High performance neural network for solving coronary artery flow velocity field based on fluid component concentration

Rapid methods that can replace traditional inefficient computational fluid dynamics (CFD) for solving flow field are missing. We reconstructed three-dimensional (3D) coronary vascular tree models based on coronary computed tomography angiography (CCTA) images from 205 patients. Two fluid materials, blood and contrast agent, were mixed to simulate the flow field with concentration information under diverse boundary conditions, obtaining 2255 CFD simulations as deep learning samples. A dual-path physics-data multi-derived neural network (PDMNN) was designed, inputting geometric 3D point cloud and concentration information, respectively, and outputting 3D flow velocity field. Flow velocity in the coronary artery was clinically measured in 26 patients to verify the proposed PDMNN. For the 100 cases in a test set, the mean square error of the flow field velocity between the CFD calculations and the PDMNN predictions is 0.0309. However, the time taken by the PDMNN is significantly reduced (10 s VS 0.5 h). Clinically measured mean blood flow velocity and PDMNN predictions did not yield statistically significant differences (0.00 ± 0.05 m/s, P > 0.05). The proposed PDMNN present excellent computation accuracy and efficiency, holding a significant technical value for the clinical and engineering application.

Authors

Institutions

Publication Details

Journal
Physics of Fluids
Published
2025-01-01
DOI
https://doi.org/10.1063/5.0244812
Primary Topic
Advanced MRI Techniques and Applications
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

High performance neural network for solving coronary artery flow velocity field based on fluid component concentration

Aike Qiao, Jie Liu, Hao Sun, Bao Li et al.
Physics of Fluids
Advanced MRI Techniques and Applications
article

High performance neural network for solving coronary artery flow velocity field based on fluid component concentration

Aike Qiao, Jie Liu, Hao Sun, Bao Li, Zijie Wang, Liyuan Zhang, Jinping Dong, Liyuan Kong, Boyan Mao, Tengfei Li, Xueke Li, Lihua Wang, Yang Yang, Honghui Zhang, Youjun Liu, Jian Liu, Luyao Fan, Huanmei Guo, Guangfei Li, Chang Hou, Suqin Huang, Yanping Zhang
article en

Abstract

Rapid methods that can replace traditional inefficient computational fluid dynamics (CFD) for solving flow field are missing. We reconstructed three-dimensional (3D) coronary vascular tree models based on coronary computed tomography angiography (CCTA) images from 205 patients. Two fluid materials, blood and contrast agent, were mixed to simulate the flow field with concentration information under diverse boundary conditions, obtaining 2255 CFD simulations as deep learning samples. A dual-path physics-data multi-derived neural network (PDMNN) was designed, inputting geometric 3D point cloud and concentration information, respectively, and outputting 3D flow velocity field. Flow velocity in the coronary artery was clinically measured in 26 patients to verify the proposed PDMNN. For the 100 cases in a test set, the mean square error of the flow field velocity between the CFD calculations and the PDMNN predictions is 0.0309. However, the time taken by the PDMNN is significantly reduced (10 s VS 0.5 h). Clinically measured mean blood flow velocity and PDMNN predictions did not yield statistically significant differences (0.00 ± 0.05 m/s, P > 0.05). The proposed PDMNN present excellent computation accuracy and efficiency, holding a significant technical value for the clinical and engineering application.

Physics of FluidsVol. 37(1)
Minzu University of China (CN), Beijing University of Chinese Medicine (CN), Peking University (CN), Beijing University of Technology (CN), Peking University People's Hospital (CN), Second Affiliated Hospital of Zhejiang University (CN), National Institute of Metrology (CN)
National Natural Science Foundation of China, China Postdoctoral Science Foundation, Natural Science Foundation of Beijing Municipality, National Key Research and Development Program of China
Openalex Percentile: Top 99%
Advanced MRI Techniques and Applications
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.