Background: Diabetes mellitus (DM) is a chronic disease with hyperglycemia. If not treated in time, it may lead to lower limb amputation. At the initial stage, the detection of diabetes-related foot ulcer (DFU) is very difficult. Deep learning has demonstrated state-of-the-art performance in various fields and has been used to analyze images of DFUs.Objective: This article reviewed current applications of deep learning to the early detection of DFU to avoid limb amputation or infection.Methods: Relevant literature on deep learning models, including in the classification, object detection, and semantic segmentation for images of DFU, published during the past 10 years, were analyzed.Results: Currently, the primary uses of deep learning in early DFU detection are related to different algorithms. For classification tasks, improved classification models were all based on convolutional neural networks (CNNs). The model with parallel convolutional layers based on GoogLeNet and the ensemble model outperformed the other models in classification accuracy. For object detection tasks, the models were based on architectures such as faster R-CNN, You-Only-Look-Once (YOLO) v3, YOLO v5, or EfficientDet. The refinements on YOLO v3 models achieved an accuracy of 91.95% and the model with an adaptive faster R-CNN architecture achieved a mean average precision (mAP) of 91.4%, which outperformed the other models. For semantic segmentation tasks, the models were based on architectures such as fully convolutional networks (FCNs), U-Net, V-Net, or SegNet. The model with U-Net outperformed the other models with an accuracy of 94.96%. Taking segmentation tasks as an example, the models were based on architectures such as mask R-CNN. The model with mask R-CNN obtained a precision value of 0.8632 and a mAP of 0.5084.Conclusion: Although current research is promising in the ability of deep learning to improve a patient’s quality of life, further research is required to better understand the mechanisms of deep learning for DFUs.

Treatment for anterior cruciate ligament (ACL) tears depends on the condition of the ligament. We aimed to identify different tear statuses from preoperative MRI using deep learning-based radiomics with sex and age. We reviewed 862 patients with preoperative MRI scans reflecting ACL status from Hunan Provincial People’s Hospital. Based on sagittal proton density-weighted images, a fully automated approach was developed that consisted of a deep learning model for segmenting ACL tissue (ACL-DNet) and a deep learning-based recognizer for ligament status classification (ACL-SNet). The efficacy of the proposed approach was evaluated by using the sensitivity, specificity and area under the receiver operating characteristic curve (AUC) and compared with that of a group of three orthopedists in the holdout test set. The ACL-DNet model yielded a Dice coefficient of 98% ± 6% on the MRI datasets. Our proposed classification model yielded a sensitivity of 97% and a specificity of 97%. In comparison, the sensitivity of alternative models ranged from 84 to 90%, while the specificity was between 86 and 92%. The AUC of the ACL-SNet model was 99%, demonstrating high overall diagnostic accuracy. The diagnostic performance of the clinical experts as reflected in the AUC was 96%, 92% and 88%, respectively. The fully automated model shows potential as a highly reliable and reproducible tool that allows orthopedists to noninvasively identify the ACL status and may aid in optimizing different techniques, such as ACL remnant preservation, for ACL reconstruction.

Male pattern hair loss (MPHL) is a common dermatological condition with significant psychological and clinical impacts. Traditional grading systems, such as the Norwood-Hamilton and Basic and Specific (BASP) classifications, rely on subjective assessments, limiting accuracy and reproducibility. This study introduces an AI-based grading framework that incorporates a novel area ratio metric to provide a more objective and standardized assessment of MPHL severity. A total of 761 images from 257 patients were analyzed to develop and evaluate an AI-based framework for grading MPHL. The framework utilizes the area ratio metric as a quantitative alternative to the traditional BASP length ratio. Model performance was assessed using precision and recall metrics, with bounding box and mask evaluations validating the accuracy and consistency of hair loss region identification. The AI model achieved an average precision of 97.6% in bounding box evaluations and 96.1% in mask assessments, demonstrating high accuracy in identifying hair loss regions. However, challenges in detecting smaller regions were reflected in slightly lower recall values for mask evaluations. Stratification accuracy was consistently high for Grades I, II, IV, and VI, with variability observed in intermediate grades due to boundary overlap. The novel area ratio metric outperformed the BASP length ratio, particularly in higher MPHL grades, offering a more reliable and objective framework for hair loss classification. This study shows that AI can improve MPHL diagnostics by using a data-driven and standardized grading system. The area ratio metric enhances precision and consistency, especially in advanced MPHL grades, offering better diagnostic accuracy and supporting personalized hair loss treatments.

Background and objectives: Osteoporosis (OP) presents a significant health issue in rheumatoid arthritis (RA) patients, yet existing machine learning (ML) studies on OP prediction in this population are limited by low accuracy, a narrow range of considered risk factors, and a lack of interpretability. This study aims to develop an interpretable machine learning model using the CNN-SVM algorithm, integrated with interpretability techniques, for individualized osteoporosis risk assessment in RA patients. The model specifically focuses on the osteopenia stage, which has been overlooked in previous research, to better capture the different risk factors involved in the progression of osteoporosis in RA patients. Methods: We recruited 314 RA patients from the Department of Rheumatology and Immunology. Participants were categorized into osteoporosis, osteopenia, and normal groups based on lumbar spine or hip bone mineral density (BMD) T-scores. We constructed ML model to assess osteoporosis using a novel classification algorithm, CNN-SVM, and employed SHapley Additive exPlanations (SHAP) and Sankey diagram to investigate significant risk factors, rank risk factor contributions, and provide individualized feature contribution explanations. Results: A total of 16 candidate variables were included, and three classification models were constructed to predict osteoporosis versus osteopenia, osteoporosis versus normal, and osteopenia versus normal. The AUC values for the models were 0.83, 0.93, and 0.74, respectively. Feature importance analysis using SHAP identified several key predictors. Factors such as Vitamin D supplements, Synovitis in Both Knees, and gender were crucial for distinguishing normal from osteopenia. For differentiating osteoporosis, Alendronate Sodium, weight, and age consistently ranked as highly influential features across different comparisons. Feature importance analysis was performed, ranking risk factors and providing individualized explanations of feature contributions. Conclusions: The developed interpretable ML model shows promise for screening osteoporosis risk in patients with RA. Its ability to identify individual risk factors highlights its potential to facilitate personalized prevention and management strategies, pending further validation.