Unsupervised patch-based dynamic MRI reconstruction using learnable tensor function with implicit neural representation

TL;DR

This paper introduces TenF-INR, an unsupervised framework combining low-rank tensor modeling with implicit neural representations, significantly improving dynamic MRI reconstruction from highly undersampled data without external training.

Contribution

The paper proposes a novel unsupervised method that integrates learnable tensor functions with INR and patch-based nonlocal tensor modeling for efficient dynamic MRI reconstruction.

Findings

Achieves up to 21-fold acceleration in MRI imaging.

Outperforms state-of-the-art methods in image quality and accuracy.

Effectively reconstructs fine spatiotemporal details in dynamic MRI.

Abstract

Dynamic MRI suffers from limited spatiotemporal resolution due to long acquisition times. Undersampling k-space accelerates imaging but makes accurate reconstruction challenging. Supervised deep learning methods achieve impressive results but rely on large fully sampled datasets, which are difficult to obtain. Recently, implicit neural representations (INR) have emerged as a powerful unsupervised paradigm that reconstructs images from a single undersampled dataset without external training data. However, existing INR-based methods still face challenges when applied to highly undersampled dynamic MRI, mainly due to their inefficient representation capacity and high computational cost. To address these issues, we propose TenF-INR, a novel unsupervised framework that integrates low-rank tensor modeling with INR, where each factor matrix in the tensor decomposition is modeled as a learnable factor function. Specifically,we employ INR to model learnable tensor functions within a low-rank decomposition, reducing the parameter space and computational burden. A patch-based nonlocal tensor modeling strategy further exploits temporal correlations and inter-patch similarities, enhancing the recovery of fine spatiotemporal details. Experiments on dynamic cardiac and abdominal datasets demonstrate that TenF-INR achieves up to 21-fold acceleration, outperforming both supervised and unsupervised state-of-the-art methods in image quality, temporal fidelity, and quantitative accuracy.