Geometric Uncertainty in Patient-Specific Cardiovascular Modeling with Convolutional Dropout Networks
Geometric Uncertainty in Patient-Specific Cardiovascular Modeling with Convolutional Dropout Networks
复制标题
DOI：
10.1016/j.cma.2021.114038
复制
发表时间：
2020-09
影响因子：
7.2
通讯作者：
Gabriel Maher;Casey M. Fleeter;D. Schiavazzi;A. Marsden
中科院分区：
文献类型：
--
作者：
Gabriel Maher;Casey M. Fleeter;D. Schiavazzi;A. Marsden
我们提出了一种新的方法来从给定临床获取的图像体积的患者特定的心血管模型的条件分布中生成样本。首先使用回归方法训练具有丢弃层的卷积神经网络结构用于血管管腔分割，以实现对血管管腔表面的贝叶斯估计。然后将该网络集成到路径规划患者特定的建模管道中，以生成心血管模型家族。我们通过量化几何不确定性对三个患者特定解剖结构的血流动力学的影响来展示我们的方法，这三个解剖结构是：一个主-髂分叉部，一个腹主动脉瘤和一个左冠状动脉的子模型。提出的方法引入的一个关键创新是能够直接从训练数据中学习几何不确定性。结果表明，几何不确定性如何产生与壁面剪应力和速度量级的其他不确定性源相当或更大的变异系数，但对压力的影响有限。具体地说，这适用于以小血管为特征的解剖结构，以及在网络训练中不常见的局部血管病变。
We propose a novel approach to generate samples from the conditional distribution of patient-specific cardiovascular models given a clinically acquired image volume. A convolutional neural network architecture with dropout layers is first trained for vessel lumen segmentation using a regression approach, to enable Bayesian estimation of vessel lumen surfaces. This network is then integrated into a path-planning patient-specific modeling pipeline to generate families of cardiovascular models. We demonstrate our approach by quantifying the effect of geometric uncertainty on the hemodynamics for three patient-specific anatomies, an aorto-iliac bifurcation, an abdominal aortic aneurysm and a sub-model of the left coronary arteries. A key innovation introduced in the proposed approach is the ability to learn geometric uncertainty directly from training data. The results show how geometric uncertainty produces coefficients of variation comparable to or larger than other sources of uncertainty for wall shear stress and velocity magnitude, but has limited impact on pressure. Specifically, this is true for anatomies characterized by small vessel sizes, and for local vessel lesions seen infrequently during network training.