Skip to content

Proximal Gradient Descent Network (PGD-Net) for Magnetic Resonance Fingerprinting, MICCAI'2020

Notifications You must be signed in to change notification settings

edongdongchen/PGD-Net

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Proximal Gradient Descent Network (PGD-Net) for Magnetic Resonance Fingerprinting

This is the PyTorch implementation of MICCAI'20 paper

Compressive MR Fingerprinting reconstruction with Neural Proximal Gradient iterations.

By Dongdong Chen, Mike E. Davies, Mohammad Golbabaee.

The University of Edinburgh, The University of Bath.

Table of Contents

  1. Keywords
  2. Abstract
  3. Requirement
  4. Usage
  5. Citation

Keywords

Magnetic Resonance Fingerprinting (MRF), Physics, Proximal gradient Descent (PGD), Inverse problem, Deep learning.

Abstract

Consistency of the predictions with respect to the physical forward model is pivotal for reliably solving inverse problems. This consistency is mostly un-controlled in the current end-to-end deep learning methodologies proposed for the Magnetic Resonance Fingerprinting (MRF) problem. To address this, we propose PGD-Net, a learned proximal gradient descent framework that directly incorporates the forward acquisition and Bloch dynamic models within a recurrent learning mechanism. The PGD-Net adopts a compact neural proximal model for de-aliasing and quantitative inference, that can be flexibly trained on scarce MRF training datasets. Our numerical experiments show that the PGD-Net can achieve a superior quantitative inference accuracy, much smaller storage requirement, and a comparable runtime to the recent deep learning MRF baselines, while being much faster than the dictionary matching schemes.

Requirement

  1. PyTorch >=1.0
  2. CUDA >=8.5

Usage

  1. check the demo_train() and demo_test() in main.py
  2. the neura network architecture of PGD-Net ('proxnet') is defined in network_arch.py
  3. the forward and adjoint operators are implemented in operators.py
  4. note: the data was from a partner company and we are restricted from sharing. Users need to specify their own dataset. Our code can be flexibly transferred or directly used on other customized MRF dataset.

Citation

If you use these models in your research, please cite:

@inproceedings{chen2020compressive,
	author = {Dongdong Chen and Mike E. Davies and Mohammad Golbabaee},
	title = {Compressive MR Fingerprinting reconstruction with Neural Proximal Gradient iterations},
	booktitle={International Conference on Medical image computing and computer-assisted intervention (MICCAI)},
	year = {2020}
}

About

Proximal Gradient Descent Network (PGD-Net) for Magnetic Resonance Fingerprinting, MICCAI'2020

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages