Micro–Computed Tomography–Guided Artificial Intelligence for Pulp Cavity and Tooth Segmentation on Cone-beam Computed Tomography

IntroductionThis study proposes a novel data pipeline based on micro–computed tomographic (micro-CT) data for training the U-Net network to realize the automatic and accurate segmentation of the pulp cavity and tooth on cone-beam computed tomographic (CBCT) images.MethodsWe collected CBCT data and micro-CT data of 30 teeth. CBCT data were processed and transformed into small field of view and high-resolution CBCT images of each tooth. Twenty-five sets were randomly assigned to the training set and the remaining 5 sets to the test set. We used 2 data pipelines for U-Net network training: one manually labeled by an endodontic specialist as the control group and one processed from the micro-CT data as the experimental group. The 3-dimensional models constructed using micro-CT data in the test set were taken as the ground truth. The Dice similarity coefficient, precision rate, recall rate, average symmetric surface distance, Hausdorff distance, and morphologic analysis were used for performance evaluation.ResultsThe segmentation accuracy of the experimental group measured by the Dice similarity coefficient, precision rate, recall rate, average symmetric surface distance, and Hausdorff distance were 96.20% ± 0.58%, 97.31% ± 0.38%, 95.11% ± 0.97%, 0.09 ± 0.01 mm, and 1.54 ± 0.51 mm in the tooth and 86.75% ± 2.42%, 84.45% ± 7.77%, 89.94% ± 4.56%, 0.08 ± 0.02 mm, and 1.99 ± 0.67 mm in the pulp cavity, respectively, which were better than the control group. Morphologic analysis suggested the segmentation results of the experimental group were better than those of the control group.ConclusionsThis study proposed an automatic and accurate approach for tooth and pulp cavity segmentation on CBCT images, which can be applied in research and clinical tasks.     

Apical Constriction: Location and Dimensions in Molars—A Micro–Computed Tomography Study

Introduction

The existence of the apical constriction has been repeatedly questioned. The aim of the present study was to validate the existence of the apical constriction and determine its location and dimensions in molars by using substantial micro–computed tomography analysis. Methods: Ninety human molars with 271 canals were evaluated. Teeth with resorption, defects, or incomplete root formation as well as wisdom teeth were excluded. Patients' age was categorized into 3 groups. Teeth were scanned by micro–computed tomography with a resolution of 27 μm. Multi-threshold segmentation was performed to trace the canal outline in a total of 25,093 sections. In each cross section, 88 parameters, eg, area, circumference, and maximum and minimum diameter were recorded and analyzed. The apical constriction (AC) was defined to be the narrowest area extending along a distance of 0.1 mm or more at the apex. Size and form of the constriction were recorded as well as the distance to the apical foramen (AC-AF) and apex (AC-A).

Results

The mean distance of AC-AF was 0.2 mm (99% confidence interval, 0.15–0.24; range, 0–0.6 mm), and of AC-A it was 0.9 mm (99% confidence interval, 0.86–1.0; range, 0.1–1.7 mm). The type of canal had no influence on AC-AF and AC-A. In 76% of all canals the apical constriction was parallel. The mean size of constriction in molars was instrument size 30. Patients aged 30 or younger had significantly wider constrictions.

Conclusions

The apical constriction was found to be located at or close to the foramen. The most common form was the parallel form.