A novel neural network architecture, known as DL-ESPIRiT, is proposed to reconstruct rapidly acquired cardiac MRI data without field-of-view limitations which are present in previously proposed deep learning-based reconstruction frameworks. Additionally, a novel convolutional neural network based on separable 3D convolutions is integrated into DL-ESPIRiT to more efficiently learn spatiotemporal priors for dynamic image reconstruction. The network is trained on fully-sampled 2D cardiac cine datasets collected from eleven healthy volunteers with IRB approval. DL-ESPIRiT is compared against a state-of-the-art parallel imaging and compressed sensing method known as l1-ESPIRiT. The reconstruction accuracy of both methods is evaluated on retrospectively undersampled datasets (R=12) with respect to standard image quality metrics as well as automatic deep learning-based segmentations of left ventricular volumes. Feasibility of this approach is demonstrated in reconstructions of prospectively undersampled data which were acquired in a single heartbeat per slice.
@article{arxiv.1911.05845,
title = {Accelerating cardiac cine MRI using a deep learning-based ESPIRiT reconstruction},
author = {Christopher M. Sandino and Peng Lai and Shreyas S. Vasanawala and Joseph Y. Cheng},
journal= {arXiv preprint arXiv:1911.05845},
year = {2020}
}
Comments
29 pages, 9 figures, 1 table, 7 supplementary videos, Submitted to Magnetic Resonance in Medicine