Enhancing Explainability in Oral Cancer Detection with Grad-CAM Visualizations

Author(s)

Barros da Silva, Arnaldo, V ; Saldivia-Siracusa, Cristina ; Carlos de Souza, Eduardo Santos ; Damaceno Araujo, Anna Luiza ; Lopes, Marcio Ajudarte ; Vargas, Pablo Agustin ; Kowalski, Luiz Paulo ; Santos-Silva, Alan Roger ; de Carvalho, Andre C. P. L. F. ; Quiles, Marcos G.

• Document type: Journal article
• Source: COMPUTATIONAL SCIENCE AND ITS APPLICATIONS-ICCSA 2024, PT I; v. 14813, p. 14-pg., 2024-01-01.

Abstract

Late diagnosis of oral cancer significantly compromises patient outcomes. A promising approach to speed up the diagnostic process involves the use of Deep Learning (DL) models for medical image analysis. However, a notable challenge with these models is their lack of interpretability. To address this, techniques like Gradient-weighted Class Activation Mapping (Grad-CAM) have been developed. Grad-CAM generates heatmaps that highlight image regions most influential for classification decisions. In our study, we evaluated the performance of two DL models renowned for their high accuracy in oral cancer classification. Our analysis extended beyond mere accuracy metrics; we employed Grad-CAM to provide visual explanations of the models' decisions. Furthermore, we investigated subclass accuracy rates and the distribution of prediction confidences to gain a deeper insight into the models' performance and robustness in oral cancer detection. This comprehensive evaluation approach offers a more nuanced understanding of the capabilities and limitations of DL methods in the context of oral cancer diagnosis. (AU)

• FAPESP's process: 20/09835-1 - IARA - Artificial Intelligence in the Remaking of Urban Environments
• Grantee: André Carlos Ponce de Leon Ferreira de Carvalho
• Support Opportunities: Research Grants - Research Centers in Engineering Program
• FAPESP's process: 22/09285-7 - Chemical space exploration via semi-supervised learning for design of new materials
• Grantee: Marcos Gonçalves Quiles
• Support Opportunities: Regular Research Grants