Evaluación de arquitecturas convolucionales preentrenadas en la detección de cáncer oral
DOI:
https://doi.org/10.66104/eecb2s81Palabras clave:
Aprendizaje Profundo, Visión por Computador, Cáncer Oral, Red Neuronal ConvolucionalResumen
El cáncer oral sigue siendo uno de los principales desafíos de salud pública, especialmente en los países en desarrollo, donde la detección tardía contribuye significativamente a la alta mortalidad asociada a la enfermedad. Los métodos automatizados basados en Visión por Computador y Aprendizaje Profundo han demostrado un gran potencial para apoyar el diagnóstico temprano, proporcionando soporte objetivo a la evaluación clínica. En este estudio, se investigó el desempeño de tres arquitecturas convolucionales preentrenadas ampliamente consolidadas en la literatura—DenseNet121, GoogLeNet y ResNet18—aplicadas a la clasificación binaria de imágenes intraorales, utilizando un conjunto de datos público con 950 muestras. El estudio emplea transfer learning y validación cruzada con 5 folds, lo que permite analizar la capacidad de generalización de los modelos. Los resultados muestran que DenseNet121 presentó el mejor desempeño entre las arquitecturas evaluadas (F1-score = 0.9510), destacándose principalmente en sensibilidad y equilibrio general entre las métricas. Los hallazgos refuerzan el potencial de las CNN como herramientas complementarias en el proceso de cribado de lesiones orales, señalando su aplicabilidad futura en entornos clínicos reales.
Descargas
Referencias
SUNG, H. et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians, v. 71, n. 3, p. 209--249, 2021. DOI: 10.3322/caac.21660. DOI: https://doi.org/10.3322/caac.21660
WARNAKULASURIYA, S. Global epidemiology of oral and oropharyngeal cancer. Oral Oncology, v. 45, n. 4--5, p. 309--316, 2009. DOI: 10.1016/j.oraloncology.2008.06.002. DOI: https://doi.org/10.1016/j.oraloncology.2008.06.002
SPEIGHT, P. M. et al. Oral potentially malignant disorders: risk of progression to malignancy. Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology, v. 125, n. 6, p. 612--627, 2018. DOI: 10.1016/j.oooo.2017.12.011. DOI: https://doi.org/10.1016/j.oooo.2017.12.011
WELIKALA, R. A. et al. Automated detection and classification of oral lesions using deep learning for early detection of oral cancer. IEEE Access, v. 8, p. 132677--132693, 2020. DOI: 10.1109/ACCESS.2020.3010180. DOI: https://doi.org/10.1109/ACCESS.2020.3010180
FU, Q. et al. A deep learning algorithm for detection of oral cavity squamous cell carcinoma from photographic images: a retrospective study. EClinicalMedicine, v. 27, p. 100558, 2020. DOI: 10.1016/j.eclinm.2020.100558. DOI: https://doi.org/10.1016/j.eclinm.2020.100558
WARIN, K. et al. Automatic classification and detection of oral cancer in photographic images using deep learning algorithms. Journal of Oral Pathology & Medicine, v. 50, n. 9, p. 911--918, 2021. DOI: 10.1111/jop.13227. DOI: https://doi.org/10.1111/jop.13227
DENG, J. et al. ImageNet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), p. 248--255, 2009. DOI: 10.1109/CVPR.2009.5206848. DOI: https://doi.org/10.1109/CVPR.2009.5206848
TAJBAKHSH, N. et al. Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Transactions on Medical Imaging, v. 35, n. 5, p. 1299--1312, 2016. DOI: 10.1109/TMI.2016.2535302. DOI: https://doi.org/10.1109/TMI.2016.2535302
SZEGEDY, C. et al. Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), p. 1--9, 2015. DOI: 10.1109/CVPR.2015.7298594. DOI: https://doi.org/10.1109/CVPR.2015.7298594
HE, K. et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), p. 770--778, 2016. DOI: 10.1109/CVPR.2016.90. DOI: https://doi.org/10.1109/CVPR.2016.90
HUANG, G. et al. Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), p. 4700--4708, 2017. DOI: 10.1109/CVPR.2017.243. DOI: https://doi.org/10.1109/CVPR.2017.243
NOGUEIRA, M.; GOMES, E. Histopathological imaging dataset for oral cancer analysis: a study with a data leakage warning. In: Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies -- BIOSIGNALS, p. 811--818, 2025. DOI: 10.5220/0013382100003911. DOI: https://doi.org/10.5220/0013382100003911
PARAMASIVAM, M. E. et al. Oral cancer detection using convolutional neural network. In: 2024 4th International Conference on Innovative Practices in Technology and Management (ICIPTM), p. 1--6, 2024. DOI: 10.1109/ICIPTM59628.2024.10563232. DOI: https://doi.org/10.1109/ICIPTM59628.2024.10563232
DEVINDI, G. A. I. et al. Multimodal deep convolutional neural network pipeline for AI-assisted early detection of oral cancer. IEEE Access, v. 12, 2024. DOI: 10.1109/ACCESS.2024.3454338. DOI: https://doi.org/10.1109/ACCESS.2024.3454338
ZAIDPY. Oral cancer dataset. Kaggle, 2022. Disponível em: https://www.kaggle.com/datasets/zaidpy/oral-cancer-dataset. Acesso em: 2024.
Descargas
Publicado
Número
Sección
Licencia
Derechos de autor 2026 Maria Isabelly de Brito Rodrigues, Wanderson de Vasconcelos Rodrigues da Silva, Ricardo Moura Sekeff Budaruiche, Iallen Gabio de Sousa Santos
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
Authors who publish in this journal agree to the following terms:
Authors retain copyright and grant the journal the right of first publication, with the work simultaneously licensed under the Creative Commons Attribution License, which permits the sharing of the work with proper acknowledgment of authorship and initial publication in this journal;
Authors are authorized to enter into separate, additional agreements for the non-exclusive distribution of the version of the work published in this journal (e.g., posting in an institutional repository or publishing it as a book chapter), provided that authorship and initial publication in this journal are properly acknowledged, and that the work is adapted to the template of the respective repository;
Authors are permitted and encouraged to post and distribute their work online (e.g., in institutional repositories or on their personal websites) at any point before or during the editorial process, as this may lead to productive exchanges and increase the impact and citation of the published work (see The Effect of Open Access);
Authors are responsible for correctly providing their personal information, including name, keywords, abstracts, and other relevant data, thereby defining how they wish to be cited. The journal’s editorial board is not responsible for any errors or inconsistencies in these records.
PRIVACY POLICY
The names and email addresses provided to this journal will be used exclusively for the purposes of this publication and will not be made available for any other purpose or to third parties.
Note: All content of the work is the sole responsibility of the author and the advisor.
