Open AccessA comparative study of convolutional neural networks for classification of pigmented skin lesions
Author(s) -
Natalia Camillo do Carmo,
JeanFrançois Mari
Publication year - 2021
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/wvc.2021.18909
Subject(s) - skin cancer , convolutional neural network , skin lesion , artificial intelligence , melanoma , computer science , dermatology , pattern recognition (psychology) , deep learning , contextual image classification , artificial neural network , residual neural network , lesion , medicine , cancer , pathology , image (mathematics) , cancer research
Skin cancer is one of the most common types of cancer in Brazil and its incidence rate has increased in recent years. Melanoma cases are more aggressive compared to nonmelanoma skin cancer. Machine learning-based classification algorithms can help dermatologists to diagnose whether skin lesion is melanoma or non-melanoma cancer. We compared four convolutional neural networks architectures (ResNet-50, VGG16, Inception-v3, and DenseNet-121) using different training strategies and validation methods to classify seven classes of skin lesions. The experiments were executed using the HAM10000 dataset which contains 10,015 images of pigmented skin lesions. We considered the test accuracy to determine the best model for each strategy. DenseNet-121 was the best model when trained with fine-tuning and data augmentation, 90% (k-fold crossvalidation). Our results can help to improve the use of machine learning algorithms for classifying pigmented skin lesions.