Search Results (56)

Background/Objectives: Scaphoid fractures are a common wrist injury, typically diagnosed and treated through X-ray imaging, a process that is often time-consuming. Among the various types of scaphoid fractures, occult and nondisplaced fractures pose significant diagnostic challenges due to their subtle appearance and variable bone density, complicating accurate identification via X-ray images. Therefore, creating a reliable assist diagnostic system based on deep learning for the scaphoid fracture detection and localization is critical. Methods: This study proposes a scaphoid fracture detection and localization framework based on diffusion models. In Stage I, we augment the training data set by embedding fracture anomalies. Pseudofracture regions are generated on healthy scaphoid images, producing healthy and fractured data sets, forming a self-supervised learning strategy that avoids the complex and time-consuming manual annotation of medical images. In Stage II, a diffusion-based reconstruction model learns the features of healthy scaphoid images to perform high-quality reconstruction of pseudofractured scaphoid images, generating healthy scaphoid images. In Stage III, a U-Net-like network identifies differences between the target and reconstructed images, using these differences to determine whether the target scaphoid image contains a fracture. Results: After model training, we evaluated its diagnostic performance on real scaphoid images by comparing the model’s results with precise fracture locations further annotated by physicians. The proposed method achieved an image area under the receiver operating characteristic curve (AUROC) of 0.993 for scaphoid fracture detection, corresponding to an accuracy of 0.983, recall of 1.00, and precision of 0.975. For fracture localization, the model achieved a pixel AUROC of 0.978 and a pixel region overlap of 0.921. Conclusions: This study shows promise as a reliable, powerful, and scalable solution for the scaphoid fracture detection and localization. Experimental results demonstrate the strong performance of the denoising diffusion models; these models can significantly reduce diagnostic time while precisely localizing potential fracture regions, identifying conditions overlooked by the human eye. Full article

Background/Objectives: Demodex mites are a common yet underdiagnosed cause of ocular surface diseases, including blepharitis and meibomian gland dysfunction (MGD). Traditional diagnosis via microscopic examination is labor-intensive and time-consuming. This study aimed to develop a deep learning-based system for the automated detection and quantification of Demodex mites from microscopic eyelash images. Methods: We collected 1610 microscopic images of eyelashes from patients clinically suspected to have ocular demodicosis. After quality screening, 665 images with visible Demodex features were annotated and processed. Two deep learning models, YOLOv11 and RT-DETR, were trained and evaluated using standard metrics. Grad-CAM visualization was applied to confirm model attention and feature localization. Results: Both YOLO and RT-DETR models were able to detect Demodex mites in our microscopic images. The YOLOv11 boxing model revealed an average precision of 0.9441, sensitivity of 0.9478, and F1-score of 0.9459 in our detection system, while the RT-DETR model showed an average precision of 0.7513, sensitivity of 0.9389, and F1-score of 0.8322. Moreover, Grad-CAM visualization confirmed the models’ focus on relevant mite features. Quantitative analysis enabled consistent mite counting across overlapping regions, with a confidence level of 0.4–0.8, confirming stable enumeration performance. Conclusions: The proposed artificial intelligence (AI)-based detection system demonstrates strong potential for assisting ophthalmologists in diagnosing ocular demodicosis efficiently and accurately, reducing reliance on manual microscopy and enabling faster clinical decision making. Full article

