On the Foundation Model for Cardiac MRI Reconstruction

TL;DR

This paper introduces a versatile foundation model for cardiac MRI reconstruction that adapts to various imaging parameters, improving image quality across different protocols without retraining.

Contribution

The study presents a novel foundation model utilizing adaptive unrolling, channel-shifting, and PCP-UNet with prompts, enabling flexible and high-quality MRI reconstruction across diverse settings.

Findings

Significantly improved image quality across multiple CMR protocols

Outperforms conventional ML-based reconstruction methods

Effective adaptation to different acceleration rates and sampling patterns

Abstract

In recent years, machine learning (ML) based reconstruction has been widely investigated and employed in cardiac magnetic resonance (CMR) imaging. ML-based reconstructions can deliver clinically acceptable image quality under substantially accelerated scans. ML-based reconstruction, however, also requires substantial data and computational time to train the neural network, which is often optimized for a fixed acceleration rate or image contrast. In practice, imaging parameters are often tuned to best suit the diagnosis, which may differ from the training data. This can result in degraded image quality, and multiple trained networks are needed to fulfill the clinical demands. In this study, we propose a foundation model that uses adaptive unrolling, channel-shifting, and Pattern and Contrast-Prompt-UNet (PCP-UNet) to tackle the problem. In particular, the undersampled data goes through a different number of unrolled iterations according to its acceleration rate. Channel-shifting improves reconstructed data quality. The PCP-UNet is equipped with an image contrast and sampling pattern prompt. In vivo CMR experiments were performed using mixed combinations of image contrasts, acceleration rates, and (under)sampling patterns. The proposed foundation model has significantly improved image quality for a wide range of CMR protocols and outperforms the conventional ML-based method.