AI-powered classification of oral pre-‎cancer: a histopathological image ‎approach

Authors

  • Dr. Sharmila Sengupta

    Department of Computer Engineering and Vivekanand Education Society's Institute of Technology, Chembur, Mumbai, India

  • Dr. Priya R. L

    Department of Computer Engineering and Vivekanand Education Society's Institute of Technology, Chembur, Mumbai, India

  • Anuj Bagad

    Department of Computer Engineering and Vivekanand Education Society's Institute of Technology, Chembur, Mumbai, India

  • Aayush Talreja

    Department of Computer Engineering and Vivekanand Education Society's Institute of Technology, Chembur, Mumbai, India

  • Mansi Bellani

    Department of Computer Engineering and Vivekanand Education Society's Institute of Technology, Chembur, Mumbai, India

  • Dr Harsha Karwa

    Department of Oral Pathology and Microbiology, Government Dental College & Hospital, Mumbai, India

  • Dr Shrijha G

    Department of Oral Pathology and Microbiology, Government Dental College & Hospital, Mumbai, India

How to Cite

Sengupta , D. S. ., L, D. P. R., Bagad , A. ., Talreja, A. . ., Bellani , M. ., Karwa , D. H. ., & G, D. S. . (2025). AI-powered classification of oral pre-‎cancer: a histopathological image ‎approach. International Journal of Basic and Applied Sciences, 14(1), 377-387. https://doi.org/10.14419/8c1tmt79

Received date: April 23, 2025

Accepted date: May 18, 2025

Published date: May 23, 2025

DOI:

https://doi.org/10.14419/8c1tmt79

Keywords:

Atypical Mitotic Figures; Irregular Epithelial Stratification; Hyperchromasia; Apoptotic Mitoses; Keratinization; Loss of Polarity of Basal Cells; ‎Keratin Pearls; Rete Ridges; Histopathological Images; H&E Stains; Template Matching; Digital Pathology

Abstract

A high fatality rate characterises the prognosis outlook for oral cancer due to delayed diagnosis and significantly hinders the ‎advancements in early detection techniques. Traditional histological investigation, a cornerstone of precancerous lesion diagnosis, faces ‎substantial challenges in terms of labour intensity in manually processing tissue samples, is time-consuming and the inferences are mostly ‎guided by microscopic investigation. Therefore, a system is proposed for oral dysplasia grading from histopathological tissues using machine ‎learning. Distinguished from other methodologies, this approach incorporates a comprehensive array of features, not limited to cell nuclei ‎properties but also morphometric analysis of epithelial stratification and enhancements in digital pathology. Moreover, early pre-cancer ‎grading enhances the survival chances of patients by identifying abnormalities that might be missed through conventional examination. The ‎study presented here has an overall accuracy of 94%, considering the limited training cases available under each feature. This approach would ‎benefit both doctors and patients by streamlining the diagnostic process and improving its outcomes. The fundamentals of oral cancer ‎surgical management, when it comes to risk factors, regional predispositions, treatment response, and outcome, oral cavity squamous cell ‎carcinoma (OSCC) is a heterogeneous illness. Surgery is the main treatment option for oral malignancies, even though non-surgical ‎treatment is used in other head and neck subsites. Adjuvant treatment, such as radiation or chemoradiation, is then administered based on ‎the risk factors of the final histopathology. Before beginning treatment, a multidisciplinary tumor board must discuss each patient ‎and develop a treatment strategy. This chapter aims to explain the fundamental surgical concepts used in the reconstruction of defects and the ‎management of various oral cavity subsites. The surgical management the technical process of brain arteriovenous malformation (bAVM) ‎excision, patient selection for surgery, and perioperative care that optimizes the likelihood of the best result are all included in surgical ‎treatment‎.

