A clinical decision support system for micro panoramic melanoma detection and grading using soft computing technique

摘要

Computer aided algorithms plays pivotal role in disease diagnosis and treatment planning for therapeutic applications. This research work proposes a clinical decision support system for melanoma detection using SVM machine learning algorithm. Prior to classification, preprocessing, lesion segmentation, feature extraction and feature optimization are done. The performance of the SVM classifier was compared with the other classical classifiers and superior results are produced. A novel total dermascopic score was proposed in this work that generates efficient results, when compared with the classical total dermascopic score. The SVM when coupled with RFE for feature selection and ranking generates efficient results, when compared with the other machine learning classifiers. The performance evaluation was done by metrics like sensitivity, specificity and accuracy. The SVM has highest classification accuracy of 96.4%, when compared with the other algorithms. (C) 2020 Published by Elsevier Ltd.