Search Results (1,391,399)

This study measured parameters automatically by marking the point for measuring each parameter on whole-spine radiographs. Between January 2020 and December 2021, 1017 sequential lateral whole-spine radiographs were retrospectively obtained. Of these, 819 and 198 were used for training and testing the performance of the landmark detection model, respectively. To objectively evaluate the program’s performance, 690 whole-spine radiographs from four other institutions were used for external validation. The combined dataset comprised radiographs from 857 female and 850 male patients (average age 42.2 ± 27.3 years; range 20–85 years). The landmark localizer showed the highest accuracy in identifying cervical landmarks (median error 1.5–2.4 mm), followed by lumbosacral landmarks (median error 2.1–3.0 mm). However, thoracic landmarks displayed larger localization errors (median 2.4–4.3 mm), indicating slightly reduced precision compared with the cervical and lumbosacral regions. The agreement between the deep learning model and two experts was good to excellent, with intraclass correlation coefficient values >0.88. The deep learning model also performed well on the external validation set. There were no statistical differences between datasets in all parameters, suggesting that the performance of the artificial intelligence model created was excellent. The proposed automatic alignment analysis system identified anatomical landmarks and positions of the spine with high precision and generated various radiograph imaging parameters that had a good correlation with manual measurements. Full article

Underwater images suffer from low contrast and color distortion. In order to improve the quality of underwater images and reduce storage and computational resources, this paper proposes a lightweight model Rep-UWnet to enhance underwater images. The model consists of a fully connected convolutional network and three densely connected RepConv blocks in series, with the input images connected to the output of each block with a Skip connection. First, the original underwater image is subjected to feature extraction by the SimSPPF module and is processed through feature summation with the original one to be produced as the input image. Then, the first convolutional layer with a kernel size of 3 × 3, generates 64 feature maps, and the multi-scale hybrid convolutional attention module enhances the useful features by reweighting the features of different channels. Second, three RepConv blocks are connected to reduce the number of parameters in extracting features and increase the test speed. Finally, a convolutional layer with 3 kernels generates enhanced underwater images. Our method reduces the number of parameters from 2.7 M to 0.45 M (around 83% reduction) but outperforms state-of-the-art algorithms by extensive experiments. Furthermore, we demonstrate our Rep-UWnet effectively improves high-level vision tasks like edge detection and single image depth estimation. This method not only surpasses the contrast method in objective quality, but also significantly improves the contrast, colorimetry, and clarity of underwater images in subjective quality. Full article

Clarifying the relationship between urbanization and farmland abandonment in urban agglomerations (UAs) is crucial to guide the formulation of arable land management policies and strategies for sustainable urban development. Despite numerous studies confirming the correlation between farmland abandonment and certain urbanization factors, the exploration of the patterns and underlying mechanisms of farmland abandonment in China’s UAs remains worthy of systematic investigation. In this study, we conducted an analysis of the spatiotemporal trends in farmland abandonment and examined the key drivers of farmland abandonment in four representative Chinese UAs—Beijing–Tianjin–Hebei (BTH), Chengdu–Chongqing (CC), Pearl River Delta (PRD), and Yangtze River Delta (YRD). Our findings reveal that farmland abandonment has been intensified with increasing fragmentation and aggregation patches across these UAs. Abandonment experience was the main driver of continuous abandonment. Moreover, natural conditions persistently influenced farmland abandonment in the BTH, while land urbanization and economic urbanization were predominant drivers in the CC. The abandonment in the PRD was mainly driven by population urbanization, while the abandonment in the YRD was primarily driven by economic urbanization and land urbanization. The research findings provide data support and scientific explanation for land policy-making in these typical UAs under different development strategies. Full article

Background: Leukoencephalopathy with brainstem and spinal cord involvement and lactate elevation is an inherited disease caused by pathogenic biallelic variants in the gene DARS2, which encodes mitochondrial aspartyl-tRNA synthetase. This disease is characterized by slowly progressive spastic gait, cerebellar symptoms, and leukoencephalopathy with brainstem and spinal cord involvement. Case Presentation: Peripheral blood samples were collected from four patients from four unrelated families to extract genomic DNA. All patients underwent partial exon analysis of the DARS2 gene using Sanger sequencing, which detected the c.228-21_228-20delinsC variant in a heterozygous state. Further DNA from three patients was analyzed using a next-generation sequencing-based custom AmpliSeq™ panel for 59 genes associated with leukodystrophies, and one of the patients underwent whole genome sequencing. We identified a novel pathogenic variant c.1675-1256_*115delinsGCAACATTTCGGCAACATTCCAACC in the DARS2 gene. Three patients (patients 1, 2, and 4) had slowly progressive cerebellar ataxia, and two patients (patients 1 and 2) had spasticity. In addition, two patients (patients 2 and 4) showed signs of axonal neuropathy, such as decreased tendon reflexes and loss of distal sensitivity. Three patients (patients 1, 2, and 3) also had learning difficulties. It should be noted the persistent presence of characteristic changes in brain MRI in all patients, which emphasizes its importance as the main diagnostic tool for suspicion and subsequent confirmation of LBSL. Conclusions: We found a novel indel variant in the DARS2 gene in four patients with LBSL and described their clinical and genetic characteristics. These results expand the mutational spectrum of LBSL and aim to improve the laboratory diagnosis of this form of leukodystrophy. Full article

Highly interactive honeypots can form reliable connections by responding to attackers to delay and capture intranet attacks. However, current research focuses on modeling the attacker as part of the environment and defining single-step attack actions by simulation to study the interaction of honeypots. It ignores the iterative nature of the attack and defense game, which is inconsistent with the correlative and sequential nature of actions in real attacks. These limitations lead to insufficient interaction of the honeypot response strategies generated by the study, making it difficult to support effective and continuous games with attack behaviors. In this paper, we propose an autonomous attack response framework (named AARF) to enhance interaction based on multi-agent dynamic games. AARF consists of three parts: a virtual honeynet environment, attack agents, and defense agents. Attack agents are modeled to generate multi-step attack chains based on a Hidden Markov Model (HMM) combined with the generic threat framework ATT&CK (Adversarial Tactics, Techniques, and Common Knowledge). The defense agents iteratively interact with the attack behavior chain based on reinforcement learning (RL) to learn to generate honeypot optimal response strategies. Aiming at the sample utilization inefficiency problem of random uniform sampling widely used in RL, we propose the dynamic value label sampling (DVLS) method in the dynamic environment. DVLS can effectively improve the sample utilization during the experience replay phase and thus improve the learning efficiency of honeypot agents under the RL framework. We further couple it with a classic DQN to replace the traditional random uniform sampling method. Based on AARF, we instantiate different functional honeypot models for deception in intranet scenarios. In the simulation environment, honeypots collaboratively respond to multi-step intranet attack chains to defend against these attacks, which demonstrates the effectiveness of AARF. The average cumulative reward of the DQN with DVLS is beyond eight percent, and the convergence speed is improved by five percent compared to a classic DQN. Full article

The Ca Mau Peninsula, situated in the Mekong Delta of Vietnam, features low-lying terrain. In addition to the challenges posed by climate change, land subsidence in the area is exacerbated by the overexploitation of groundwater and intensive agricultural practices. In this study, we assessed the land subsidence susceptibility in the Ca Mau Peninsula utilizing three boosting machine learning models: AdaBoost, Gradient Boosting, and Extreme Gradient Boosting (XGB). Eight key factors were identified as the most influential in land subsidence within Ca Mau: land cover (LULC), groundwater depth, digital terrain model (DTM), normalized vegetation index (NDVI), geology, soil composition, distance to roads, and distance to rivers and streams. The dataset includes 2011 points referenced from the Persistent Scattering SAR Interferometry (PSI) method, of which 1011 points are subsidence points and the remaining are non-subsidence points. The sample points were split, with 70% allocated to the training set and 30% to the testing set. Following computation and execution, the three models underwent evaluation for accuracy using statistical metrics such as the receiver operating characteristic (ROC) curve, area under the curve (AUC), specificity, sensitivity, and overall accuracy (ACC). The research findings revealed that the XGB model exhibited the highest accuracy, achieving an AUC and ACC above 0.88 for both the training and test sets. Consequently, XGB was chosen to construct a land subsidence susceptibility map for the Ca Mau Peninsula. In addition, 31 subsidence points measured by leveling surveys between 2005 and 2020, provided by the Department of Survey, Mapping and Geographic Information Vietnam, were used for validating the land subsidence susceptibility from the XGB method. The findings indicate a 70.9% accuracy rate in predicting subsidence susceptibility compared to the leveling measurement points. Full article

Previous studies have shown encouraging results regarding the efficacy and safety of nutraceuticals, such as “red yeast rice (RYR) extract”, on reducing hypercholesterolemia in humans. A systematic review and meta-analysis was conducted from January 2012 to May 2022. The search was strictly focused on clinical trials that examined the association between RYR extract consumption and parameters of the lipid profile in humans. Fourteen double-blinded clinical trials were identified. The interventions lasted 4–24 weeks. In most studies, there was one intervention group and one control group. RYR extract consumption statistically significantly reduced total cholesterol (mean absolute reduction: 37.43 mg/dL; 95% confidence interval [CI]: −47.08, −27.79) and low-density lipoprotein cholesterol (LDL-C; mean absolute reduction: 35.82 mg/dL; 95% CI: −43.36, −28.29), but not high-density lipoprotein cholesterol, triglycerides and apolipoproteins A-I and B. As regards the safety, RYR extract was considered a safe choice with neither threatening nor frequent side effects. The consumption of RYR extract by people with hypercholesterolemia was associated with statistically significant reduction in total cholesterol and LDL-C, whereas it was not associated with an increase in life-threatening side effects. Further research on specific subpopulations and outcomes could establish a consensus on determining the clinical benefits and potential risks, if any, of this nutraceutical. Full article

With the surging interest in electric vehicles (EVs), there is a need for advancements in the development and dismantling of lithium-ion batteries (LIBs), which are highly important for the circular economy. This paper introduces an intelligent hybrid task planner designed for multi-robot disassembly and demonstrates its application to an EV lithium-ion battery pack. The objective is to enable multiple robots to operate collaboratively in a single workspace to execute battery disassembly tasks efficiently and without collisions. This approach can be generalized to almost any disassembly task. The planner uses logical and hierarchical strategies to identify object locations from data captured by cameras mounted on each robot’s end-effector, orchestrating coordinated pick-and-place operations. The efficacy of this task planner was assessed through simulations with three trajectory-planning algorithms: RRT, RRTConnect, and RRTStar. Performance evaluations focused on completion times for battery disassembly tasks. The results showed that completion times were similar across the planners, with 543.06 s for RRT, 541.89 s for RRTConnect, and 547.27 s for RRTStar, illustrating that the effectiveness of the task planner is independent of the specific joint-trajectory-planning algorithm used. This demonstrates the planner’s capability to effectively manage multi-robot disassembly operations. Full article

Endometrial cancer (EC) poses a significant health issue among women, and its incidence has been rising for a couple of decades. Surgery remains its principal treatment method and may have a curative, staging, or palliative aim. The type and extent of surgery depends on many factors, and the risks and benefits should be carefully weighed. While simple hysterectomy might be sufficient in early stage EC, modified-radical hysterectomy is sometimes indicated. In advanced disease, the evidence suggests that, similarly to ovarian cancer, optimal cytoreduction improves survival rate. The role of lymphadenectomy in EC patients has long been a controversial issue. The rationale for systematic lymphadenectomy and the procedure of the sentinel lymph node biopsy are thoroughly discussed. Finally, the impact of the molecular classification and new International Federation of Gynecology and Obstetrics (FIGO) staging system on EC treatment is outlined. Due to the increasing knowledge on the pathology and molecular features of EC, as well as the new advances in the adjuvant therapies, the surgical management of EC has become more complex. In the modern approach, it is essential to adjust the extent of the surgery to a specific patient, ensuring an optimal, made-to-measure personalized surgery. This narrative review focuses on the intricacies of surgical management of EC and aims at summarizing the available literature on the subject, providing an up-to-date clinical guide. Full article

