing student behaviour. Previous research has employed neural networks for classroom activity detection and speaker role identification. However, these recordings are often affected by background noise that can hinder further analysis, and the literature has only sought to identify noise with general filters and not specifically designed for classrooms. Although the use of high-end microphones and environmental monitoring can mitigate this problem, these solutions can be costly and potentially disruptive to the natural classroom environment. In this context, we propose the development of a neural network model that can specifically detect and filter out background noise in classroom recordings. This model would allow the use of lower quality recordings without compromising analysis capability, thus facilitating data collection in natural educational environments and reducing the costs associated with high-end recording equipment.

Background: The transversus abdominis plane (TAP) block has gained increasing importance as a very effective pain relief in for caesarean section. This study aimed to compare bupivacaine (Group B), bupivacaine with dexmedetomidine (Group BD) and bupivacaine with dexamethasone (Group BDx) applied in ultrasound-guided TAP block in the treatment of CS postoperative pain. Material and Method: American Society of Anesthesiologists I and II pregnant women who underwent cesarean section were included in the study. Forty patients were admitted in each group. All patients were applied TAP block with ultrasound guidance by administering the medications of the group in which they were included. Results: Body mass index (BMI) and operation duration were higher in Group B (p*=0.01 and 0.004, respectively). Instant tramadol requirement and amount were higher in Group B at some of follow up times. Patient satisfaction scale were better in Group BD and Group BDx. Conclusion: TAP block significantly reduces pain after cesarean section, prolongs the time to first analgesic request, and reduces the need for additional opioid analgesics. The addition of adjuvant to the TAP block usually improves the postoperative clinical condition. However, some special conditions such as body mass index (BMI) may negatively affect the clinical situation. Comprehensive, standardized, randomized controlled studies are needed to compare results under different conditions.

Artifact metrics is a technology for authenticating artifacts based on their unique characteristics. The artifact-metric system offers "clone resistance," i.e., it makes it highly improbable to create another object exhibiting the same measured values as a genuine artifact. However, determined adversaries may still attempt to create imitations or clones with close physical characteristics to those of registered products, even if they cannot perfectly replicate the genuine product. Such clones serve to deceive users into believing they are genuine rather than counterfeits. Thus, in this study, we consider a scenario in which we measure raster-scanning-generated clones via a non-raster scanning method. Further, we employ image processing techniques to generate image data representing the clones and theoretically assess the filtering effects on these images. Our findings reveal that applying filters to specific frequency components in the spatial frequency domain can effectively highlight differences between raster-scanning-created clones and the corresponding genuine artifacts. Thus, we demonstrate directional emphasis filtering in artifact metrics as an effective approach for rejecting raster-scanning-created clones.

This research paper investigates ultra-wideband (UWB) localization systems by focusing on the use of average filter (AVG), Kalman filter (KF), and extended Kalman filter (EKF) algorithms, as well as a novel integrated filtering method that incorporates low-pass filter (LPF) into AVG, KF, and EKF. The study aims to improve localization loss in indoor environments using a TurtleBot robot equipped with a camera to observe ground truth positions. To evaluate the effectiveness of the proposed algorithms, a comprehensive comparison of the raw and filtered data with the camera-based ground truth observations is performed. Quantitative analyses of the results, including max, min, max-min, and mean error, are performed to evaluate the localization performance of the algorithms and the integrated filtering method. The results reveal that the integrated filtering method has performed better accuracy in comparison with existing methods.

Recently, e-commerce companies have been adopting and continuously enhancing personalized product recommendation systems, and there is active research in this field within academia. However, personalized product recommendations in offline retail stores have not yielded significant outcomes thus far. Especially for small-format offline retail businesses like convenience stores, where customer information might be limited, providing personalized product recommendations poses even greater challenges. To address this issue, this study aimed to find a solution by shifting the perspective on recommendation methods and altering the target of recommendations in existing personalized recommendation models. In this study, recommending products that customers need in an offline store was defined as suggesting products that should be introduced and displayed within the store. In other words, the recommendation focus shifted from individuals to the stores themselves. This recommendation system proposes products that individual stores have not yet introduced but are anticipated to be purchased by customers among the products managed by the headquarters. Building upon this, we devised a store-based product recommendation system. The widely used user-based collaborative filtering model, a common technique in existing recommendation systems, was adapted into a store-based collaborative filtering model. Furthermore, various rules and logic pertinent to store operations and business considerations for convenience stores were integrated to implement this store product recommendation system. The accuracy and effectiveness of the system were demonstrated through its application in actual convenience stores. Results from the pilot implementation of the system showed that 88% of the newly recommended products in individual stores were sold based on one week of sales data, and the sales revenue was 1.75 times higher than the average sales revenue of those products across the entire company. Survey results on business owners' satisfaction yielded a score of 4.2 out of 5, indicating a high level of contentment. Additional observed effects included the expansion of product range and reduction in order lead times. However, 12% of the total recommended SKUs did not sell within one week, and 34% of the SKUs did not meet the overall average sales quantity. This research holds significance in extending the scope of personalized recommendation studies from primarily online platforms to offline retail businesses like convenience stores. It provides tangible methodologies and outcomes that can be implemented in real-world settings through the construction and validation of an actual system. The study also suggests avenues for future research to address some of the identified limitations.

Several researchers have contemplated deep learning-based post-filters to increase the quality of statistical parametric speech synthesis, which perform a mapping of the synthetic speech to the natural speech, considering the different parameters separately and trying to reduce the gap between them. The Long Short-term Memory (LSTM) Neural Networks have been applied successfully in this purpose, but there are still many aspects to improve in the results and in the process itself. In this paper, we introduce a new pre-training approach for the LSTM, with the objective of enhancing the quality of the synthesized speech, particularly in the spectrum, in a more efficient manner. Our approach begins with an auto-associative training of one LSTM network, which is used as an initialization for the post-filters. We show the advantages of this initialization for the enhancing of the Mel-Frequency Cepstral parameters of synthetic speech. Results show that the initialization succeeds in achieving better results in enhancing the statistical parametric speech spectrum in most cases when compared to the common random initialization approach of the networks.

