A Deep Learning-Based Image Processing Framework for Oral Lesion Classification

N. V. Soma Sekhar Vissamsetti; Gandla Shivakanth

doi:10.48084/etasr.15583

Authors

N. V. Soma Sekhar Vissamsetti Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Hyderabad, India
Gandla Shivakanth Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Hyderabad, India

Volume: 16 | Issue: 2 | Pages: 33266-33271 | April 2026 | https://doi.org/10.48084/etasr.15583

Received: 16 October 2025 | Revised: 11 November 2025 | Accepted: 21 November 2025 | Online: 13 February 2026

Corresponding author: Gandla Shivakanth

Abstract

Early detection of Oral Squamous Cell Carcinoma (OSCC) remains critical for improving patient survival, yet conventional screening techniques are limited by subjectivity, invasiveness, and inadequate accessibility in low-resource settings. This study presents a deep learning-based image processing framework designed to classify oral cavity images into three diagnostic categories: healthy, Oral Potentially Malignant Disorders (OPMD), and OSCC. The proposed system integrates optimized preprocessing steps, including noise reduction, adaptive histogram equalization, and color normalization, with a lightweight Convolutional Neural Network (CNN) architecture fine-tuned through transfer learning. Using the AI4OralHealth dataset comprising 3,000 annotated intraoral images, the model achieved a test accuracy of 93.44%, macro-averaged recall of 92.67%, and specificity of 96.15%, outperforming baseline architectures such as VGG16, ResNet-50, and MobileNetV2. Activation map visualization confirmed that the network focused on clinically relevant lesion regions, enhancing interpretability and clinical trust. These results demonstrate the feasibility of deploying Explainable Artificial Intelligence (XAI) systems for automated oral lesion screening and early OSCC detection, particularly in resource-constrained clinical and community environments. The modular design also allows future integration with histopathological and optical imaging modalities, supporting scalable mobile Health (mHealth)-based diagnostic applications.

Keywords:

Oral Squamous Cell Carcinoma (OSCC), deep learning, image classification, Convolutional Neural Network (CNN), Explainable Artificial Intelligence (XAI), mobile Health (mHeath)

Downloads

Download data is not yet available.

References

"Comprehensive assessment of evidence on oral cancer prevention released." World Health Organization. https://www.who.int/news/item/29-11-2023-comprehensive-assessment-of-evidence-on-oral-cancer-prevention-released-29-november-2023.

A. D. Shrestha, P. Vedsted, P. Kallestrup, and D. Neupane, "Prevalence and incidence of oral cancer in low- and middle-income countries: A scoping review," European Journal of Cancer Care, vol. 29, no. 2, Mar. 2020, Art. no. e13207.

N. Haj-Hosseini, J. Lindblad, B. Hasséus, V. V. Kumar, N. Subramaniam, and J.-M. Hirsch, "Early Detection of Oral Potentially Malignant Disorders: A Review on Prospective Screening Methods with Regard to Global Challenges," Journal of Maxillofacial and Oral Surgery, vol. 23, no. 1, pp. 23–32, Feb. 2024.

A. K. Jeihooni, F. Jafari, A. K. Jeihooni, and F. Jafari, "Oral Cancer: Epidemiology, Prevention, Early Detection, and Treatment," in Oral Cancer - Current Concepts and Future Perspectives, London, UK: IntechOpen, 2021, ch. 1.

"Flourescent Oral Cancer Screening (or other screening devices)." Esposito Family Dental. https://www.espositofamilydental.com/our-technology/flourescent-oral-cancer-screening-or-other-screening-devices.

S. Deorah, A. Singh, and S. Gupta, "Beyond tissue: Liquid biopsy’s promise in unmasking oral cancer," Oral Oncology Reports, vol. 9, Mar. 2024, Art. no. 100162.

S. B. Khanagar et al., "Application and Performance of Artificial Intelligence (AI) in Oral Cancer Diagnosis and Prediction Using Histopathological Images: A Systematic Review," Biomedicines, vol. 11, no. 6, June 2023, Art. no. 1612.

D. Khanna et al., "A prospective study on diagnostic accuracy of technology-enabled early detection of oral cancer and epidemiology of tobacco and other substances use in rural India," Cancer, vol. 131, no. 1, Jan. 2025, Art. no. e35702.

P. Chakraborty, T. Chandrapragasam, A. Arunachalam, and S. Rafiammal, "Artificial Intelligence-based Oral Cancer Screening System using Smartphones," Engineering, Technology & Applied Science Research, vol. 13, no. 6, pp. 12054–12057, Dec. 2023.

E. Ramesh, A. Ganesan, K. C. Lakshmi, and P. M. Natarajan, "Artificial intelligence—based diagnosis of oral leukoplakia using deep convolutional neural networks Xception and MobileNet-v2," Frontiers in Oral Health, vol. 6, Mar. 2025, Art. no. 1414524.

M. Kantharimuthu, M. M, S. P, A. A. M. G, K. B. S. N, and J. D. K, "Oral Cancer Prediction Using a Probability Neural Network (PNN)," Asian Pacific Journal of Cancer Prevention, vol. 24, no. 9, pp. 2991–2995, Sept. 2023.

H. M. Afify, K. K. Mohammed, and A. Ella Hassanien, "Novel prediction model on OSCC histopathological images via deep transfer learning combined with Grad-CAM interpretation," Biomedical Signal Processing and Control, vol. 83, May 2023, Art. no. 104704.

W. Yuan et al., "Noninvasive diagnosis of oral squamous cell carcinoma by multi-level deep residual learning on optical coherence tomography images," Oral Diseases, vol. 29, no. 8, pp. 3223–3231, 2023.

R. Javed, M. S. M. Rahim, T. Saba, and A. Rehman, "A comparative study of features selection for skin lesion detection from dermoscopic images," Network Modeling Analysis in Health Informatics and Bioinformatics, vol. 9, no. 1, Dec. 2019, Art. no. 4.

T. Saba, "Automated lung nodule detection and classification based on multiple classifiers voting," Microscopy Research and Technique, vol. 82, no. 9, pp. 1601–1609, Sept. 2019.

N. S. Piyarathne et al., "A comprehensive dataset of annotated oral cavity images for diagnosis of oral cancer and oral potentially malignant disorders," Oral Oncology, vol. 156, Sept. 2024, Art. no. 106946.