Deep Learning-Based Detection of Separated Root Canal Instruments in Panoramic Radiographs Using a U<sup>2</sup>-Net Architecture

<b>Background:</b> Separated endodontic instruments are a significant complication in root canal treatment, affecting disinfection and long-term prognosis. Their detection on panoramic radiographs is challenging, particularly in complex anatomy or for less experienced clinicians. <b&g...

Full description

Saved in:
Bibliographic Details
Main Authors: Nildem İnönü, Umut Aksoy, Dilan Kırmızı, Seçil Aksoy, Nurullah Akkaya, Kaan Orhan
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/14/1744
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:<b>Background:</b> Separated endodontic instruments are a significant complication in root canal treatment, affecting disinfection and long-term prognosis. Their detection on panoramic radiographs is challenging, particularly in complex anatomy or for less experienced clinicians. <b>Objectives:</b> This study aimed to develop and evaluate a deep learning model using the U<sup>2</sup>-Net architecture for automated detection and segmentation of separated instruments in panoramic radiographs from multiple imaging systems. <b>Methods:</b> A total of 36,800 panoramic radiographs were retrospectively reviewed, and 191 met strict inclusion criteria. Separated instruments were manually segmented using the Computer Vision Annotation Tool. The U<sup>2</sup>-Net model was trained and evaluated using standard performance metrics: Dice coefficient, IoU, precision, recall, and F1 score. <b>Results:</b> The model achieved a Dice coefficient of 0.849 (95% CI: 0.840–0.857) and IoU of 0.790 (95% CI: 0.781–0.799). Precision was 0.877 (95% CI: 0.869–0.884), recall was 0.847 (95% CI: 0.839–0.855), and the F1-score was 0.861 (95% CI: 0.853–0.869). <b>Conclusions:</b> These results demonstrate a strong overlap between predictions and ground truth, indicating high segmentation accuracy. The U<sup>2</sup>-Net model showed robust performance across radiographs from various systems, suggesting its clinical utility in aiding detection and treatment planning. Further multicenter studies are recommended to confirm generalizability.
ISSN:2075-4418