External Validation of the Effect of the Combined Use of Object Detection for the Classi fi cation of the C-Shaped Canal Con fi guration of the Mandibular Second Molar in Panoramic Radiographs: A Multicenter Study

Abstract

Introduction: The purposes of this study were to evaluate the effect of the combined use of object detection for the classi fication of the C -shaped canal anatomy of the mandibular second molar in panoramic radiographs and to perform an external validation on a multicenter dataset. Methods: The panoramic radiographs of 805 patients were collected from 4 institutes across two countries. The CBCT data of the same patients were used as "Groundtruth ". Five datasets were generated: one for training and validation, and 4 as external validation datasets. Work flow 1 used manual cropping to prepare the image patches of mandibular second molars, and then classi fication was performed using Ef ficientNet. Work flow 2 used two combined methods with a preceding object detection (YOLOv7) performed for automated image patch formation, followed by classi fication using Ef ficientNet. Work flow 3 directly classi fied the root canal anatomy from the panoramic radiographs using the YOLOv7 prediction outcomes. The classi fication performance of the 3 work flows was evaluated and compared across 4 external validation datasets. Results: For Work flows 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 signi ficant differences existed between the AUC values of Work flows 1, 2, and 3 across the 4 datasets. Conclusions: The deep learning systems of the 3 work flows achieved signi ficant accuracy in predicting the C -shaped canal in mandibular second molars across all test datasets. (J Endod 2024;50:627-636.)