Homologous recombination deficiency (HRD) is a clinically relevant biomarker that predicts sensitivity to PARP inhibitors and enables personalized cancer therapy. Validated local HRD testing solutions are essential to ensure timely and equitable access, ultimately improving treatment outcomes. We evaluated a shallow whole-genome sequencing (sWGS) approach for genomic instability (GI) assessment combined with a 52-gene targeted panel in ovarian cancer. Validation used reference materials and 24 archival samples with prior HRD characterization, comparing performance with the Myriad myChoice^® HRD test. A prospective cohort of 124 newly diagnosed ovarian cancer patients was then analyzed. sWGS-derived GI status showed strong concordance with the reference test (95.8% overall agreement; κ = 0.913; NPV 100%, PPV 93.3%). Pathogenic BRCA1/2 variants were detected in 30 patients (24.19%). An additional 22.76% were BRCA1/2-negative but GI-positive, giving an overall HRD prevalence of 47.15%. Platinum sensitivity occurred in 90.0% (18/20) of HRD-positive patients with follow-up. Among 12 patients assessed for PARP-inhibitor response, the overall response rate was 66.7% (95% CI 39.1–86.2) and disease control rate 83.3% (95% CI 55.2–95.3). TP53 alterations were most frequent (62.90%), followed by BRCA1 (19.35%) and BRCA2 (4.83%). Pathogenic variants in other HR-pathway genes (ATM, CHEK2, BRIP1, RAD51C, BARD1) appeared in 9.57% of BRCA-wild-type cases, with heterogeneous GI impact. Two cases showed concurrent BRCA2 variants and microsatellite instability, indicating possible eligibility for anti-PD-1/PD-L1 therapy in addition to PARPi. This first comprehensive analysis of Romanian ovarian cancer patients suggests that integrating sWGS-based genomic instability assessment with BRCA testing can improve HRD detection and reflects the heterogeneity of HR-pathway variants. Preliminary clinical observations were consistent with known HRD-associated treatment responses, although larger studies are needed to confirm these findings. Full article

As the foundational carrier of socio-economic development and ecological security, territorial space reflects the degree of coordination between functional structure and efficiency output. However, most existing evaluation methods overlook the heterogeneous functional endowments of spatial units and therefore cannot reasonably assess the efficiency that each unit should achieve under comparable conditions. To address this limitation, this study proposes a function-oriented and interpretable framework for territorial spatial efficiency evaluation based on the Production–Living–Ecological (PLE) paradigm. An entropy-weighted indicator system is constructed to measure production, living, and ecological efficiency, and an XGBoost–SHAP model is developed to infer the nonlinear mapping between functional attributes and efficiency performance and to estimate the ideal efficiency of each spatial unit under Quanzhou’s prevailing macro-environment. By comparing ideal and observed efficiency, functional–efficiency deviations are identified and spatially diagnosed. The results show that territorial efficiency exhibits strong spatial heterogeneity: production and living efficiency concentrate in the southeastern coastal belt, whereas ecological efficiency dominates in the northwestern mountainous region. The mechanisms differ substantially across dimensions. Production efficiency is primarily driven by neighborhood living and productive conditions; living efficiency is dominated by structural inheritance and strengthened by service-related spillovers; and ecological efficiency depends overwhelmingly on local ecological endowments with additional neighborhood synergy. Approximately 45% of spatial units achieve functional–efficiency alignment, while peri-urban transition zones and hilly areas present significant negative deviations. This study advances territorial efficiency research by linking functional structure to efficiency generation through explainable machine learning, providing an interpretable analytical tool and actionable guidance for place-based spatial optimization and high-quality territorial governance. Full article

The intensification of urban heat in high-density cities has raised growing concerns for public health, infrastructural resilience, and environmental sustainability. As large-scale, multi-functional open spaces, sports stadiums play an underexplored role in shaping urban thermal patterns. This study investigates the spatial and temporal thermal characteristics of eight representative stadiums in central Shanghai and the Pudong New Area from 2018 to 2023. A dual-framework approach is proposed: the Stadium-based Urban Island Regulation (SUIR) model conceptualizes stadiums as active cooling agents across micro to macro spatial scales, while the Multi-source Thermal Cognition System (MTCS) integrates multi-sensor satellite data—Landsat, MODIS, Sentinel-1/2—with anthropogenic and ecological indicators to diagnose surface temperature dynamics. Remote sensing fusion and machine learning analyses reveal clear intra-stadium thermal heterogeneity: track zones consistently recorded the highest land surface temperatures (up to 37.5 °C), while grass fields exhibited strong cooling effects (as low as 29.8 °C). Buffer analysis shows that cooling effects were most pronounced within 300–500 m, varying with local morphology. A spatial diffusion model further demonstrates that stadiums with large, vegetated buffers or proximity to water bodies exert a broader regional cooling influence. Correlation and Random Forest regression analyses identify the building volume (r = 0.81), NDVI (r = −0.53), nighttime light intensity, and traffic density as key thermal drivers. These findings offer new insight into the role of stadiums in urban heat mitigation and provide practical implications for scale-sensitive, climate-adaptive urban planning strategies. Full article

