Machine Learning-Accelerated Vascular Reconstruction for Rapid CFD-Based Hemodynamic Analysis via Composite Score-Driven Centerline Optimization
Authors:
- Tong ZhangTZTong Zhang
- Yong LiaoYLYong Liao
- Yongjian LiYLYongjian Li
- Zujie GaoZGZujie Gao
- Derong QiuDQDerong Qiu
- Lin ZhLZLin Zh
- Timothy Shao Ern TanTTTimothy Shao Ern Tan
- Haosheng ChenHCHaosheng Chen
Preprint
- 18 August 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Background and Objectives: Reconstructing three-dimensional vascular models for computational fluid dynamics (CFD) is time-consuming, limiting clinical application. Conventional centerline-based approaches generate redundant control points, reducing efficiency. We propose a machine learning-accelerated framework for rapid vascular reconstruction via centerline optimization.Methods: A surrogate neural network predicts the Dice similarity coefficient (DSC) for fast estimation of volumetric overlap. A composite score (CS) balancing geometric fidelity and data reduction guides optimal threshold selection.Results: The method achieves >500-fold computation time reduction while maintaining high accuracy. In an abdominal aortic network, control points were reduced by 70% with DSC = 0.8698. CFD simulations confirm hemodynamic consistency with original models.Conclusions: This approach provides an efficient, scalable solution for generating CFD-ready vascular models, with potential for clinical decision-making and interventional planning.Keywords
This publication has 15 references indexed in Scilit:
- Patient-Specific Numerical Simulations of Coronary Artery Hemodynamics and Biomechanics: A Pathway to Clinical UseCardiovascular Engineering and Technology, 2024
- Modeling and hexahedral meshing of cerebral arterial networks from centerlinesMedical Image Analysis, 2023
- Watertight modeling and segmentation of bifurcated Coronary arteries for blood flow simulation using CT imagingComputerized Medical Imaging and Graphics, 2016
- Full-hexahedral structured meshing for image-based computational vascular modelingMedical Engineering & Physics, 2011
- Patient-specific computational fluid dynamics: structured mesh generation from coronary angiographyMedical & Biological Engineering & Computing, 2010
- Image-Based Modeling of Blood Flow and Vessel Wall Dynamics: Applications, Methods and Future DirectionsAnnals of Biomedical Engineering, 2010
- An image-based modeling framework for patient-specific computational hemodynamicsMedical & Biological Engineering & Computing, 2008
- Evaluation of hexahedral, prismatic and hybrid mesh styles for simulating respiratory aerosol dynamicsComputers & Fluids, 2008
- Geometric reconstruction for computational mesh generation of arterial bifurcations from CT angiographyComputerized Medical Imaging and Graphics, 2002
- Hemodynamic Shear Stress and Its Role in AtherosclerosisJAMA, 1999