Computer aided diagnosis of skin carcinomas based on textural characteristics

Abstract

Computer aided diagnostics CAD has become one of the major research subjects in medical imaging and diagnostics radiology. The basic concept of CAD is to provide the computer aided output as a second opinion to assist the radiologist. It improves the diagnostic accuracy and reduces image reading and interpretation time. In this paper, we propose a method of discriminating different skin carcinomas based upon their textural attributes by using wavelets. Single mother wavelet is designed to distinguish between the healthy and infected skin tissues. Classification is performed by SVMs, proposed method shows accuracy of 89%.