Department of Convergence Medicine, University of Ulsan College of Medicine, Asan Medical Center, 388-1 Pungnap2-dong, Songpa-gu, Seoul, Republic of Korea.
Biomedical Research Institute & Department of Radiology, Seoul National University Hospital (SNUH), 101, Daehak-ro Jongno-gu, Seoul, 03080, Republic of Korea.
J Digit Imaging. 2020 Feb;33(1):221-230. doi: 10.1007/s10278-019-00223-1.
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.
肺叶分割在胸部 CT 中被用于分析肺功能和手术规划。然而，由于 80%的患者存在不完全和/或虚假的裂孔，因此准确的肺叶分割具有一定难度。此外，慢性阻塞性肺疾病（COPD）等肺部疾病可能会增加区分叶裂的难度。叶裂的强度与血管和气道壁相似，这可能导致自动分割中的分割错误。在这项研究中，开发了一种基于 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。从三个中心获得了 196 名正常和轻度至中度 COPD 患者的容积式胸部 CT 扫描。使用常规图像处理方法对每个扫描进行分割，并由胸部放射科专家进行手动校正，以创建金标准。然后，使用具有深度学习神经网络（CNN）的 3D U-Net 架构对 CT 图像中的叶区进行分割，使用单独的训练、验证和测试数据集。此外，还使用 40 个独立的外部 CT 图像来评估模型。使用四个准确性指标（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））对传统和深度学习方法的分割结果与金标准进行定量比较。在内部验证中，该分割方法在 DSC、JSC、MSD 和 HSD 方面的准确性很高（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，在 DSC、JSC、MSD 和 HSD 方面也获得了很高的准确性（分别为 0.96±0.02、0.92±0.04、1.31±0.56 和 27.89±7.50）。该方法用于左右肺叶分割的时间分别为 6.49±1.19s 和 8.61±1.08s。尽管已经开发了各种自动肺叶分割方法，但很难开发出一种稳健的分割方法。然而，基于深度学习的 3D U-Net 方法显示出了合理的分割准确性和计算时间。此外，该方法可以在临床工作流程中适应和应用于严重的肺部疾病。