Partial discharge (PD) is not only a critical indicator but also a major accelerating factor of insulation degradation in power transformers. Accurate identification of PD types is essential for diagnosing insulation defects and locating faults in transformers. Traditional methods based on phase-resolved partial discharge (PRPD) patterns typically rely on expert interpretation and manual feature extraction, which are increasingly being supplanted by Convolutional Neural Networks (CNNs) due to their ability to automatically extract features and deliver high classification accuracy. However, the inherent subtlety and diversity of characteristic differences among PRPD patterns, coupled with substantial noise resulting from complex electromagnetic interference, present significant hurdles to achieving accurate identification. This paper proposes a transformer partial discharge identification method based on Deep Residual Shrinkage Network (DRSN) to address these challenges. The method integrates dual-path feature extraction to capture both local and global features, incorporates a channel-domain adaptive soft-thresholding mechanism to effectively suppress noise interference, and utilizes the Focal Loss function to enhance the model’s attention to hard-to-classify samples. To validate the proposed method, given the scarcity of diverse real-world transformer PD data, an experimental platform was utilized to generate and collect PD data by artificially simulating various discharge defect models, including tip discharge, surface discharge, air-gap discharge and floating discharge. Data diversity was then enhanced through sample augmentation and noise simulation, to minimize the gap between experimental data and real-world on-site data. Experimental results demonstrate that the proposed method achieves superior partial discharge recognition accuracy and strong noise robustness on the experimental dataset. For future work, it is essential to collect more real transformer PD data to further validate and strengthen the model’s generalization capability, thereby ensuring its robust performance and applicability in practical scenarios. Full article

Electroencephalogram (EEG) analysis is essential for diagnosing neurological disorders but typically requires expert interpretation and significant time. Purpose: This study aims to automate the classification of normal and abnormal EEG recordings to support clinical diagnosis and reduce manual workload. Automating the initial screening of EEGs can help clinicians quickly identify potential neurological abnormalities, enabling timely intervention and guiding further diagnostic and treatment strategies. Methodology: We utilized the Temple University Hospital EEG dataset to develop a DenseNet-based deep learning model. To enable a fair comparison of different EEG representations, we used three input types: signal images, spectrograms, and scalograms. To reduce dimensionality and simplify computation, we focused on two channels: T5 and O1. For interpretability, we applied Local Interpretable Model-agnostic Explanations (LIME) and Gradient-weighted Class Activation Mapping (Grad-CAM) to visualize the EEG regions influencing the model’s predictions. Key Findings: Among the input types, spectrogram-based representations achieved the highest classification accuracy, indicating that time-frequency features are especially effective for this task. The model demonstrated strong performance overall, and the integration of LIME and Grad-CAM provided transparent explanations of its decisions, enhancing interpretability. This approach offers a practical and interpretable solution for automated EEG screening, contributing to more efficient clinical workflows and better understanding of complex neurological conditions. Full article

The evaluation of large language models (LLMs) increasingly relies on other LLMs acting as automated judges. While this approach offers scalability and efficiency, it raises serious concerns regarding evaluator reliability, positional bias, and ranking stability. This paper presents a scalable framework for diagnosing positional bias and instability in LLM-based evaluation by using controlled pairwise comparisons judged by multiple independent language models. The system supports mirrored comparisons with reversed response order, prompt injection, and surface-level perturbations (e.g., paraphrasing, lexical noise), enabling fine-grained analysis of evaluator consistency and verdict robustness. Over 3600 pairwise comparisons were conducted across five instruction-tuned open-weight models using ten open-ended prompts. The top-performing model (gemma:7b-instruct) achieved a 66.5% win rate. Evaluator agreement was uniformly high, with 100% consistency across judges, yet 48.4% of verdicts reversed under mirrored response order, indicating strong positional bias. Kendall’s Tau analysis further showed that local model rankings varied substantially across prompts, suggesting that semantic context influences evaluator judgment. All evaluation traces were stored in a graph database (Neo4j), enabling structured querying and longitudinal analysis. The proposed framework provides not only a diagnostic lens for benchmarking models but also a blueprint for fairer and more interpretable LLM-based evaluation. These findings underscore the need for structure-aware, perturbation-resilient evaluation pipelines when benchmarking LLMs. The proposed framework offers a reproducible path for diagnosing evaluator bias and ranking instability in open-ended language tasks. Future work will apply this methodology to educational assessment tasks, using rubric-based scoring and graph-based traceability to evaluate student responses in technical domains. Full article

