Open Access

ARTICLE

Optimized Convolutional Neural Network Models for Skin Lesion Classification

by Juan Pablo Villa-Pulgarin¹, Anderson Alberto Ruales-Torres^1,2, Daniel Arias-Garzón¹, Mario Alejandro Bravo-Ortiz¹, Harold Brayan Arteaga-Arteaga¹, Alejandro Mora-Rubio¹, Jesus Alejandro Alzate-Grisales¹, Esteban Mercado-Ruiz¹, M. Hassaballah³, Simon Orozco-Arias^4,5, Oscar Cardona-Morales¹, Reinel Tabares-Soto^1,*

1 Department of Electronics and Automation, Universidad Autónoma de Manizales, Manizales, 170001, Colombia
2 SEDMATEC, Corporación Universitaria Autónoma de Nariño, Pasto, 520002, Colombia
3 Department of Computer Science, Faculty of Computers and Information, South Valley University, Qena, 83523, Egypt
4 Department of Computer Science, Universidad Autónoma de Manizales, Manizales, 170001, Colombia
5 Department of Systems and Informatics, Universidad de Caldas, Manizales, 170001, Colombia

* Corresponding Author: Reinel Tabares-Soto. Email:

(This article belongs to the Special Issue: Recent Advances in Deep Learning, Information Fusion, and Features Selection for Video Surveillance Application)

Computers, Materials & Continua 2022, 70(2), 2131-2148. https://doi.org/10.32604/cmc.2022.019529

Received 16 April 2021; Accepted 14 June 2021; Issue published 27 September 2021

Abstract

Skin cancer is one of the most severe diseases, and medical imaging is among the main tools for cancer diagnosis. The images provide information on the evolutionary stage, size, and location of tumor lesions. This paper focuses on the classification of skin lesion images considering a framework of four experiments to analyze the classification performance of Convolutional Neural Networks (CNNs) in distinguishing different skin lesions. The CNNs are based on transfer learning, taking advantage of ImageNet weights. Accordingly, in each experiment, different workflow stages are tested, including data augmentation and fine-tuning optimization. Three CNN models based on DenseNet-201, Inception-ResNet-V2, and Inception-V3 are proposed and compared using the HAM10000 dataset. The results obtained by the three models demonstrate accuracies of 98%, 97%, and 96%, respectively. Finally, the best model is tested on the ISIC 2019 dataset showing an accuracy of 93%. The proposed methodology using CNN represents a helpful tool to accurately diagnose skin cancer disease.

---

Keywords

---

Citations