Advanced diagnostic instruments are crucial for the accurate detection and treatment of lung diseases, which affect millions of individuals globally. This study examines the effectiveness of deep learning and transfer learning models using a hybrid dataset, created by merging four individual datasets from Bangladesh and global sources. The hybrid dataset significantly enhances model accuracy and generalizability, particularly in detecting COVID-19, pneumonia, lung opacity, and normal lung conditions from chest X-ray images. A range of models, including CNN, VGG16, VGG19, InceptionV3, Xception, ResNet50V2, InceptionResNetV2, MobileNetV2, and DenseNet121, were applied to both individual and hybrid datasets. The results showed superior performance on the hybrid dataset, with VGG16, Xception, ResNet50V2, and DenseNet121 each achieving an accuracy of 99%. This consistent performance across the hybrid dataset highlights the robustness of these models in handling diverse data while maintaining high accuracy. To understand the models implicit behavior, explainable AI techniques were employed to illuminate their black-box nature. Specifically, LIME was used to enhance the interpretability of model predictions, especially in cases of misclassification, contributing to the development of reliable and interpretable AI-driven solutions for medical imaging.

With the growing capabilities of language models like ChatGPT to process text and images, this study evaluated their accuracy in detecting supernumerary teeth on periapical radiographs. A customized GPT-4V model (CGPT-4V) was also developed to assess whether domain-specific training could improve diagnostic performance compared to standard GPT-4V and GPT-4o models. One hundred eighty periapical radiographs (90 with and 90 without supernumerary teeth) were evaluated using GPT-4 V, GPT-4o, and a fine-tuned CGPT-4V model. Each image was assessed separately with the standardized prompt "Are there any supernumerary teeth in the radiograph above?" to avoid contextual bias. Three dental experts scored the responses using a three-point Likert scale for positive cases and a binary scale for negatives. Chi-square tests and ROC analysis were used to compare model performances (p < 0.05). Among the three models, CGPT-4 V exhibited the highest accuracy, detecting supernumerary teeth correctly in 91% of cases, compared to 77% for GPT-4o and 63% for GPT-4V. The CGPT-4V model also demonstrated a significantly lower false positive rate (16%) than GPT-4V (42%). A statistically significant difference was found between CGPT-4V and GPT-4o (p < 0.001), while no significant difference was observed between GPT-4V and CGPT-4V or between GPT-4V and GPT-4o. Additionally, CGPT-4V successfully identified multiple supernumerary teeth in radiographs where present. These findings highlight the diagnostic potential of customized GPT models in dental radiology. Future research should focus on multicenter validation, seamless clinical integration, and cost-effectiveness to support real-world implementation.

Foundation models leveraging vision-language pretraining have shown promise in chest X-ray (CXR) interpretation, yet their real-world performance across diverse populations and diagnostic tasks remains insufficiently evaluated. This study benchmarks the diagnostic performance and generalizability of foundation models versus traditional convolutional neural networks (CNNs) on multinational CXR datasets. We evaluated eight CXR diagnostic models - five vision-language foundation models and three CNN-based architectures - across 37 standardized classification tasks using six public datasets from the USA, Spain, India, and Vietnam, and three private datasets from hospitals in China. Performance was assessed using AUROC, AUPRC, and other metrics across both shared and dataset-specific tasks. Foundation models outperformed CNNs in both accuracy and task coverage. MAVL, a model incorporating knowledge-enhanced prompts and structured supervision, achieved the highest performance on public (mean AUROC: 0.82; AUPRC: 0.32) and private (mean AUROC: 0.95; AUPRC: 0.89) datasets, ranking first in 14 of 37 public and 3 of 4 private tasks. All models showed reduced performance on pediatric cases, with average AUROC dropping from 0.88 +/- 0.18 in adults to 0.57 +/- 0.29 in children (p = 0.0202). These findings highlight the value of structured supervision and prompt design in radiologic AI and suggest future directions including geographic expansion and ensemble modeling for clinical deployment. Code for all evaluated models is available at https://drive.google.com/drive/folders/1B99yMQm7bB4h1sVMIBja0RfUu8gLktCE