Structural magnetic resonance imaging (sMRI) is a vital tool for diagnosing neurological brain diseases. However, sMRI scans often show significant structural changes only in limited brain regions due to localised atrophy, making the identification of discriminative features a key challenge. Importantly, the human brain exhibits inherent bilateral symmetry, and deviations from this symmetry—such as asymmetric atrophy—are strong indicators of early Alzheimer’s disease (AD). Patch-based methods help capture local brain changes for early AD diagnosis, but they often struggle with fixed-size limitations, potentially missing subtle asymmetries or broader contextual cues. To address these limitations, we propose a novel augmented reality (AR)-enhanced patch-level explainable deep learning (ARE-PaLED) system. It includes an adaptive multi-scale patch extraction network (AMPEN) to adjust patch sizes based on anatomical characteristics and spatial context, as well as an informative patch selection algorithm (IPSA) to identify discriminative patches, including those reflecting asymmetry patterns associated with AD; additionally, an AR module is proposed for future immersive explainability, complementing the patch-level interpretation framework. Evaluated on 1862 subjects from the ADNI and AIBL datasets, the framework achieved an accuracy of 92.5% (AD vs. NC) and 85.9% (AD vs. MCI). The proposed ARE-PaLED demonstrates potential as an interpretable and immersive diagnostic aid for sMRI-based AD diagnosis, supporting the interpretation of model predictions for AD diagnosis. Full article

Background and Objectives: Chronic mucosal infection with Helicobacter pylori (H. pylori) plays a key role in the development of gastroduodenal disorders such as chronic gastritis, peptic ulcers, gastric lymphoma, and gastric cancer by triggering local immune responses and inducing hypoxic and inflammatory conditions in the gastric mucosa. This study aims to evaluate the potential diagnostic value of hypoxia-inducible factors HIF-1α and HIF-2α, along with transmembrane prolyl 4-hydroxylase (P4H-TM), as biomarkers in H. pylori-positive patients. Additionally, the study investigates the association between these markers and alterations in lipid profiles, as well as their involvement in the molecular mechanisms underlying gastric conditions like gastritis, particularly in the context of H. pylori infection. Materials and Methods: This study was conducted at Istanbul Avcılar Murat Kölük State Hospital’s General Surgery Outpatient Clinic. A total of 60 participants were included: 40 patients diagnosed with chronic gastritis (20 H. pylori-positive and 20 H. pylori-negative) and 20 healthy controls confirmed negative by 13C-urea breath test. Blood samples were collected for ELISA analysis of HIF-1α, HIF-2α, and P4H-TM levels. Additionally, lipid profiles were measured and compared among the groups. Results: No significant differences were found among the groups in terms of demographic factors such as age, sex, or body mass index (BMI). However, significant variations were observed in the levels of HIF-1α, HIF-2α, and P4H-TM across all groups (p < 0.001 for each marker). These markers were substantially elevated in the H. pylori-positive gastritis group compared to both the H. pylori-negative and healthy control groups. Receiver Operating Characteristic (ROC) curve analysis revealed that all evaluated markers exhibited strong diagnostic accuracy in differentiating H. pylori-positive individuals from other groups. HIF-1α (AUC: 0.983) and HIF-2α (AUC: 0.981) both achieved 100% sensitivity with specificities of 93.3% and 91.1%, respectively. P4H-TM showed an AUC of 0.927, with 85% sensitivity and 95.6% specificity. Conclusions: These findings indicate that HIF-1α, HIF-2α, and P4H-TM may serve as effective biomarkers for diagnosing H. pylori-positive patients and may be linked to changes in lipid metabolism. The elevated expression of these markers in response to H. pylori infection highlights their potential roles in the inflammatory and hypoxic pathways that contribute to the pathogenesis of gastric diseases such as gastritis. Full article