The InSAR technique measures the displacement of an indicator using SAR image interference. The technique of interfering two SAR images among InSAR techniques is called Differential InSAR (D-InSAR). In the process of D-InSAR, the filtering technique is used in the Unwrapped Mask, usually using the GoldStein method. However, since the Goldstein method removes the noise on the path, it is difficult to derive the displacement value in the agricultural area where the relative coherence is low. In Korea, more than 50% of the whole country consists of mountainous regions and agricultural regions, so it is difficult to use the Goldstein technique polysynthetically. In this study, we set the test-bed for the urban area and the agricultural area based on Coherence, and introduce Goldstein and Boxcar Filter, one of the Goldstein and LSM techniques. Through this process, we want to draw the conclusion which is displacement values ​​in the agricultural area.

We develop an interactive likelihood (ILH) for sequential Monte-Carlo (SMC) methods for image-based multiple target tracking applications. The purpose of the ILH is to improve tracking accuracy by reducing the need for data association. In addition, we integrate a recently developed deep neural network for pedestrian detection along with the ILH with a multi-Bernoulli filter. We evaluate the performance of the multi-Bernoulli filter with the ILH and the pedestrian detector in a number of publicly available datasets (2003 PETS INMOVE, AFL, and TUD-Stadtmitte) using standard, well-known multi-target tracking metrics (OSPA and CLEAR MOT). In all datasets, the ILH term increases the tracking accuracy of the multi-Bernoulli filter.

This study addresses the challenge of treating skin cancer effectively, especially in visible areas like the face, where traditional methods may be undesirable. Current options, including surgery and radiation therapy, have limitations such as complexity, expense, and imprecise dose delivery. The proposed solution involves additively manufacturing personalized patches using diagnostic imaging data, offering a targeted and controlled dose of beta-emitting isotopes like Y-90. The patches, tailored to the tumor's shape and depth, aim to minimize damage to healthy tissues and structures. Through 3D printing technology we demonstrated the feasibility of creating individualized applicators filled with radioisotopes, that have the potential to deliver therapeutic doses while ensuring patient comfort and affordability. This innovative approach, based on radiation delivery simulations, offers a promising future alternative to conventional radiation therapy methods. Clinical trials are required to validate its efficacy and safety, but the potential for reduced radiation exposure and enhanced treatment precision positions this personalized and targeted therapy as a valuable advancement in skin cancer treatment.

One of the efficient data mining tools is density-based clustering, including the density grid-based clustering. However, a common drawback always existing in clusters made by the density grid-based method is the existence of weakly connected grids deriving mainly from noise. Appearing such an unwanted connection with a high frequency reduces the accuracy of the obtained cluster data space (CDS) and its application efficiency. Here, we present an essential improvement to overcome this problem. First, we describe a concept of the weak-connected grid cell (WCG) and present a fuzzy-type approximation to depict the density-based distribution of data points at grid nodes. Then, we propose a strategy of searching WCG for density grid-based clustering (SWCG-DGB) to set up a CDS, filter noise, and tune the created CDS. A buffer is deployed during this phase to collect border points and filter noise, which improves the computational time significantly, especially for noisy datasets. Results from numerical surveys reflected the compared efficiency of this method in clustering validity, including the accuracy of the number of clusters.

The main purpose of this work is to contribute to understanding the mechanism of oxidation of the polymeric components of common disposable masks used during the COVID-19 pandemic to offer the chemical basis to predict their long-term behaviour under typical environmental conditions. Artificial ageing of representative mask layers under isothermal conditions (110℃) or accelerated photoageing showed that all the PP-made components underwent a fast oxidation process, following the typical hydrocarbon oxidation mechanism. In particular, yellowing and the melting temperature drop are early indicators of their diffusion-limited oxidation. Morphology changes also induced a loss of mechanical properties, observable as embrittlement of the fabric fibres. Results were validated through preliminary outdoor ageing of masks, which allows us to predict they will suffer fast and extensive oxidation only in the case of contemporary exposure to sunlight and relatively high environmental temperature, leading to their extensive breakdown in the form of microfiber fragments, i.e., microplastics.

In the context of reinforcement learning (RL), ensuring both safety and performance is crucial, especially in real-world scenarios where mistakes can lead to severe consequences. This study aims to address this challenge by integrating temporal logic constraints into RL algorithms, thereby providing a formal mechanism for safety verification. We employ a combination of theoretical and empirical methods, including the use of temporal logic for formal verification and extensive simulations to validate our approach. Our results demonstrate that the proposed method not only maintains high levels of safety but also achieves comparable performance to traditional RL algorithms. Importantly, our approach fills a critical gap in existing literature by offering a solution that is both mathematically rigorous and empirically validated. The study concludes that the integration of temporal logic into RL offers a promising avenue for developing algorithms that are both safe and efficient. This work lays the foundation for future research aimed at generalizing this approach to various complex systems and applications.

ABSTRACT Objectives: Typical Diagnostic Reference Levels (DRL) in terms of Computed Tomography Dose Index (CTDI) and patient dose in terms of Effective Dose (ED ) and Size Specific Dose Estimate (SSDE) were estimated in Computed Tomography (CT) guided biopsy procedures. Materials and Methods: A total of 226 CT biopsy procedures - Iliac bone, liver, lung, mediastinum and para-aortic tissue - were retrospectively analyzed and Typical DRL extracted based on ICRP 135 instructions. Results: For helical mode acquisitions, DRLs in terms of CTDIvol were 9.7 mGy for Iliac bone, 8.9 mGy for liver, 8.8 mGy for lung, 7.9 mGy for mediastinal mass and 9 mGy for para-aortic lymph nodes biopsy procedures. For biopsy acquisitions, DRL values were 7.3 mGy, 7.7 mGy, 5.6 mGy, 5.6 mGy and 7.4 mGy respectively. Also, SSDE median values ranged from 7.6 mGy to 10 mGy for biopsy acquisitions and 11,3 mGy to 12,6 mGy for helical acquisitions, as well as the median values for effective dose ranged from 1.6 mSv to 5,7 mSv for biopsy scans and 3.9 to 9.3 mSv for helical scans. Conclusions: The use of DLR as an optimization tool for CT-guided biopsy procedures revealed that helical scans across the entire anatomical region greatly affect radiation dose compared to biopsy acquisitions.

