Filter Results
3510351 results
  • The Rmd file contains all the scripts used to generate figures for the manuscript. It can be viewed in R Studio.
    Data Types:
    • Software/Code
  • This is the network weights linked to the publication:Fully Automated Myocardial Strain Estimation from Cardiovascular MRI–tagged Images Using a Deep Learning Framework in the UK Biobank The deep learning models were trained on 4,508 CMR-tagged images from the U.K. Biobank dataset. GitHub code: https://github.com/EdwardFerdian/mri-tagging-strain
    Data Types:
    • Software/Code
  • In this study, we developed a super resolution deep learning algorithm to enhance spatial resolution of 4D Flow MRI. The neural network was trained using synthetic 4D Flow MRI dataset generated from aortic CFD simulations. The network was then tested on actual 4D Flow MRI of a phantom and volunteer data. You can download the pre-trained 4DFlowNet on this site. Publication:https://www.frontiersin.org/articles/10.3389/fphy.2020.00138/full github:https://github.com/EdwardFerdian/4DFlowNet
    Data Types:
    • Software/Code
  • The files contain the network weights linked to the publication:Fully Automated Myocardial Strain Estimation from Cardiovascular MRI–tagged Images Using a Deep Learning Framework in the UK Biobank The deep learning models were trained on 4,508 CMR-tagged images from the U.K. Biobank dataset.
    Data Types:
    • Software/Code
  • This item contains the software used for analysis, modeling, and visualization of the Alpine Fault laser ultrasonics data, as presented in the manuscript "Constraining microfractures in foliated Alpine Fault rocks with laser ultrasonics". This software can be used to reproduce the results and figures presented in the manuscript when combined with the laser ultrasonics data of the five rock samples in this repository. The sample_analysis.py script performs calculations with the sample physical properties and P-wave arrival times to calculate the values stored in the rp_data.p files. This script relies on the alpine_fault_rock_data.csv file. The other three Python scripts reproduce the figures presented in the manuscript and supporting information. The GassDEM.zip file contains all the input data, software, and modeling scripts to run the differential effective medium (DEM) modeling. Elastic stiffness matrices estimated from EBSD data and modeled in the MTEX software are included, as are individual modeling scripts for each of the four samples. Refer to the details of the README.txt file in this archive to install and run the DEM software. To run the Python scripts, an installation of Python scientific libraries is required (e.g. Anaconda). Also, the scripts rely heavily on the PlaceScan library to handle the raw experimental data. See https://github.com/jsimpsonUoA/PlaceScan for download and installation instructions. The DEM code has been adapted from the code written by Eunyoung Kim, as presented in "GassDem: A MATLAB program for modeling the anisotropic seismic properties of porous medium using differential effective medium theory and Gassmann’s poroelastic relationship" (2019), Computers and Geosciences. Please see https://github.com/ekim1419/GassDem for details. This software has been tested and successfully run on an installation of Ubuntu 16.04 LTS. Changes may be required to run the software on other operating systems.
    Data Types:
    • Software/Code
  • The Rmd file contains all the scripts used to generate figures for the manuscript. It can be viewed in R Studio.
    Data Types:
    • Software/Code
  • In this study, we developed a super resolution deep learning algorithm to enhance spatial resolution of 4D Flow MRI. The neural network was trained using synthetic 4D Flow MRI dataset generated from aortic CFD simulations. The network was then tested on actual 4D Flow MRI of a phantom and volunteer data. You can download the pre-trained 4DFlowNet on this site. Publication:https://www.frontiersin.org/articles/10.3389/fphy.2020.00138/full github:https://github.com/EdwardFerdian/4DFlowNet
    Data Types:
    • Software/Code
  • This is the network weights linked to the publication:Fully Automated Myocardial Strain Estimation from Cardiovascular MRI–tagged Images Using a Deep Learning Framework in the UK Biobank The deep learning models were trained on 4,508 CMR-tagged images from the U.K. Biobank dataset. GitHub code: https://github.com/EdwardFerdian/mri-tagging-strain
    Data Types:
    • Software/Code
  • Data Types:
    • Software/Code
  • In this study, we developed a super resolution deep learning algorithm to enhance spatial resolution of 4D Flow MRI. The neural network was trained using synthetic 4D Flow MRI dataset generated from aortic CFD simulations. The network was then tested on actual 4D Flow MRI of a phantom and volunteer data. You can download the pre-trained 4DFlowNet on this site. The zip file contains the TF1.8 version. For TF2.0 with Keras please use the HDF5 file pre-trained weights. Publication:https://www.frontiersin.org/articles/10.3389/fphy.2020.00138/full github:https://github.com/EdwardFerdian/4DFlowNet
    Data Types:
    • Software/Code