A survey, review, and future trends of skin lesion segmentation and classification

Md. Kamrul Hasan, Md. Asif Ahamad, Choon Hwai Yap, Guang Yang

Abstract: Highlights•Summarize 594 articles for ordering all essential actions into high-, medium-, and low-frequency.•Explore the future trends and existing requirements from datasets’ utilization frequencies.•Analyze the effectiveness and trends of preprocessing and augmentation techniques in skin lesions.•Investigate a range of segmentation, classification, and evaluation techniques for highlighting the trends.•Review training and hyperparameter settings (batch size, learning rate, loss function, optimizer, and epoch).