Automated classification of oral potentially malignant disorders and oral squamous cell carcinoma using a convolutional neural network framework: a cross-sectional study

Autor(es):Mostrar menos -

Saldivia-Siracusa, Cristina ; Souza, Eduardo Santos Carlos de ; Silva, Arnaldo Vitor Barros da ; Araujo, Anna Luiza Damaceno ; Pedroso, Caique Mariano ; Silva, Tarcilia Aparecida da ; Ana, Maria Sissa Pereira Sant ' ; Fonseca, Felipe Paiva ; Pontes, Helder Antonio Rebelo ; Quiles, Marcos G. ; Lopes, Marcio Ajudarte ; Vargas, Pablo Agustin ; Khurram, Syed Ali ; Pearson, Alexander T. ; Lingen, Mark W. ; Kowalski, Luiz Paulo ; Hunter, Keith D. ; Carvalho, Andre Carlos Ponce de Leon Ferreira de ; Santos-Silva, Alan Roger

• Tipo de documento: Artigo Científico
• Fonte: LANCET REGIONAL HEALTH-AMERICAS; v. 47, p. 13-pg., 2025-07-01.

Resumo

Background Artificial Intelligence (AI) models hold promise as useful tools in healthcare practice. We aimed to develop and assess AI models for automatic classification of oral potentially malignant disorders (OPMD) and oral squamous cell carcinoma (OSCC) clinical images through a Deep Learning (DL) approach, and to explore explain-ability using Gradient-weighted Class Activation Mapping (Grad-CAM). Methods This study assessed a dataset of 778 clinical images of OPMD and OSCC, divided into training, model optimization, and internal testing subsets with an 8:1:1 proportion. Transfer learning strategies were applied to pre-train 8 convolutional neural networks (CNN). Performance was evaluated by mean accuracy, precision, recall, specificity, F1-score and area under the receiver operating characteristic (AUROC) values. Grad-CAM qualitative appraisal was performed to assess explainability. Findings ConvNeXt and MobileNet CNNs showed the best performance. Transfer learning strategies enhanced performance for both algorithms, and the greatest model achieved mean accuracy, precision, recall, F1-score and AUROC of 0.799, 0.837, 0.756, 0.794 and 0.863 during internal testing, respectively. MobileNet displayed the lowest computational cost. Grad-CAM analysis demonstrated discrepancies between the best-performing model and the highest explainability model. Interpretation ConvNeXt and MobileNet DL models accurately distinguished OSCC from OPMD in clinical photographs taken with different types of image-capture devices. Grad-CAM proved to be an outstanding tool to improve performance interpretation. Obtained results suggest that the adoption of DL models in healthcare could aid in diagnostic assistance and decision-making during clinical practice. (AU)

• Processo FAPESP: 21/14585-7 - Inteligência artificial aplicada ao diagnóstico clínico e histopatológico do Câncer de Cabeça e Pescoço
• Beneficiário: Anna Luiza Damaceno Araujo
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado
• Processo FAPESP: 22/07276-0 - Preditores clinicopatológicos e digitais de recorrência e malignização da leucoplasia oral e da leucoplasia verrucosa proliferativa: um estudo clínico adjunto ao uso da inteligência artificial
• Beneficiário: Caique Mariano Pedroso
• Modalidade de apoio: Bolsas no Brasil - Doutorado
• Processo FAPESP: 22/13069-8 - Inteligência artificial no diagnóstico clínico e histopatológico de carcinoma espinocelular oral incipiente: um estudo multicêntrico internacional
• Beneficiário: Cristina Saldivia Siracusa
• Modalidade de apoio: Bolsas no Brasil - Doutorado
• Processo FAPESP: 24/20694-1 - Desenvolvimento de um Programa de Rastreamento de Desordens Orais Potencialmente Malignas e Carcinoma Espinocelular de Cavidade Oral na América Latina e Caribe.
• Beneficiário: Alan Roger dos Santos Silva
• Modalidade de apoio: Bolsas no Exterior - Pesquisa