Visual grounding (VG) is the capability to identify the specific regions in an image associated with a particular text description. In medical imaging, VG enhances interpretability by highlighting relevant pathological features corresponding to textual descriptions, improving model transparency and trustworthiness for wider adoption of deep learning models in clinical practice. Current models struggle to associate textual descriptions with disease regions due to inefficient attention mechanisms and a lack of fine-grained token representations. In this paper, we empirically demonstrate two key observations. First, current VLMs assign high norms to background tokens, diverting the model's attention from regions of disease. Second, the global tokens used for cross-modal learning are not representative of local disease tokens. This hampers identifying correlations between the text and disease tokens. To address this, we introduce simple, yet effective Disease-Aware Prompting (DAP) process, which uses the explainability map of a VLM to identify the appropriate image features. This simple strategy amplifies disease-relevant regions while suppressing background interference. Without any additional pixel-level annotations, DAP improves visual grounding accuracy by 20.74% compared to state-of-the-art methods across three major chest X-ray datasets.

Self-supervised learning has emerged as a powerful paradigm for training deep neural networks, particularly in medical imaging where labeled data is scarce. While current approaches typically rely on synthetic augmentations of single images, we propose VET-DINO, a framework that leverages a unique characteristic of medical imaging: the availability of multiple standardized views from the same study. Using a series of clinical veterinary radiographs from the same patient study, we enable models to learn view-invariant anatomical structures and develop an implied 3D understanding from 2D projections. We demonstrate our approach on a dataset of 5 million veterinary radiographs from 668,000 canine studies. Through extensive experimentation, including view synthesis and downstream task performance, we show that learning from real multi-view pairs leads to superior anatomical understanding compared to purely synthetic augmentations. VET-DINO achieves state-of-the-art performance on various veterinary imaging tasks. Our work establishes a new paradigm for self-supervised learning in medical imaging that leverages domain-specific properties rather than merely adapting natural image techniques.

This study explores the use of Federated Learning (FL) for tuberculosis (TB) diagnosis using chest X-rays in low-resource settings across Africa. FL allows hospitals to collaboratively train AI models without sharing raw patient data, addressing privacy concerns and data scarcity that hinder traditional centralized models. The research involved hospitals and research centers in eight African countries. Most sites used local datasets, while Ghana and The Gambia used public ones. The study compared locally trained models with a federated model built across all institutions to evaluate FL's real-world feasibility. Despite its promise, implementing FL in sub-Saharan Africa faces challenges such as poor infrastructure, unreliable internet, limited digital literacy, and weak AI regulations. Some institutions were also reluctant to share model updates due to data control concerns. In conclusion, FL shows strong potential for enabling AI-driven healthcare in underserved regions, but broader adoption will require improvements in infrastructure, education, and regulatory support.

Large language models (LLMs) have demonstrated remarkable capabilities in various domains, including radiology report generation. Previous approaches have attempted to utilize multimodal LLMs for this task, enhancing their performance through the integration of domain-specific knowledge retrieval. However, these approaches often overlook the knowledge already embedded within the LLMs, leading to redundant information integration and inefficient utilization of learned representations. To address this limitation, we propose RADAR, a framework for enhancing radiology report generation with supplementary knowledge injection. RADAR improves report generation by systematically leveraging both the internal knowledge of an LLM and externally retrieved information. Specifically, it first extracts the model's acquired knowledge that aligns with expert image-based classification outputs. It then retrieves relevant supplementary knowledge to further enrich this information. Finally, by aggregating both sources, RADAR generates more accurate and informative radiology reports. Extensive experiments on MIMIC-CXR, CheXpert-Plus, and IU X-ray demonstrate that our model outperforms state-of-the-art LLMs in both language quality and clinical accuracy