This work deals with the evaluation of adhesive single-lap joints using ultrasonic guided waves. An adhesive bonded lap joint can be modelled as a three-layer system made up of two adherents and an adhesive. The propagation of guided waves in the joint is developed from matrix formulations. The behavior of the different guided wave modes that propagate in the bonded region is characterized and it is found that their relative amplitudes can be estimated based on the properties of the incoming wave that propagates in the non-bonded region. It was verified that the excitation of these modes is ruled by the degree in which the shapes of both modes match each other. A 3D simulation of two aluminium bonded plates using 500 kHz ultrasonic transducers in a pitch and catch configuration was implemented using the Matlab k-Wave toolbox. Scattering effects due to some produced defects located in the bond line of the lap joints were simulated. Experimental setup with some artificial defects produced in the aluminum joints were used in order to compare with the simulated. Qualitative agreement was observed for the two approaches. The observed deviation can be due to the different characteristics of the experimental and simulated defects.

EUS–TA in unresectable pancreatic cancer requires not only a tissue diagnosis but also tissue collection in anticipation of comprehensive genomic profiling. However, the optimal puncture target remains controversial. Therefore, the Primary and Metastatic Lesions in Pancreatic Cancer (PRIMATE) study was designed to clarify the optimal target by comparing the success rates for meeting OncoGuide NCC Oncopanel (NOP) analysis criteria on pre-check primary and metastatic lesion specimens obtained during the same EUS–TA session in patients with invasive pancreatic ductal adenocarcinoma. In this ongoing prospective study, two specimens, each from primary and metastatic lesions, are obtained by EUS–TA (typically using a 19G fine-needle biopsy needle) in patients with invasive pancreatic ductal adenocarcinoma. The primary endpoint is the proportion of EUS–TA specimens that meet NOP analysis criteria during pre-check (i.e., tumor cellularity ≥ 20% and tissue area ≥ 4 mm2), which are then compared between primary and metastatic lesions. This study has been approved by the National Cancer Center Institutional Review Board (Research No. 2022-168). The results of this study will be reported at an international conference and published in an international peer-reviewed journal. The trial registration number is UMIN 000048966.

Airborne distributed position and orientation system (ADPOS), which integrates multi-inertia measurement units(IMUs), data-processing computer and Global Navigation Satellite System (GNSS), serves as a key sensor in new higher-resolution airborne remote sensing, such as array SAR, multinode imaging loads and so on. ADPOS can provide multinode high accuracy spatio-temporal reference information to realize multinode motion compensation with the various state estimation methods such as Central Difference Kalman Filtering (CDKF), modifed CDKF. However, these methods focus on noise optimization based on known nonlinear models and its linear minimum variance estimation criterion, which cannot gain better estimation performance for high-dimensional nonlinear systems. For this reason, the variational optimization process based on conjugate gradient algorithm is proposed for the estimation of filtering update step, which is more efficient than linear minimum variance estimation criterion. Therefore, aiming at ADPOS with high-dimensional and nonlinearity, Central Difference Variational Filtering (CDVF) using variational optimization based on conjugate gradient algorithm for mean correction in the filtering update stage is devoted to advancing the estimation accuracy of multinode motion parameters. A real ADPOS flight test has been conducted, the experimental results show that the accuracy of the slave motion parameters has a distinct progress than the up to date CDKF, and the compensation performance is distinct.

This study introduces a Fiber Specklegram Sensor (FSS) design for temperature measurement utilizing a single-multi-single mode optical fiber configuration. FSS technology offers unique advantages for potential development into portable sensing systems. This investigation explores an FSS design compatible with miniaturization by optimizing the interrogation system based on the relationship between speckle grain size and filtering fiber area. Temperature variations are detected through fluctuations in optical power at the sensor output, offering a simple and reduced interrogation scheme. The performance of the FSS is assessed through post-calibration measurements compared to a commercial Fiber Bragg Grating (FBG) sensor, demonstrating comparable results. These findings pave the way for compact and portable fiber optic temperature sensing systems leveraging FSS advantages while maintaining compatibility with established fiber optic measurements.

Short Message Service (SMS) is becoming the secure medium of communication due to large-scale global coverage, reliability, and power efficiency. As person--to--person (P2P) messaging is less secure than application-to-person (A2P) messaging, anyone can send a message, leading to the attack. Attackers mistreat this opportunity to spread malicious content, perform harmful activities, and abuse other people, commonly known as spam. Moreover, such messages can waste a lot of time, and important messages are sometimes overlooked. As a result, accurate spam detection in SMS and its computational time are burning issues. In this paper, we conduct six different experiments to detect SMS spam from the dataset of 5574 messages using machine learning classifiers such as Multinomial Naïve Bayes (MNB) and Support Vector Machine (SVM), considering variations of \textit{Term Frequency-- Inverse Document Frequency (TF--IDF)} features for exploring the trade-off among accuracy, F1-score and computational time. The experiments achieve the best result of the accuracy of 98.50\%, F1--score of 98\%, and area under roc curve (AUC) of 0.97 for multinomial naïve bayes classifier with TF--IDF after stemming.

: Image guided superficial radiation therapy (IGSRT) combines superficial radiation therapy (SRT) with full dermal visualization (FDV) via high resolution dermal ultrasound (HRDUS) for the treatment of non-melanoma skin cancer (NMSC). The gold standard for IGSRT delivery includes a comprehensive cancer care model with support for the dermatologists by a multidisciplinary team. When delivered in this model, IGSRT can achieve cure rates of 99% for treatment of NMSC. This paper focuses on the benefits of IGSRT during therapy. Medical records from 7 dermatology clinics of 883 patients with 1,507 cases of NMSC treated with IGSRT be-tween 2017 and 2018 were retrospectively reviewed. 92% of the NMSC lesions showed daily depth fluctuations, 60.32% of lesions did not require changes during therapy, and nearly 40% of lesions required at least one compensatory change during therapy. 83% of NMSC lesions were labeled high-risk based on the 2024 NCCN guidelines. Increasing and decreasing tumor depth measurements during IGSRT inform dermatologists when adaptive changes in energy (kV), TDF and dose will result in more efficacy and less toxicity, respectively.

Neural radiance fields (NeRF) leverage a neural representation to encode scenes, obtaining photo-realistic rendering of novel views. However, NeRF has notable limitations. A significant drawback is that it does not capture surface geometry and only renders the object surface colors. Furthermore, the training of NeRF is exceedingly time-consuming. We propose Depth-NeRF as a solution to these issues. Specifically, our approach employs a fast depth completion algorithm to denoise and complete the depth maps generated by RGB-D cameras. These improved depth maps guide the sampling points of NeRF to be distributed closer to the scene's surface, benefiting from dense depth information. Furthermore, we have optimized the network structure of NeRF and integrated depth information to constrain the optimization process, ensuring that the termination distribution of the ray is consistent with the scene’s geometry. Compared to NeRF, our method accelerates the training speed by 18% and significantly reduces the RMSE between the rendered scene depth and the ground truth depth, which indicates that our method can better capture the geometric information of the scene. With these improvements, we can train the NeRF model more efficiently and achieve more accurate rendering results.

Targeted image-guided oncologic surgery (IGOS) relies on the recognition of cell surface-associated proteins, which should be abundantly present on the tumor cells but preferably absent on cells in surrounding healthy tissue. The transmembrane receptor tyrosine kinase EphA2, a member of the A class of the Eph receptor family, has been reported to be highly overexpressed in several tumor types including breast, lung, brain, prostate, and colon cancer, and is considered amongst the most promising cell membrane-associated tumor antigens by the NIH. Another member of the Eph receptor family belonging to the B class, EphB4, has also been found to be up-regulated in multiple cancer types. In this study, EphaA2 and EphB4 are evaluated as target for IGOS of colorectal cancer by immunohistochemistry (IHC) using a tissue microarray (TMA) consisting of 168 pairs of tumor and normal tissue. The IHC sections were scored for staining intensity and percentage of cells stained. The results show a significantly enhanced staining intensity and more widespread distribution in tumor tissue compared with adjacent normal tissue for EphA2 as well as EphB4. Based on its more consistently higher score in colorectal tumor tissue compared to normal tissue, EphB4 appears to be an especially promising candidate for IGOS of colorectal cancer.

With the dramatic increase in world population, continued advances in modern greenhouse agriculture and plant growth practices are expected to help overcome the global problem of future food shortages. Next generation greenhouse design practices will need to address a range of issues, ranging from energy and land use efficiency to providing plant-optimised growth techniques. In this paper, we focus on investigating the optimum irradiation spectra matched to the lettuce species (Lactuca sativa, L.), which is commonly grown in greenhouse environments, in order to develop low-emissivity glass panes that maximize the biomass productivity of glass greenhouses. This low-emissivity glass passes the solar spectral components needed for crop growth, while rejecting other unwanted radiations, leading to significant energy savings and other beneficial effects related to greenhouse climate control, in a range of climates. This is due to reducing both the solar heat gain and photosaturation, which can raise the temperature of the crops to harmful levels. Experimental results show that substantial biomass productivity improvements in lettuce (up to ~14.7%) can be attained using spectrally optimized illumination, compared with white light irradiation. We also report on the development of advanced metal-dielectric thin-film filters that produce the optimum illumination spectrum when exposed to sunlight.

Evolution remains an incessant process in viruses, allowing them to elude host immune response and induce severe diseases, impacting the diagnostic and vaccine effectiveness. Predicting emerging viral genomes is crucial, particularly in diseases like dengue, where viruses disrupt host cells, leading to fatal outcomes. Deep learning has been applied to predict dengue fever cases; there has been relatively less emphasis on its significance in forecasting emerging Dengue Virus (DENV) serotype. While Recurrent Neural Networks (RNN) were originally designed for modeling temporal sequences, our proposed DL-DVE generative and classification model, trained on complete genome data of DENV, transcends traditional approaches by learning semantic relationships between nucleotides in a continuous vector space instead of representing contextual meaning of nucleotide characters. Leveraging 2000 publicly available DENV complete genome sequences, our Long Short-Term Memory (LSTM) based generative and Feedforward Neural Network (FNN) based classification DL-DVE model showcases proficiency in learning intricate patterns and generating sequences for emerging serotype of DENV. The generative model showed accuracy of 93% and the classification model provided insight into the specific serotype label, corroborated by BLAST search verification. Evaluation metrics such as ROC-AUC value 0.818, accuracy, precision, recall and F1 score all to be around 99.00%, demonstrated the classification model’s reliability.  Our model classified the generated sequences as DENV-4, exhibiting 65.99% similarity to DENV-4 and around 63-65% similarity with other serotypes, indicating notable distinction from other serotypes. Moreover, the intra-serotype divergence of sequences with a minimum 90% similarity underscored their uniqueness. We analyzed the conserved motifs in the genome through MEME Suite (version 5.5.5). Our research strives to contribute to the ongoing fight against the Dengue virus by offering predictive insights into its genomic evolution. Looking ahead, proactive predictive modeling before mutations occur holds potential for guiding vaccine design and diagnostic kit development.

Cervical cancer remains a major public health problem. Despite the screening programs, cervical cancer is the second most commonly diagnosed cancer. Most of the cases occur in less developed countries, and it is the third leading cause of cancer death among females. In 2000–2007, the five-year relative survival rate for European women diagnosed with cervical cancer was 62%.[1] Standard treatment for locally advanced cervical cancer reveals external beam radiotherapy (EBRT) with concurrent chemotherapy followed by image-guided adaptive brachytherapy (IGABT) boost [2, 3]. In the last years, the Gynaecological (GYN) working group composed of Group Européen de Curiethérapie-European Society for Therapeutic Radiology and Oncology (GEC-ESTRO) has developed new recommendations for the treatment of cervical cancer based on IGABT. The treatment plan includes 3-dimensional (3D) imaging based on magnetic resonance imaging (MRI) or computed tomography (CT), adaptive to the target volume and organ at risk [4–6]. The brachytherapy insertion is made under anaesthesia. At the time of the application insertion, the ultrasound is used to guide the dilatation of the uterine canal and assess the depth of the uterine cavity. In this paper, we review the data available in international literature about the use of ultrasound (US) in brachytherapy treatment of cervical cancer.

The influence of preoperative examination of oral squamous cell carcinoma (OSCC) mucosal surrounding by VELscope (Visually Enhanced Lesion Scope) on the radicality of surgical treatment of OSCC was the goal of this study.It is the first analysis of its kind with a total number of 122 patients suffering from OSCC with homogenous distribution of different tumor stages randomized into a study and a control group and enrolled in our study after meeting the inclusion criteria. The preoperative checkup by VELscope accompanied by the marking of the range of a loss of fluorescence in the study group was performed before the surgery. We have developed a unique mucosal tattoo marking technique for this purpose. The pathohistological results after surgical treatment, i.e. the margin status, were then compared. We achieved the pathological free margin (pFM) in 55 patients, the pathological close margin (pCM) in 6 cases and we encountered no case of the pathological positive margin (pPM) in the mucosal layer in the study group. In comparison, the control group results revealed pPM in 7 cases, pCM in 14 cases and pFM in 40 of all cases in the mucosal layer. This study proved that the preoperative autofluorescence evaluation of a tumor mucosal surrounding can enhance the ability to reach the pFM resection.

Structural health monitoring of lightweight constructions made of composite materials can be performed using guided ultrasonic waves. If modern fiber metal laminates are used, this requires integrated sensors that can record the inner displacement oscillations caused by the propagating guided ultrasonic waves. Therefore, we have developed a robust MEMS vibrometer that can be integrated with structural and functional compliance. This vibrometer is directly sensitive to the high-frequency displacements from structure-borne ultrasound when excited between its first and second natural frequency. The vibrometer is mostly realized by processes earlier developed for a pressure sensor but with additional femtosecond laser ablation and wafer bonding. The piezoresistive transducer made from silicon is encapsulated between top and bottom glass lids. The natural frequencies are experimentally determined using an optical micro vibrometer setup. The vibrometer functionality and usability for structural health monitoring are demonstrated on a customized test rig by recording application-relevant guided ultrasonic wave packages with a central frequency of 100 kHz at a distance of 200 mm from the exciting ultrasound transducer.

Monte Carlo Filtering (MCF) is one of the methods of Experimental Statistical Energy Analysis (E-SEA), which allows the correction of a negative LF (Loss Factor). In this article, a modification of the MCF method, called DESA (Diagonal Extension of the Search Area), is proposed. The technique applies a non-uniform extension of the search area when generating a population of normalized energy matrices. The degree of expansion of the search area is controlled by the Diagonal Penalty Factor (DPF). The authors demonstrated the method's effectiveness on a system that could not be identified in several frequency bands by the classical MCF method. After applying DESA, it was possible to fill in the problematic bands that were missing CLF and DLF values. The paper also proposes a way to minimize the errors introduced by using overly high DPF values.

Usually, in ground-penetrating radar (GPR) datasets the user defines the limits between the useful signal and the noise through standard filtering to isolate the effective signal as much as possible. However, there are true reflections that mask the coherent reflectors that can be considered noise. In archaeological sites these clutter reflections are caused by scattering with origin in subsurface elements (e.g., isolated masonry, ceramic objects and archaeological collapses). Its elimination is difficult because the wavelet parameters similar to coherent reflections and there is a risk of creating artifacts. In this study a procedure to filtering the clutter reflection noise (CRN) from GPR datasets is presented. The CRN filter is a singular value decomposition-based method (SVD), applied in the 2D spectral domain. This CRN filtering was tested in a dataset obtained from a controlled laboratory environment, to establish a mathematical control of this algorithm. Also, it has been applied in a 3D-GPR dataset acquired in the Roman villa of Horta da Torre (Fronteira, Portugal), which is an uncontrolled environment. The results show an increase in the quality of archaeological-GPR planimetry that were verified via archaeological excavation.

In addition to image filtering in the spatial and frequency domains, fractal characteristics induced algorithms offers considerable flexibility in the design and implementations of image processing solutions in areas such as image enhancement, image restoration, image data compression and spectrum of applications of practical interests. Facing up to a real-world problem of identifying workpiece surface defects, a generic adaptive fractal filtering algorithm is proposed, which shows advantages on the problems of target recognition, feature extraction and image denoising at multiple scales. First, we reveal the physical principles underlying between signal SNR and its representative fractal dimension indicative parameters, validating that the fractal dimension can be used to adaptively obtain the image features. Second, an adaptive fractal filtering algorithm (Abbreviated as AFFA) is proposed according to the identified correlation between the image fractal dimensions and the scales of objects, and it is verified by a benchmarking image processing case study. Third, by using the proposed fractal filtering algorithm, surface defects on a flange workpiece are identified. Compared to conventional image processing algorithms, the proposed algorithm shows superior computing simplicity and better performance Numerical analysis and engineering case studies show that the fractal dimension is eligible for deriving an adaptive filtering algorithm for diverse-scale object identification, and the proposed AFFA is feasible for general application in workpiece surface defect detection.

Photogrammetry involves aerial photography of the earth’s surface and subsequently processing the images to provide a more accurate depiction of the area (Orthophotography). It’s used by the Spanish Instituto Geográfico Nacional to update road cartography but requires a significant amount of manual labor due to the need to perform visual inspection of all tiled images. Deep Learning techniques (artificial neural networks with more than one hidden layer) can perform road detection but it is still unclear how to find the optimal network architecture. Our system applies grammar guided genetic programming to the search of deep neural network architectures. In this kind of evolutive algorithm all the population individuals (here candidate network architectures) are constrained to rules specified by a grammar that defines valid and useful structural patterns to guide the search process. Grammar used includes well-known complex structures (e.g. Inception-like modules) combined with a custom designed mutation operator (dynamically links the mutation probability to structural diversity). Pilot results show that the system is able to design models for road detection that obtain test accuracies similar to that reached by state of the art models when evaluated over a dataset from the Spanish National Aerial Orthophotography Plan.

Nerve hydrodissection (HD), a technique used when treating nerve entrapments, involves using an anesthetic or solution such as saline or 5% dextrose solution to separate the nerve from the surrounding tissue, fascia, or adjacent structures. This technique aims to treat neuropathic pain, or pain caused by the nerve. Ultrasound-guided HD of peripheral nerves has gained significant attention in the medical profession and pain management fields in recent years. This is due to a number of high impact publications of randomized control trials demonstrating the efficacy and safety of this technique for the treatment of carpal tunnel syndrome. Even the 20th edition of Harrison’s Principles of Internal Medicine textbook lists injection of 5% dextrose as an alternative local treatment that does not have the side effects of corticosteroids. At present, there is no review of the current literature on this technique. This manuscript will summarize and discuss the following: 1) the different approaches to doing ultrasound-guided HD of nervous structures, 2) its usages in different clinical situations, 3) its clinical pearls, 4) the solution used, and 5) the postulated mechanisms of action.

Purpose: We hypothesized that a recently introduced epibulbar micro-shunt (PRESERFLO, P) produces nycthemeral (24h) intraocular pressure (IOP) profiles different from ab-interno trabeculectomy (Trabectome, T). P is a flow restrictor that drains fluid into the sub-tenon space. In contrast, T increases conventional outflow, which is limited by episcleral venous pressure. Methods: In this prospective cohort, we analyzed 68 patients (34 P and 34 T) who presented for 24-h IOP monitoring 6 to 12 months after surgery. IOP and tonographic outflow facility were measured in the habitual position using a pneumatonometer. The IOP variation was considered the primary outcome measure. Glaucoma medications were also compared. Results: P had a higher baseline IOP than T (24.8±10.0 vs. 17.3±7.9 mmHg, p=0.001). Postoperatively, P and T had similar nycthemeral IOP profiles, but IOP in P was significantly lower than in T, except at 4 pm. P had a lower absolute IOP variation than T (5.8±2.6 vs. 7.1±2.7 mmHg, p=0.049). The relative IOP variation was similar in both (34.8±13.2 vs. 37.2±13.1, p=0.45) as was the tonographic outflow facility (0.35±0.23 vs. 0.26±0.18 µl/min/mmHg, p=0.097). Conclusion: Nycthemeral IOP profiles of P and T were similar, but P had lower IOPs and less variation than T. This could reflect how T, unlike P, is more impacted by habitual, positional factors, especially at night.

Drained peatlands are significant sources of the greenhouse gas (GHG) carbon dioxide. Rewetting is a proven strategy to protect carbon stocks; however, it can lead to increased emissions of the potent GHG methane. The response to rewetting of soil microbiomes as drivers of these processes is poorly understood, as are biotic and abiotic factors that control community composition. We analyzed the pro- and eukaryotic microbiomes of three contrasting pairs of minerotrophic fens subject to decade-long drainage and subsequent rewetting. Also, abiotic soil properties including moisture, dissolved organic matter, methane fluxes and ecosystem respiration rates. The composition of the microbiomes was fen-type-specific, but all rewetted sites showed higher abundance of anaerobic taxa compared to drained sites. Based on multi-variate statistics and network analyses we identified soil moisture as major driver of community composition. Furthermore, salinity drove the separation between coastal and freshwater fen communities. Methanogens were more than tenfold more abundant in rewetted than in drained sites, while their abundance was lowest in the coastal fen, likely due to competition with sulfate reducers. The microbiome compositions were reflected in methane fluxes from the sites. Our results shed light on the factors that structure fen microbiomes via environmental filtering.

Image restoration plays a vital role in image processing and pattern recognition in producing better recognition accuracy. It was observed that, most of the traditional restoration algorithms were meant for removing a single type of noise and efforts have been made towards the use of partial differential equation model (PDE), to restore different types of images such as super-resolution, bleeding through and deblurring. This research work deployed hybridized shock filter, shock diffusion of higher order PDE to remove degraded images that have been affected by atmospheric turbulence and water smear images. Degraded images of different types were acquired from various sources. The degraded images were subjected to shock filter algorithm, shock diffusion of higher order PDE. The shock filter was combined with PDE, likewise the shock diffusion was also combined with PDE, and the three algorithms were also combined to test the efficiency of the hybridized method on different degraded images. The result was validated using Mean Square Error, Structural Similarity Index Measure (SSIM), Peak-to-Noise-Signal -Ratio (PNSR) and universal quality index (UQI). From the result, it was observed that the combination of many image restoration algorithms does not give better results whereas, the combination of two of the algorithms has really proved effective.

Due to the SARS-CoV-2 pandemic a shortage of personal protective equipment, including surgical facemasks and Filtering Facepiece Particle Respirators has occurred. SARS-CoV-2 has a 79,5-82% homology to SARS-CoV. The SARS-CoV UVC sensitivity is described in literature. We have performed UVC transmission measurements of surgical facemasks and respirators. In addition, we performed UVC disinfection experiments of S. aureus with surgical facemasks and respirators. Results show that we can achieve an 8-log reduction of S. aureus in the inner layers of FFP1 respirators and the exterior of surgical facemasks. Furthermore, we showed a 7-log reduction of S. aureus in the inner layers of FFP2 respirators. We conclude that UVC disinfection is an effective, safe and scalable method for reuse of surgical facemask and respirators.