The extracellular matrix (ECM) is composed of complex fibrillar proteins, proteoglycans, and macromolecules, generated by stromal, immune, and cancer cells. The components and organisation of the matrix evolves as tumours progress to invasive disease and metastasis. In many solid tumours, dense fibrotic ECM has been hypothesised to impede therapy response by limiting drug and immune cell access. Interventions to target individual components of the ECM, collectively termed the matrisome, have, however, revealed complex tumour-suppressor, tumour-promoter, and immune-modulatory functions, which have complicated clinical translation. The degree to which distinct components of the matrisome can dictate tumour phenotypes and response to therapy is the subject of intense study. A primary aim is to identify therapeutic opportunities within the matrisome, which might support a better response to existing therapies. Many matrix signatures have been developed which can predict prognosis, immune cell content, and immunotherapy responses. In this review, we will examine key components of the matrisome which have been associated with advanced tumours and therapy resistance. We have primarily focussed here on targeting matrisome components, rather than specific cell types, although several examples are described where cells of origin can dramatically affect tumour roles for matrix components. As we unravel the complex biochemical, biophysical, and intracellular transduction mechanisms associated with the ECM, numerous therapeutic opportunities will be identified to modify tumour progression and therapy response. Full article

Background: Clinical case illustrations of patients with an impairment of personality functioning (IPF) have repeatedly reported that progress during psychotherapy is reflected by alterations in dream content. However, quantitative studies based on samples of psychotherapy patients are scarce. As a core component of both personality functioning and contemporary psychodynamic dream theory, the construct of affect regulation is of specific significance in this context. Aims: To test if improvement in personality functioning in the course of psychotherapy is associated with an increasing ability to regulate affects in dreams. Method: In a longitudinal design, affect regulation was compared in N = 94 unsolicited dream reports from the first vs. last third of long term psychotherapy of ten patients with initial IPF. Dream reports were transcribed from recordings of the sessions. Expert ratings of the level of personality functioning were obtained using the Scales of Psychological Capacities. The capacity for affect regulation was assessed using the Zurich Dream Process Coding System. Group differences were assessed using linear mixed models, controlling for dream length as well as the nested structure of this data set. Results: Patients demonstrated an increased capacity for affect regulation in dreams that was primarily evident in three core features: the complexity of dream elements (cf., e.g., parameter attributes, p = 0.024); the extent of affective involvement in the dream ego (cf., e.g., parameter subject feeling, p = 0.014); and the flexibility to regulate the dynamics of safety/involvement processes (p = < 0.001). This pattern was especially prominent in a subgroup (n = 7) of patients with more pronounced improvements in personality functioning. Conclusion: These findings support the hypotheses that decreasing IPF during psychotherapy is associated with increases in the capacity for affect regulation in dreams. Thus, researchers and therapists can utilize dream reports to illuminate the important aspects of treatment progress in clinical practice. Full article

To improve the power generation efficiency of offshore wind turbines and address the problem of high fire monitoring and warning costs, we propose a data-driven fire warning method based on transfer learning for wind turbines in this paper. This paper processes wind turbine operation data in a SCADA system. It uses an extreme gradient-boosting tree (XGBoost) algorithm to build an offshore wind turbine unit fire warning model with a multiparameter prediction function. This paper selects some parameters from the dataset as input variables for the model, with average cabin temperature, average outdoor temperature, average cabin humidity, and average atmospheric humidity as output variables. This paper analyzes the distribution information of input and output variables and their correlation, analyzes the predicted difference, and then provides an early warning for wind turbine fires. This paper uses this fire warning model to transfer learning to different models of offshore wind turbines in the same wind farm to achieve fire warning. The experimental results show that the prediction performance of the multiparameter is accurate, with an average MAPE of 0.016 and an average RMSE of 0.795. It is better than the average MAPE (0.051) and the average RMSE (2.020) of the prediction performance of a backpropagation (BP) neural network, as well as the average MAPE (0.030) and the average RMSE (1.301) of the prediction performance of random forest. The transfer learning model has good prediction performance, with an average MAPE of 0.022 and an average RMSE of 1.469. Full article

