Deep Representation Learning-Based Oral Potentially Malignant Disorders Detection Model

Samah Alzanin; Mohammed Alonazi

doi:10.48084/etasr.17920

Authors

Samah Alzanin Department of Computer Science, College of Computer Engineering and Sciences, Prince Sattam bin Abdulaziz University, Kharj, Saudi Arabia
Mohammed Alonazi Department of Information Systems, College of Computer Engineering and Sciences, Prince Sattam bin Abdulaziz University, Al-Kharj, Saudi Arabia

Volume: 16 | Issue: 3 | Pages: 34894-34899 | June 2026 | https://doi.org/10.48084/etasr.17920

Received: 2 February 2026 | Revised: 25 February 2026, 6 March 2026, and 17 March 2026 | Accepted: 27 March 2026 | Online: 6 June 2026
Corresponding author: Samah Alzanin

Abstract

Clinical Decision Support Systems (CDSSs) play a crucial role in modern healthcare by enabling health professionals to efficiently analyze patient data and make accurate, evidence-based clinical decisions. In the context of CDSSs, the analysis of Oral Potentially Malignant Disorders (OPMDs) has seen advances through digital technologies, as Computer-Aided Diagnosis (CAD) techniques that incorporate Artificial Intelligence (AI) and image processing play a vital role in early detection. Deep Learning (DL) in OPMD diagnosis has the capacity to handle intricate patterns, employ differences in image quality, and continuously improve with more data. Incorporation of DL into oral healthcare not only improves diagnostic accuracy but also has the potential to streamline screening, minimize human errors, and provide earlier intervention, eventually improving patient outcomes and supporting the overall treatment of oral health conditions. This study presents an Improved Oral Potentially Malignant Disorder Diagnosis using a Stacked Sparse Autoencoder (IOPMDD-SSAE) model to support clinical decisions in the recognition and classification of OPMD. Oral images of patients can be uploaded to a CDSS, where IOPMDD-SSAE can analyze them, offering an accurate and automatic investigation. IOPMDD-SSAE uses a Wiener Filtering (WF) technique to remove noise. The complex and intrinsic features of the oral images are captured by an SE-ResNet model. Finally, OPMD detection and classification take place using an SSAE. A comparison of IOPMDD-SSAE with existing methods demonstrated a superior accuracy of 98.08% on the Oral cancer (Lips and Tongue) images dataset.

Keywords:

oral cancer, Internet of Things (IoT), Wiener filtering, computer-aided diagnosis, clinical decision support

References

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.

S. M. Sagari, V. P. Malagi, and B. Chandrahas, "A Novel Feature Extraction Approach Using Deformable Adaptive Instance-Based U-Net Architecture for Segmentation and Classification of Oral Mucosal Lesion," Engineering, Technology & Applied Science Research, vol. 15, no. 4, pp. 25228–25234, Aug. 2025.

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, June 2021.

M. Parola, F. A. Galatolo, G. La Mantia, M. G. C. A. Cimino, G. Campisi, and O. Di Fede, "Towards explainable oral cancer recognition: Screening on imperfect images via Informed Deep Learning and Case-Based Reasoning," Computerized Medical Imaging and Graphics, vol. 117, Oct. 2024, Art. no. 102433.

X. Liang, Q. Chen, Y. Cao, B. Liu, S. Chen, and X. Liu, "Automated Scene Classification in Endoscopy Videos Using Convolutional Neural Networks," in 2024 IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), June 2024, pp. 157–161.

E. S. Mira et al., "Early Diagnosis of Oral Cancer Using Image Processing and Artificial Intelligence," Fusion: Practice and Applications, vol. 14, no. 1, pp. 293–308, 2024.

R. Alabdan, A. Alruban, A. M. Hilal, and A. Motwakel, "Artificial-Intelligence-Based Decision Making for Oral Potentially Malignant Disorder Diagnosis in Internet of Medical Things Environment," Healthcare, vol. 11, no. 1, Dec. 2022.

R. Dharani, S. Revathy, and K. Danesh, "Fuzzy Genetic Particle Swarm Optimization Convolution Neural Network Based On Oral Cancer Identification System," Journal of Applied Engineering and Technological Science (JAETS), vol. 5, no. 1, pp. 150–169, Dec. 2023.

M. Shariff, P. Singh SM, S. DP, V. MH, and A. S. Poornima, "Convolutional neural network for detection of oral cavity leading to oral cancer from photographic images," International Journal of Computing and Digital Systems, vol. 15, no. 1, pp. 865–877, 2024.

F. Jubair, O. Al-karadsheh, D. Malamos, S. Al Mahdi, Y. Saad, and Y. Hassona, "A novel lightweight deep convolutional neural network for early detection of oral cancer," Oral Diseases, vol. 28, no. 4, pp. 1123–1130, 2022.

M. Al Duhayyim et al., "Sailfish Optimization with Deep Learning Based Oral Cancer Classification Model," Computer Systems Science and Engineering, vol. 45, no. 1, pp. 753–767, 2023.

Z. Guo, S. Ao, and B. Ao, "Few-shot learning based oral cancer diagnosis using a dual feature extractor prototypical network," Journal of Biomedical Informatics, vol. 150, Feb. 2024, Art. no. 104584.

H. Myriam et al., "Advanced Meta-Heuristic Algorithm Based on Particle Swarm and Al-Biruni Earth Radius Optimization Methods for Oral Cancer Detection," IEEE Access, vol. 11, pp. 23681–23700, 2023.

Z. Lin et al., "Deep learning-based electrical impedance spectroscopy analysis for malignant and potentially malignant oral disorder detection," Scientific Reports, vol. 15, no. 1, June 2025, Art. no. 19458.

K. M. Desai et al., "Screening of oral potentially malignant disorders and oral cancer using deep learning models," Scientific Reports, vol. 15, no. 1, May 2025, Art. no. 17949.

J. Adeoye and Y. X. Su, "COCOH: A Multimodal Deep Learning Framework for Cancer Risk Assessment of Oral Potentially Malignant Disorders." medRxiv, Jan. 05, 2026.

X. Liang et al., "Enhancing polyp detection in endoscopy with cross-channel self-attention fusion," Smart Health, vol. 36, June 2025, Art. no. 100578.

Y. He, Q. Chen, Z. Xiong, X. Liang, Y. Cao, and B. Liu, "One-stage Framework for Thyroid Nodule Detection with Mixup and Negative Sample Utilization," in 2025 IEEE International Conference on Image Processing (ICIP), Sept. 2025, pp. 2205–2210.

R. Hardie, "A Fast Image Super-Resolution Algorithm Using an Adaptive Wiener Filter," IEEE Transactions on Image Processing, vol. 16, no. 12, pp. 2953–2964, Sept. 2007.

J. Hu, L. Shen, and G. Sun, "Squeeze-and-Excitation Networks," in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 2018, pp. 7132–7141.

Y. Bengio, P. Lamblin, D. Popovici, and H. Larochelle, "Greedy Layer-Wise Training of Deep Networks," in Advances in Neural Information Processing Systems, 2006, vol. 19.

"Oral Cancer (Lips and Tongue) images." Kaggle, [Online]. Available: https://www.kaggle.com/datasets/shivam17299/oral-cancer-lips-and-tongue-images.