In this study, a data driven approach to predicting hemodynamics based diagnostic factors for ischemic severity of stenotic lesion of coronary by a machine learning technique was proposed. For a training dataset, we generated total 1,116 coronary vessel models with various geometric features of a stenosis and conducted 3D-0D coupled blood flow dynamics simulations. We employed a fully connected deep neural network model with four hidden layers and a sigmoidal activation function. This novel approach produced a promising outcome for near-real time assessment of coronary lesion severity with reasonable accuracy.
Coronary circulation, Stenosis severity, Computational fluid dynamics, Machine learning, Hemodynamic factor, Geometric features, Physiological index
 Toth, G et al., Evolving concepts of angiogram: fractional flow reserve discordances in 4000 coronary stenosis, Eur. Heart J. Vol.35, 2014, pp. 2831-2838.
 Itu, L. et al., A patient-specific reduced-order model for coronary circulation. In: 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI), Barcelona, Spain, 2012, pp. 832-835.
 Itu, L. et al., A machine-learning approach for computation of fractional flow reserve from coronary computed tomography, J. Appl. Physio. Vol.121, 2016, pp. 42-52.
 Choi, H. et al., A fractional four-step finite element formulation of the unsteady incompressible Navier-Stokes equations using SUPG and linear equal-order element methods, Comp. Meth. App. Mech. Eng., Vol.143, 1997, pp. 333-348.
 McClure, N. TensorFlow machine learning cookbook, Packt Publishing Ltd., 2014.
Cite this paper
Duc Minh Tran, Minh Tuan Nguyen, Sang-Wook Lee. (2018) A Data Driven Approach to Predicting Hemodynamic Factors of Coronary Stenosis Severity. International Journal of Biology and Biomedicine, 3, 30-31
Copyright © 2018 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0