Ebrahimi Saman, Bagchi Prosenjit
Mechanical and Aerospace Engineering Department, Rutgers, The State University of New Jersey, Piscataway, NJ 08854, USA.
PNAS Nexus. 2024 Jan 31;3(2):pgae043. doi: 10.1093/pnasnexus/pgae043. eCollection 2024 Feb.
Blood velocity and red blood cell (RBC) distribution profiles in a capillary vessel cross-section in the microcirculation are generally complex and do not follow Poiseuille's parabolic or uniform pattern. Existing imaging techniques used to map large microvascular networks in vivo do not allow a direct measurement of full 3D velocity and RBC concentration profiles, although such information is needed for accurate evaluation of the physiological variables, such as the wall shear stress (WSS) and near-wall cell-free layer (CFL), that play critical roles in blood flow regulation, disease progression, angiogenesis, and hemostasis. Theoretical network flow models, often used for hemodynamic predictions in experimentally acquired images of the microvascular network, cannot provide the full 3D profiles either. In contrast, such information can be readily obtained from high-fidelity computational models that treat blood as a suspension of deformable RBCs. These models, however, are computationally expensive and not feasible for extension to the microvascular network at large spatial scales up to an organ level. To overcome such limitations, here we present machine learning (ML) models that bypass such expensive computations but provide highly accurate and full 3D profiles of the blood velocity, RBC concentration, WSS, and CFL in every vessel in the microvascular network. The ML models, which are based on artificial neural networks and convolution-based U-net models, predict hemodynamic quantities that compare very well against the true data but reduce the prediction time by several orders. This study therefore paves the way for ML to make detailed and accurate hemodynamic predictions in spatially large microvascular networks at an organ-scale.
微循环中毛细血管横截面的血流速度和红细胞（RBC）分布情况通常很复杂，并不遵循泊肃叶的抛物线或均匀模式。现有的用于体内大微血管网络成像的技术无法直接测量完整的三维速度和红细胞浓度分布，尽管准确评估生理变量（如壁面切应力（WSS）和近壁无细胞层（CFL））需要这些信息，而这些生理变量在血流调节、疾病进展、血管生成和止血中起着关键作用。理论网络流动模型常用于对微血管网络实验获取图像的血流动力学预测，但也无法提供完整的三维分布。相比之下，从将血液视为可变形红细胞悬浮液的高保真计算模型中可以很容易地获得此类信息。然而，这些模型计算成本高昂，在大空间尺度扩展到器官水平的微血管网络时不可行。为了克服这些限制，我们在此提出机器学习（ML）模型，该模型绕过此类昂贵的计算，但能提供微血管网络中每条血管的血流速度、红细胞浓度、壁面切应力和近壁无细胞层的高精度完整三维分布。基于人工神经网络和基于卷积的U-net模型的ML模型预测的血流动力学量与真实数据非常吻合，但预测时间缩短了几个数量级。因此，本研究为机器学习在器官尺度的大空间微血管网络中进行详细准确的血流动力学预测铺平了道路。
