InVAErt networks for amortized inference and identifiability analysis of lumped parameter hemodynamic models
This repository contains pre-trained neural network models, training dataset and all related scripts. For additional information, please refer to the publications below:
-
InVAErt networks for amortized inference and identifiability analysis of lumped parameter hemodynamic models, Guoxiang Grayson Tong, Carlos A. Sing-Long Collao, and Daniele E. Schiavazzi.
-
InVAErt networks: A data-driven framework for model synthesis and identifiability analysis, Guoxiang Grayson Tong, Carlos A. Sing-Long Collao, and Daniele E. Schiavazzi.
DNN_tools.py
: common functions for deep neural network modeling.Model.py
: neural network modules.NF_tools.py
: functions used by the Real-NVP based normalizing flow model.Training_tools.py
: training and testing functions of the inVAErt networks.EHR_tools.py
: functions used in the study of the EHR dataset.cvsim6_scripts.py
: functions used in the study of the CVSim-6 model.plotter.py
: common plotting functions.
CVSIM6-Training-Data
: dataset used in this paper.CVSim6_stiffness_pictures
: results of the CVSim-6 stiffness analysis.ExternalData
: the EHR dataset.cvsim6-explicit-RK4.py
: explicit RK4 solver for the CVSim-6 system.cvsim6-stiffness_analysis.py
: functions for the stiffness analysis of the CVSim-6 system.cvsim6-system-test.py
: testing CVSim-6 solver with the reference parameter set.cvsim6-training-data-generator.py
: parallel training data generator.cvsim6_plotting_functions.py
: plotting functions for the stiffness analysis.cvsim6_simulator.py
: an implicit, adaptive solver for the CVSim-6 system.
Structural_id_study
: pre-trained models for the structural identifiability analysis.EHR
: pre-trained models for the study of the EHR dataset.
Pytorch
: 2.4.1CUDA
: 11.8Python
: 3.10.12numpy
: 1.26.4scipy
: 1.12.0matplotlib
: 3.9.2mpi4py
: 4.0.0sklearn
: 1.5.2