论文标题
使用深度全卷积网络提取CT扫描中肺气道
Extraction of Pulmonary Airway in CT Scans Using Deep Fully Convolutional Networks
论文作者
论文摘要
准确，自动且完全提取医学图像中肺气道在分析胸部CT体积（例如肺癌检测，慢性阻塞性肺疾病（COPD）和支气管镜辅助手术导航）中起着重要作用。但是，由于气道的复杂树状结构，此任务仍然是挑战。在这份技术报告中，我们使用两阶段的完全卷积网络（FCN）自动从多站点进行胸CT扫描中的肺气道。具体而言，我们首先采用带有U形网络架构的3D FCN，以粗分辨率分割肺气道，以加速医学图像分析管道。然后，另一个3D FCN进行了训练，可以通过精细的分辨率进行分段肺气道。在2022 MICCAI多站点多域气道树建模（ATM）挑战中，对报告的方法进行了300例公共培训集和50个案例的独立私人验证集评估。由此产生的骰子相似性系数（DSC）为0.914 $ \ pm $ 0.040，假负错误（FNE）为0.079 $ \ pm $ 0.042，误差（FPE）为0.090 $ \ pm $ 0.066 $ 0.066独立私人验证集。
Accurate, automatic and complete extraction of pulmonary airway in medical images plays an important role in analyzing thoracic CT volumes such as lung cancer detection, chronic obstructive pulmonary disease (COPD), and bronchoscopic-assisted surgery navigation. However, this task remains challenges, due to the complex tree-like structure of the airways. In this technical report, we use two-stage fully convolutional networks (FCNs) to automatically segment pulmonary airway in thoracic CT scans from multi-sites. Specifically, we firstly adopt a 3D FCN with U-shape network architecture to segment pulmonary airway in a coarse resolution in order to accelerate medical image analysis pipeline. And then another one 3D FCN is trained to segment pulmonary airway in a fine resolution. In the 2022 MICCAI Multi-site Multi-domain Airway Tree Modeling (ATM) Challenge, the reported method was evaluated on the public training set of 300 cases and independent private validation set of 50 cases. The resulting Dice Similarity Coefficient (DSC) is 0.914 $\pm$ 0.040, False Negative Error (FNE) is 0.079 $\pm$ 0.042, and False Positive Error (FPE) is 0.090 $\pm$ 0.066 on independent private validation set.
