Skin Lesion Classification Using Deep Learning Methods

Authors:
  • ESE.Yu. Shchetinin
    E.Yu. Shchetinin
  • ADA.V. Demidova
    A.V. Demidova
  • DKD.S. Kulyabov
    D.S. Kulyabov
  • LSL.A. Sevastyanov
    L.A. Sevastyanov
Publisher website
Google Scholar
Abstract
In this paper, we propose an approach to solving the problem of recognizing skin lesions, namely melanoma, based on the analysis of dermoscopic images using deep learning methods. For this purpose, the architecture of a deep convolutional neural network was developed, which was applied to the processing of dermoscopic images of various skin lesions contained in the HAM10000 data set. The data under study were preprocessed to eliminate noise, contamination, and change the size and format of images. In addition, since the disease classes are unbalanced, a number of transformations were performed to balance them. The data obtained in this way were divided into two classes: Melanoma and Benign. Computer experiments using the built deep neural network based on the data obtained in this way have shown that the proposed approach provides 94% accuracy on the test sample, which exceeds similar results obtained by other algorithms.

This publication has 20 references indexed in Scilit: