Impact of Transfer Learning on Convolutional Neural Networks for Odontogenic Tumor Diagnosis

Transfer learning with ImageNet weights enhanced the performance of most CNNs, with EfficientNetV2B0 showing the greatest responsiveness to pretraining and DenseNet121 demonstrating intrinsic robustness to initialization. These results highlight the potential of CNN-based frameworks to support the differential diagnosis of odontogenic tumors-an inherently challenging task due to morphological overlap-while establishing reproducible methodological baselines that contribute to the global development of explainable, ensemble-based, and clinically reliable AI systems in oral pathology.

Authors

Institutions

Publication Details

Journal
Head and Neck Pathology
Published
2026-02-19
DOI
https://doi.org/10.1007/s12105-025-01875-y
Primary Topic
Oral and Maxillofacial Pathology
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Impact of Transfer Learning on Convolutional Neural Networks for Odontogenic Tumor Diagnosis

MáRCIO CAMPOS OLIVEIRA, Leonor V. González-Pérez, Anna Luíza Damaceno Araújo, Matheus Cardoso Moraes et al.
Head and Neck Pathology
Oral and Maxillofacial Pathology
article

Impact of Transfer Learning on Convolutional Neural Networks for Odontogenic Tumor Diagnosis

MáRCIO CAMPOS OLIVEIRA, Leonor V. González-Pérez, Anna Luíza Damaceno Araújo, Matheus Cardoso Moraes, Giovanna Calabrese dos Santos, Anderson Faria Claret, Roberto Gerber-Mora, Felipe Martins Silveira, Manoela Domingues Martin, Katya Pulido-Díaz, Thaís Cerqueira Reis Nakamura, Ronell Bologna-Molina, Vanesa Pereira Prado, Pablo Agustin Vargas, Jeconias Câmara, Hélder Antônio Rebelo Pontes, Daniela Giraldo-Roldán
article en

Abstract

Transfer learning with ImageNet weights enhanced the performance of most CNNs, with EfficientNetV2B0 showing the greatest responsiveness to pretraining and DenseNet121 demonstrating intrinsic robustness to initialization. These results highlight the potential of CNN-based frameworks to support the differential diagnosis of odontogenic tumors-an inherently challenging task due to morphological overlap-while establishing reproducible methodological baselines that contribute to the global development of explainable, ensemble-based, and clinically reliable AI systems in oral pathology.

Head and Neck PathologyVol. 20(1)
Universidade Federal do Rio Grande do Sul (BR), Universidade de São Paulo (BR), Universidad de la República de Uruguay (UY), Universidade Estadual de Campinas (UNICAMP) (BR), Universidad Autónoma Metropolitana (MX), Universidade Estadual de Feira de Santana (BR), Hospital Israelita Albert Einstein (BR), Universidad de Antioquia (CO), Microsoft (Brazil) (BR), Fundação de Apoio à Universidade Federal de São Paulo (BR), Methodist University of Piracicaba (BR), ACICAFOC (CR), Universidade Federal do Pará (BR), Universidade Federal do Amazonas (BR), Universidade Federal de São Paulo (BR)
Openalex Percentile: Top 52%
Oral and Maxillofacial Pathology
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.