MELANOMA SKIN CANCER DETECTION USING A COMPUTER-ASSISTED APPROACH THROUGH ARTIFICIAL NEURAL NETWORK AND IMAGE PROCESSING

The unchecked development of abnormal skin cells is known as skin cancer. Unrepaired DNA damage to skin cells causes mutations, or genetic defects, which cause the skin cells to replicate rapidly and develop malignant tumours. Image analysis is a popular technique for detecting skin cancer based on how the infected region appears on the skin. Artificial Neural Networks (ANN) are a subset of Artificial Intelligence that has recently been recognised as a brand new technique in computer science for image processing. Neural networks are a hot topic in medicine right now, particularly in fields like radiology, urology, cardiology, and oncology. In a call network with a lot of calls, a neural network is extremely important. In this article, a computerised approach for using Neural Networks in the field of medical image processing is presented. The ultimate goal of this paper is to develop low-cost emergency support networks for processing medical photographs. It has been used to analyse Melanoma parameters such as Asymmetry, Border, Color, Diameter (ABCD), and others that are measured using MATLAB from skin cancer images in order to create diagnostic algorithms that may enhance emergency department triage procedures. We use ANN in the classification stage with Back Propagation Algorithm for melanoma skin cancer using ABCD rules. At first, we use known goal values to train the network. The network has been well-trained with a 96.9% accuracy rate, and the unknown values are then checked for cancer classification. This form of classification appears to be more effective in the classification of skin cancer. Skin cancer is also widely regarded as one of the most dangerous types of cancer present in humans. Melanoma, Basal and Squamous cell Carcinoma are three forms of skin cancer, with Melanoma being the most volatile. Melanoma cancer may be treated more effectively if detected early. Many developed technologies have shown that computer vision can play an important role in medical image diagnosis. We introduce a computer-assisted approach for detecting Melanoma Skin Cancer utilising Image Processing techniques in this article. The skin lesion picture is fed into the device, and then analyses it using cutting-edge image analysis methods to determine whether or not skin cancer is present. Through analysing texture, scale, and form for image segmentation and feature levels, the Lesion Image Analysis tools search for different Melanoma parameters such as asymmetry, border, colour, diameter, (ABCD), and so on. The picture is classified as Normal skin and Melanoma cancer lesion using the derived function parameters.