Title

Deep learning–assisted detection of additional canals: A comparative study with endodontic specialists

Authors

Sangeeta Nawal¹, Pallavi Kumbhare², Priyatam Maruti Karade³,*, K.S Darshan⁴, Alwin Antony⁵ & Mohd Zeeshan Ahmad⁶

Affiliation

¹Department of Conservative Dentistry and Endodontics, SMS Medical College and Hospital, Jaipur, Rajasthan, India; ²Department of Conservative Dentistry and Endodontics, School of Dental Sciences, Sri Satya Sai University of Technology and Medical Sciences, Sehore, India; ³Department of Conservative Dentistry and Endodontics, Bharati Vidyapeeth (Deemed to be University) Dental College and Hospital, Sangli, India; ⁴Department of Oral & Maxillofacial Surgery, Sharavathi Dental College & Hospital, Shimoga, India; ⁵Department of Public Health Dentistry, Sharavathi Dental College & Hospital, Shimoga, India; ⁶Department of Conservative Dentistry & Endodontics, Rama Dental College Hospital & Research Centre, Kanpur, Uttar Pradesh, India; *Corresponding author

Email

Sangeeta Nawal - E-mail: drnawal86@gmail.com
Pallavi Kumbhare - E-mail: pallavi.w11@gmail.com
Priyatam Maruti Karade - E-mail: priyatam.karade@bharatividyapeeth.edu
K.S. Darshan - E-mail: ksdarshan95@gmail.com
Alwin Antony - E-mail: alwin4543@gmail.com
Mohd Zeeshan Ahmad - E-mail: askzeeshan9@gmail.com

Article Type

Research Article

Date

Received September 1, 2026; Revised September 30, 2026; Accepted September 30, 2026, Published September 30, 2026

Abstract

Missed root canals are a major cause of endodontic treatment failure due to limitations in conventional diagnostic methods. Therefore, it is of interest to evaluate the diagnostic performance of deep learning–assisted CBCT analysis in detecting additional canals in mandibular molars and compared it with endodontic specialists. A total of 60 extracted teeth were analyzed using AI-based software and expert evaluation, with findings validated against a reference standard. AI-assisted analysis showed higher sensitivity and comparable specificity, with improved consistency in detecting complex canal anatomy. Thus, data shows the potential of deep learning–assisted CBCT analysis as a reliable adjunct for detecting additional root canals with improved sensitivity and consistency.

Keywords

Artificial intelligence (AI), deep learning (DL), cone-beam computed tomography (CBCT), root canal anatomy, additional canals, endodontics, diagnostic accuracy

Citation

Nawal et al. Bioinformation 22(9): 5805-5808 (2026)

Edited by

Ritik Kashwani

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.