A new machine-learning methodology for detection of epithelial dysplasia in oral leukoplakia lesions
Research on Biomedical Engineering · 2026-06 · 42 (2)
DOI: 10.1007/s42600-026-00482-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Research on Biomedical Engineering, online erschienen am 01.06.2026. Verfasst von Karoline da Rocha und 3 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidade Federal De Santa Catarina.
Abstract (Originalsprache)
Purpose
Oral squamous cell carcinoma (OSCC) is the most common oral cancer, with high mortality rates, making early detection crucial. Malignant transformation is preceded by oral potentially malignant disorders (OPMDs), with leukoplakia being the most frequent. Epithelial dysplasia (ED) is a key histological feature for predicting the risk of progression to OSCC. However, its diagnosis relies on subjective visual assessment by pathologists, which is influenced by experience and emotional state. This study aims to develop a Machine Learning (ML), based methodology to assist in ED detection in leukoplakia lesions.
Methods
The proposed methodology integrates histopathological image analysis with complementary patient data. Epithelial regions were selected for cutout extraction based on pathologist knowledge and combined with risk factors from patient data. A multilayer perceptron artificial neural network (MLP-ANN) was trained and evaluated. Performance was compared with a pre-trained convolutional neural network (ResNet-50V2) using the McNemar test.
Results
The MLP-ANN achieved an area under the curve (AUC) of 0.9484. No statistically significant difference was found between the proposed method and the pre-trained CNN. However, the proposed approach was approximately 9.7 times faster in computational time.
Conclusions
The proposed ML-based methodology demonstrated competitive classification performance along with improved computational efficiency. Refining the confidence criterion for intermediate classification results may further enhance its diagnostic accuracy, supporting pathologists in ED detection.
Förderung
- Universidade Federal De Santa Catarina
Zitieren
APA
Rocha, K. D., Bermudez, J. C. M., Rivero, E. R. C., & Costa, M. H. (2026). A new machine-learning methodology for detection of epithelial dysplasia in oral leukoplakia lesions. Research on Biomedical Engineering, 42(2). https://doi.org/10.1007/s42600-026-00482-2
Vancouver
Rocha KD, Bermudez JCM, Rivero ERC, Costa MH. A new machine-learning methodology for detection of epithelial dysplasia in oral leukoplakia lesions. Research on Biomedical Engineering. 2026;42(2). doi:10.1007/s42600-026-00482-2
BibTeX
@article{Rocha2026,
author = {Rocha, Karoline da and Bermudez, José C. M. and Rivero, Elena R. C. and Costa, Márcio H.},
title = {A new machine-learning methodology for detection of epithelial dysplasia in oral leukoplakia lesions},
journal = {Research on Biomedical Engineering},
year = {2026},
volume = {42},
number = {2},
doi = {10.1007/s42600-026-00482-2}
}
EUVIMED