Toward Accessible Dermatology: Skin Lesion Classification Using Deep Learning Models on Mobile-Acquired Images

Abstract--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 convo-lutional neural networks and Transformer-based architectures, demonstrating that Transformer models, particularly the Swin Transformer, achieve superior performance by effectively capturing global contextual features. T o 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 AIassisted dermatological screening and early diagnosis in resource-limited environments. Skin diseases are among the most common health problems worldwide, impacting millions of individuals across the world. According to the World Health Organization(WHO), more than 900 million people are affected by various skin conditions, with skin disorders ranking as the fourth leading cause of nonfatal disease burden worldwide [1]. These diseases range from mild infections to life-threatening chronic disorders.