AI-Based Working Length Determination in Curved Root Canals

NCT07787078 | Not Yet Recruiting

• 1 other identifier: ALKU-EC-2026-64
• Study Type: observational
• Target: 200
• Locations: 0 countries
• Sites: N/A

Brief Summary

This study tests whether artificial intelligence (AI) can accurately measure the length of curved root canals from dental x-rays. Curved root canals are hard to measure correctly, and wrong measurements can lower the success of root canal treatment. Adults over 18 years old who need root canal treatment can take part. Researchers will use x-rays taken during the patient's normal treatment. No extra x-rays, procedures, or visits are needed. An AI program will be trained to measure canal length automatically, and its measurements will be compared to measurements made by a human expert. The results may show whether AI can measure root canal length faster and more consistently, which could help dentists plan treatment more accurately in the future.

Conditions

Endodontic Working Length Determination

Keywords

Deep learning; Working Length Determination; Root Canal Curvature; Periapical Radiography

Outcome Measures

Primary Outcomes (4)

• Sensitivity of AI Model in Detecting Curved Root Canal Length

  Agreement between the AI-predicted root canal length and the length determined by a human observer on periapical radiographs, assessed by sensitivity, calculated as TP/(TP+FN), where TP (true positive) represents the overlapping region between the ground truth and predicted segmentation, and FN (false negative) represents the region present in the ground truth but not in the prediction.

  Measured once, at the time of model testing following completion of radiograph collection (estimated 12 months from study initiation)

• Precision of AI Model in Detecting Curved Root Canal Length

  Agreement between the AI-predicted root canal length and the length determined by a human observer on periapical radiographs, assessed by precision, calculated as TP/(TP+FP), where FP (false positive) represents the region present in the prediction but not in the ground truth.

  Measured once, at the time of model testing following completion of radiograph collection (estimated 12 months from study initiation)

• F1 Score of AI Model in Detecting Curved Root Canal Length

  F1 score of the AI-predicted root canal segmentation compared to ground truth on periapical radiographs, calculated as 2TP/(2TP+FP+FN), representing the harmonic mean of precision and sensitivity and interpreting the overlap between the ground truth and predicted pixels.

  Measured once, at the time of model testing following completion of radiograph collection (estimated 12 months from study initiation)

• Intersection over Union (IoU) of AI Model in Detecting Curved Root Canal Length

  Intersection over Union between the AI-predicted root canal segmentation and the ground truth segmentation on periapical radiographs, calculated as TP/(TP+FN+FP), representing the overlapping area between the predicted result and the ground truth segmentation area.

  Measured once, at the time of model testing following completion of radiograph collection (estimated 12 months from study initiation)

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population consists of adult patients (18 years and older) presenting for routine root canal treatment at the Department of Endodontics, Alanya Alaaddin Keykubat University Faculty of Dentistry, who have radiographically identified curved root canals. No sex-based restriction is applied. Periapical radiographs obtained during the working length confirmation stage of standard clinical care will be used; no additional radiographic exposure or procedure will be performed for research purposes.

You may qualify if:

• Eligibility Criteria
• Age 18 years or older
• Presenting for routine root canal treatment at Alanya Alaaddin Keykubat University Faculty of Dentistry
• Radiographically identified curved root canal(s)
• Periapical radiograph obtained using the paralleling technique during working length confirmation
• Willing and able to provide informed consent

You may not qualify if:

• Age under 18 years
• Root canals without curvature
• Periapical radiographs of insufficient diagnostic quality (e.g., distortion, poor image quality preventing accurate canal length assessment)
• Unwillingness to provide informed consent

Sponsors & Collaborators

• Alanya Alaaddin Keykubat University: lead

Related Publications (2)

• Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJWL. Artificial intelligence in radiology. Nat Rev Cancer. 2018 Aug;18(8):500-510. doi: 10.1038/s41568-018-0016-5.

  PMID: 29777175 BACKGROUND

• Schwendicke F, Samek W, Krois J. Artificial Intelligence in Dentistry: Chances and Challenges. J Dent Res. 2020 Jul;99(7):769-774. doi: 10.1177/0022034520915714. Epub 2020 Apr 21.

  PMID: 32315260 BACKGROUND

Study Officials

• Hatice Büyüközer Özkan, Associate Professor (Doç. Dr.)

  Alanya Alaaddin Keykubat University, Faculty of Dentistry

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Hatice Büyüközer Özkan, Doç. Dr. (Associate Professor)

CONTACT

05309710252; hatice.ozkan@alanya.edu.tr

Tuğba Gök

CONTACT

05522521446; tugba.gok@alanya.edu.tr

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: CROSS SECTIONAL
• Target Duration: 1 Day
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Associate Professor

Study Record Dates

• First Submitted: August 18, 2026
• First Posted: August 26, 2026
• Study Start (Estimated): September 22, 2026
• Primary Completion (Estimated): November 22, 2026
• Study Completion (Estimated): December 22, 2026
• Last Updated: August 26, 2026

Record last verified: 2026-08

Data Sharing

• IPD Sharing: Will not share