Optimizing Vitiligo Diagnosis With Resnet And Swin Transformer Deep Learning Models: A Study On Performance And Interpretability

This article discusses the use of deep learning models to enhance the diagnostic accuracy of vitiligo, a skin disease characterized by the loss of melanin. The study compares five different models and finds that the Swin Transformer Large model performs the best in classification and interpretability. The model not only accurately identifies vitiligo but also highlights the specific regions associated with the diagnosis.