Machine-Learning Identification of Hemodynamics in Coronary Arteries in the Presence of Stenosis

• URL: http://arxiv.org/abs/2111.01950v1
• Date: Tue, 2 Nov 2021 23:51:06 GMT
• Title: Machine-Learning Identification of Hemodynamics in Coronary Arteries in the Presence of Stenosis
• Authors: Mohammad Farajtabar, Morsal Momeni Larimi, Mohit Biglarian, Morteza Miansari
• Abstract summary: An artificial neural network (ANN) model is trained using synthetic data to predict the pressure and velocity within the arterial network. The efficiency of the model was verified using three real geometries of LAD's vessels.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Prediction of the blood flow characteristics is of utmost importance for understanding the behavior of the blood arterial network, especially in the presence of vascular diseases such as stenosis. Computational fluid dynamics (CFD) has provided a powerful and efficient tool to determine these characteristics including the pressure and velocity fields within the network. Despite numerous studies in the field, the extremely high computational cost of CFD has led the researchers to develop new platforms including Machine Learning approaches that instead provide faster analyses at a much lower cost. In this study, we put forth a Deep Neural Network framework to predict flow behavior in a coronary arterial network with different properties in the presence of any abnormality like stenosis. To this end, an artificial neural network (ANN) model is trained using synthetic data so that it can predict the pressure and velocity within the arterial network. The data required to train the neural network were obtained from the CFD analysis of several geometries of arteries with specific features in ABAQUS software. Blood pressure drop caused by stenosis, which is one of the most important factors in the diagnosis of heart diseases, can be predicted using our proposed model knowing the geometrical and flow boundary conditions of any section of the coronary arteries. The efficiency of the model was verified using three real geometries of LAD's vessels. The proposed approach precisely predicts the hemodynamic behavior of the blood flow. The average accuracy of the pressure prediction was 98.7% and the average velocity magnitude accuracy was 93.2%. According to the results of testing the model on three patient-specific geometries, model can be considered as an alternative to finite element methods as well as other hard-to-implement and time-consuming numerical simulations.

Related papers

• MedDiffusion: Boosting Health Risk Prediction via Diffusion-based Data Augmentation [58.93221876843639]
  This paper introduces a novel, end-to-end diffusion-based risk prediction model, named MedDiffusion. It enhances risk prediction performance by creating synthetic patient data during training to enlarge sample space. It discerns hidden relationships between patient visits using a step-wise attention mechanism, enabling the model to automatically retain the most vital information for generating high-quality data.
  arXiv  Detail & Related papers  (2023-10-04T01:36:30Z)
• Voxel2Hemodynamics: An End-to-end Deep Learning Method for Predicting Coronary Artery Hemodynamics [24.8579242043367]
  Local hemodynamic forces play an important role in determining the functional significance of coronary arterial stenosis. We propose an end-to-end deep learning framework, which could predict the coronary artery hemodynamics from CCTA images.
  arXiv  Detail & Related papers  (2023-05-30T15:12:52Z)
• Continuous time recurrent neural networks: overview and application to forecasting blood glucose in the intensive care unit [56.801856519460465]
  Continuous time autoregressive recurrent neural networks (CTRNNs) are a deep learning model that account for irregular observations. We demonstrate the application of these models to probabilistic forecasting of blood glucose in a critical care setting.
  arXiv  Detail & Related papers  (2023-04-14T09:39:06Z)
• Learning Reduced-Order Models for Cardiovascular Simulations with Graph Neural Networks [1.2643625859899612]
  We develop one-dimensional reduced-order models that simulate blood flow dynamics using a graph neural network trained on three-dimensional hemodynamic simulation data. Our method exhibits superior performance compared to physics-based one-dimensional models, while maintaining high efficiency at inference time.
  arXiv  Detail & Related papers  (2023-03-13T17:32:46Z)
• SE(3) symmetry lets graph neural networks learn arterial velocity estimation from small datasets [3.861633648502351]
  Hemodynamic velocity fields in coronary arteries could be the basis of valuable biomarkers for diagnosis, prognosis and treatment planning. Velocity fields are typically obtained from patient-specific 3D artery models via computational fluid dynamics (CFD) We propose graph neural networks (GNN) as an efficient black-box surrogate method to estimate 3D velocity fields.
  arXiv  Detail & Related papers  (2023-02-17T09:42:38Z)
• Mesh Neural Networks for SE(3)-Equivariant Hemodynamics Estimation on the Artery Wall [13.113110989699571]
  We consider the estimation of vector-valued quantities on the wall of three-dimensional geometric artery models. We employ group equivariant graph convolution in an end-to-end SE(3)-equivariant neural network that operates directly on triangular surface meshes. We show that our method is powerful enough to accurately predict transient, vector-valued WSS over the cardiac cycle while conditioned on a range of different inflow boundary conditions.
  arXiv  Detail & Related papers  (2022-12-09T18:16:06Z)
• EINNs: Epidemiologically-Informed Neural Networks [75.34199997857341]
  We introduce a new class of physics-informed neural networks-EINN-crafted for epidemic forecasting. We investigate how to leverage both the theoretical flexibility provided by mechanistic models as well as the data-driven expressability afforded by AI models.
  arXiv  Detail & Related papers  (2022-02-21T18:59:03Z)
• A Deep Learning Approach to Predicting Collateral Flow in Stroke Patients Using Radiomic Features from Perfusion Images [58.17507437526425]
  Collateral circulation results from specialized anastomotic channels which provide oxygenated blood to regions with compromised blood flow. The actual grading is mostly done through manual inspection of the acquired images. We present a deep learning approach to predicting collateral flow grading in stroke patients based on radiomic features extracted from MR perfusion data.
  arXiv  Detail & Related papers  (2021-10-24T18:58:40Z)
• Physics-informed neural networks for improving cerebral hemodynamics predictions [0.0]
  In this work, we put forth a physics-informed deep learning framework that augments sparse clinical measurements with fast computational fluid dynamics simulations. Our framework employs in-vivo real-time TCD velocity measurements at several locations in the brain and the baseline vessel cross-sectional areas acquired from 3D images. We validated the predictions of our model against in-vivo velocity measurements obtained via 4D MRI scans.
  arXiv  Detail & Related papers  (2021-08-25T22:19:41Z)
• Simultaneous boundary shape estimation and velocity field de-noising in Magnetic Resonance Velocimetry using Physics-informed Neural Networks [70.7321040534471]
  Magnetic resonance velocimetry (MRV) is a non-invasive technique widely used in medicine and engineering to measure the velocity field of a fluid. Previous studies have required the shape of the boundary (for example, a blood vessel) to be known a priori. We present a physics-informed neural network that instead uses the noisy MRV data alone to infer the most likely boundary shape and de-noised velocity field.
  arXiv  Detail & Related papers  (2021-07-16T12:56:09Z)
• Learning Dynamic and Personalized Comorbidity Networks from Event Data using Deep Diffusion Processes [102.02672176520382]
  Comorbid diseases co-occur and progress via complex temporal patterns that vary among individuals. In electronic health records we can observe the different diseases a patient has, but can only infer the temporal relationship between each co-morbid condition. We develop deep diffusion processes to model "dynamic comorbidity networks"
  arXiv  Detail & Related papers  (2020-01-08T15:47:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.