Proposition of Convolutional Neural Network Based System for Skin Cancer Detection

Abstract

Skin cancer automated diagnosis tools play a vital role in timely screening, helping dermatologists focus on melanoma cases. Best arts on automated melanoma screening use deep learning-based approaches, especially deep convolutional neural networks (CNN) to improve performances. Because of the large number of parameters that could be involved during training in CNN many training samples are needed to avoid overfitting problem. Gabor filtering can efficiently extract spatial information including edges and textures, which may reduce the features extraction burden to CNN. In this paper, we proposed a Gabor Convolutional Network (GCN) model to improve the performance of automated diagnosis of skin cancer systems. The model combines a CNN model and Gabor filtering and serves three functions: generation of Gabor filter banks, CNN construction and filter injection. We performed experiments with dermoscopic images and results were interpreted according to classification accuracy. The results we have obtained show that our GCN offers the best classification accuracy with a value of 96.39% against 94.02% for the CNN model.