Development and Validation of a Deep Learning Model to Predict Endodontic Retreatment Difficulty From Periapical Radiographs (Ai Retreatment)

Cairo University (CU)

Status: Not yet enrolling

Conditions: Non-surgical Retreatment; Perforation; Endodontic Retreatment; Poor Obturation; Deep Learning Model; Obturation Quality; Missed Canals; Endodontics; AI (Artificial Intelligence); SEPARATED INSTRUMENT; DIFFICULTY ASSESSMENT

Treatments: Diagnostic Test: Deep Learning Model to Predict Endodontic Retreatment Difficulty from Periapical Radiographs

Study type: Interventional

Funder types: Other

Identifiers

NCT07611279

newendo7.1.1

Details and patient eligibility

About

The aim of this study is to develop and evaluate an artificial intelligence-based model capable of analyzing periapical radiographs of maxillary and mandibular molars to predict the difficulty level of non-surgical root canal retreatment. By integrating deep learning techniques with routinely acquired periapical radiographs, this study aims to enhance diagnostic support, improve clinical decision-making, and facilitate appropriate case selection or referral in endodontic practice.

Enrollment: 123 estimated patients

Sex: All

Volunteers: No Healthy Volunteers

Inclusion criteria

Periapical radiographs of maxillary and mandibular molars requiring non-surgical endodontic retreatment will be included. Radiographs should exhibit satisfactory image quality, characterized by adequate sharpness, contrast, and minimal distortion or noise to allow accurate assessment of relevant anatomical and treatment-related features. Images should clearly display the tooth of interest, surrounding periapical structures, and any existing root canal filling materials or restorations.

Exclusion criteria

Deciduous teeth, non-restorable, non-treated teeth

Trial design

Primary purpose: Diagnostic

Allocation: N/A

Interventional model: Single Group Assignment

Masking: None (Open label)

---

123 participants in 1 patient group

Deep Learning Model to Predict Endodontic Retreatment Difficulty from Periapical Radiographs

Experimental group

Description:

This study will employ a retrospective diagnostic accuracy design focused on the development and validation of a deep learning-based model for automated prediction of endodontic retreatment difficulty in maxillary and mandibular molars using periapical radiographs. The methodology will involve radiographic data acquisition, expert annotation of case difficulty according to standardized criteria, deep learning model development and training, and comprehensive performance evaluation of the proposed system.

Treatment:

Diagnostic Test: Deep Learning Model to Predict Endodontic Retreatment Difficulty from Periapical Radiographs