A scan-specific unsupervised method for parallel MRI reconstruction via implicit neural representation

TL;DR

This paper introduces an unsupervised implicit neural representation approach for parallel MRI reconstruction, effectively reducing artifacts and noise from highly undersampled data without needing high-quality training datasets.

Contribution

It presents a novel INR-based method that models MRI images as continuous functions learned directly from undersampled k-space data, improving reconstruction quality.

Findings

Outperforms existing methods in artifact suppression

Effective at high acceleration rates

Works without fully sampled training data

Abstract

Parallel imaging is a widely-used technique to accelerate magnetic resonance imaging (MRI). However, current methods still perform poorly in reconstructing artifact-free MRI images from highly undersampled k-space data. Recently, implicit neural representation (INR) has emerged as a new deep learning paradigm for learning the internal continuity of an object. In this study, we adopted INR to parallel MRI reconstruction. The MRI image was modeled as a continuous function of spatial coordinates. This function was parameterized by a neural network and learned directly from the measured k-space itself without additional fully sampled high-quality training data. Benefitting from the powerful continuous representations provided by INR, the proposed method outperforms existing methods by suppressing the aliasing artifacts and noise, especially at higher acceleration rates and smaller sizes of the auto-calibration signals. The high-quality results and scanning specificity make the proposed method hold the potential for further accelerating the data acquisition of parallel MRI.