References

  1. Gupta, R. K., Manhas, J., & Kour, M. (2022). Hybrid Feature Extraction Based Ensemble Classification Model to Diagnose Oral ‎Carcinoma Using Histopathological Images. Journal of Scientific Research, 66(3), 219-226. Banaras Hindu University. https://doi.org/10.37398/JSR.2022.660327.
  2. Panigrahi, S., Nanda, B.S., Bhuyan et al. (2023). Classifying histopathological images of oral squamous cell carcinoma using deep transfer ‎learning. Heliyon, 9(2023), e13444. https://doi.org/10.1016/j.heliyon.2023.e13444.
  3. ‎Rahman AU, Alqahtani A, Aldhafferi N, Nasir MU, Khan MF, Khan MA, Mosavi A. “Histopathologic Oral Cancer Prediction Using Oral ‎Squamous Cell Carcinoma Biopsy Empowered with Transfer Learning.” Sensors (Basel). 2022 May 18;22(10):3833. doi: ‎‎10.3390/s22103833. PMID: 35632242; PMCID: PMC9146317.‎ https://doi.org/10.3390/s22103833.
  4. 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, https://doi.org/10.1109/ACCESS.2020.3010180.
  5. ‎B R, Nanditha & Annegowda, Geetha. (2022). “Oral Cancer Detection using Machine Learning and Deep Learning Techniques.” ‎International Journal of Current Research and Review. 14. 64-70. https://doi.org/10.31782/IJCRR.2021.14104.
  6. Bashir, S., Mahmood, H., Shaban, M., et al. (2020). “Automated grade classification of oral epithelial dysplasia using morphometric ‎analysis of his-tology images.” in H.K. Hahn & M.A. Mazurowski (Eds.), Medical Imaging 2020: Digital Pathology (Vol. 11320, pp. page ‎range). Society of Pho-to-Optical Instrumentation Engineers (SPIE). ‎ https://doi.org/10.1117/12.2549705.
  7. Aldhebaib, A., Khanagar, S. B., Alkadi, L., Alghilan, M. A., Kalagi, S., Awawdeh, M., Bijai, L. K., Vishwanathaiah, S., & Singh, O. G. ‎‎(2023). “Application and Performance of Artificial Intelligence (AI) in Oral Cancer Diagnosis and Prediction Using Histopathological Images: ‎A Systemat-ic Review.” Biomedicines, 11(6), 1612. MDPI. https://doi.org/10.3390/biomedicines11061612.
  8. ‎Kritsasith, W., & Suebnukarn, S. (2024). “Deep Learning in Oral Cancer: A Systematic Review. “BMC Oral Health, 24, Article 39. BioMed ‎Central. https://doi.org/10.1186/s12903-024-03993-5.
  9. Dixit, S., Kumar, A., & Srinivasan, K. (2023). “A Current Review of Machine Learning and Deep Learning Models in Oral Cancer ‎Diagnosis: Re-cent Technologies, Open Challenges, and Future Research Directions. Diagnostics”, 13(7), 1353. MDPI. https://doi.org/10.3390/diagnostics13071353..‎
  10. ‎Vanesa Pereira-Prado et.al. “Artificial Intelligence for Image Analysis in Oral Squamous Cell Carcinoma: A Review”, Diagnostics (Basel) ‎‎2023 Jul 20;13(14):2416. https://doi.org/10.3390/diagnostics13142416.‎
  11. Chaudhary, N., Rai, A., Rao, A.M. et al. “High-resolution AI image dataset for diagnosing oral submucous fibrosis and squamous cell ‎carcinoma.” Sci Data 11, 1050 (2024). https://doi.org/10.1038/s41597-024-03836-6.‎
  12. Jiakuan Peng et.al., “Oral epithelial dysplasia detection and grading in oral leukoplakia using deep learning”, BMC Oral Health, 2024 Apr ‎‎9;24:434. https://doi.org/10.1186/s12903-024-04191-z.
  13. ‎Simran Uppal et.al., “Machine learning methods in predicting the risk of malignant transformation of oral potentially malignant disorders: ‎A sys-tematic review”, International Journal of Medical Informatics, Volume 186, June 2024, 105421‎ https://doi.org/10.1016/j.ijmedinf.2024.105421.
  14. Rachelle Wolk, et.al. “Proceedings of the North American Society of Head and Neck Pathology Companion Meeting, New Orleans, LA, ‎March 12, 2023: Oral Cavity Dysplasia: Why Does Histologic Grading Continue to be Contentious?”, Head Neck Pathol ,2023 May ‎‎15;17(2):292–298. https://doi.org/10.1007/s12105-023-01544-y.
  15. ‎John Adeoye et.al., “Deep Learning Predicts the Malignant-Transformation-Free Survival of Oral Potentially Malignant Disorders” , ‎Cancers (Basel) 2021 Dec 1;13(23):6054. https://doi.org/10.3390/cancers13236054.
  16. Amann, J., Blasimme, A., Vayena, E. et al. Explainability for artificial intelligence in healthcare: a multidisciplinary perspective. BMC ‎Med Inform Decis Mak 20, 310 (2020). https://doi.org/10.1186/s12911-020-01332-6.‎

Downloads

How to Cite

Sengupta , D. S. ., L, D. P. R., Bagad , A. ., Talreja, A. . ., Bellani , M. ., Karwa , D. H. ., & G, D. S. . (2025). AI-powered classification of oral pre-‎cancer: a histopathological image ‎approach. International Journal of Basic and Applied Sciences, 14(1), 377-387. https://doi.org/10.14419/8c1tmt79

Received date: April 23, 2025

Accepted date: May 18, 2025

Published date: May 23, 2025