Skin Disease Detection Using Deep Learning

Abstract

Early and accurate diagnosis of skin diseases is essential for effective treatment and improved patient outcomes. This paper presents SkinScan AI, a deep learning-based framework for automated skin disease detection and classification from dermoscopic images using the HAM10000 benchmark dataset. The proposed DenseNet121 model classifies skin lesions into seven clinically significant categories: Actinic Keratoses (akiec), Basal Cell Carcinoma (bcc), Benign Keratosis-like Lesions (bkl), Dermatofibroma (df), Melanoma (mel), Melanocytic Nevi (nv), and Vascular Lesions (vasc). To address dataset imbalance, the framework incorporates MixUp augmentation, focal loss with label smoothing, minority-class weighting, and oversampling. A two-stage fine-tuning strategy with Test-Time Augmentation (TTA) improves model generalization and prediction robustness. Comparative evaluation with a custom CNN baseline and EfficientNetB3 demonstrates that DenseNet121 achieves the best performance, obtaining 81.82% TTA accuracy, a weighted F1-score of 0.8096, and an AUC of 0.9441. Grad-CAM provides visual explanations by highlighting lesion-relevant regions, improving model interpretability and increasing user confidence in the prediction process. The trained model is deployed as a Flask-based web application with secure authentication, prediction history, severity assessment, medication guidance, doctor referral recommendations, and downloadable PDF reports. Experimental results demonstrate that the proposed framework effectively handles class imbalance while providing accurate, interpretable, and practical decision support for computer-aided skin disease diagnosis. The system offers a scalable and user-friendly solution that can assist healthcare professionals and improve access to reliable preliminary skin disease screening.