Enhancing Explainability in Oral Cancer Detection with Grad-CAM Visualizations

Autor(es)

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.

• Tipo de documento: Artigo Científico
• Fonte: COMPUTATIONAL SCIENCE AND ITS APPLICATIONS-ICCSA 2024, PT I; v. 14813, p. 14-pg., 2024-01-01.

Resumo

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)

• Processo FAPESP: 20/09835-1 - IARA - Inteligência Artificial Recriando Ambientes
• Beneficiário: André Carlos Ponce de Leon Ferreira de Carvalho
• Modalidade de apoio: Auxílio à Pesquisa - Programa Centros de Pesquisa em Engenharia
• Processo FAPESP: 22/09285-7 - Exploração do espaço químico via aprendizado semissupervisionado para geração de novos materiais
• Beneficiário: Marcos Gonçalves Quiles
• Modalidade de apoio: Auxílio à Pesquisa - Regular