Magnetic Resonance Image Processing Transformer for General Accelerated Image Reconstruction

TL;DR

This paper introduces MR-IPT, a transformer-based MRI reconstruction model trained on diverse datasets, which outperforms existing methods in quality and robustness across various acceleration factors and sampling patterns.

Contribution

The paper presents a unified ViT-based framework for MRI reconstruction that generalizes across multiple acceleration settings, unlike traditional models requiring separate training.

Findings

MR-IPT outperforms CNN and existing transformer methods in reconstruction quality.

It maintains high performance under unseen acquisition setups.

The model demonstrates strong robustness and adaptability across diverse sampling patterns.

Abstract

Recent advancements in deep learning have enabled the development of generalizable models that achieve state-of-the-art performance across various imaging tasks. Vision Transformer (ViT)-based architectures, in particular, have demonstrated strong feature extraction capabilities when pre-trained on large-scale datasets. In this work, we introduce the Magnetic Resonance Image Processing Transformer (MR-IPT), a ViT-based framework designed to enhance the generalizability and robustness of accelerated MRI reconstruction. Unlike conventional deep learning models that require separate training for different acceleration factors, MR-IPT is pre-trained on a large-scale dataset encompassing multiple undersampling patterns and acceleration settings, enabling a unified reconstruction framework. By leveraging a shared transformer backbone, MR-IPT effectively learns universal feature representations, allowing it to generalize across diverse reconstruction tasks. Extensive experiments demonstrate that MR-IPT outperforms both CNN-based and existing transformer-based methods, achieving superior reconstruction quality across varying acceleration factors and sampling masks. Moreover, MR-IPT exhibits strong robustness, maintaining high performance even under unseen acquisition setups, highlighting its potential as a scalable and efficient solution for accelerated MRI. Our findings suggest that transformer-based general models can significantly advance MRI reconstruction, offering improved adaptability and stability compared to traditional deep learning approaches.