Fully Automated Lung Lobe Segmentation in Volumetric Chest CT with 3D U-Net: Validation with Intra- and Extra-Datasets
Fully Automated Lung Lobe Segmentation in Volumetric Chest CT with 3D U-Net: Validation with Intra- and Extra-Datasets
复制标题
使用3D U - Net在胸部容积CT中进行全自动肺叶分割：数据集内和数据集外验证
DOI：
10.1007/s10278-019-00223-1
复制
发表时间：
2020-02-01
影响因子：
4.4
通讯作者：
Seo, Joon Beom
中科院分区：
文献类型：
--
作者：
Park, Jongha;Yun, Jihye;Seo, Joon Beom
胸部CT中的肺叶分割已被用于肺功能分析和手术规划。然而，准确的肺叶分割是困难的，因为80%的患者具有不完整和/或假裂隙。此外，肺部疾病，如慢性阻塞性肺病（COPD）可能会增加区分叶裂的难度。肺叶裂隙与血管和气道壁的强度相似，这可能导致自动分割中的分割错误。在这项研究中，开发了一种使用3D U-Net的全自动肺叶分割方法，并使用内部和外部数据集进行了验证。对三个中心196例正常和轻中度COPD患者进行胸部容积CT扫描。使用常规图像处理方法对每次扫描进行分割，并由专业胸部放射科医生手动校正以创建金标准。然后，使用具有深度卷积神经网络（CNN）的3D U-Net架构，使用单独的训练、验证和测试数据集对CT图像中的叶区域进行分割。此外，40个独立的外部CT图像用于评估模型。传统和深度学习方法的分割结果与金标准进行了定量比较，使用了四个准确度指标，包括Dice相似系数（DSC），Jaccard相似系数（JSC），平均表面距离（MSD）和Hausdorff表面距离（HSD）。在内部验证中，DSC、JSC、MSD和HSD的分割方法实现了高准确度（分别为0.97 +/- 0.02、0.94 +/- 0.03、0.69 +/- 0.36和17.12 +/- 11.07）。在外部验证中，DSC、JSC、MSD和HSD也获得了高准确度（分别为0.96 +/- 0.02、0.92 +/- 0.04、1.31 +/- 0.56和27.89 +/- 7.50）。该方法对左肺和右肺的肺叶分割分别花费6.49 +/- 1.19 s和8.61 +/- 1.08 s。虽然已经开发了各种自动肺叶分割方法，但是很难开发鲁棒的分割方法。然而，基于深度学习的3D U-Net方法显示出合理的分割精度和计算时间。此外，该方法可以适应并应用于临床工作流程中的严重肺部疾病。
Lung lobe segmentation in chest CT has been used for the analysis of lung functions and surgical planning. However, accurate lobe segmentation is difficult as 80% of patients have incomplete and/or fake fissures. Furthermore, lung diseases such as chronic obstructive pulmonary disease (COPD) can increase the difficulty of differentiating the lobar fissures. Lobar fissures have similar intensities to those of the vessels and airway wall, which could lead to segmentation error in automated segmentation. In this study, a fully automated lung lobe segmentation method with 3D U-Net was developed and validated with internal and external datasets. The volumetric chest CT scans of 196 normal and mild-to-moderate COPD patients from three centers were obtained. Each scan was segmented using a conventional image processing method and manually corrected by an expert thoracic radiologist to create gold standards. The lobe regions in the CT images were then segmented using a 3D U-Net architecture with a deep convolutional neural network (CNN) using separate training, validation, and test datasets. In addition, 40 independent external CT images were used to evaluate the model. The segmentation results for both the conventional and deep learning methods were compared quantitatively to the gold standards using four accuracy metrics including the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), mean surface distance (MSD), and Hausdorff surface distance (HSD). In internal validation, the segmentation method achieved high accuracy for the DSC, JSC, MSD, and HSD (0.97 +/- 0.02, 0.94 +/- 0.03, 0.69 +/- 0.36, and 17.12 +/- 11.07, respectively). In external validation, high accuracy was also obtained for the DSC, JSC, MSD, and HSD (0.96 +/- 0.02, 0.92 +/- 0.04, 1.31 +/- 0.56, and 27.89 +/- 7.50, respectively). This method took 6.49 +/- 1.19 s and 8.61 +/- 1.08 s for lobe segmentation of the left and right lungs, respectively. Although various automatic lung lobe segmentation methods have been developed, it is difficult to develop a robust segmentation method. However, the deep learning-based 3D U-Net method showed reasonable segmentation accuracy and computational time. In addition, this method could be adapted and applied to severe lung diseases in a clinical workflow.