ABSTRACT
Skin disease is a significant health concern globally, with early detection being crucial for successful treatment. The use of Artificial Intelligence (AI) and deep learning techniques has shown promise in improving the accuracy and efficiency of skin disease diagnosis. In this study, we propose an improved Faster R-CNN (Region-based Convolutional Neural Network) algorithm for the prediction of skin disease types based on dermoscopic images. The proposed algorithm leverages advancements in deep learning architectures and object detection methods to accurately classify skin lesions into different disease types, including melanoma, basal cell carcinoma, and squamous cell carcinoma. Key enhancements include feature fusion mechanisms, region proposal refinement, and attention mechanisms to improve localization and classification performance. We evaluate the performance of our proposed algorithm on a large-scale dermatology dataset comprising diverse skin lesion images. Experimental results demonstrate superior accuracy, sensitivity, and specificity compared to existing methods. The improved Faster R-CNN algorithm achieves robust skin disease type prediction, facilitating early detection and personalized treatment planning for patients.
