Early Prediction of Oral Precancerous Lesions Using Artificial Intelligence

Early Prediction of Oral Precancerous Lesions Using Artificial Intelligence Publisher

Summary: Can texture analysis in images detect oral precancerous lesions? Research suggests GLCM features show 88% accuracy, highlighting potential non-invasive diagnostic tools. #OralHealth #AIinMedicine

Rathinavelu P K ; Pillai V ; Yadalam P K ; Thilagar S S ; Raee A ; Heboyan A

Source: Frontiers in Dentistry Published:2026

Abstract

Objectives: Oral potentially malignant disorders may present as white, red, or mixed red-white lesions and require accurate early recognition. This study evaluated whether texture-analysis features extracted from clinical digital images could distinguish oral precancerous lesions from other ora l mucosal lesions and normal mucosa using gray-level co-occurrence matrix (GLCM), gray-level run-length matrix (GLRLM), and wavelet analysis. Materials and Methods: Sixty-four clinical digital images were selected according to predefined inclusion and exclusion criteria. The dataset included leukoplakia, erythroplakia, oral submucousfibrosis, candidiasis, lichen planus, leukoderma, frictional keratosis, white spongy nevus, and normal mucosa. Regions of interest were extracted from each image, and texture features were derived using GLCM, GLRLM, and wavelet analysis. A support vector machine (SVM) classifier wasthen used to categorize images as oral precancerouslesions or non-precancerous/normal mucosa. Results: GLCM yielded the highest classification accuracy (88%), followed by GLRLM (81%) and wavelet analysis (79%). The corresponding sensitiv it y values were 77%, 64%, and 60%, and the specificity values were 93%, 90%, and 89%, respectively. The positive predictive values were 83% for GLCM, 75% for GLRLM, and 75% for wavelet analysis. Conclusion: GLCM-based texture features provided the best diagnostic performance in this dataset. These image-analysis methods may be useful as non-invasive adjuncts to conventional clinical examination and histopathological diagnosis; however, larger datasetsand external validation are required before clinical implementation. Copyright © 2026The Authors.

Style	Citing Format
MLA	Rathinavelu P K, et al.. "Early Prediction of Oral Precancerous Lesions Using Artificial Intelligence." Frontiers in Dentistry, vol. 23, no. , 2026, pp. -.
APA	Rathinavelu P K, Pillai V, Yadalam P K, Thilagar S S, Raee A, Heboyan A (2026). Early Prediction of Oral Precancerous Lesions Using Artificial Intelligence. Frontiers in Dentistry, 23(), -.
Chicago	Rathinavelu P K, Pillai V, Yadalam P K, Thilagar S S, Raee A, Heboyan A. "Early Prediction of Oral Precancerous Lesions Using Artificial Intelligence." Frontiers in Dentistry 23, no. (2026): -.
Harvard	Rathinavelu P K et al. (2026) 'Early Prediction of Oral Precancerous Lesions Using Artificial Intelligence', Frontiers in Dentistry, 23(), pp. -.
Vancouver	Rathinavelu P K, Pillai V, Yadalam P K, Thilagar S S, Raee A, Heboyan A. Early Prediction of Oral Precancerous Lesions Using Artificial Intelligence. Frontiers in Dentistry. 2026;23():-.
BibTex	@article{ author = {Rathinavelu P K and Pillai V and Yadalam P K and Thilagar S S and Raee A and Heboyan A}, title = {Early Prediction of Oral Precancerous Lesions Using Artificial Intelligence}, journal = {Frontiers in Dentistry}, volume = {23}, number = {}, pages = {-}, year = {2026} }
RIS	TY - JOUR AU - Rathinavelu P K AU - Pillai V AU - Yadalam P K AU - Thilagar S S AU - Raee A AU - Heboyan A TI - Early Prediction of Oral Precancerous Lesions Using Artificial Intelligence JO - Frontiers in Dentistry VL - 23 IS - SP - EP - PY - 2026 ER -

Science Communicator Platform

Authors

Abstract