Department of Imaging and Pathology, Faculty of Medicine, OMFS-IMPATH Research Group, KU Leuven, Leuven, Belgium.
Department of Oral Diagnosis, Division of Oral Radiology, Piracicaba Dental School, University of Campinas, Piracicaba, Brazil.
Dentomaxillofac Radiol. 2023 Nov;52(8):20230321. doi: 10.1259/dmfr.20230321. Epub 2023 Oct 23.
To develop and validate a novel artificial intelligence (AI) tool for automated segmentation of mandibular incisive canal on cone beam computed tomography (CBCT) scans.
After ethical approval, a data set of 200 CBCT scans were selected and categorized into training (160), validation (20), and test (20) sets. CBCT scans were imported into Virtual Patient Creator and ground truth for training and validation were manually segmented by three oral radiologists in multiplanar reconstructions. Intra- and interobserver analysis for human segmentation variability was performed on 20% of the data set. Segmentations were imported into Mimics for standardization. Resulting files were imported to 3-Matic for analysis using surface- and voxel-based methods. Evaluation metrics involved time efficiency, analysis metrics including Dice Similarity Coefficient (DSC), Intersection over Union (IoU), Root mean square error (RMSE), precision, recall, accuracy, and consistency. These values were calculated considering AI-based segmentation and refined-AI segmentation compared to manual segmentation.
Average time for AI-based segmentation, refined-AI segmentation and manual segmentation was 00:10, 08:09, and 47:18 (284-fold time reduction). AI-based segmentation showed mean values of DSC 0.873, IoU 0.775, RMSE 0.256 mm, precision 0.837 and recall 0.890 while refined-AI segmentation provided DSC 0.876, IoU 0.781, RMSE 0.267 mm, precision 0. 852 and recall 0.902 with the accuracy of 0.998 for both methods. The consistency was one for AI-based segmentation and 0.910 for manual segmentation.
An innovative AI-tool for automated segmentation of mandibular incisive canal on CBCT scans was proofed to be accurate, time efficient, and highly consistent, serving pre-surgical planning.
开发和验证一种用于在锥形束计算机断层扫描（CBCT）扫描上自动分割下颌切牙管的新型人工智能（AI）工具。
经过伦理批准后，选择了 200 个 CBCT 扫描数据集，并将其分为训练集（160 个）、验证集（20 个）和测试集（20 个）。将 CBCT 扫描导入 Virtual Patient Creator，并由三名口腔放射科医生在多平面重建中手动分割训练和验证的真实数据。对数据集的 20%进行了人类分割可变性的同内和同外观察者分析。将分割导入 Mimics 进行标准化。将生成的文件导入 3-Matic 以使用基于表面和基于体素的方法进行分析。评估指标包括时间效率、分析指标，包括骰子相似系数（DSC）、交并比（IoU）、均方根误差（RMSE）、精度、召回率、准确性和一致性。这些值是根据基于 AI 的分割和改进后的 AI 分割与手动分割进行计算的。
基于 AI 的分割、改进后的 AI 分割和手动分割的平均时间分别为 00:10、08:09 和 47:18（时间减少 284 倍）。基于 AI 的分割显示平均 DSC 为 0.873、IoU 为 0.775、RMSE 为 0.256mm、精度为 0.837 和召回率为 0.890，而改进后的 AI 分割提供了 DSC 为 0.876、IoU 为 0.781、RMSE 为 0.267mm、精度为 0.852 和召回率为 0.902，两种方法的准确性均为 0.998。基于 AI 的分割的一致性为 1，手动分割的一致性为 0.910。
一种用于在 CBCT 扫描上自动分割下颌切牙管的创新型 AI 工具已被证明准确、高效且高度一致，可用于术前规划。
