文献速递口腔颌面外科口腔正畸

卷积神经网络自动分割咽气道空间

Automatic segmentation of the pharyngeal airway space with convolutional neural network.
PubMed 文献 · J Dent · 2021-05-30

本研究基于103例正颌手术患者的CT/CBCT影像,构建3D U-Net模型自动分割咽气道空间。模型精确率0.97±0.01、召回率0.96±0.03、Dice评分0.97±0.02、IoU 0.93±0.03,95%豪斯多夫距离最大差异0.98±0.74mm。Newtom VGi evo CBCT设备表现优于Promax 3D Max和CT设备。

要点

  • 3D U-Net模型可高精度自动分割咽气道空间,Dice评分达0.97±0.02。
  • 自动分割与手工标注的95%豪斯多夫距离最大差异为0.98±0.74mm。
  • 不同采集设备性能有差异,Newtom VGi evo CBCT表现更优。

核心结论

  • 所提出的3D U-Net模型为CT/CBCT图像中咽气道空间分割提供了一种准确且省时的方法。

研究设计与样本

  • 研究获取了103例正颌手术患者的CT和CBCT扫描数据,设备包括1台CT和2台CBCT。
  • 数据集划分为训练集48例、测试集25例和验证集30例,基于观察者手工分割的金标准训练3D U-Net模型。

主要发现

  • 模型分割的精确率为0.97±0.01,召回率为0.96±0.03。
  • 自动分割与金标准之间的95%豪斯多夫距离最大差异为0.98±0.74mm。
  • Dice评分为0.97±0.02,IoU为0.93±0.03。
  • 基于采集设备分析,Newtom VGi evo CBCT表现优于Promax 3D Max和CT设备。

临床怎么用

  • 该方法可帮助临床医生准确高效地诊断、规划治疗和随访牙颌面畸形及阻塞性睡眠呼吸暂停患者。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVES: 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). METHODS: 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. RESULTS: 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. CONCLUSION: The proposed 3D U-Net model offered an accurate and time-efficient method for the segmentation of PAS from CT/CBCT images. CLINICAL SIGNIFICANCE: 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.

来源:J Dent,查看原文。版权归原作者所有。

引用

  1. Shujaat S, Jazil O, Willems H, et al. Automatic segmentation of the pharyngeal airway space with convolutional neural network. J Dent. 2021. PMID: 34077802. doi:10.1016/j.jdent.2021.103705

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。