Toward Accessible Dermatology: Skin Lesion Classification Using Deep Learning Models on Mobile-Acquired Images
Preprint
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 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.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- An Attention‐Guided Deep Learning Approach for Classifying 39 Skin Lesion TypesInternational Journal of Imaging Systems and Technology, 2025
- EfficientSkinDis: An EfficientNet-based classification model for a large manually curated dataset of 31 skin diseasesBiomedical Signal Processing and Control, 2023
- An in-depth analysis of Convolutional Neural Network architectures with transfer learning for skin disease diagnosisHealthcare Analytics, 2023
- Skin lesion detection based on deep neural networksChemometrics and Intelligent Laboratory Systems, 2022
- Enhanced deep bottleneck transformer model for skin lesion classificationBiomedical Signal Processing and Control, 2022
- A comparative study of fourteen deep learning networks for multi skin lesion classification (MSLC) on unbalanced dataNeural Computing and Applications, 2022
- Artificial intelligence-based image classification methods for diagnosis of skin cancer: Challenges and opportunitiesComputers in Biology and Medicine, 2020
- PAD-UFES-20: A skin lesion dataset composed of patient data and clinical images collected from smartphonesData in Brief, 2020
- Dermatologist-level classification of skin cancer with deep neural networksNature, 2017
- The Global Burden of Skin Disease in 2010: An Analysis of the Prevalence and Impact of Skin ConditionsJournal of Investigative Dermatology, 2014