Dual Arbitrary Scale Super-Resolution for Multi-Contrast MRI

TL;DR

This paper introduces Dual-ArbNet, a novel neural network that enables high-quality multi-contrast MRI super-resolution at arbitrary scales, overcoming fixed-resolution limitations and improving clinical imaging flexibility.

Contribution

The proposed Dual-ArbNet employs implicit neural representations and a curriculum learning strategy to achieve arbitrary scale super-resolution for multi-contrast MRI images, a significant advancement over fixed-scale methods.

Findings

Outperforms state-of-the-art methods across various scale factors

Demonstrates strong generalization in two public MRI datasets

Shows potential for clinical application in flexible MRI imaging

Abstract

Limited by imaging systems, the reconstruction of Magnetic Resonance Imaging (MRI) images from partial measurement is essential to medical imaging research. Benefiting from the diverse and complementary information of multi-contrast MR images in different imaging modalities, multi-contrast Super-Resolution (SR) reconstruction is promising to yield SR images with higher quality. In the medical scenario, to fully visualize the lesion, radiologists are accustomed to zooming the MR images at arbitrary scales rather than using a fixed scale, as used by most MRI SR methods. In addition, existing multi-contrast MRI SR methods often require a fixed resolution for the reference image, which makes acquiring reference images difficult and imposes limitations on arbitrary scale SR tasks. To address these issues, we proposed an implicit neural representations based dual-arbitrary multi-contrast MRI super-resolution method, called Dual-ArbNet. First, we decouple the resolution of the target and reference images by a feature encoder, enabling the network to input target and reference images at arbitrary scales. Then, an implicit fusion decoder fuses the multi-contrast features and uses an Implicit Decoding Function~(IDF) to obtain the final MRI SR results. Furthermore, we introduce a curriculum learning strategy to train our network, which improves the generalization and performance of our Dual-ArbNet. Extensive experiments in two public MRI datasets demonstrate that our method outperforms state-of-the-art approaches under different scale factors and has great potential in clinical practice.