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

Kerstin Hammernik, Jo Schlemper, Chen Qin, Jinming Duan, Ronald M. Summers, Daniel Rueckert

Research output: Contribution to journalArticlepeer-review

41 Scopus citations


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.

Original languageEnglish
Pages (from-to)1859-1872
Number of pages14
JournalMagnetic Resonance in Medicine
Issue number4
StatePublished - Oct 2021
Externally publishedYes


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


Dive into the research topics of 'Systematic evaluation of iterative deep neural networks for fast parallel MRI reconstruction with sensitivity-weighted coil combination'. Together they form a unique fingerprint.

Cite this