Literature DB >> 34110037

Systematic evaluation of iterative deep neural networks for fast parallel MRI reconstruction with sensitivity-weighted coil combination.

Kerstin Hammernik1,2, Jo Schlemper3, Chen Qin1,4, Jinming Duan1,5, Ronald M Summers6, Daniel Rueckert1,2.   

Abstract

PURPOSE: To systematically investigate the influence of various data consistency layers and regularization networks with respect to variations in the training and test data domain, for sensitivity-encoded accelerated parallel MR image reconstruction. THEORY AND METHODS: Magnetic resonance (MR) image reconstruction is formulated as a learned unrolled optimization scheme with a down-up network as regularization and varying data consistency layers. The proposed networks are compared to other state-of-the-art approaches on the publicly available fastMRI knee and neuro dataset and tested for stability across different training configurations regarding anatomy and number of training samples.
RESULTS: Data consistency layers and expressive regularization networks, such as the proposed down-up networks, form the cornerstone for robust MR image reconstruction. Physics-based reconstruction networks outperform post-processing methods substantially for R = 4 in all cases and for R = 8 when the training and test data are aligned. At R = 8, aligning training and test data is more important than architectural choices.
CONCLUSION: In this work, we study how dataset sizes affect single-anatomy and cross-anatomy training of neural networks for MRI reconstruction. The study provides insights into the robustness, properties, and acceleration limits of state-of-the-art networks, and our proposed down-up networks. These key insights provide essential aspects to successfully translate learning-based MRI reconstruction to clinical practice, where we are confronted with limited datasets and various imaged anatomies.
© 2021 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.

Keywords:  data consistency; deep learning; domain shift; down-up networks; fastMRI; iterative image reconstruction; parallel imaging

Year:  2021        PMID: 34110037     DOI: 10.1002/mrm.28827

Source DB:  PubMed          Journal:  Magn Reson Med        ISSN: 0740-3194            Impact factor:   4.668


  2 in total

1.  Alternating Learning Approach for Variational Networks and Undersampling Pattern in Parallel MRI Applications.

Authors:  Marcelo V W Zibetti; Florian Knoll; Ravinder R Regatte
Journal:  IEEE Trans Comput Imaging       Date:  2022-05-20

2.  Bayesian Uncertainty Estimation of Learned Variational MRI Reconstruction.

Authors:  Dominik Narnhofer; Alexander Effland; Erich Kobler; Kerstin Hammernik; Florian Knoll; Thomas Pock
Journal:  IEEE Trans Med Imaging       Date:  2022-02-02       Impact factor: 10.048

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.