Basal Cell Carcinoma Prediction in Pigmented Skin Infection using Intelligent Techniques

Abstract

Melanoma is considered as a most lethal form of cancer. Design and development of computer-aided intelligent algorithms for early detection of skin cancer is the emerging research area. Despite many conventional mechanisms, a new type of cancer caused by unrepaired Deoxyribonucleic acid (DNA) within the skin cells. Due to its nature of rapid genetic mutations on the skin, it widely affects other body parts if not treated at early stages of intelligent computing evidenced the development of automated medical diagnosis and recommendation systems. It is possible to identify between melanoma and other classification of skin cancer based on the symmetry, color, size, form, and other characteristics of lesions. Numerous efforts are made by many researchers to develop various deep learning and machine learning inspired classification and segmentation algorithms to analyses skin lesion images. In existing the algorithm used for this research was naïve bayes, support vector machine etc. Here, after several methods such as data pre-processing, image segmentation, feature extraction and the feature extraction and the proposed algorithm of adaboost method, which is used to tune the algorithm to predict the skin infection. Finally, the proposed model has achieved 92.5% accuracy when compared with existing work.