Two step approach for detecting and segmenting the second mesiobuccal canal of maxillary first molars on cone beam computed tomography (CBCT) images via artificial intelligence

• Published in: BMC oral health Vol. 25; no. 1; pp. 1404 - 14
• Main Authors: Mansour, Sally, Anter, Enas, Mohamed, Ali Khater, Dahaba, Mushira M., Mousa, Arwa
• Format: Journal Article
• Language: English
• Published: London BioMed Central 08.09.2025; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Accuracy; Adult; Artificial Intelligence; Classification; CNN; Computed tomography; Cone-Beam Computed Tomography - methods; CT imaging; Deep Learning; Dental Pulp Cavity - diagnostic imaging; Dentistry; Endodontics; Female; Humans; Imaging, Three-Dimensional; Male; Maxilla; Maxilla - diagnostic imaging; MB2 canal; Medical imaging equipment; Medicine; Molar - anatomy & histology; Molar - diagnostic imaging; Molars; Morphology; Neural networks; Oral and Maxillofacial Surgery; Root canals; Second mesiobuccal canal; Segmentation; Software; Systematic review; Teeth; Tomography; Deep learning; CNN; Second mesiobuccal canal; Cone beam computed tomography; Endodontics; Artificial intelligence; MB2 canal; CBCT
• ISSN: 1472-6831; 1472-6831
• DOI: 10.1186/s12903-025-06796-4

Aim The purpose of this study was to assess the accuracy of a customized deep learning model based on CNN and U-Net for detecting and segmenting the second mesiobuccal canal (MB2) of maxillary first molar teeth on cone beam computed tomography (CBCT) scans. Methodology CBCT scans of 37 patients were imported into 3D slicer software to crop and segment the canals of the mesiobuccal (MB) root of the maxillary first molar. The annotated data were divided into two groups: 80% for training and validation and 20% for testing. The data were used to train the AI model in 2 separate steps: a classification model based on a customized CNN and a segmentation model based on U-Net. A confusion matrix and receiver-operating characteristic (ROC) analysis were used in the statistical evaluation of the results of the classification model, whereas the Dice-coefficient (DCE) was used to express the segmentation accuracy. Results F1 score, testing accuracy, recall and precision values were 0.93, 0.87, 1.0 and 0.87 respectively, for the cropped images of MB root of maxillary 1st molar teeth in the testing group. The testing loss was 0.4, and the area under the curve (AUC) value was 0.57. The segmentation accuracy results were satisfactory, where the DCE of training was 0.85 and DCE of testing was 0.79. Conclusion MB2 in the maxillary first molar can be precisely detected and segmented via the developed AI algorithm in CBCT images. Trial registration Current Controlled Trial Number NCT05340140. April 22, 2022.