The development of larger models for medical image analysis has led to increased performance. However, it also affected our ability to explain and validate model decisions. Models can use non-relevant parts of images, also called spurious correlations or shortcuts, to obtain high performance on benchmark datasets but fail in real-world scenarios. In this work, we challenge the capacity of convolutional neural networks (CNN) to classify chest X-rays and eye fundus images while masking out clinically relevant parts of the image. We show that all models trained on the PadChest dataset, irrespective of the masking strategy, are able to obtain an area under the curve (AUC) above random. Moreover, the models trained on full images obtain good performance on images without the region of interest (ROI), even superior to the one obtained on images only containing the ROI. We also reveal a possible spurious correlation in the Chákṣu dataset while the performances are more aligned with the expectation of an unbiased model. We go beyond the performance analysis with the usage of the explainability method SHAP and the analysis of embeddings. We asked a radiology resident to interpret chest X-rays under different masking to complement our findings with clinical knowledge.

The aim of this study was to develop a hybrid diagnostic framework integrating radiomic and deep features for accurate and reproducible detection and classification of wrist fractures using X-ray images. A total of 3,537 X-ray images, including 1,871 fracture and 1,666 non-fracture cases, were collected from three healthcare centers. Radiomic features were extracted using the PyRadiomics library, and deep features were derived from the bottleneck layer of an autoencoder. Both feature modalities underwent reliability assessment via Intraclass Correlation Coefficient (ICC) and cosine similarity. Feature selection methods, including ANOVA, Mutual Information (MI), Principal Component Analysis (PCA), and Recursive Feature Elimination (RFE), were applied to optimize the feature set. Classifiers such as XGBoost, CatBoost, Random Forest, and a Voting Classifier were used to evaluate diagnostic performance. The dataset was divided into training (70%) and testing (30%) sets, and metrics such as accuracy, sensitivity, and AUC-ROC were used for evaluation. The combined radiomic and deep feature approach consistently outperformed standalone methods. The Voting Classifier paired with MI achieved the highest performance, with a test accuracy of 95%, sensitivity of 94%, and AUC-ROC of 96%. The end-to-end model achieved competitive results with an accuracy of 93% and AUC-ROC of 94%. SHAP analysis and t-SNE visualizations confirmed the interpretability and robustness of the selected features. This hybrid framework demonstrates the potential for integrating radiomic and deep features to enhance diagnostic performance for wrist and forearm fractures, providing a reliable and interpretable solution suitable for clinical applications.

Tuberous breast deformity (TBD) is a congenital condition characterized by constriction of the breast base, parenchymal hypoplasia, and areolar herniation. The absence of a universally accepted classification system complicates diagnosis and surgical planning, leading to variability in clinical outcomes. Artificial intelligence (AI) has emerged as a powerful adjunct in medical imaging, enabling objective, reproducible, and data-driven diagnostic assessments. This study introduces an AI-driven diagnostic tool for tuberous breast deformity (TBD) classification using a Siamese Network trained on paired frontal and lateral images. Additionally, the model generates a continuous Tuberosity Score (ranging from 0 to 1) based on embedding vector distances, offering an objective measure to enhance surgical planning and improved clinical outcomes. A dataset of 200 expertly classified frontal and lateral breast images (100 tuberous, 100 non-tuberous) was used to train a Siamese Network with contrastive loss. The model extracted high-dimensional feature embeddings to differentiate tuberous from non-tuberous breasts. Five-fold cross-validation ensured robust performance evaluation. Performance metrics included accuracy, precision, recall, and F1-score. Visualization techniques, such as t-SNE clustering and occlusion sensitivity mapping, were employed to interpret model decisions. The model achieved an average accuracy of 96.2% ± 5.5%, with balanced precision and recall. The Tuberosity Score, derived from the Euclidean distance between embeddings, provided a continuous measure of deformity severity, correlating well with clinical assessments. This AI-based framework offers an objective, high-accuracy classification system for TBD. The Tuberosity Score enhances diagnostic precision, potentially aiding in surgical planning and improving patient outcomes.