Abstract—Melanoma is the deadliest kind of skin cancer. However, it’s hard to identify melanoma during its early to mid stages by visual examination. So, there is a call for an automated model which assists in early diagnosis of skin cancer. This paper introduces an enhanced automated computer-aided model for skin diagnosis using deep learning. The model integrates an enhanced segmentation phase for locating the infected lesion of the skin and a Convolution Neural Network (CNN) is designed as a feature extractor. A classifier model has been designed based on multiclass linear Support Vector Machine (SVM) trained with CNN features extracted from the digital skin images dataset. The experimental results show an outstanding performance in the terms of sensitivity, specificity and accuracy compared with others in literature.
Index Terms—computer-aided model, convolutional neural network feature, deep learning, digital skin image, and support vector machine
Cite: Doaa A. Shoieb, Sherin M. Youssef, and Walid M. Aly, "Computer-Aided Model for Skin Diagnosis Using Deep Learning," Journal of Image and Graphics, Vol. 4, No. 2, pp. 122-129, December 2016. doi: 10.18178/joig.4.2.122-129
Copyright © 2012-2024 Journal of Image and Graphics, All Rights Reserved