The air-handling unit (AHU) is an essential component of heating, ventilation, and air-conditioning (HVAC) systems. Hence, detecting the faults in AHUs is essential for maintaining continuous HVAC operation and preventing system breakdowns. The advent of artificial intelligence has transformed the AHU fault diagnosis techniques. Specifically, deep learning has obviated the necessity for manual feature extraction and selection, thereby streamlining the fault diagnosis process. While conventional convolutional neural networks (CNNs) effectively detect defects, incorporating more spatial variables could enhance their performance further. This paper presents a hybrid architecture combining a CNN model with a long short-term memory (LSTM) model to diagnose the faults in AHUs. The advantages of the LSTM model and convolutional layers are combined to identify significant patterns in the input data, which considerably facilitates the detection of AHU defects. The hybrid design enhances the network’s capability to capture both local and global characteristics, thus improving its ability to differentiate between normal and abnormal circumstances. The proposed approach achieves strong diagnostic accuracy, exhibiting high sensitivity to nuanced fault patterns. Furthermore, its efficacy is corroborated through comparisons with state-of-the-art AHU fault identification techniques. Full article

30 percent of infertile men are diagnosed with idiopathic infertility. This study aimed to assess oxidative stress in the semen of 77 patients with idiopathic infertility by measuring F₂-isoprostane (F₂-IsoP), resolvin D1 (RvD1) levels, and semen parameters. The presence and localization of 8-IsoProstaglandin F_2α were determined using immunofluorescence. No significant correlations were observed for F₂-IsoP and RvD1 levels with the semen variables. Based on F₂-IsoP levels, individuals were classified into two groups: Group 1 (F₂-IsoPs ≤ 29.96 ng/mL, 51%) and Group 2 (F₂-IsoPs > 29.96 ng/mL, 49%). In comparison to Group 1, Group 2 showed significantly higher F₂-IsoP levels (13.33 ng/mL vs. 44.80 ng/mL; p < 0.05), a lower progressive motility percentage (30% vs. 25%; p < 0.05), and increased RvD1 levels (36.09% vs. 44.94%). Immunofluorescence analysis revealed a different localization of 8-IsoProstaglandin F_2α in the ejaculated sperm of Group 1 compared to that observed in Group 2. A weak signal was detected in the sperm tail (Group 1, 79.1% vs. Group 2, 36.9; p < 0.01). In spermatozoa of Group 2 patients, a strong signal in the acrosome, midpiece, and tail was highlighted. These findings suggest the need to test oxidative stress during routine semen analysis in patients with idiopathic infertility to improve diagnosis and treatment. Full article

In the electric locomotive traction transmission system, a four-quadrant rectifier has a high fault rate owing to the complicated control and bad operating conditions, and the fault directly affects the system’s safety and stability. To address such an issue, a rectifier fault diagnosis approach regarding a local tangent space alignment (LTSA) dimensionality reduction to optimize the high-dimensional energy entropy feature is proposed. Firstly, the fault signal is analyzed by using different wavelet functions through wavelet packet multi-resolution decomposition technology so as to extract the frequency band information of the signal. Each wavelet function corresponds to a specific frequency band; the energy–information entropy ratio of each frequency band coefficient is calculated, and then, the wavelet function and optimal frequency band, which are appropriate for the fault signal, are determined. Secondly, the energy entropy of each coefficient in the optimal frequency band is calculated to form the high-dimensional energy entropy feature. The LTSA algorithm is adopted to optimize the high-dimensional feature, through the fault sample number and clustering results, solve the difficulty of selecting the inherent dimension and nearest neighbor number in high-dimensional data, and obtain the simple and effective low-dimensional feature vector to describe the fault features, which reduces the conflict and redundancy between features. Finally, the optimized fault features are used as an input to the classifier support vector machine (SVM), and the fault types are obtained through training and testing. To validate the efficacy of the presented approach, it is tested from the aspects of noise environment, sample proportion and algorithm complexity, and compared with advanced methods. The results indicate that the proposed technique attains an average accuracy of 99.0625% in four-quadrant rectifier fault diagnosis. Under a different signal-to-noise ratio (SNR) and different training and test ratios, the average value after 30 diagnoses is better. Compared with other methods, this method shows a high diagnostic rate and strong robustness in terms of output voltage, noise, training and test ratio. Full article

