HOME   |    PDF   |   


Title

Comparing artificial intelligence-based detection of periapical lesions using CBCT and intraoral radiographs

 

Authors

Trishna Saikia1,*, Polysmita Ojah2, Panchali Bora3, Srinivasan Bhuvaneshwari4, Rajkumari Gupta5 & Mausami Malgaonkar6

 

Affiliation

1Department of Oral Medicine and Radiology, Government Dental College, Dibrugarh, India; 2Department of Prosthodontics and Crown & Bridge, Government Dental College, Dibrugarh, India; 3Department of Oral Pathology, Microbiology and Forensic Odontology, Government Dental College, Dibrugarh, India; 4Department of Oral Medicine and Radiology, Geetanjali Dental and Research Institute, Udaipur, Rajasthan, India; 5Department of Oral Pathology, Vyas Dental College, Jodhpur, Rajasthan, India; 6Department of Public Health Dentistry, MGM Dental College and Hospital, Kamothe, Navi Mumbai, India; *Corresponding author

 

Email

Trishna Saikia - E-mail: saikia.trishna2401@gmail.com
Polysmita Ojah - E-mail: polysmita012@gmail.com
Panchali Bora - E-mail: borapanchi3@gmail.com
Srinivasan Bhuvaneshwari - E-mail: drbhuvana1976@gmail.com
Rajkumari Gupta - E-mail: rajkumarigupta776@gmail.com
Mausami Malgaonkar - E-mail: drmoshu@gmail.com

 

Article Type

Research Article

 

Date

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

 

Abstract

Accurate detection of periapical lesions is essential for endodontic diagnosis and artificial intelligence may improve interpretation of dental radiographs. Therefore, it is of interest to evaluate the artificial intelligence-assisted detection of periapical lesions on CBCT and digital intraoral periapical radiographs against consensus diagnoses by expert radiologists. Artificial intelligence showed higher sensitivity (95.2% vs. 83.9%), specificity (94.7% vs. 89.5%) and diagnostic accuracy (95.0% vs. 86.0%). Agreement with expert radiologists was almost perfect for CBCT (κ=0.90) and substantial for intraoral radiographs (κ=0.73), indicating greater diagnostic reliability with CBCT. These findings advance knowledge by supporting artificial intelligence-assisted cone-beam computed tomography interpretation as a reliable adjunct for accurate detection of periapical lesions in endodontic diagnosis.

 

Keywords

Artificial intelligence (AI), cone-beam computed tomography (CBCT), periapical lesion, intraoral periapical radiography, deep learning, endodontic diagnosis

 

Citation

Saikia et al. Bioinformation 22(10): 6969-6974 (2026)

 

Edited by

Vini Mehta

 

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.