ABSTRACT
OBJECTIVES: Artificial intelligence (AI) techniques like convolutional neural network (CNN) are a promising breakthrough that can help clinicians analyze medical imaging, diagnose taurodontism, and make therapeutic decisions. The purpose of the study is to develop and evaluate the function of CNN-based AI model to diagnose teeth with taurodontism in panoramic radiography. METHODS: 434 anonymized, mixed-sized panoramic radiography images over the age of 13 years were used to develop automatic taurodont tooth segmentation models using a Pytorch implemented U-Net model. Datasets were split into train, validation, and test groups of both normal and masked images. The data augmentation method was applied to images of trainings and validation groups with vertical flip images, horizontal flip images, and both flip images. The Confusion Matrix was used to determine the model performance. RESULTS: Among the 43 test group images with 126 labels, there were 109 true positives, 29 false positives, and 17 false negatives. The sensitivity, precision, and F1-score values of taurodont tooth segmentation were 0.8650, 0.7898, and 0.8257, respectively. CONCLUSIONS: CNN's ability to identify taurodontism produced almost identical results to the labeled training data, and the CNN system achieved close to the expert level results in its ability to detect the taurodontism of teeth.
Subject(s)
Artificial Intelligence , Deep Learning , Radiography, Panoramic , Neural Networks, Computer , AlgorithmsABSTRACT
BACKGROUND: Dentistry has undergone an evolution in endodontics practice caused by the advancement of rotary techniques for root canal preparation and their subsequent incorporation into the teaching of dentistry undergraduates. This research aimed to evaluate the shaping ability of third-year dental students as their first experience in rotary instrumentation using ProTaper Universal (PTU) and ProTaper Next (PTN) (Dentsply Maillefer) rotary instruments in simulated curved canals. METHODS: Forty students instrumented 200 simulated canals with a 40° curvature in resin blocks according to the manufacturer's instructions with PTU and 39 students and 195 canals with PTN files. The canals were prepared at a speed of 300 rpm using a 16:1 reduction hand-piece powered by an electric motor (Xsmart; Dentsply Maillefer). The final apical preparation was set to F2 for the PTU and X2 for the PTN group. The change in canal curvature was evaluated based on Schneider technique using the AutoCAD 2007 software on post-digital photographs. The incidence of instrument fracture and deformation, the incidence of ledge, the change in working length (WL), and the working time were noted. The data were analyzed with Student's t-test and Chi-Square test at a significance level of 0.05 using SPSS. RESULTS: PTN maintained the original canal curvature better, resulting in fewer fractures and ledges, and shaped the canals faster than the PTU (P < 0.05). The mean curves of the resin canals after the instrumentation for the PTU and PTN groups were 24.03° ± 3.14° and 25.64° ± 2.72°, respectively. Thirty-three (17.4%) PTU and 18 (9.3%) PTN files fractured (p < 0.05). Nine (4.5%) PTU and 2 (2.6%) PTN deformed (p > 0.05). The change in WL after instrumentation was 0.97 mm ± 0.95 mm in PTU and 0.96 mm ± 0.80 mm in PTN (p < 0.05). The mean times were 627 s ± 18 s for PTU and 379 s ± 18 s for PTN (p < 0.000). DISCUSSION: PTN can be recommended in severely curved root canals in terms of maintenance of the original canal curvature, superior instrument fracture and fewer ledges. Even if training before preparation provides an acceptable level of canal shaping for preclinical students, the use of NiTi rotary instruments should be included in the undergraduate dental curriculum, contributing to an increase in the quality of root canal shaping and, consequently, to an improvement of the clinical experience of students.
