Convolutional Neural Networks on Assembling Classification Models to Detect Melanoma Skin Cancer

Authors

DOI:

https://doi.org/10.3991/ijoe.v18i14.34435

Keywords:

melanoma, skin cancer, convolutional neural networks, classification model, deep learning

Abstract


In 2020, there were more than 1.2 million new skin cancer diagnoses, and melanoma was the most recurrent type of cancer. On the other hand, melanoma is the least common but most serious form of skin cancer affecting both men and women. This work aims to assemble classification models to detect a case of melanoma with high accuracy based on a Convolutional Neural Networks system. The methodology considers training 21 models for image classification, with the best assembly performance of  EfficientNet and VGG-19 architectures,  the data augmentation technique was used to the images to improve its performance. The results show 92.85% of accuracy, 71.50% of sensitivity, and 94.89% of specificity, with an improvement of 0.06% in accuracy and specificity. The assembly of the classification models achieved higher accuracy in melanoma skin cancer image classification.

Author Biographies

Hugo Vega-Huerta, UNIVERSIDAD NACIONAL MAYOR DE SAN MARCOS

Doctor in Systems Engineering at UNFV, Master in Administration Science at UNMSM. Is a principal professor at UNMSM and a researcher specializing in Artificial Intelligence. He was Academic Vice Dean at the Faculty of Systems Engineering at UNMSM, Director of the Software Engineering Program at URP. Is responsible for the YACHAY Research Group at UNMSM. (email: hvegah@unmsm.edu.pe)

Renzo Villanueva-Alarcon, Universidad Nacional Mayor de San Marcos

is a systems engineer at UNMSM with experience in the analysis, design, and implementation of Business Intelligence solutions in the financial sector. I am characterized by responsibility, a sense of teamwork, and constantly learning new technologies related to advanced analytics.

(email: renzo.villanueva@unmsm.edu.pe).

David Mauricio, Universidad Nacional Mayor de San Marcos

Doctor of Science in Systems Engineering and Computing, and Master of Science in Applied Mathematics from the Federal University of Rio de Janeiro, Brazil. He has been a professor at the North Fluminense State University of Brazil (1994-1998), and since 1998 he has been a professor at the National University of San Marcos. Areas of interest: Mathematical Programming, Artificial Intelligence, Software Engineering, Entrepreneurship (email: dmauricios@unmsm.edu.pe).

Juan Gamarra-Moreno, Universidad Nacional Mayor de San Marcos

Research professor in Artificial Intelligence at Universidad Nacional Mayor de San Marcos

Advisor of undergraduate thesis projects related to Artificial Intelligence

juan.gamarra@unmsm.edu.pe

Hugo D. Calderon-Vilca, Universidad Nacional Mayor de San Marcos

PhD in Computer Science, research professor of the "Artificial Intelligence" Group of the Universidad Nacional Mayor de San Marcos - Peru, advisor of undergraduate and graduate thesis projects related to Neural Networks, Machine Learning and Natural Language Processing. Professor of doctoral programs in other universities. (email: hcalderonv@unmsm.edu.pe)

Diego Rodriguez, Universidad Peruana de Ciencias Aplicadas

is a Peruvian researcher member of the research group in medicine and health sciences at Universidad Peruana de Ciencias Aplicadas (UPC), he has collaborated on IA projects related to biomedicine, and he has published scientific articles indexed on Scopus and IEEE (email: U202115933@upc.edu.pe)

Ciro Rodriguez, Universidad Nacional Mayor de San Marcos

is a Peruvian researcher, and engineering educator at National University Mayor de San Marcos (UNMSM), in Lima Peru. He is member of the International Alliance for Sensing and IoT Collaboration (IASIC), and he belongs to the research group of Information Technologies Applied to Data Science (ITDATA), He is reviewer at  Multimedia Tools and Applications and Applied Sciences MDPI (email: crodriguezro@unmsm.edu.pe).

 

Downloads

Published

2022-11-22

How to Cite

Vega-Huerta, H., Villanueva-Alarcón, R., Mauricio, D., Gamarra Moreno, J., Calderon Vilca, H. D. ., Rodriguez, D., & Rodriguez, C. (2022). Convolutional Neural Networks on Assembling Classification Models to Detect Melanoma Skin Cancer. International Journal of Online and Biomedical Engineering (iJOE), 18(14), pp. 59–76. https://doi.org/10.3991/ijoe.v18i14.34435

Issue

Section

Papers