Federated learning (FL) has emerged as one of the de-facto privacy-preserving paradigms that can effectively work with decentralized data sources (e.g., hospitals) without acquiring any private data. Recently, applications of FL have vastly expanded into multiple domains, particularly the medical domain, and FL is becoming one of the mainstream technologies of the near future. In this study, we provide insights into FL fundamental concepts (e.g., the difference from centralized learning, functions of clients and servers, workflows, and nature of data), architecture and applications in the general medical domain, synergies with emerging technologies, key challenges (medical domain), and potential research prospects. We discuss major taxonomies of the FL systems and enlist technical factors in the FL ecosystem that are the foundation of many adversarial attacks on these systems. We also highlight the promising applications of FL in the medical domain by taking the recent COVID-19 pandemic as an application use case. We highlight potential research and development trajectories to further enhance the persuasiveness of this emerging paradigm from the technical point of view. We aim to concisely present the progress of FL up to the present in the medical domain including COVID-19 and to suggest future research trajectories in this area. Full article

Patient outcomes after percutaneous coronary intervention (PCI) have improved over the last 30 years due to better techniques, therapies, and care processes. This study evaluated contemporary predictors of post-PCI major adverse cardiovascular events (MACE) and summarized risk in a parsimonious risk prediction model. Methods: The Cardiovascular Patient-Level Analytical Platform (CLiPPeR) is an observational dataset of baseline variables and longitudinal outcomes from the American College of Cardiology’s CathPCI Registry^® and national claims data. Cox regression was used to evaluate 2–6 years of patient follow-up (mean: 2.56 years), ending in December 2017, after index PCI between 2012 and 2015 (N = 1,450,787), to examine clinical and procedural predictors of MACE (first myocardial infarction, stroke, repeat PCI, coronary artery bypass grafting, and mortality). Cox analyses of post-PCI MACE were landmarked 28 days after index PCI. Results: Overall, 12.4% (n = 179,849) experienced MACE. All variables predicted MACE, with cardiogenic shock, cardiac arrest, four diseased coronary vessels, and chronic kidney disease having hazard ratios (HRs) ≥ 1.50. Other major predictors of MACE were in-hospital stroke, three-vessel disease, anemia, heart failure, and STEMI presentation. The index revascularization and discharge prescription of aspirin, P2Y₁₂ inhibitor, and lipid-lowering medication had HR ≤ 0.67. The primary Cox model had c-statistic c = 0.761 for MACE versus c = 0.701 for the parsimonious model and c = 0.752 for the parsimonious model plus treatment variables. Conclusions: In a nationally representative US sample of post-PCI patients, predictors of longitudinal MACE risk were identified, and a parsimonious model efficiently encapsulated them. These findings may aid in assessing care processes to further improve care post-PCI outcomes. Full article

Lipedema is a subcutaneous adipose tissue disorder characterized by increased pathological adipocytes mainly in the extremities. Vitamin D is stored in adipocytes, and serum levels inversely correlate with BMI. As adipocytes are removed during liposuction, lipedema patients might be prone to further substantial vitamin D loss while their levels are already decreased. Therefore, we examined the effect of liposuction on perioperative serum 25-hydroxyvitamin D levels. Methods: In patients undergoing lipedema liposuction, blood samples were obtained pre- and postoperatively. Statistical analyses were performed to correlate the volume of lipoaspirate, patients’ BMI and number of sessions to vitamin D levels. Results: Overall, 213 patients were analyzed. Mean liposuction volume was 6615.33 ± 3884.25 mL, mean BMI was 32.18 ± 7.26 kg/m². mean preoperative vitamin D levels were 30.1 ± 14.45 ng/mL (borderline deficient according to the endocrine society) and mean postoperative vitamin D levels were 21.91 ± 9.18 ng/mL (deficient). A significant decrease in serum vitamin D was seen in our patients (p < 0.001) of mean 7.83 ng/mL. The amount of vitamin D loss was not associated with BMI or aspiration volume in our patients (p > 0.05). Interestingly, vitamin D dynamics showed a steady drop regardless of volume aspirated or preoperative levels. Conclusion: Many lipedema patients have low vitamin D levels preoperatively. Liposuction significantly reduced these levels additionally, regardless of aspirated volume or BMI. However, vitamin D loss was constant and predictable; thus, patients at risk are easily identified. Overall, lipedema patients undergoing liposuction are prone to vitamin D deficiency, and the long-term effects in this population are currently unknown. Full article