Implicit Neural Networks with Fourier-Feature Inputs for Free-breathing Cardiac MRI Reconstruction

TL;DR

This paper introduces an implicit neural network approach with Fourier features for reconstructing free-breathing cardiac MRI, achieving high-quality images without additional patient data, though with higher computational costs.

Contribution

It presents a novel implicit neural network method with Fourier features for real-time cardiac MRI reconstruction, improving image quality over existing methods without extra patient data.

Findings

Achieves comparable or better image quality than state-of-the-art CNNs.

Outperforms recent implicit representation methods in Fourier domain.

Requires higher computational resources.

Abstract

Cardiac magnetic resonance imaging (MRI) requires reconstructing a real-time video of a beating heart from continuous highly under-sampled measurements. This task is challenging since the object to be reconstructed (the heart) is continuously changing during signal acquisition. In this paper, we propose a reconstruction approach based on representing the beating heart with an implicit neural network and fitting the network so that the representation of the heart is consistent with the measurements. The network in the form of a multi-layer perceptron with Fourier-feature inputs acts as an effective signal prior and enables adjusting the regularization strength in both the spatial and temporal dimensions of the signal. We study the proposed approach for 2D free-breathing cardiac real-time MRI in different operating regimes, i.e., for different image resolutions, slice thicknesses, and acquisition lengths. Our method achieves reconstruction quality on par with or slightly better than state-of-the-art untrained convolutional neural networks and superior image quality compared to a recent method that fits an implicit representation directly to Fourier-domain measurements. However, this comes at a relatively high computational cost. Our approach does not require any additional patient data or biosensors including electrocardiography, making it potentially applicable in a wide range of clinical scenarios.