Machine Learning Models in the Detection of MB2 Canal Orifice in CBCT Images

Abstract

Objectives: The objective of the present study was to determine the accuracy of machine learning (ML) models in the detection of mesiobuccal (MB2) canals in axial cone-beam computed tomography (CBCT) sections.

Methods: A total of 2500 CBCT scans from the oral radiology department of University Dental Hospital, Sharjah were screened to obtain 277 high-resolution, small field-of-view CBCT scans with maxillary molars. Among the 277 scans, 160 of them showed the presence of MB2 orifice and the rest (117) did not. Two-dimensional axial images of these scans were then cropped. The images were classified and labelled as N (absence of MB2) and M (presence of MB2) by 2 examiners. The images were embedded using Google's Inception V3 and transferred to the ML classification model. Six different ML models (logistic regression [LR], naïve Bayes [NB], support vector machine [SVM], K-nearest neighbours [Knn], random forest [RF], neural network [NN]) were then tested on their ability to classify the images into M and N. The classification metrics (area under curve [AUC], accuracy, F1-score, precision) of the models were assessed in 3 steps.

Results: NN (0.896), LR (0.893), and SVM (0.886) showed the highest values of AUC with specified target variables (steps 2 and 3). The highest accuracy was exhibited by LR (0.849) and NN (0.848) with specified target variables. The highest precision (86.8%) and recall (92.5%) was observed with the SVM model.

Conclusion: The success rates (AUC, precision, recall) of ML algorithms in the detection of MB2 were remarkable in our study. It was also observed that when the target variable was specified, significant success rates such as 86.8% in precision and 92.5% in recall were achieved. The present study showed promising results in the ML-based detection of MB2 canal using axial CBCT slices.

Keywords: Artificial intelligence; Cone-beam computed tomography; Machine learning; Root canal.

Fig. 1

A, Sagittal cone-beam computed tomorgraphy (CBCT) section showing the level at which axial images were obtained. Using the technique by Normando et al. B, Cropped axial CBCT section with maxillary first molar with mesiobuccal orifice (red arrow).

Fig. 2

Original image (A) and preprocessed image (B) with increased sharpness. Snap of the code for image filter in Python Imaging Library.

Fig. 3

A, Workflow of the model analysis. (B) Screenshot of the program used in the study showing details of the classification model. (Orange data mining version 3.38.1)

Fig. 4

Confusion matrix for logistic regression (showing number of instances)

Fig. 5

A, Area under the curve–receiver operating characteristic (AUC-ROC) of the 6 machine learning (ML) models with specified target variable M. (B) AUC-ROC of the 6 ML models with specified target variable N.