Cardiac magnetic resonance (CMR) is an essential clinical tool for the assessment of cardiovascular disease. Deep learning (DL) has recently revolutionized the field through image reconstruction techniques that allow unprecedented data undersampling rates. These fast acquisitions have the potential to considerably impact the diagnosis and treatment of cardiovascular disease. Herein, we provide a comprehensive review of DL-based reconstruction methods for CMR. We place special emphasis on state-of-the-art unrolled networks, which are heavily based on a conventional image reconstruction framework. We review the main DL-based methods and connect them to the relevant conventional reconstruction theory. Next, we review several methods developed to tackle specific challenges that arise from the characteristics of CMR data. Then, we focus on DL-based methods developed for specific CMR applications, including flow imaging, late gadolinium enhancement, and quantitative tissue characterization. Finally, we discuss the pitfalls and future outlook of DL-based reconstructions in CMR, focusing on the robustness, interpretability, clinical deployment, and potential for new methods.

Purpose: The aim of this work is to shed light on the issue of reproducibility in MR image reconstruction in the context of a challenge. Participants had to recreate the results of “Advances in sensitivity encoding with arbitrary k‐space trajectories" by Pruessmann et al.Methods: The task of the challenge was to reconstruct radially acquired multicoil k‐space data (brain/heart) following the method in the original paper, reproducing its key figures. Results were compared to consolidated reference implementations created after the challenge, accounting for the two most common programming languages used in the submissions (Matlab/Python).Results: Visually, differences between submissions were small. Pixel‐wise differences originated from image orientation, assumed field‐of‐view, or resolution. The reference implementations were in good agreement, both visually and in terms of image similarity metrics.Discussion and Conclusion: While the description level of the published algorithm enabled participants to reproduce CG‐SENSE in general, details of the implementation varied, for example, density compensation or Tikhonov regularization. Implicit assumptions about the data lead to further differences, emphasizing the importance of sufficient metadata accompanying open datasets. Defining reproducibility quantitatively turned out to be nontrivial for this image reconstruction challenge, in the absence of ground‐truth results. Typical similarity measures like NMSE of SSIM were misled by image intensity scaling and outlier pixels. Thus, to facilitate reproducibility, researchers are encouraged to publish code and data alongside the original paper. Future methodological papers on MR image reconstruction might benefit from the consolidated reference implementations of CG‐SENSE presented here, as a benchmark for methods comparison.

While multiple cardiovascular magnetic resonance (CMR) methods provide excellent reproducibility of global circumferential and global longitudinal strain, achieving highly reproducible segmental strain is more challenging. Previous single-center studies have demonstrated excellent reproducibility of displacement encoding with stimulated echoes (DENSE) segmental circumferential strain. The present study evaluated the reproducibility of DENSE for measurement of whole-slice or global circumferential (Ecc), longitudinal (Ell) and radial (Err) strain, torsion, and segmental Ecc at multiple centers. Six centers participated and a total of 81 subjects were studied, including 60 healthy subjects and 21 patients with various types of heart disease. CMR utilized 3 T scanners, and cine DENSE images were acquired in three short-axis planes and in the four-chamber long-axis view. During one imaging session, each subject underwent two separate DENSE scans to assess inter-scan reproducibility. Each subject was taken out of the scanner and repositioned between the scans. Intra-user, inter-user-same-site, inter-user-different-site, and inter-user-Human-Deep-Learning (DL) comparisons assessed the reproducibility of different users analyzing the same data. Inter-scan comparisons assessed the reproducibility of DENSE from scan to scan. The reproducibility of whole-slice or global Ecc, Ell and Err, torsion, and segmental Ecc were quantified using Bland–Altman analysis, the coefficient of variation (CV), and the intraclass correlation coefficient (ICC). CV was considered excellent for CV ≤ 10%, good for 10% < CV ≤ 20%, fair for 20% < CV ≤ 40%, and poor for CV > 40. ICC values were considered excellent for ICC > 0.74, good for ICC 0.6 < ICC ≤ 0.74, fair for ICC 0.4 < ICC ≤ 0.59, poor for ICC < 0.4. Based on CV and ICC, segmental Ecc provided excellent intra-user, inter-user-same-site, inter-user-different-site, inter-user-Human-DL reproducibility and good–excellent inter-scan reproducibility. Whole-slice Ecc and global Ell provided excellent intra-user, inter-user-same-site, inter-user-different-site, inter-user-Human-DL and inter-scan reproducibility. The reproducibility of torsion was good–excellent for all comparisons. For whole-slice Err, CV was in the fair-good range, and ICC was in the good–excellent range. Multicenter data show that 3 T CMR DENSE provides highly reproducible whole-slice and segmental Ecc, global Ell, and torsion measurements in healthy subjects and heart disease patients.

Purpose: To introduce and demonstrate a software library for time‐optimal gradient waveform optimization with a wide range of applications. The software enables direct on‐the‐fly gradient waveform design on the scanner hardware for multiple vendors.Methods: The open‐source gradient optimization (GrOpt) toolbox was implemented in C with both Matlab and Python wrappers. The toolbox enables gradient waveforms to be generated based on a set of constraints that define the features and encodings for a given acquisition. The GrOpt optimization routine is based on the alternating direction method of multipliers (ADMM). Additional constraints enable error corrections to be added, or patient comfort and safety to be adressed. A range of applications and compute speed metrics are analyzed. Finally, the method is implemented and tested on scanners from different vendors.Results: Time‐optimal gradient waveforms for different pulse sequences and the constraints that define them are shown. Additionally, the ability to add, arbitrary motion (gradient moment) compensation or limit peripheral nerve stimulation is demonstrated. There exists a trade‐off between computation time and gradient raster time, but it was observed that acceptable gradient waveforms could be generated in 1‐40 ms. Gradient waveforms generated and run on the different scanners were functionally equivalent, and the images were comparable.Conclusions: GrOpt is an open source toolbox that enables on‐the‐fly optimization of gradient waveform design, subject to a set of defined constraints. GrOpt was presented for a range of imaging applications, analyzed in terms of computational complexity, and implemented to run on the scanner for a multi‐vendor demonstration.