Subglottal Impedance-Based Inverse Filtering (IBIF) allows for the continuous, non-invasive estimation of glottal airflow from a surface accelerometer placed over the anterior neck skin below the larynx, which has been shown to be advantageous for the ambulatory monitoring of vocal function. However, during long-term ambulatory recordings over several days, conditions may drift from the laboratory environment where the IBIF parameters were initially estimated due to sensor positioning, skin attachment, and temperature, among other factors. Observation uncertainties and model mismatch may result in significant deviations in the glottal airflow estimates, but are very difficult to quantify in ambulatory conditions due to a lack of a reference signal. To address this issue, we propose a Kalman filter implementation of the IBIF filter, which allows for both estimating the model uncertainty and adapting the airflow estimates to correct for signal deviations. One-way ANOVA results from laboratory experiments using the Rainbow Passage indicate a an improvement on amplitude-based measures for PVH subjects compared to IBIF which shows a statistically difference with respect to the reference oral airflow (p=0.02,F=4.1). MFDR from PVH subjects is slightly different to the oral airflow when compared to IBIF (p=0.04, F=3.3). Other measures did not have significant differences with either Kalman or IBIF, with the exception of H1H2, whose performance deteriorates for both methods. Overall, both methods show similar flottal airflow measures, with the advantage of Kalman by improving amplitude estimation. Moreover, Kalman filter deviations from the IBIF output airflow might suggest a better representation of some fine details in the ground-truth glottal airflow signal. Other applications may take more advantage from the adaptation offered by the Kalman filter implementation.

Periacetabular osteotomy (PAO) is an effective approach for surgical treatment of developmental dysplasia of the hip (DDH). However, due to the complex anatomical structure around the hip and limited field of view (FoV) during the surgery, it is challenging for surgeons to perform a PAO surgery. To solve this challenge, we propose a robot-assisted augmented reality (AR)-guided surgical navigation system for PAO. The system mainly consists of a robot arm, an optical tracker, and a Microsoft HoloLens 2 which is a state-of-the-art (SOTA) optical see-through head-mounted display (OST-HMD). For AR guidance, we propose an optical marker-based virtual-physical registration method to estimate a transformation from the optical tracker coordinate system (COS) to the virtual space COS, such that virtual models can be superimposed on the corresponding physical counterparts. Furthermore, to guide the osteotomy, the developed system automatically aligns the bone saw with osteotomy planes planned in preoperative images, and then provides surgeons with not only robot assistance but also AR guidance. Comprehensive experiments were conducted to evaluate both virtual-physical registration accuracy and osteotomy accuracy of the developed navigation system. The proposed virtual-physical registration method achieved an average mean absolute distance error (mADE) of 1.96 ± 0.43 mm. The developed system achieved an average distance deviation of 0.82 ± 0.17 mm and an average angular deviation of 3.77 ± 0.85 . Experimental results demonstrated high virtual-physical registration accuracy. The sub-millimeter distance deviation demonstrated the osteotomy accuracy of the proposed system.

Haze always shrouds satellite images, obscuring valuable geographic information for military surveillance, natural calamity surveillance and mineral resource exploration. Satellite image dehazing (SID) provides the possibility for better applications of satellite images. Most of the existing dehazing methods are tailored for natural images and are not very effective for satellite images with non-homogeneous haze since the semantic structure information and inconsistent attenuation are not fully considered. To tackle this problem, this study proposes a hierarchical semantic-guided contextual structure-aware network (SCSNet) for satellite image dehazing. Specifically, a hybrid CNN-transformer architecture integrated with a hierarchical semantic guidance (HSG) module is presented to learn semantic structure information by synergetically complementing local representation from non-local features. Furthermore, a cross-layer fusion (CLF) module is specially designed to replace the traditional skip connection during the feature decoding stage, so as to reinforce the attention to the spatial regions and feature channels with more serious attenuation. The results on the SateHaze1k, RS-Haze, and RSID datasets demonstrate that the proposed SCSNet can achieve effective dehazing and outperforms existing state-of-the-art methods.

Background: Glioblastoma remains a challenging brain tumor to treat due to its infiltrative nature. Accurately identifying tumor boundaries during surgery is crucial for successful tumor resection. This study introduces an innovative intraoperative visualization method utilizing a surgical fluorescence microscope to precisely locate tumor cells. The focus of the study is on IR-Glint, a novel preparation comprising Cy7.5-labeled aptamers Gli-233nt and Gli-55_3L specific to human glioblastoma. Methods: The aptamers were modified using molecular modeling and quantum chemical techniques. The effectiveness of the preparation was assessed using flow cytometry and microscopy on primary cultures of human glioblastoma. In vivo studies were conducted on mouse and rabbit models, employing orthotopic xenotransplantation of human brain glioblastoma with various imaging techniques, including PET/CT, in vivo fluorescence visualization, confocal laser scanning, and surgical microscopy. Results: The experiments validated the potential of IR-Glint for intraoperative visualization of glioblastoma using infrared imaging. Surface application of the aptamer-based formulation on the brain allowed clear visualization of the tumor, aiding surgeons in tumor resection. This approach also reduces the dosage required and mitigates potential toxic effects on the patient. Conclusions: This study demonstrates the promising potential of using in-frared dye-labeled aptamers for intraoperative visualization of glioblastoma. By improving surgical treatment outcomes in neurosurgery, this novel approach may pave the way for future advancements in the field.

