Unsupervised reconstruction of accelerated cardiac cine MRI using Neural Fields

TL;DR

This paper introduces an unsupervised neural field-based method for reconstructing accelerated cardiac cine MRI from undersampled data, achieving high-quality images without large training datasets.

Contribution

The work presents a novel unsupervised neural implicit representation approach for cardiac MRI reconstruction, eliminating the need for extensive training data.

Findings

Achieved good image quality at 26x and 52x undersampling factors.

Provided comparable spatial and improved temporal depiction over existing methods.

Validated on in-vivo golden-angle radial multi-coil acquisitions.

Abstract

Cardiac cine MRI is the gold standard for cardiac functional assessment, but the inherently slow acquisition process creates the necessity of reconstruction approaches for accelerated undersampled acquisitions. Several regularization approaches that exploit spatial-temporal redundancy have been proposed to reconstruct undersampled cardiac cine MRI. More recently, methods based on supervised deep learning have been also proposed to further accelerate acquisition and reconstruction. However, these techniques rely on usually large dataset for training, which are not always available. In this work, we propose an unsupervised approach based on implicit neural field representations for cardiac cine MRI (so called NF-cMRI). The proposed method was evaluated in in-vivo undersampled golden-angle radial multi-coil acquisitions for undersampling factors of 26x and 52x, achieving good image quality, and comparable spatial and improved temporal depiction than a state-of-the-art reconstruction technique.