Implicit Neural Representation-Based MRI Reconstruction Method with Sensitivity Map Constraints

TL;DR

This paper introduces INR-CRISTAL, a novel MRI reconstruction method that jointly estimates coil sensitivity maps and images using implicit neural representations, improving accuracy, artifact removal, and robustness at high acceleration rates.

Contribution

It proposes a joint estimation network with sensitivity map regularization, enhancing MRI reconstruction quality and robustness over existing INR-based methods.

Findings

More accurate coil sensitivity estimation with fewer artifacts

Superior reconstruction performance in artifact removal and structure preservation

Enhanced robustness to calibration signals and higher acceleration rates

Abstract

Magnetic Resonance Imaging (MRI) is a widely utilized diagnostic tool in clinical settings, but its application is limited by the relatively long acquisition time. As a result, fast MRI reconstruction has become a significant area of research. In recent years, Implicit Neural Representation (INR), as a scan-specific method, has demonstrated outstanding performance in fast MRI reconstruction without fully-sampled images for training. High acceleration reconstruction poses a challenging problem, and a key component in achieving high-quality reconstruction with much few data is the accurate estimation of coil sensitivity maps. However, most INR-based methods apply regularization constraints solely to the generated images, while overlooking the characteristics of the coil sensitivity maps. To handle this, this work proposes a joint coil sensitivity map and image estimation network, termed INR-CRISTAL. The proposed INR-CRISTAL introduces an extra sensitivity map regularization in the INR networks to make use of the smooth characteristics of the sensitivity maps. Experimental results show that INR-CRISTAL provides more accurate coil sensitivity estimates with fewer artifacts, and delivers superior reconstruction performance in terms of artifact removal and structure preservation. Moreover, INR-CRISTAL demonstrates stronger robustness to automatic calibration signals and the acceleration rate compared to existing methods.