Department of Computer Science, UNC Charlotte, Charlotte, NC, USA.
Research and Development Department, Shenzhen Keya Medical Technology, Co., Ltd., Guangdong, China.
Comput Med Imaging Graph. 2020 Mar;80:101688. doi: 10.1016/j.compmedimag.2019.101688. Epub 2019 Dec 28.
Extensive research has been devoted to the segmentation of the coronary artery. However, owing to its complex anatomical structure, it is extremely challenging to automatically segment the coronary artery from 3D coronary computed tomography angiography (CCTA). Inspired by recent ideas to use tree-structured long short-term memory (LSTM) to model the underlying tree structures for NLP tasks, we propose a novel tree-structured convolutional gated recurrent unit (ConvGRU) model to learn the anatomical structure of the coronary artery. However, unlike tree-structured LSTM proposed for semantic relatedness as well as sentiment classification in natural language processing, our tree-structured ConvGRU model considers the local spatial correlations in the input data as the convolutions are used for input-to-state as well as state-to-state transitions, thus more suitable for image analysis. To conduct voxel-wise segmentation, a tree-structured segmentation framework is presented. It consists of a fully convolutional network (FCN) for multi-scale discriminative feature extraction and the final prediction, and a tree-structured ConvGRU layer for anatomical structure modeling. The proposed framework is extensively evaluated on four large-scale 3D CCTA dataset (the largest to the best of our knowledge), and experiments show that our method is more accurate as well as efficient, compared with other coronary artery segmentation approaches.
已经有大量研究致力于冠状动脉的分割。然而，由于其复杂的解剖结构，从 3D 冠状动脉计算机断层血管造影（CCTA）自动分割冠状动脉极具挑战性。受最近利用树结构长短期记忆（LSTM）来为自然语言处理任务建模底层树结构的思想的启发，我们提出了一种新颖的树结构卷积门控循环单元（ConvGRU）模型来学习冠状动脉的解剖结构。然而，与用于自然语言处理中语义相关性和情感分类的树结构 LSTM 不同，我们的树结构 ConvGRU 模型考虑了输入数据中的局部空间相关性，因为卷积用于输入到状态以及状态到状态的转换，因此更适合图像分析。为了进行体素级分割，提出了一种树结构分割框架。它由用于多尺度判别特征提取和最终预测的全卷积网络（FCN）以及用于解剖结构建模的树结构 ConvGRU 层组成。在四个大规模 3D CCTA 数据集（据我们所知最大的数据集）上进行了广泛的评估，实验表明与其他冠状动脉分割方法相比，我们的方法更准确且高效。
