Accelerating cardiac cine MRI using a deep learning-based ESPIRiT reconstruction

TL;DR

This paper introduces DL-ESPIRiT, a deep learning framework that accelerates cardiac cine MRI reconstruction by integrating novel neural network architectures, enabling high-quality images from rapid, undersampled data without field-of-view limitations.

Contribution

The paper presents DL-ESPIRiT, a new neural network architecture with separable 3D convolutions for efficient spatiotemporal learning in cardiac MRI reconstruction, outperforming existing methods.

Findings

DL-ESPIRiT achieves higher reconstruction accuracy than $l_1$-ESPIRiT.

The method effectively reconstructs prospectively undersampled data in a single heartbeat.

Deep learning-based segmentation confirms the clinical viability of the reconstructions.

Abstract

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 $l_1$-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.