Tooth image segmentation and root canal measurement based on deep learning.

Indroduction: This study aims to develop a automated method for tooth segmentation and root canal measurement based on cone beam computed tomography (CBCT) images, providing objective, efficient, and accurate measurement results to guide and assist clinicians in root canal diagnosis grading, instrument selection, and preoperative planning. Methods: We utilizes Attention U-Net to recognize tooth descriptors, crops regions of interest (ROIs) based on the center of mass of these descriptors, and applies an integrated deep learning method for segmentation. The segmentation results are mapped back to the original coordinates and position-corrected, followed by automatic measurement and visualization of root canal lengths and angles. Results: Quantitative evaluation demonstrated a segmentation Dice coefficient of 96.33%, Jaccard coefficient of 92.94%, Hausdorff distance of 2.04 mm, and Average surface distance of 0.24 mm - all surpassing existing methods. The relative error of root canal length measurement was 3.42% (less than 5%), and the effect of auto-correction was recognized by clinicians. Discussion: The proposed segmentation method demonstrates favorable performance, with a relatively low relative error between automated and manual measurements, providing valuable reference for clinical applications.