Deep Unfolding Convolutional Dictionary Model for Multi-Contrast MRI Super-resolution and Reconstruction

TL;DR

This paper introduces a deep unfolding convolutional dictionary model for multi-contrast MRI super-resolution and reconstruction, explicitly modeling shared and unique features to improve performance over existing methods.

Contribution

It proposes a novel multi-contrast convolutional dictionary model guided by optimization algorithms, with learnable proximal operators and multi-scale dictionaries for enhanced MRI reconstruction.

Findings

Outperforms state-of-the-art methods in MRI super-resolution and reconstruction

Effectively models shared and unique features across contrasts

Demonstrates superior quantitative and qualitative results

Abstract

Magnetic resonance imaging (MRI) tasks often involve multiple contrasts. Recently, numerous deep learning-based multi-contrast MRI super-resolution (SR) and reconstruction methods have been proposed to explore the complementary information from the multi-contrast images. However, these methods either construct parameter-sharing networks or manually design fusion rules, failing to accurately model the correlations between multi-contrast images and lacking certain interpretations. In this paper, we propose a multi-contrast convolutional dictionary (MC-CDic) model under the guidance of the optimization algorithm with a well-designed data fidelity term. Specifically, we bulid an observation model for the multi-contrast MR images to explicitly model the multi-contrast images as common features and unique features. In this way, only the useful information in the reference image can be transferred to the target image, while the inconsistent information will be ignored. We employ the proximal gradient algorithm to optimize the model and unroll the iterative steps into a deep CDic model. Especially, the proximal operators are replaced by learnable ResNet. In addition, multi-scale dictionaries are introduced to further improve the model performance. We test our MC-CDic model on multi-contrast MRI SR and reconstruction tasks. Experimental results demonstrate the superior performance of the proposed MC-CDic model against existing SOTA methods. Code is available at https://github.com/lpcccc-cv/MC-CDic.