Automatic Segmentation of Melanoma affected region for Computer-Aided Diagnosis

The most critical condition among various cancer diseases is skin cancer. According to the various medical studies, the skin cancer is mainly divided into two categories, namely, non-melanoma and melanoma skin cancer. Melanoma is the most dangerous form of skin cancer and it is unpredictable as it can spread to whole body if not detected whereas non-melanoma is further categorized as, Squamous Cell Carcinoma (SCC) and Basal Cell Carcinima (BCC). The main cause that incites the melanocyte cell is sunburn caused by the bright beams of the sun. This paper focuses on the identification of melanoma during early stage by using image processing. Segmentation process is implemented to ascertain whether the skin is benign, atypical or melanoma. Some techniques such as k-means clustering thresholding and morphological operations have been discussed in this paper.