Real‐time cardiac MRI using an undersampled spiral k‐space trajectory and a reconstruction based on a variational network

Abstract

Purpose Cardiac MRI represents the gold standard to determine myocardial function. However, the current clinical standard protocol, a segmented Cartesian acquisition, is time‐consuming and can lead to compromised image quality in the case of arrhythmia or dyspnea. In this article, a machine learning–based reconstruction of undersampled spiral k‐space data is presented to enable free breathing real‐time cardiac MRI with good image quality and short reconstruction times. Methods Data were acquired in free breathing with a 2D spiral trajectory corrected by the gradient system transfer function. Undersampled data were reconstructed by a variational network (VN), which was specifically adapted to the non‐Cartesian sampling pattern. The network was trained with data from 11 subjects. Subsequently, the imaging technique was validated in 14 subjects by quantifying the difference to a segmented reference acquisition, an expert reader study, and by comparing derived volumes and functional parameters with values obtained using the current clinical gold standard. Results The scan time for the entire heart was below 1 min. The VN reconstructed data in about 0.9 s per image, which is considerably shorter than conventional model‐based approaches. The VN furthermore performed better than a U‐Net and not inferior to a low‐rank plus sparse model in terms of achieved image quality. Functional parameters agreed, on average, with reference data. Conclusions The proposed VN method enables real‐time cardiac imaging with both high spatial and temporal resolution in free breathing and with short reconstruction time.

HyperSLICE: HyperBand optimized spiral for low‐latency interactive cardiac examination

“…The optimized spiral raw data were also retrospectively reconstructed using (1) a simple gridded reconstruction (the equivalent to the input to the network); (2) navigator‐less spiral SToRM, 27 which is a state‐of‐the‐art compressed‐sensing reconstruction; and (3) spiral VarNet 28 reconstruction, which is an unrolled ML network architecture including data consistency. The gridded, SToRM, and VarNet reconstructions were performed offline using open‐source codes 27–29 . VarNet was retrained on the same data set and same optimized trajectory as the proposed HyperSLICE network.…”

“…HyperSLICE interactive images were reconstructed in near real time during scanning using Gadgetron 26 for low‐latency communication with an external computer (Linux Workstation with NVIDIA GeForce RTX 3060 12GB, in which reconstruction times were recorded). The optimized spiral raw data were also retrospectively reconstructed using (1) a simple gridded reconstruction (the equivalent to the input to the network); (2) navigator‐less spiral SToRM, 27 which is a state‐of‐the‐art compressed‐sensing reconstruction; and (3) spiral VarNet 28 reconstruction, which is an unrolled ML network architecture including data consistency. The gridded, SToRM, and VarNet reconstructions were performed offline using open‐source codes 27–29 .…”

“…The gridded, SToRM, and VarNet reconstructions were performed offline using open-source codes. [27][28][29] VarNet was retrained on the same data set and same optimized trajectory as the proposed HyperSLICE network. The Cartesian data sets used for comparison were reconstructed on the scanner platform using the scanner software reconstructions (including GRAPPA).…”

The future of CMR: All-in-one vs. real-time CMR (Part 2)

“…Real-time imaging can also result in hundreds if not thousands of images (often obtained with unknown respiratory and ECG stage) with analysis that is not currently automated. On-the-fly real-time CMR image reconstruction may be approached by the application of dedicated graphics processing unit (GPU)-based reconstructors [111] , or the use of deep-learning techniques [112] , [113] , [117] , both successfully tested in few clinical studies, but still lacking full integration into the vendors clinical systems. For more efficient analysis of the data, synchronization with the ECG [45] and/or respiration [50] is mandatory for selecting data from the same cardiac and respiratory phase for functional quantification with available analysis packages.…”