Weakly Supervised Pneumonia Localization from Chest X-Rays Using Deep Neural Network and Grad-CAM Explanations
This work addresses pneumonia screening for radiological diagnostics by enhancing transparency and clinical trust in AI-assisted tools, though it is incremental as it applies existing methods to a specific medical imaging task.
The study tackled pneumonia classification and localization from chest X-rays using a weakly supervised deep learning framework with Grad-CAM explanations, achieving high accuracy of 96-98% across models like ResNet-18 and EfficientNet-B0 while generating clinically relevant heatmaps.
This study proposes a weakly supervised deep learning framework for pneumonia classification and localization from chest X-rays, utilizing Grad-CAM explanations. Instead of costly pixel-level annotations, our approach uses image-level labels to generate clinically meaningful heatmaps that highlight regions affected by pneumonia. We evaluate seven pre-trained architectures and the Vision Transformer under identical training conditions, using focal loss and patient-wise splits to prevent data leakage. Experimental results suggest that all models achieved high accuracy (96-98%), with ResNet-18 and EfficientNet-B0 showing the best overall performance and MobileNet-V2 providing an efficient lightweight alternative. Grad-CAM heatmap visualizations confirm that the proposed models focus on clinically relevant lung regions, supporting the use of interpretable AI for radiological diagnostics. This work highlights the potential of weakly supervised, explainable models that enhance the transparency of pneumonia screening and clinical trust in AI-assisted screening.