Root canal treatment planning by automatic tooth and root canal segmentation in dental CBCT with deep multi-task feature learning.

Accurate and automatic segmentation of individual tooth and root canal from cone-beam computed tomography (CBCT) images is an essential but challenging step for dental surgical planning. In this paper, we propose a novel framework, which consists of two neural networks, DentalNet and PulpNet, for efficient, precise, and fully automatic tooth instance segmentation and root canal segmentation from CBCT images. We first use the proposed DentalNet to achieve tooth instance segmentation and identification. Then, the region of interest (ROI) of the affected tooth is extracted and fed into the PulpNet to obtain precise segmentation of the pulp chamber and the root canal space. These two networks are trained by multi-task feature learning and evaluated on two clinical datasets respectively and achieve superior performances to several comparing methods. In addition, we incorporate our method into an efficient clinical workflow to improve the surgical planning process. In two clinical case studies, our workflow took only 2 min instead of 6 h to obtain the 3D model of tooth and root canal effectively for the surgical planning, resulting in satisfying outcomes in difficult root canal treatments.

Evaluation of 3D-printed oval root canal preparation by small field-of-view cone beam CT and computer-aided technique / 口腔疾病防治

Objective@# To evaluate the effect of 3D-printed oval root canal preparation by using small field-of-view cone beam CT (CBCT) combined with computer-aided technologies.@*Methods@#An extracted tooth with a suitable single oval canal was selected by small field-of-view CBCT scanning. Three-dimensional (3D)-printed resin teeth were obtained based on the CBCT data after data conversion and processing. 50 general dentists were selected to prepare the oval root canal of the resin teeth with X-Gold rotary Ni-Ti instruments. Small field-of-view CBCT was applied to scan the oval root canals before and after preparation. Then, computer-aided technologies were used to calculate and compare these CBCT data, analyzing the effects of oval root canal cleaning as well as the root canal deviation by 3D reconstruction and rendering of the images.@*Results @#Among the 50 cases, the mean unprepared area of the oval root canal wall was（56.20 ± 11.91）% and the mean maximum deviation distance of the root canal was（0.140 ± 0.041）mm. There was no correlation between root canal cleanliness and deviation (r=0.18, P=0.212).@*Conclusion @# Combined with small field-of-view CBCT and computer-aided technology, we can effectively quantitatively evaluate the root canal preparation effect.

Applicability and accuracy of Demirjian and Willems methods in a population of Eastern Chinese subadults.

BACKGROUND: To assess the validity of the Demirjian and Willems dental age estimation methods in a population of Eastern Chinese 11-18-year-old subadults. SAMPLES AND METHODS: A total of 1622 orthopantomograms (787 boys and 835 girls) aged from 11.00 to 18.99 years old from a Chinese Han population were evaluated in the study. Dental ages were calculated using both Demirjian and Willems method. Statistical significance was set at p<0.05 and for each method, discrepancies between chronological age (CA) and dental age (DA) were statistically analyzed by paired t-tests. Special age interval analysis was conducted by Chi-square tests to compare the accuracy of the Demirjian and the Willems methods. RESULTS: Demirjian method underestimated CA 0.66±1.45 y (p<0.001) in boys and 0.62±1.61 y (p<0.001) in girls while Willems method underestimated 0.90±1.32 y (p<0.001) and 0.97±1.56 y (p<0.001) in boys and girls, respectively. The mean absolute error (MAE) value between the CA and the DA (CA-DA) using the Demirjian method and the Willems method were 1.31 and 1.29 y for boys, respectively, and 1.35 and 1.43 y for girls, respectively. CONCLUSIONS: It is suggested that the Demirjian method was found to be more accurate compared with the Willems method. However, the Demirjian method may not be satisfactory for 11-18-year-old children of Eastern China. It is recommended that a modified Demirjian method for better dental age estimation for Eastern Chinese juvenile individuals.