AppendiGrade: An XAI-Enhanced Deep Learning Framework for Grading Appendicitis in Ultrasound with Gaussian Blur and Grad-CAM

Development of a deep learning model for intussusception using point-of-care ultrasound

Objective Intussusception is a pediatric emergency with delays in diagnosis. We sought to develop a novel deep learning model for the detection of target sign on point-of-care ultrasound (POCUS) images. Materials and methods POCUS image/video clip media files obtained during emergency department (ED) visits were included for study. Images underwent preprocessing to enhance and resize the region of interest (ROI), ImageNet high dimensional feature extraction and further training using various machine learning models, including classical machine learning, ensemble learning, transfer learning, and fine-tuning. Outputs were analyzed on a patient case, individual image frame and relative threshold bases. Results A POCUS image database of originally 785 media files from 49 patients, 8 of whom were positive for intussusception, was converted to 1,582 intussusception and 1,965 normal images for training. The output results show that the fine-tuning models performed better than the classical machine, ensemble and transfer learning models across three different analyses, and that the threshold-based approach to intussusception cases resulted in the greatest predictive performance. Discussion Intussusception is a potential candidate for development of deep learning tools due to limited capacity for pediatric focused imaging and accurate diagnosis. Prior studies are limited and have used either large private datasets or formal radiology studies. Modeling involved converting dynamic video files into several static images. Fine-tuning models were best adapted to the screening nature of POCUS images. Conclusion Our work demonstrated the feasibility of developing a deep learning model for the detection of intussusception using a smaller dataset of POCUS images.

PharyTriFuse: Knowledge- and LLM-Augmented Deep Learning for Bacterial Pharyngitis Detection from Smartphone Throat Images

Bacterial pharyngitis requires timely antibiotic treatment, whereas most non-bacterial cases are self-limited; diagnostic errors may therefore lead to missed infections or unnecessary antibiotic use. This study proposes PharyTriFuse, a multimodal framework that integrates throat-image analysis with large language model (LLM) reasoning and a medical knowledge graph (KG) to classify bacterial versus non-bacterial pharyngitis from smartphone-acquired oropharyngeal images. Experiments were conducted on the public PGUPharyngitis dataset over 742 images using a stratified 72%/8%/20% train/validation/test split. Images were standardized using CLAHE and redness enhancement to reduce acquisition variability. Two visual backbones (EfficientNet-B4 and ConvNeXt-Base) were evaluated under four configurations: AI-only, AI+LLM, AI+KG, and AI+LLM+KG. Performance was assessed using standard classification metrics and inference efficiency. Results show that incorporating LLM reasoning and structured medical knowledge improves classification performance over vision-only baselines while maintaining real-time inference capability under certain configurations. These findings suggest that multimodal AI systems can enhance smartphone-based decision support for pharyngitis assessment.

Improving COVID-19 Detection Using Deep Learning on Chest X-Ray Images: A Comprehensive Study

YOLO11-based deep learning system for automated tubal patency classification in hysterosalpingography: a comparative study for clinical decision support.

In the United States, around 500,000 hysterosalpingography (HSG) procedures are performed annually. One fluoroscopic procedure that is frequently used to evaluate tubal patency in infertile women is hysterosalpingography. Clinical decision-making depends on the fast and accurate classification of tubal patency results, but this procedure still depends on radiologist skill, which varies greatly across clinical situations. In order to automatically classify tubal patency categories in HSG pictures, this study suggests using YOLO11, a cutting-edge deep learning architecture. Three baseline models YOLOv8n, ResNet50, and EfficientNetB0 were used to train and evaluate YOLO11s using a publicly accessible clinical dataset of 892 real HSG images annotated by three board-certified radiologists and arranged into four pathological categories: bilateral patency, bilateral blockage, bilateral partial patency, and unilateral patency. Standardized training techniques were used to conduct experiments on GPU-accelerated infrastructure. With an inference speed of 19.98 ms per image and an overall test accuracy of 76%, YOLO11s demonstrated clinically relevant performance for the Unilateral Patency class (F1-score = 0.83, recall = 0.96). YOLO11s demonstrated competitive accuracy with much fewer parameters than ResNet50 (5.4 M vs. 25.6 M), outperforming ResNet50 (75.0%) and YOLOv8n (67.12%), matching EfficientNetB0 (76.19%) within 0.2%. The main factor restricting performance on minority classes was found to be class imbalance, with Unilateral Patency accounting for 66% of training images. While the results are promising for a novel application domain, the model's failure on clinically critical minority classes (Bilateral Blockage, Bilateral Patency) means it is not yet suitable for unsupervised clinical use. The proposed system should be considered as an exploratory research baseline requiring further development, class-imbalance mitigation, and prospective clinical validation before any clinical decision support application.

