Computer-Aided Diagnosis of Melanoma Skin Cancer: A Review

Skin cancer has a major impact on society in India and across the world. According to the figures given by the National Cancer Institute and SEER, estimated new cases of Melanoma in 2017 are 87,110. This figure is approximated 5.2% of all new cancer in 2017. As per the data obtained from the WORLD HEALTH RANKINGS, the death rate per 1,00000 is highest in New Zealand with 7.68% then Australia with 6.52%. It has been proved from the study that melanoma skin cancer is almost curable if it is diagnosed early and treated correctly; otherwise, it can spread to other parts of the body and become incurable. This paper presents the comparative study of various phases of computer-aided melanoma skin cancer detection system with the aim of providing the development achieved in the melanoma skin cancer detection by the research community from earlier period to the current time. This method starts from the image acquisition step followed by image preprocessing, segmentation, feature extraction, feature selection and classification steps. The input to this system is an image of affected skin area, and output labels this input image benign or malignant melanoma.