SE(3)对称性让图神经网络能够从小数据集中学习动脉速度估计
SE(3) symmetry lets graph neural networks learn arterial velocity estimation from small datasets
AI总结：
提出一种SE(3)等变图神经网络作为黑盒替代方法，从合成动脉模型中学习并高效估计3D血流速度场，相比CFD实现36倍加速，且显著减少所需训练数据量。
摘要：
冠状动脉中的血流动力学速度场可以作为心血管疾病诊断、预后和治疗计划的宝贵生物标志物的基础。速度场通常通过计算流体力学（CFD）从患者特定的3D动脉模型中获取。然而，CFD模拟需要专家进行细致的设置且耗时，这阻碍了其在临床实践中的大规模应用。为了解决这个问题，我们提出将图神经网络（GNN）作为一种高效的黑盒替代方法，用于估计映射到动脉腔四面体网格顶点的3D速度场。我们在合成动脉模型和基于CFD的真实速度场上训练这些GNN。一旦GNN训练完成，与CFD相比，在新的未见过的动脉中获取速度估计可实现36倍的加速。我们展示了如何构建一个独立于输入网格空间方向的SE(3)等变GNN，并展示了与基线神经网络相比，这如何减少了所需的训练数据量。
英文摘要：
Hemodynamic velocity fields in coronary arteries could be the basis of valuable biomarkers for diagnosis, prognosis and treatment planning in cardiovascular disease. Velocity fields are typically obtained from patient-specific 3D artery models via computational fluid dynamics (CFD). However, CFD simulation requires meticulous setup by experts and is time-intensive, which hinders large-scale acceptance in clinical practice. To address this, we propose graph neural networks (GNN) as an efficient black-box surrogate method to estimate 3D velocity fields mapped to the vertices of tetrahedral meshes of the artery lumen. We train these GNNs on synthetic artery models and CFD-based ground truth velocity fields. Once the GNN is trained, velocity estimates in a new and unseen artery can be obtained with 36-fold speed-up compared to CFD. We demonstrate how to construct an SE(3)-equivariant GNN that is independent of the spatial orientation of the input mesh and show how this reduces the necessary amount of training data compared to a baseline neural network.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
