Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Aug 22;15(1):30834.
doi: 10.1038/s41598-025-14450-w.

Performance of deep learning models for the classification and object detection of different oral white lesions using photographic images

Siribang-On Piboonniyom Khovidhunkit  1 , Kunchidsong Phosri  2 , Bhornsawan Thanathornwong  3 , Dulyapong Rungraungrayabkul  4 , Suvit Poomrittigul  5 , Treesukon Treebupachatsakul  6
Affiliations

Performance of deep learning models for the classification and object detection of different oral white lesions using photographic images

Siribang-On Piboonniyom Khovidhunkit et al. Sci Rep. .

Abstract

Computer vision adjunctive technology for oral lesion diagnoses has been developed to detect and identify Oral Potentially Malignant Disorders (OPMDs) and non-OPMDs. The early detection of OPMDs can reduce the risk of oral cancer development, improving the survival rate of the patients. This study aims to evaluate the computer vision technique in the white oral lesion domain within the scope of photographic images. Deep learning techniques for the classification of Convolution Neural Networks (CNNs) and transformer neural networks, and one-stage models of YOLOv7 and YOLOv8 were utilized to classify and detect five classes of OPMDs and non-OPMDs oral white lesions including oral leukoplakia, oral lichen planus, pseudomembranous candidiasis, oral ulcers covered with pseudomembrane and other white benign oral lesions. From the evaluation results of classification, the IFormerBase model achieves overperformance compared to CNN models with accuracy, precision, and F1 score of more than 80% on the test set. The best model for object detection is YOLOv7 with 84.5% mean Average Precision (mAP) at Intersection over Union (IoU) threshold of 0.3 and 74.5% at IoU of 0.5 on the test set. Object detection results reveal promising automatic oral lesion identification, which can be further developed to enhance the lesion screening system.

Keywords: Cancer; Classification; Deep learning; Object detection; Oral white lesions.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests. Ethics approval and consent to participate: This study was approved by the Ethical Committee of the Faculty of Dentistry/Faculty of Pharmacy, Mahidol University COA.NO.MU-DT/PY-IRB 2021/092.2010, which was in full compliance with International Guidelines for Human Research Protection including the Helsinki Declaration, the Belmont Report, CIOMS Guideline, and the International Conference on Harmonization in Good Clinical Practice. The date of ethics approval was 20 October 2021. Since the images used in this study were intraoral images, participant identification was not applicable. Informed consent in Thai language was obtained from all the participants in the study.

Figures

Fig. 1
Fig. 1
Examples of image dataset of each class; (a) Leukoplakia, (b) Lichen planus, (c) Pseudomembranous candidiasis, (d) Other white benign oral lesions, and (e) Ulcers covered with pseudomembrane.
Fig. 2
Fig. 2
Definition of true positive, false positive, and false negative. Green boxes are ground truth. Red boxes are predicted correctly. (a) is true positive, (b), (c), and (d) are false positive, (e) is false negative.
Fig. 3
Fig. 3
Results of confusion matrices of unseen test on IFormerBase model.
Fig. 4
Fig. 4
Validation set results of ROC curve and AUC score of IFormerBase.
Fig. 5
Fig. 5
The PR-curve plots of four detection models: (a) YOLOv7 model, (b) YOLOv7x model, (c) YOLOv8n model, and (d) YOLOv8x model.
Fig. 6
Fig. 6
Example of images detected by YOLOv7. Green box is the ground truth. The predicted boxes are: (a) Leukoplakia (grey), (b) Lichen planus (red), (c) Pseudomembranous candidiasis (purple), (d) Other white benign oral lesions (orange), and (e) Ulcer covered with pseudomembrane (blue).
See this image and copyright information in PMC

References

    1. Zahid, E., Bhatti, O., Zahid, M. A. & Stubbs, M. Overview of common oral lesions. Malays Fam Physician. 17 (3), 9–21. 10.51866/rv.37 (2022). - PMC - PubMed
    1. Mortazavi, H. et al. Oral white lesions: an updated clinical diagnostic decision tree. Dent. J. (Basel). 7 (1), 15. 10.3390/dj7010015 (2019). - PMC - PubMed
    1. Hellstein, J. W. & Marek, C. L. Candidiasis: red and white manifestations in the oral cavity. Head Neck Pathol.13 (1), 25–32. 10.1007/s12105-019-01004-6 (2019). - PMC - PubMed
    1. Philipone, E. M. & Peters, S. M. Ulcerative and inflammatory lesions of the oral mucosa. Oral Maxillofac. Surg. Clin. North. Am.35 (2), 219–226. 10.1016/j.coms.2022.10.001 (2023). - PubMed
    1. van der Waal, I. Oral leukoplakia, the ongoing discussion on definition and terminology. Med. Oral Patol. Oral Cir. Bucal. 20 (6), e685–e692. 10.4317/medoral.21007 (2015). - PMC - PubMed

MeSH terms

LinkOut - more resources