|
Title |
A clinicopathological and surgical outcome correlation in odontogenic cysts using AI-based radiographic analytics
|
|
Authors |
Prachurya Dakshinakabat1,*, Aravind A. Vijayan2, Drishti Bhatt3, Raihan Hariz4, Nazrana Maqbool5, Ankit Mohapatra6, Md Kafeel Ahmed7 & Rubeena Naaz8
|
|
Affiliation |
1Department of Oral Pathology, Geetanjali Dental & Research Institute, Geetanjali University, Udaipur, India; 2Department of Dentistry, Mount Zion Medical College, Chayalode, Adoor, Kerala, India; 3Department of Oral and Maxillofacial Surgery, Himachal Institute of Dental Sciences, Paonta Sahib, Sirmaur, Himachal Pradesh, India; 4Department of Oral Pathology, Malabar Dental College, Kerala, India; 5Department of Oral Medicine and Radiology, M.M. College of Dental Sciences and Research, Maharishi Markandeshwar (Deemed to be University), India; 6Department of Public Health Dentistry, Hi-Tech Dental College and Hospital, Health Park, Pandara, Bhubaneswar, Odisha, India; 7Department of Periodontology, Panineeya Mahavidyalaya Institute of Dental Sciences and Research Centre, Hyderabad, Telangana, India; 8Chief Dental Surgeon, SRK Dental Clinic, Hyderabad, Telangana, India; *Corresponding author
|
|
|
Prachurya Dakshinakabat - E-mail:
prachurya143@gmail.com
|
|
Article Type |
Research Article
|
|
Date |
Received October 1, 2026; Revised October 31, 2026; Accepted October 31, 2026, Published October 31, 2026
|
|
Abstract |
Radiolucent odontogenic cysts often show overlapping imaging features, making pre-operative diagnosis challenging. Therefore, it is of interest to evaluate the artificial intelligence (AI) radiographic model against histopathology in 100 cases. The model showed 88% diagnostic agreement with histopathology, with higher confidence in concordant predictions than discordant cases (90.1% vs. 68.5%, p < 0.001). Radicular cysts were most common (63%), while keratocysts showed significantly greater volume and mean radiodensity (p ≤ 0.002) and higher recurrence (33.3% vs. 4.4%, p = 0.015). Thus, the AI model showed useful diagnostic performance and calibration as a decision-support tool while maintaining histopathology as the diagnostic reference standard. |
|
Keywords |
Odontogenic cysts, artificial intelligence, deep learning, cone-beam computed tomography, histopathology, odontogenic keratocyst
|
|
Citation |
Dakshinakabat et al. Bioinformation 22(10): 7099-7102 (2026)
|
|
Edited by |
Ritik Kashwani
|
|
ISSN |
0973-2063
|
|
Publisher |
|
|
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.
|
|
|
|