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

link to paper

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

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.

This was a very interesting read - thank you! Thinking about the future of clinical scanning - what do the authors think will be some of the first big impacts of deep neural networks for reconstruction? Will low-latency, real-time 4D MRI be feasible soon? Or will vendors start to bring more low-field systems that can produce high-quality images?