Articles

Explainable Pneumonia Detection in Chest X-Rays: A Comparative Study of CNNs and Vision Transformers

/0 Comments/in /by

Pneumonia is a leading cause of global mortality, especially among children and the elderly, and chest radiography (CXR) remains the most widely used modality for its diagnosis. While deep learning has reached or exceeded radiologist-level performance on this task, the resulting models are still treated as opaque black boxes, which is a critical barrier to clinical deployment. In this work, we present a comparative and interpretable computer-aided-diagnosis (CAD) framework for pneumonia detection that combines three modern image-recognition backbones—a convolutional ResNet-50, a Swin Transformer (Swin-T), and a modernised convolutional network (ConvNeXt-T)—with Gradient-weighted Class Activation Mapping++ (Grad-CAM++) explanations. The three backbones were fine-tuned on the public Kermany chest X-ray dataset using a class-balanced training subset, weighted cross-entropy and an early-stopping protocol, and then evaluated on the held-out test set of 624 images. The Swin-T backbone achieved the best overall performance with a test accuracy of 95.51%, an F1-score of 0.95 and only 11 false negatives out of 234 normal cases, outperforming both ResNet-50 (93.11%) and ConvNeXt-T (88.94%). Grad-CAM++ heatmaps generated from the convolutional and transformer feature maps consistently localised on the affected pulmonary regions, providing radiologically plausible visual evidence for each prediction. Compared with five recent state-of-the-art pneumonia detectors, our Swin-T-based pipeline reaches a competitive accuracy while delivering layer-faithful visual explanations, supporting its use as a transparent decision-support tool in clinical workflows.

Lung Disease Classification Using Transfer Learning on Chest X-ray Images

/in /by

Lung diseases remain a significant global health concern, necessitating the development of rapid and accurate diagnostic methods. While previous research has shown the promise of deep learning models, particularly transfer learning with architectures such as ResNet and VGG, limitations persist in evaluation scope, class imbalance handling, and model interpretability. This study proposes an enhanced deep learning framework for multi-label classification of thoracic diseases using chest X-ray images, addressing these gaps through comprehensive evaluation metrics, advanced data augmentation, and explainable AI (XAI) techniques. The NIH ChestX-ray14 dataset is utilized, with class imbalance mitigated via synthetic minority oversampling and weighted focal loss. Multiple state-of-the-art CNN architectures, including EfficientNet and ResNet variants, are benchmarked using precision, recall, F1 Score, AUC, and accuracy. Moreover, Gradient-weighted Class Activation Mapping (Grad-CAM) is integrated to visualize pathological regions, improving clinical interpretability. The offered framework can perform better in all assessment criteria, achieving an AUC of 0.91 with EfficientNet-B0, and provides interpretable outputs critical for deployment in real-world diagnostic settings. This work advances automated radiological diagnosis by addressing key methodological shortcomings and offers a reliable, explainable solution for lung disease detection.