Decoupling Multi-Contrast Super-Resolution: Self-Supervised Implicit Re-Representation for Unpaired Cross-Modal Synthesis

TL;DR

This paper introduces a novel self-supervised framework for multi-contrast super-resolution in MRI that leverages population priors and patient data without requiring paired datasets, achieving high-fidelity results at arbitrary scales.

Contribution

It proposes a decoupled, two-stage MCSR framework combining population-level priors with patient-specific data using implicit neural representations, without needing paired training data.

Findings

Outperforms existing methods on multiple datasets.

Maintains robustness at extreme upscaling factors (16x, 32x).

Operates efficiently without paired datasets or fixed scales.

Abstract

Multi-contrast super-resolution (MCSR) is crucial for enhancing MRI but current deep learning methods are limited. They typically require large, paired low- and high-resolution (LR/HR) training datasets, which are scarce, and are trained for fixed upsampling scales. While recent self-supervised methods remove the paired data requirement, they fail to leverage valuable population-level priors. In this work, we propose a novel, decoupled MCSR framework that resolves both limitations. We reformulate MCSR into two stages: (1) an unpaired cross-modal synthesis (uCMS) module, trained once on unpaired population data to learn a robust anatomical prior; and (2) a lightweight, patient-specific implicit re-representation (IrR) module. This IrR module is optimized in a self-supervised manner to fuse the population prior with the subject's own LR target data. This design uniquely fuses population-level knowledge with patient-specific fidelity without requiring any paired LR/HR or paired cross-modal training data. By building the IrR module on an implicit neural representation, our framework is also inherently scale-agnostic. Our method demonstrates superior quantitative performance on different datasets, with exceptional robustness at extreme scales (16x, 32x), a regime where competing methods fail. Our work presents a data-efficient, flexible, and computationally lightweight paradigm for MCSR, enabling high-fidelity, arbitrary-scale