A clinical decision support system for micro panoramic melanoma detection and grading using soft computing technique. (15th October 2020)

• Record Type: Journal Article
• Authors: Reshma, M.; Priestly Shan, B
• Is Part Of: Measurement. Volume 163(2020)
• Publication Date: 2020-10-15
• Subjects: Preprocessing -- Skin lesion segmentation -- Feature extraction -- Support Vector Machine; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2020.108024
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: Clinical decision support system for melanoma detection using SVM machine learning algorithm. Preprocessing, lesion segmentation, feature extraction and feature optimization are done. Total deramascopic score was proposed. SVM has highest classification accuracy of 96.4% MATLAB 2018a has been used for Experimentation. Abstract: 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.