The field of dermatology has increasingly embraced artificial intelligence (AI) and machine
learning techniques to improve the accuracy and efficiency of diagnosing and classifying skin diseases.
Among these techniques, deep learning models, particularly convolutional neural networks (CNNs), have
demonstrated remarkable performance in medical image analysis. However, CNNs typically require large
volumes of labeled data to achieve optimal results, which presents a significant limitation when working
with small or imbalanced skin disease datasets.