Melanoma Skin Cancer Detection Using Image Processing

Abstract

Scientists have been trying to implement conventional ways across the world especially in developing and developed countries to cure the deadliest form of skin cancer in human which is known as Melanoma. But efforts are always blockaded by various challenges like high cost of sustaining traditional telemedicine and less availability of experts. There are broadly three types of skin cancer: basal cell cancer, squamous cell cancer, and melanoma. Greater than 90% of the cases are caused by exposure to ultraviolet radiation from the sun. It is important to detect cancer at the initial stage; only an expert dermatologist can classify which one is melanoma and which one is non-melanoma. A short time ago, there has been high implementation of techniques such as dermoscopy or epiluminescence light microscopy (ELM) in helping diagnosis. Using ELM is not affordable and objective, thus researchers motivated in automation diagnosis. This paper is intended to take a digital image, followed by preprocessing of the image to filter the extra noise present in the image. After this, skin lesion is subjected to segmentation and feature extraction with the implementation ABCD rule which will test the skin lesion on various parameters like asymmetry, border irregularity, color, and diameter of the lesion.