Toward Accessible Dermatology: Skin Lesion Classification Using Deep Learning Models on Mobile-Acquired Images
This work addresses the problem of inaccessible dermatological diagnosis in low-resource settings by enabling AI-assisted screening from mobile images, though it is incremental as it builds on existing deep learning methods with a new dataset.
The paper tackled skin lesion classification using deep learning on mobile-acquired images, curating a dataset of over 50 disease categories and showing that Transformer models, especially Swin Transformer, achieve superior performance by capturing global contextual features.
Skin diseases are among the most prevalent health concerns worldwide, yet conventional diagnostic methods are often costly, complex, and unavailable in low-resource settings. Automated classification using deep learning has emerged as a promising alternative, but existing studies are mostly limited to dermoscopic datasets and a narrow range of disease classes. In this work, we curate a large dataset of over 50 skin disease categories captured with mobile devices, making it more representative of real-world conditions. We evaluate multiple convolutional neural networks and Transformer-based architectures, demonstrating that Transformer models, particularly the Swin Transformer, achieve superior performance by effectively capturing global contextual features. To enhance interpretability, we incorporate Gradient-weighted Class Activation Mapping (Grad-CAM), which highlights clinically relevant regions and provides transparency in model predictions. Our results underscore the potential of Transformer-based approaches for mobile-acquired skin lesion classification, paving the way toward accessible AI-assisted dermatological screening and early diagnosis in resource-limited environments.