OMFS IMPATH Research Group, Department of Imaging & Pathology, Faculty of Medicine, KU Leuven & Oral and Maxillofacial Surgery, University Hospitals Leuven, Kapucijnenvoer 33, Leuven, Belgium.
OMFS IMPATH Research Group, Department of Imaging & Pathology, Faculty of Medicine, KU Leuven & Oral and Maxillofacial Surgery, University Hospitals Leuven, Kapucijnenvoer 33, Leuven, Belgium.
J Dent. 2021 Aug;111:103705. doi: 10.1016/j.jdent.2021.103705. Epub 2021 May 30.
This study proposed and investigated the performance of a deep learning based three-dimensional (3D) convolutional neural network (CNN) model for automatic segmentation of the pharyngeal airway space (PAS).
A dataset of 103 computed tomography (CT) and cone-beam CT (CBCT) scans was acquired from an orthognathic surgery patients database. The acquisition devices consisted of 1 CT (128-slice multi-slice spiral CT, Siemens Somatom Definition Flash, Siemens AG, Erlangen, Germany) and 2 CBCT devices (Promax 3D Max, Planmeca, Helsinki, Finland and Newtom VGi evo, Cefla, Imola, Italy) with different scanning parameters. A 3D CNN-based model (3D U-Net) was built for automatic segmentation of the PAS. The complete CT/CBCT dataset was split into three sets, training set (n = 48) for training the model based on the ground-truth observer-based manual segmentation, test set (n = 25) for getting the final performance of the model and validation set (n = 30) for evaluating the model's performance versus observer-based segmentation.
The CNN model was able to identify the segmented region with optimal precision (0.97±0.01) and recall (0.96±0.03). The maximal difference between the automatic segmentation and ground truth based on 95% hausdorff distance score was 0.98±0.74mm. The dice score of 0.97±0.02 confirmed the high similarity of the segmented region to the ground truth. The Intersection over union (IoU) metric was also found to be high (0.93±0.03). Based on the acquisition devices, Newtom VGi evo CBCT showed improved performance compared to the Promax 3D Max and CT device.
The proposed 3D U-Net model offered an accurate and time-efficient method for the segmentation of PAS from CT/CBCT images.
The proposed method can allow clinicians to accurately and efficiently diagnose, plan treatment and follow-up patients with dento-skeletal deformities and obstructive sleep apnea which might influence the upper airway space, thereby further improving patient care.
本研究提出并探讨了一种基于深度学习的三维（3D）卷积神经网络（CNN）模型在自动分割咽气道空间（PAS）中的性能。
从正颌手术患者数据库中获取了 103 例计算机断层扫描（CT）和锥形束 CT（CBCT）扫描的数据集。采集设备包括 1 台 CT（Siemens Somatom Definition Flash，Siemens AG，德国 Erlangen）和 2 台 CBCT 设备（Promax 3D Max，Planmeca，芬兰赫尔辛基和 Newtom VGi evo，Cefla，意大利伊莫拉），具有不同的扫描参数。建立了基于 3D U-Net 的 3D CNN 模型，用于自动分割 PAS。将完整的 CT/CBCT 数据集分为三组：训练集（n=48），用于根据基于观察者的手动分割训练模型；测试集（n=25），用于获取模型的最终性能；验证集（n=30），用于评估模型与基于观察者的分割相比的性能。
CNN 模型能够以最佳精度（0.97±0.01）和召回率（0.96±0.03）识别分割区域。基于 95%hausdorff 距离评分的自动分割与地面实况之间的最大差异为 0.98±0.74mm。0.97±0.02 的骰子分数证实了分割区域与地面实况的高度相似性。交并比（IoU）指标也很高（0.93±0.03）。基于采集设备，Newtom VGi evo CBCT 与 Promax 3D Max 和 CT 设备相比，性能有所提高。
提出的 3D U-Net 模型为 CT/CBCT 图像 PAS 的分割提供了一种准确、高效的方法。
该方法可以使临床医生能够准确、有效地诊断、计划治疗和随访牙颌面畸形和阻塞性睡眠呼吸暂停患者，这些患者可能会对上气道空间产生影响，从而进一步改善患者的护理。
