OMFS IMPATH Research Group, Department of Imaging and Pathology, Faculty of Medicine, University of Leuven, Leuven, Belgium.
Department of Oral & Maxillofacial Surgery, University Hospitals Leuven, KU Leuven, Leuven, Belgium.
Clin Oral Implants Res. 2023 Jun;34(6):565-574. doi: 10.1111/clr.14063. Epub 2023 Mar 23.
To develop and assess the performance of a novel artificial intelligence (AI)-driven convolutional neural network (CNN)-based tool for automated three-dimensional (3D) maxillary alveolar bone segmentation on cone-beam computed tomography (CBCT) images.
A total of 141 CBCT scans were collected for performing training (n = 99), validation (n = 12), and testing (n = 30) of the CNN model for automated segmentation of the maxillary alveolar bone and its crestal contour. Following automated segmentation, the 3D models with under- or overestimated segmentations were refined by an expert for generating a refined-AI (R-AI) segmentation. The overall performance of CNN model was assessed. Also, 30% of the testing sample was randomly selected and manually segmented to compare the accuracy of AI and manual segmentation. Additionally, the time required to generate a 3D model was recorded in seconds (s).
The accuracy metrics of automated segmentation showed an excellent range of values for all accuracy metrics. However, the manual method (95% HD: 0.20 ± 0.05 mm; IoU: 95% ± 3.0; DSC: 97% ± 2.0) showed slightly better performance than the AI segmentation (95% HD: 0.27 ± 0.03 mm; IoU: 92% ± 1.0; DSC: 96% ± 1.0). There was a statistically significant difference of the time-consumed among the segmentation methods (p < .001). The AI-driven segmentation (51.5 ± 10.9 s) was 116 times faster than the manual segmentation (5973.3 ± 623.6 s). The R-AI method showed intermediate time-consumed (1666.7 ± 588.5 s).
Although the manual segmentation showed slightly better performance, the novel CNN-based tool also provided a highly accurate segmentation of the maxillary alveolar bone and its crestal contour consuming 116 times less than the manual approach.
开发并评估一种新的基于人工智能（AI）的卷积神经网络（CNN）工具，用于对锥形束计算机断层扫描（CBCT）图像中的上颌牙槽骨进行自动三维（3D）分割。
共收集了 141 例 CBCT 扫描用于训练（n=99）、验证（n=12）和测试（n=30）的自动分割上颌牙槽骨及其嵴轮廓的 CNN 模型。在自动分割后，通过专家对分割不足或过度的 3D 模型进行细化，生成改进-AI（R-AI）分割。评估了 CNN 模型的整体性能。另外，随机选择测试样本的 30%进行手动分割，以比较 AI 和手动分割的准确性。此外，还记录了生成 3D 模型所需的时间（秒）。
自动分割的准确度指标对于所有准确度指标均显示出极佳的范围值。然而，手动方法（95%HD：0.20±0.05mm；IoU：95%±3.0；DSC：97%±2.0）的性能略优于 AI 分割（95%HD：0.27±0.03mm；IoU：92%±1.0；DSC：96%±1.0）。分割方法之间的时间消耗存在统计学上的显著差异（p<0.001）。AI 驱动的分割（51.5±10.9s）比手动分割（5973.3±623.6s）快 116 倍。R-AI 方法的时间消耗居中（1666.7±588.5s）。
虽然手动分割的性能略好，但新型基于 CNN 的工具也可以高度准确地分割上颌牙槽骨及其嵴轮廓，比手动方法快 116 倍。
