基于深度空间序列网络的4D计算机断层扫描研究中的左心室腔自动分割
Automatic Left Ventricular Cavity Segmentation via Deep Spatial Sequential Network in 4D Computed Tomography Studies
- School of Biomedical Engineering, Shanghai Jiao Tong University（上海交通大学生物医学工程学院）
- School of Computer Science, University of Sydney（悉尼大学计算机学院）
- Ruijin Hospital, Shanghai Jiaotong University School of Medicine（上海交通大学医学院附属瑞金医院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对现有深度学习方法在左心室腔时间序列分割中忽略时序信息且收缩末期效果差的问题，提出空间序列网络结合双向学习（SS-BL），在CT和MRI数据集上验证了其优越性与泛化性。
AI中文摘要：
在时间心脏图像序列（多个时间点）中对左心室腔（LVC）进行自动分割，是对其结构和功能变化进行定量分析的基本要求。基于深度学习的方法在LVC分割方面处于当前最先进水平；然而，这些方法通常设计为在单个时间点上工作，未能利用时间图像序列中的互补信息，而这些信息有助于提高分割准确性以及各时间点图像之间的一致性。此外，这些分割方法在分割收缩末期（ES）相位图像时表现不佳，此时左心室变形为最小的不规则形状，血液腔与心肌之间的边界变得不明显。为克服这些局限，我们提出了一种新方法来自动分割时间心脏图像，其中我们引入了一个空间序列（SS）网络，以无监督方式学习LVC的变形和运动特征；随后将这些特征与从双向学习（BL）中获得的序列上下文信息相整合，双向学习同时使用了图像序列的时间顺序和逆时间顺序方向。我们在心脏计算机断层扫描（CT）数据集上的实验结果表明，我们提出的具有双向学习的空间序列网络（SS-BL）方法在LVC分割方面优于现有方法。我们的方法也应用于MRI心脏数据集，结果证明了我们方法的泛化能力。
英文摘要：
Automated segmentation of left ventricular cavity (LVC) in temporal cardiac image sequences (multiple time points) is a fundamental requirement for quantitative analysis of its structural and functional changes. Deep learning based methods for the segmentation of LVC are the state of the art; however, these methods are generally formulated to work on single time points, and fails to exploit the complementary information from the temporal image sequences that can aid in segmentation accuracy and consistency among the images across the time points. Furthermore, these segmentation methods perform poorly in segmenting the end-systole (ES) phase images, where the left ventricle deforms to the smallest irregular shape, and the boundary between the blood chamber and myocardium becomes inconspicuous. To overcome these limitations, we propose a new method to automatically segment temporal cardiac images where we introduce a spatial sequential (SS) network to learn the deformation and motion characteristics of the LVC in an unsupervised manner; these characteristics were then integrated with sequential context information derived from bi-directional learning (BL) where both chronological and reverse-chronological directions of the image sequence were used. Our experimental results on a cardiac computed tomography (CT) dataset demonstrated that our spatial-sequential network with bi-directional learning (SS-BL) method outperformed existing methods for LVC segmentation. Our method was also applied to MRI cardiac dataset and the results demonstrated the generalizability of our method.
