Machine Learning Based Diagnosis of Melanoma Using Macro Images

Summary

Cancer bears a poisoning threat to human society. Melanoma, the skin cancer originates from skin layers and penetrates deep into subcutaneous layers. There exists an extensive research in melanoma diagnosis using dermatoscopic images captured through dermatoscope. While designing a diagnostic model for general handheld imaging systems is an emerging trend. This article proposes a computer aided decision support system for macro images captured by a general purpose camera. The general imaging conditions are adversely affected by the non-uniform illumination which further effect the extraction of relevant information. To mitigate it, we process an image to define a smooth illumination surface using the multi-stage illumination compensation approach and the infected region is extracted using proposed multi-mode segmentation method. The lesion information is numerated as a feature set comprising of geometry, photometry, border series and texture measures. The redundancy in feature set is reduced using information theory methods, and a classification boundary is modeled to distinguish benign and malignant samples using Support Vector Machine(SVM), Random Forest(RF), Neural Network(NN) and Fast Discriminative Mixed Membership based Naive Bayesian classifier(FDMMNB). Moreover, the experimental outcome is supported by hypothesis testing and boxplot representation for classification losses. The simulation results prove the significance of proposed model that shows an improved performance as compared to competing arts. This article is protected by copyright. All rights reserved.

http://ift.tt/2DeaB3l