Xing Haiqun, Zhang Xin, Nie Yingbin, Wang Sicong, Wang Tong, Jing Hongli, Li Fang
Department of Nuclear Medicine, Peking Union Medical College Hospital, Chinese Academy of Medical Science & Peking Union Medical College, Beijing Key Laboratory of Molecular Targeted Diagnosis and Therapy in Nuclear Medicine, Beijing, China.
GE Healthcare, Beijing, China.
Quant Imaging Med Surg. 2022 Oct;12(10):4747-4757. doi: 10.21037/qims-21-1116.
The proposed algorithm could support accurate localization of lung disease. To develop and validate an automated deep learning model combined with a post-processing algorithm to segment six pulmonary anatomical regions in chest computed tomography (CT) images acquired during positron emission tomography/computed tomography (PET/CT) scans. The pulmonary regions have five pulmonary lobes and airway trees.
Patients who underwent both PET/CT imaging with an extra chest CT scan were retrospectively enrolled. The pulmonary segmentation of six regions in CT was performed via a convolutional neural network (CNN) of DenseVNet architecture with some post-processing algorithms. Three evaluation metrics were used to assess the performance of this method, which combined deep learning and the post-processing method. The agreement between the combined model and ground truth segmentations in the test set was analyzed.
A total of 640 cases were enrolled. The combined model, which involved deep learning and post-processing methods, had a higher performance than the single deep learning model. In the test set, the all-lobes overall Dice coefficient, Hausdorff distance, and Jaccard coefficient were 0.972, 12.025 mm, and 0.948, respectively. The airway-tree Dice coefficient, Hausdorff distance, and Jaccard coefficient were 0.849, 32.076 mm, and 0.815, respectively. A good agreement was observed between our segmentation in every plot.
The proposed model combining two methods can automatically segment five pulmonary lobes and airway trees on chest CT imaging in PET/CT. The performance of the combined model was higher than the single deep learning model in each region in the test set.
所提出的算法可支持肺部疾病的准确定位。开发并验证一种结合后处理算法的自动化深度学习模型，以分割在正电子发射断层扫描/计算机断层扫描（PET/CT）扫描期间获取的胸部计算机断层扫描（CT）图像中的六个肺部解剖区域。肺部区域包括五个肺叶和气道树。
回顾性纳入同时接受PET/CT成像及额外胸部CT扫描的患者。通过具有一些后处理算法的DenseVNet架构的卷积神经网络（CNN）对CT中的六个区域进行肺部分割。使用三个评估指标来评估该方法的性能，该方法结合了深度学习和后处理方法。分析了测试集中组合模型与地面真值分割之间的一致性。
共纳入640例病例。涉及深度学习和后处理方法的组合模型比单一深度学习模型具有更高的性能。在测试集中，所有肺叶的总体Dice系数、豪斯多夫距离和杰卡德系数分别为0.972、12.025毫米和0.948。气道树的Dice系数、豪斯多夫距离和杰卡德系数分别为0.849、32.076毫米和0.815。在每个图中我们的分割之间观察到良好的一致性。
所提出的结合两种方法的模型可以在PET/CT的胸部CT成像上自动分割五个肺叶和气道树。在测试集中，组合模型在每个区域的性能均高于单一深度学习模型。
