Search

Hemodynamic prediction of carotid artery stenosis (CAS) is of great clinical significance in the diagnosis, prevention, and treatment prognosis of ischemic strokes. While computational fluid dynamics (CFD) is recognized as a useful tool, it shows a crucial issue that the high computational costs are usually required for real-time simulations of complex blood flows. Given the powerful feature-extraction capabilities, the deep learning (DL) methodology has a high potential to implement the mapping of anatomic geometries and CFD-driven flow fields, which enables accomplishing fast and accurate hemodynamic prediction for clinical applications. Based on a brain/neck CT angiography database of 280 subjects, image based three-dimensional CFD models of CAS were constructed through blood vessel extraction, computational domain meshing and setting of the pulsatile flow boundary conditions; a series of CFD simulations were undertaken. A DL strategy was proposed and accomplished in terms of point cloud datasets and a DL network with dual sampling-analysis channels. This enables multimode mapping to construct the image-based geometries of CAS while predicting CFD-based hemodynamics based on training and testing datasets. The CFD simulation was validated with the mass flow rates at two outlets reasonably agreed with the published results. Comprehensive analysis and error evaluation revealed that the DL strategy enables uncovering the association between transient blood flow characteristics and artery cavity geometric information before and after surgical treatments of CAS. Compared with other methods, our DL-based model trained with more clinical data can reduce the computational cost by 7,200 times, while still demonstrating good accuracy (error

The abnormal diameter of the coronary artery is twice or more than the normal diameter, which is a coronary artery aneurysm (CAA). According to the clinical statistics, CAA shows high occurrence on right coronary artery (RCA). The most common cause of CAA in adults is atherosclerosis, which destroys the elastic fibers in the middle layer of the blood vessel. Under the intravascular pressure, the weak wall bulges outward and form CAA. This article aims to explain the hemodynamic mechanism of coronary artery aneurysm shows high occurrence on RCA. Occurrence of CAA was simulated by the volume growth of coronary artery. Firstly, a 0–3D multi-scale model of normal coronary artery was constructed to obtain the hemodynamic environments of coronary artery. Then, fluid-structure interaction of normal and atherosclerotic blood vessel was performed to obtain volume growth rate of the coronary artery. Atherosclerosis was simulated by modifying Young’s modulus in middle layer of the blood vessel. Finally, creep simulation was performed to compare the deformation of the blood vessels under the accumulation of time. Under normal condition, the volume growth rate of the RCA is 2.28 times and 1.55 times of the LAD and the LCX. After atherosclerosis, the volume growth rate of the RCA was 2.69 times and 2.12 times of the LAD and the LCX. And the volume growth rate of the RCA was 3.85 times and 3.45 times of the LAD and the LCX after further deepening of atherosclerosis. The expansion time above the average volume growth rate of the RCA, the LAD and the LCX respectively were 0.194, 0.168 and 0.179 s. The RCA is 2.06 times the original, the LAD and LCX are 1.53 times and 1.56 times after 10 years in creep simulation. It can be concluded that the RCA is more prone to aneurysms originated from the larger expansion of the RCA under normal physiological condition, and the larger expansion is magnified under atherosclerosis condition with destroyed vessel elasticity, and further magnified during the time accumulated viscoelastic creep to develop to aneurysm eventually.