EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

The Use of Machine Learning to Support the Diagnosis of Oral Alterations

Rosana Leal do Prado, Juliane Avansini Marsicano, Amanda Keren Frois, Jacques Duílio Brancher

Pesquisa Brasileira em Odontopediatria e Clínica Integrada · 2025 · 25

DOI: 10.1590/pboci.2025.047 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pesquisa Brasileira em Odontopediatria e Clínica Integrada, 2025. Verfasst von Rosana Leal do Prado und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To verify the accuracy of deep learning models in detecting cellular alterations in histological images of oral mucosa. Material and Methods: The study compares three convolutional neural network (CNN) architectures for classifying histological images: EfficientNet-B3, MobileNet-V2, and VGG16. Efficient and focused on computer vision, each has specific advantages. A Kaggle database with 5192 images was used, divided into training (70%), validation (15%), and test (15%) sets. The CNNs were implemented using the Keras library, trained with pre-trained ImageNet weights, and evaluated using accuracy and AUC metrics.

Results

The findings indicate that EfficientNet-B3 achieved the lowest training and validation losses at epoch 30, with the highest accuracy and stability during training. Evaluation metrics showed EfficientNet-B3 with 98% accuracy and 99% sensitivity for oral squamous cell carcinoma (OSCC) images, outperforming MobileNet-V2 and VGG16. MobileNet-V2 achieved 97% accuracy and 96% sensitivity, while VGG16 reached 94% accuracy and 93% sensitivity for OSCC images. All models exhibited high sensitivity and specificity in differentiating between normal and OSCC images, as demonstrated by ROC curves. EfficientNet-B3 had the highest AUC (0.982), followed by MobileNet-V2 (AUC=0.967) and VGG16 (AUC=0.937). These findings underscore the effectiveness of EfficientNet-B3 for accurately detecting cellular alterations in histological images of oral mucosa.

Conclusion

Our study reveals the superior performance of CNNs, particularly EfficientNet-B3, in classifying histological images of OSCC.

Zitieren

APA

Prado, R. L. D., Marsicano, J. A., Frois, A. K., & Brancher, J. D. (2025). The Use of Machine Learning to Support the Diagnosis of Oral Alterations. Pesquisa Brasileira em Odontopediatria e Clínica Integrada, 25. https://doi.org/10.1590/pboci.2025.047

Vancouver

Prado RLD, Marsicano JA, Frois AK, Brancher JD. The Use of Machine Learning to Support the Diagnosis of Oral Alterations. Pesquisa Brasileira em Odontopediatria e Clínica Integrada. 2025;25. doi:10.1590/pboci.2025.047

BibTeX
@article{Prado2025,
  author = {Prado, Rosana Leal do and Marsicano, Juliane Avansini and Frois, Amanda Keren and Brancher, Jacques Duílio},
  title = {The Use of Machine Learning to Support the Diagnosis of Oral Alterations},
  journal = {Pesquisa Brasileira em Odontopediatria e Clínica Integrada},
  year = {2025},
  volume = {25},
  doi = {10.1590/pboci.2025.047}
}
Kostenlos starten →