Recommender systems as an effective information filtering system can be used to obtain information through the user's explicit or implicit behavior. On the one hand finding items that may be of interest to the user. On the other hand, the recommendation facilitates the interaction between the user and the item to increase the revenue. Recommender systems have been widely used in various fields, such as e-commerce, travel recommendation, online books and movies, social networks, etc, which can satisfy the intrinsic implicit needs of users through personalized services. In recent years, the development of deep learning has further improved the performance of recommendation systems. Although these methods improve the performance of the recommendation system, when the number of users and products increases, the recommendation system may face sparsity and cold start problems, and thus cannot achieve personalized recommendations. Knowledge graphs, which are structured data, have become the choice of many algorithms due to the high quality and wide scale of the data, and therefore many recommendation algorithms combined with knowledge graphs have emerged as a popular new direction in recommendation systems. These algorithms are able to preserve the rich connections between different entities. Moreover, when constructing the features of an entity, the entities that are far away from the central entity can also be utilized. Entities are no longer only directly connected to each other. To address the shortcomings of existing recommendation algorithms, this paper designs the recommendation algorithm GPRE using graph neural networks. GPRE focuses on expressing the user's features. The graph neural network provides GPRE with a strong generalization capability for modeling, which can provide long-range semantics between users and entities, as well as selective entity selection in the auxiliary graph neural network. Explicit semantic links are established between remote and central nodes to reduce the introduction of noise. In this paper, experiments are conducted on real-world datasets and the results are compared with baselines. The experimental results show that GPRE performs well on the experimental dataset.

Regeneration is a fundamental perpetual tissue process much attributed to functions of adult stem cell. In last decades delivery of adult stem cells to restore tissue structure is widely adopted in regenerative medicine. However, delivery of stem cells can not complete the task of human body regeneration effectively as far as cells need a basis to form a tissue. Certain improvement can be achieved when cells are organized to cells sheets (CS) – primitive tissue-engineered structures comprising of viable cells and ECM proteins. This led us to an assumption that after damage an intermediate feeder is structure formed as a ground for future tissue resulting in gradients of stimuli required to attract other cells (vascular, neural, epithelial, parenchyma etc.) in an organized manner. This feeder acquires increasing heterogeneity and becomes a guiding feeder that provides basic level of organization to increase complexity of structure up to normal tissue. We also highlight potential role of adult mesenchymal stromal cells (MSC) as the main source of guiding feeder and support it by our recent knowledge of their biological function. Finally, we assume that CS known to be a feasible delivery tool in therapeutics resemble guiding feeder and show our own data indicating properties of MSC-based CS. Furthermore, this concept shifts our understanding of therapeutic mechanism underlying a widely known delivery method for regenerative medicine.

This study aims to apply a Recommendation System with Content Based Filtering method with Jaccard Similarity and Cosine Similarity algorithms on the E-Learning Platform. Recommendation systems deal with how to provide personalized recommendations to users efficiently. The Content Based Filtering method with Jaccard Similarity and Cosine Similarity algorithms can be used to calculate the similarity value between E-Courses on the E-Learning Platform. Implementation for Recommendation System using Google Colaboratory with Python programming language. In the application of the Recommendation System dataset, Coursera Free Dataset consists of 975 instances. The recommendation results use the Jaccard Similarity algorithm with an average similarity value of 0.3 while the value of Cosine Similarity with the average similarity value is 0.6 where the similarity value of Cosine Similarity is higher. Based on the results of the Mean Absolute Error in the low recommendation system, the average MAE value for all iterations of Jaccard Similarity algorithm is 0.013 and for the Cosine Similarity algorithm the average MAE value for all iterations is 0.014. This shows that the Recommendation System with Jaccard Similarity and Cosine Similarity algorithms can be used on the E-Learning Platform to provide efficiency solutions for personalized recommendations.

Ensuring precise segmentation of colorectal polyps holds critical importance in the early diagnosis and treatment of colorectal cancer. Nevertheless, existing deep learning-based segmentation methods are fully-supervised, requiring extensive precise manual pixel-level annotation data, which leads to high annotation costs. Additionally, it remains challenging to train large-scale segmentation models when confronted with limited colonoscopy data. To address these issues, we introduce the general segmentation foundation model—Segment Anything Model (SAM) into the field of medical image segmentation. Fine-tuning the foundation model is an effective approach to tackle sample scarcity. However, current SAM fine-tuning techniques still rely on precise annotations. To overcome this limitation, we propose WSPoly-SAM, a novel weakly-supervised approach for colonoscopy polyp segmentation. WSPoly-SAM utilizes weak annotations to guide SAM in generating segmentation masks, which are then treated as pseudo-labels to guide the fine-tuning of SAM, thereby reducing the dependence on precise annotations data. To improve the reliability and accuracy of pseudo-labels, we have designed a series of enhancement strategies to improve the quality of pseudo-labels and mitigate the negative impact of low-quality pseudo-labels. Experimental results on five medical image datasets demonstrate that WSPoly-SAM outperforms current fully-supervised mainstream polyp segmentation networks on the Kvasir-SEG, ColonDB, CVC-300, and ETIS datasets. Furthermore, by using different amounts of training data in weakly-supervised and fully-supervised experiments, it is found that weakly-supervised fine-tuning can save 70% to 73% of annotation time costs compared to fully-supervised fine-tuning. This study provides a new perspective on the combination of weakly-supervised learning and SAM models, significantly reducing annotation time and offering insights for further development in the field of colonoscopy polyp segmentation.

Lassa virus (LASV) is responsible for a type of acute viral haemorrhagic fever referred to as Lassa fever. Lack of adequate treatment and preventive measures against LASV resulted in a high mortality rate in its endemic regions. In this study, a multi-epitope vaccine was designed using immunoinformatics as a prophylactic agent against the virus. Following a rigorous assessment, the vaccine was built using T-cell (N_CTL=8 and N_HTL=6) and B-cell (N_LBL=4) epitopes from each LASV-derived protein with suitable linkers and adjuvant. The physicochemistry, immunogenic potency and safeness of the designed vaccine (~68 kDa) were assessed. In addition, chosen CTL and HTL epitopes of our vaccine showed 97.37% worldwide population coverage. Besides, disulphide engineering also improved the stability of the chimeric vaccine. Molecular docking of our vaccine protein with toll-like receptor (TLR2) showed binding efficiency followed by dynamic simulation for stable interaction. Furthermore, higher levels of cell-mediated immunity and rapid antigen clearance were suggested by immune simulation and repeated-exposure simulation, respectively. Finally, the optimized codons were used in in silico cloning to ensure higher expression within E. coli K12 bacterium. With further assessment both in vitro and in vivo, we believe that our proposed peptide-vaccine would be potential immunogen against Lassa fever.