Boron-containing compounds (BCCs) have been proposed for the treatment of diabetes and its complications. Recent studies have reported an improvement in the design and development of pharmaceutical formulations (often gels) containing boric acid applied to the foot ulcers of humans diagnosed with diabetes. The proposed mechanisms of action of boric acid include antimicrobial effects, the modulation of inflammation and metabolism, and the induction of cell differentiation. On the other hand, recent studies have suggested that boronic acids are potent antibacterial and antifungal compounds, effective modulators of inflammation, and inducers of vascular regeneration as well as inducers of healing, and they confer attractive properties such as adhesion, interaction, and the formation of complexes in formulations. Moreover, only a handful of studies conducted in animals have suggested the effective role of some BCCs as potent enhancers of wound healing, including their actions on induced and/or infected wounds in animals with disrupted metabolism. Also, it should be mentioned that no strong interactions between boric acid and the boronic acids present in formulations have been described. The developed combination could act as an additive and complementary therapy in the treatment of diabetic ulcers in humans. Further studies are required to support the hypothesis that this combination acts through diverse mechanisms to improve healing while avoiding or limiting a local or disseminated infection. Furthermore, the safety of BCCs used for foot ulcers should be established, as should the role of these formulations as a complementary therapy in current protocols for treating patients with diabetic foot ulcers. Full article

Background/Objectives: The study aimed to compare the treatment effectiveness of patients with locally advanced rectal cancer undergoing standard neoadjuvant therapy or total neoadjuvant therapy. It also sought to identify prognostic factors for disease-free survival and overall survival and parameters predictive of pathological complete response. Materials and Methods: A retrospective analysis was conducted on 239 patients diagnosed with locally advanced rectal cancer between 2016 and 2022 at several medical centers in Turkey. Clinical data, including neoadjuvant chemoradiotherapy types, chemotherapy regimens, surgical outcomes, and survival metrics, were collected. Statistical analyses included chi-square tests, Kaplan–Meier survival analysis, and Cox proportional hazard models to evaluate prognostic factors for disease-free survival and overall survival and logistic regression to identify predictors of pathological complete response. Results: Among 239 patients, 46.9% received total neoadjuvant therapy, while 53.1% underwent standard neoadjuvant therapy. Total neoadjuvant therapy was associated with a significantly higher pathological complete response rate (45.5% vs. 14.9% in standard neoadjuvant therapy; p < 0.001) and longer disease-free survival (median 124.2 vs. 72.4 months). The 3-year overall survival rate for all patients was 90.7%, and disease-free survival was 76.8%. Multivariate analysis identified pathological complete response (HR: 2.34), total neoadjuvant therapy (HR: 5.12), and type of surgery (HR: 8.12) as independent prognostic factors for disease-free survival, and pathological complete response and absence of lymphovascular invasion as independent prognostic factors for overall survival. Logistic regression analysis showed that total neoadjuvant therapy (OR: 4.40) and initial neoadjuvant chemotherapy (OR: 2.02) were independent predictors of achieving pathological complete response. Conclusions: Total neoadjuvant therapy significantly improves pathological complete response rates, disease-free survival, and overall survival in patients with locally advanced rectal cancer compared to standard neoadjuvant therapy. Total neoadjuvant therapy and achieving pathological complete response are strong independent prognostic factors for both disease-free survival and overall survival, suggesting that a more intensive neoadjuvant approach may lead to better outcomes in locally advanced rectal cancer. The increased pathological complete responses rate with total neoadjuvant therapy has created an opportunity for the development of new treatment modalities and the advancement of non-surgical management strategies in the future. Full article