STL‐DeepBDC: A Robust Few‐Shot Learning Framework for Multiclass Ovarian Tumor Classification in Ultrasound Outperforms Conventional Transfer Learning

ABSTRACT Background Accurate preoperative pathological classification of malignant and borderline ovarian tumors (OMTs) can support surgical planning, fertility preservation, and prognosis, but ultrasound‐based subtype assessment remains difficult because imaging phenotypes are heterogeneous, class imbalance is common, and interpretation varies among operators. This study developed and evaluated an exploratory deep learning framework for multiclass ovarian tumor classification under small‐sample conditions. Methods This single‐center retrospective study used ultrasound images from patients with surgically and pathologically confirmed OMTs treated between August 2017 and October 2022. Six pathological types were included. After quality control, preprocessing, and augmentation, the dataset was split at the patient level into training, validation, and test sets at a 5:3:2 ratio. An optimized ConvNeXt model served as the baseline. STL‐DeepBDC combined stratified transfer learning with a Deep Bilinear Discriminative Covariance module. Performance was evaluated using accuracy, sensitivity, specificity, macro‐F1 score, AUC, AUPRC, and Grad‐CAM. Results STL‐DeepBDC outperformed the optimized ConvNeXt baseline. Accuracy increased from 0.51 to 0.67, macro‐average sensitivity from 0.53 to 0.68, specificity from 0.87 to 0.92, and macro‐F1 score from 0.52 to 0.66. Macro‐average AUC improved from 0.75 to 0.87, and macro‐average AUPRC from 0.49 to 0.63. Category‐level AUCs ranged from 0.76 to 0.94 and AUPRCs from 0.51 to 0.78, suggesting more stable discrimination across six pathological types under class imbalance. Ablation analysis supported the contributions of STL and DeepBDC. Grad‐CAM highlighted clinically relevant regions, including thickened cyst walls, papillary projections, septations, and solid components. Conclusion STL‐DeepBDC provides an exploratory, interpretable framework for ultrasound‐based multiclass ovarian tumor classification in a limited‐sample setting. Larger multicenter studies with external validation are required before clinical implementation.

A deep learning-based study on automated CT diagnosis of kidney stones, hydronephrosis and pyonephrosis.

Automated identification of urinary system diseases on non-contrast computed tomography (NCCT) can facilitate early diagnosis and inform treatment decisions. However, kidney stones, hydronephrosis, and pyonephrosis share overlapping NCCT appearances and require diagnostic cues at different spatial scales, making accurate identification within a unified framework challenging. To address this, we constructed an integrated CT-based framework for automated identification of urinary system diseases. First, the collected CT data were split into training, validation, and test sets and processed using a unified preprocessing pipeline for resolution standardization and normalization. Subsequently, we evaluated multiple image enhancement strategies, including histogram equalization, CLAHE, Laplacian sharpening, and brightness enhancement. We conducted a systematic comparison of these enhancement methods to quantify their effects on disease identification performance. To support unified automated diagnosis of kidney stones, hydronephrosis, and pyonephrosis, we developed a multi-disease renal diagnostic network, MSF-TEA Net. Through multi-scale feature fusion and multi-evidence collaborative modeling, it effectively represents the image features of different pathological states. This model introduces Tri-Evidence Attention (TEA), which models the high-density features of small calculi targets, the global morphological changes of fluid accumulation, and the inflammatory texture features of pus accumulation. Through adaptive weighted fusion, the network enhances discrimination and diagnostic performance when complex lesions coexist. Experimental results show that, within the unified MSF-TEA Net framework, Laplacian sharpening achieves the best performance among the tested enhancement methods, with a test accuracy of 94.40% ± 1.13% and an AUC of 99.30%, outperforming the other enhancement strategies. Ablation studies further confirm the contributions of PPM, ASPP, and TEA. Overall, the proposed unified framework enables reliable identification of kidney stones, hydronephrosis, and pyonephrosis, supporting clinical decision-making.