AI Detection Model of Extra Root Canals in Mandibular Premolars Using CBCT Scans

July 1, 2026 updated by: Ayah Tarek El Sayed Abudlaah, Cairo University

Diagnostic Accuracy of a Deep Learning Model (Artificial Intelligence) for Detecting Extra Root Canals in Mandibular Premolars on CBCT Images: Diagnostic Accuracy Study.

Successful endodontic treatment depends on the complete identification and management of the entire root canal system. Missed root canals are a major cause of endodontic failure, particularly in mandibular premolars, which exhibit considerable anatomical variability and may contain additional root canals that are difficult to detect using conventional diagnostic methods.

Cone Beam Computed Tomography (CBCT) provides three-dimensional visualization of root canal anatomy and has significantly improved the detection of anatomical variations. However, interpretation of CBCT images remains dependent on the experience and expertise of the clinician, leading to potential observer variability and missed diagnoses.

Recent advances in artificial intelligence (AI), particularly deep learning models based on convolutional neural networks, have shown promising results in dental image analysis and diagnostic support. AI-assisted diagnostic systems may improve the accuracy, consistency, and efficiency of CBCT interpretation by automatically identifying complex anatomical structures.

The aim of this retrospective diagnostic accuracy study is to evaluate the performance of a newly developed deep learning model for the detection of extra root canals in mandibular premolars using CBCT images. The diagnostic accuracy of the AI model will be assessed by comparing its findings with the assessments of experienced oral and maxillofacial radiologists, which will serve as the reference standard.

A total of 272 CBCT scans of mandibular premolars from Egyptian patients will be included according to predefined eligibility criteria. Diagnostic performance will be evaluated using measures including sensitivity, specificity, positive predictive value, and negative predictive value.

The findings of this study may provide evidence regarding the clinical applicability of AI-assisted diagnostic tools in endodontics and contribute to improved detection of complex root canal anatomy, reduced incidence of missed canals, and enhanced treatment outcomes.

Study Overview

Status

Not yet recruiting

Conditions

Intervention / Treatment

Detailed Description

The goal of this observational study is to evaluate whether a deep learning artificial intelligence (AI) model can accurately detect extra root canals in mandibular premolars using Cone Beam Computed Tomography (CBCT) images in Egyptian patients. The main questions it aims to answer are:

  • Can the AI model accurately detect extra root canals in mandibular premolars on CBCT scans?
  • Is the diagnostic accuracy of the AI model comparable to that of experienced oral and maxillofacial radiologists? Researchers will compare the results generated by the AI model with the assessments of experienced radiologists, which will serve as the reference standard.

Participants will:

  • Provide previously acquired CBCT scans that meet the study eligibility criteria.
  • Have their CBCT images analyzed by the AI model.
  • Have their CBCT images independently evaluated by experienced radiologists for comparison with the AI findings.

The study findings may help determine the potential role of AI-assisted diagnostic tools in improving the detection of complex root canal anatomy and supporting endodontic diagnosis

Study Type

Interventional

Enrollment (Estimated)

272

Phase

  • Not Applicable

Contacts and Locations

This section provides the contact details for those conducting the study, and information on where this study is being conducted.

Study Contact

Participation Criteria

Researchers look for people who fit a certain description, called eligibility criteria. Some examples of these criteria are a person's general health condition or prior treatments.

Eligibility Criteria

Ages Eligible for Study

  • Adult
  • Older Adult

Accepts Healthy Volunteers

Yes

Description

Inclusion Criteria:

  • CBCT scans of mandibular molars of Egyptian patients aging from 18 to 65 years old
  • Small Field of view (FOV) including maximum a quadrant
  • Voxel size not larger than 2mm
  • Mandibular premolars showing complete root formation
  • Carious or non-carious teeth
  • Absence of artifacts.

Exclusion Criteria:

  • Mandibular first and second premolars with developmental anomalies, external or internal root resorption, root canal calcification, previous root canal treatment, post restorations, and/or root caries
  • CBCT images of sub-optimal quality or artifacts/high scatter interfering with proper assessment

Study Plan

This section provides details of the study plan, including how the study is designed and what the study is measuring.

How is the study designed?

Design Details

  • Primary Purpose: Diagnostic
  • Allocation: Randomized
  • Interventional Model: Parallel Assignment
  • Masking: None (Open Label)

Arms and Interventions

Participant Group / Arm
Intervention / Treatment
Experimental: Mandibular premolars with single canals
Diagnostic test: AI Model to detect any extra canals in mandibular premolars
It is a study to detect the diagnostic accuracy of AI model to detect extra canals in mandibular premolars
Experimental: Mandibular premolars with more than one canal
Diagnostic test: AI Model to detect any extra canals in mandibular premolars
It is a study to detect the diagnostic accuracy of AI model to detect extra canals in mandibular premolars

What is the study measuring?

Primary Outcome Measures

Outcome Measure
Measure Description
Time Frame
Diagnostic Accuracy of the Deep Learning Model for Detection of Extra Root Canals in Mandibular Premolars
Time Frame: During the procedure
Diagnostic accuracy of the AI model will be determined by comparison with expert radiologist assessment.
During the procedure

Secondary Outcome Measures

Outcome Measure
Time Frame
Sensitivity of the AI Model Specificity of the AI Model Positive Predictive Value (PPV) Negative Predictive Value (NPV)
Time Frame: During the procedure
During the procedure

Collaborators and Investigators

This is where you will find people and organizations involved with this study.

Sponsor

Cairo University

Publications and helpful links

The person responsible for entering information about the study voluntarily provides these publications. These may be about anything related to the study.

General Publications

Study record dates

These dates track the progress of study record and summary results submissions to ClinicalTrials.gov. Study records and reported results are reviewed by the National Library of Medicine (NLM) to make sure they meet specific quality control standards before being posted on the public website.

Study Major Dates

Study Start (Estimated)

July 15, 2026

Primary Completion (Estimated)

August 15, 2026

Study Completion (Estimated)

July 10, 2027

Study Registration Dates

First Submitted

June 25, 2026

First Submitted That Met QC Criteria

July 1, 2026

First Posted (Actual)

July 8, 2026

Study Record Updates

Last Update Posted (Actual)

July 8, 2026

Last Update Submitted That Met QC Criteria

July 1, 2026

Last Verified

July 1, 2026

More Information

Terms related to this study

Keywords

Other Study ID Numbers

  • 7.1.1

Plan for Individual participant data (IPD)

Plan to Share Individual Participant Data (IPD)?

UNDECIDED

Drug and device information, study documents

Studies a U.S. FDA-regulated drug product

No

Studies a U.S. FDA-regulated device product

No

This information was retrieved directly from the website clinicaltrials.gov without any changes. If you have any requests to change, remove or update your study details, please contact register@clinicaltrials.gov. As soon as a change is implemented on clinicaltrials.gov, this will be updated automatically on our website as well.

Clinical Trials on Extra Canals

Search Similar Trials

Sponsors and Collaborators

Medical Conditions

Drug Interventions

CROs by country

CROs in Ghana

Conditions

Rare Diseases

Drug Interventions

Dietary Supplements

Sponsor/Collaborators

Locations

3
Subscribe