External validation of the effect of the combined use of object detection for the classification of the C-shaped canal configuration of the mandibular second molar in panoramic radiographs: A multicenter study.
Researchers
Journal
Modalities
Models
Abstract
The purposes of this study were to evaluate the effect of the combined use of object detection for the classification of the C-shaped canal anatomy of the mandibular second molar in panoramic radiographs and to perform an external validation on a multicenter dataset.The panoramic radiographs of 805 patients were collected from four institutes across two countries. The CBCT data of the same patients were used as “Ground-truth”. Five datasets were generated: one for training and validation, and four as external validation datasets. Workflow 1 used manual cropping to prepare the image patches of mandibular second molars, and then classification was performed using EfficientNet. Workflow 2 used two combined methods with a preceding object detection (YOLOv7) performed for automated image patch formation, followed by classification using EfficientNet. Workflow 3 directly classified the root canal anatomy from the panoramic radiographs using the YOLOv7 prediction outcomes. The classification performance of the three workflows was evaluated and compared across four external validation datasets.For Workflows 1, 2, and 3, the area under the receiver operating characteristic curve (AUC) values were 0.863, 0.861, and 0.876, respectively, for the AGU dataset; 0.935, 0.945, and 0.863, respectively, for the ASU dataset; 0.854, 0.857, and 0.849, respectively, for the ODU dataset; and 0.821, 0.797, and 0.831, respectively, for the ODU low-resolution dataset. No significant differences existed between the AUC values of Workflows 1, 2, and 3 across the four datasets.The deep learning systems of the three workflows achieved significant accuracy in predicting the C-shaped canal in mandibular second molars across all test datasets.Copyright © 2024. Published by Elsevier Inc.