International Journal of Emerging Research in Engineering, Science, and Management
Vol. 4, Issue 2, pp. 07-13, Apr-Jun 2025.
https://doi.org/10.58482/ijeresm.v4i2.2

This work is licensed under a Creative Commons Attribution 4.0 International License.

Oral Lesions Classification using EfficientNet Transfer Learning Model

Devika G

Asha Gowda Karegowda

Associate Professor, Dept. of CSE, Government Engineering College, Kushalnagar, India.

Associate Professor, Dept. of MCA, Sigganga Institute of Technology, Tumkur, Karnataka, India

Abstract: Due to their wide variety of diseases, oral lesions present a substantial diagnostic problem. This research uses deep learning techniques, particularly the EfficientNetB7 model, to present an automated categorisation analysis of oral lesions. The study divides lesions into benign and malignant categories using the Oral Lesions: Cancer Detection Dataset, comprising 2270 high-resolution pictures. Known for its effectiveness in processing large-scale image collections, the EfficientNetB7 architecture is employed in this work. The model successfully distinguishes between benign and malignant tumors with an exceptional accuracy rate of 99.12%. The study highlights the diagnostic dependability of the model by analyzing its performance, including metrics for sensitivity, specificity, and accuracy. Moreover, the study investigates how interpretable the model’s predictions are, emphasizing essential aspects that support its decision-making process.

Keywords: Benign, EfficientNet-B7, Malignant, Oral Lesions, Transfer Learning.

References: 

  1. D. C. G. De Veld, M. Skurichina, M. J. H. Witjes, R. P. W. Duin, H. J. C. M. Sterenborg, and J. L. N. Roodenburg, “Clinical study for classification of benign, dysplastic, and malignant oral lesions using autofluorescence spectroscopy,” Journal of Biomedical Optics, vol. 9, no. 5, p. 940, Jan. 2004, doi: 10.1117/1.1782611.
  2. R. A. Welikala et al., “Automated Detection and Classification of Oral Lesions Using Deep Learning for Early Detection of Oral Cancer,” in IEEE Access, vol. 8, pp. 132677-132693, 2020, doi: 10.1109/ACCESS.2020.3010180.
  3. S. Warnakulasuriya, Newell. W. Johnson, and I. Van Der Waal, “Nomenclature and classification of potentially malignant disorders of the oral mucosa,” Journal of Oral Pathology and Medicine, vol. 36, no. 10, pp. 575–580, Jul. 2007, doi: 10.1111/j.1600-0714.2007.00582.x.
  4. G. Tanriver, M. S. Tekkesin, and O. Ergen, “Automated detection and classification of oral lesions using deep learning to detect oral potentially malignant disorders,” Cancers, vol. 13, no. 11, p. 2766, Jun. 2021, doi: 10.3390/cancers13112766.
  5. D. K. Das, S. Bose, A. K. Maiti, B. Mitra, G. Mukherjee, and P. K. Dutta, “Automatic identification of clinically relevant regions from oral tissue histological images for oral squamous cell carcinoma diagnosis,” Tissue and Cell, vol. 53, pp. 111–119, Jun. 2018, doi: 10.1016/j.tice.2018.06.004.
  6. Y. Liu, E. Bilodeau, B. Pollack, and K. Batmanghelich, “Automated detection of premalignant oral lesions on whole slide images using convolutional neural networks,” Oral Oncology, vol. 134, p. 106109, Sep. 2022, doi: 10.1016/j.oraloncology.2022.106109.
  7. R. Gomes et al., “Use of Artificial Intelligence in the Classification of Elementary Oral Lesions from Clinical Images,” International Journal of Environmental Research and Public Health, vol. 20, no. 5, p. 3894, Feb. 2023, doi: 10.3390/ijerph20053894.
  8. K. Warin, W. Limprasert, S. Suebnukarn, S. Jinaporntham, and P. Jantana, “Automatic classification and detection of oral cancer in photographic images using deep learning algorithms,” Journal of Oral Pathology and Medicine, vol. 50, no. 9, pp. 911–918, Aug. 2021, doi: 10.1111/jop.13227.
  9. H. Lin, H. Chen, L. Weng, J. Shao, and J. Lin, “Automatic detection of oral cancer in smartphone-based images using deep learning for early diagnosis,” Journal of Biomedical Optics, vol. 26, no. 08, Aug. 2021, doi: 10.1117/1.jbo.26.8.086007.
  10. H. Lin, H. Chen, L. Weng, J. Shao, and J. Lin, “Automatic detection of oral cancer in smartphone-based images using deep learning for early diagnosis,” Journal of Biomedical Optics, vol. 26, no. 08, Aug. 2021, doi: 10.1117/1.jbo.26.8.086007.
  11. D. F. D. D. Santos, P. R. De Faria, B. A. N. Travençolo, and M. Z. D. Nascimento, “Automated detection of tumor regions from oral histological whole slide images using fully convolutional neural networks,” Biomedical Signal Processing and Control, vol. 69, p. 102921, Jul. 2021, doi: 10.1016/j.bspc.2021.102921.
  12. M. Gobara, “Oral lesions: Malignancy Detection Dataset,” Dec. 31, 2023. https://www.kaggle.com/datasets/mohamedgobara/oral-lesions-malignancy-detection-dataset
  13. T. Izumo, “Oral premalignant lesions: from the pathological viewpoint,” International Journal of Clinical Oncology, vol. 16, no. 1, pp. 15–26, Jan. 2011, doi: 10.1007/s10147-010-0169-z.
  14. V. Liyanage, M. Tao, J. S. Park, K. N. Wang, and S. Azimi, “Malignant and non-malignant oral lesions classification and diagnosis with deep neural networks,” Journal of Dentistry, vol. 137, p. 104657, Aug. 2023, doi: 10.1016/j.jdent.2023.104657.
Download PDF