Title

Artificial intelligence in oral and maxillofacial surgery: Diagnostic accuracy for pathology and fracture detection

Authors

Saloni Bharti^1,*, Eragattapu Sulochana², Saumen Kumar De³, Aakriti Choudhary⁴, Megha Varghese⁵ & Zuben Mohanty⁶

Affiliation

¹Department of Dentistry, ESIC Medical College and Hospital, Bihta, Patna, India; ²Department of Oral Medicine and Radiology Department, Government Dental College and Hospital, Hyderabad, India; ³Department of Physical Medicine and Rehabilitation, Nil Ratan Sircar Medical College and Hospital, Acharya Jagdish Chandra Bose Road, Sealdah, Kolkata, West Bengal, India; ⁴Department of Oral and Maxillofacial Surgery, Faculty of Dental Sciences, Ramaiah University of Applied Sciences, Bangalore, Karnataka, India; ⁵Department of Periodontology Kannur Dental College, Anjarakandy, Kannur, Kerala, India; ⁶Department of Head and Neck Oncology, Acharya Harihar Post Graduate Institute of Cancer, Cuttack, Odisha, India; *Corresponding author

Email

Saloni Bharti - E-mail: drsalonibharti2424@gmail.com
Eragattapu Sulochana - E-mail: eragttapusulochana@gmail.com
Saumen Kumar De - E-mail: drsaumen16@yahoo.com
Aakriti Choudhary - E-mail: aak.chy07@gmail.com
Megha Varghese - E-mail: dr_meghavarghese@yahoo.com; Phone: +91 81578 44373
Zuben Mohanty - E-mail: drzuben@gmail.com

Article Type

Research Article

Date

Received August 1, 2026; Revised August 31, 2026; Accepted August 31, 2026, Published August 31, 2026

Abstract

Timely and accurate interpretation of complex maxillofacial imaging is important but subject to inter-observer variation especially in less experienced clinicians. Therefore, it is of interest to design and test a deep learning mandibular fracture and maxillofacial pathology detection algorithm on cone-beam computed tomography (CBCT) scans and compares its results to human operators. The training and testing of a convolutional neural network (CNN) was done on a retrospective measure of 1200 CBCT scans and compared to the diagnostic measurements of the senior and junior oral and maxillofacial surgeons on a blinded dataset. The AI model exhibited an outstanding level of accuracy with a total sensitivity of 96.5 percent and specificity of 98.1 percent and matched with senior surgeons and was far ahead of junior residents. Thus, data shows that artificial intelligence diagnostic devices are an effective supplement to clinical practice, which has the potential to increase diagnostic accuracy and standardization of care in oral and maxillofacial surgery.

Keywords

Artificial Intelligence (AI), deep learning (DL), oral and maxillofacial surgery (OMFS), cone-beam computed tomography (CBCT), diagnostic accuracy, fracture detection, pathology

Citation

Bharti et al. Bioinformation 22(8): 5128-5132 (2026)

Edited by

Rashmi Laddha

ISSN

0973-2063

Publisher

Biomedical Informatics

License

This is an Open Access article which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited. This is distributed under the terms of the Creative Commons Attribution License.