2021年5月19日 · Super-resolution (SR) plays a crucial role in improving the image quality of magnetic resonance imaging (MRI). MRI produces multi-contrast images and can provide a clear display of soft tissues.

2023年10月1日 · In this study, we propose a Dual Cross-Attention Multi-contrast Super Resolution (DCAMSR) framework for improving the spatial resolution of MRI images. As demonstrated by extensive experiments, the proposed method outperforms existing state-of-the-art techniques under various conditions, proving a powerful and flexible solution that can benefit ...

Multi-contrast MRI super-resolution (MCSR) involves us-ing multiple contrasts of MR images in the SR process. Specifically, MCSR utilizes T1 contrast images with shorter repetition time and echo time as reference images to pro-vide valuable high-frequency information during SR for T2 contrast images with longer scan times.

2023年3月27日 · Trained within minutes on a single commodity GPU, our model provides realistic super-resolution across different pairs of contrasts in our experiments with three datasets. Using Mutual Information (MI) as a metric, we find that our model converges to an optimum MI amongst sequences, achieving anatomically faithful reconstruction.

Our experimental results demonstrate that 1) the proposed networks can produce MRI super-resolution images with good image quality and outperform other multi-contrast super-resolution methods in terms of structural similarity and peak signal-to-noise ratio; 2) combining multi-contrast information in a high-level feature space leads to a ...

This study proposes a novel multi-contrast MRI SR method to establish longer-range dependencies in MR im-ages and provide suficient complementary information for the target LR image via a rectangle-window cross-attention transformer and achieve arbitrary-scale super-resolution by harnessing reference-aware implicit attention.

2023年7月5日 · 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.

2025年1月1日 · By utilizing the auxiliary information from reference images (Refs) in the easy-to-obtain modality, multi-contrast MRI super-resolution (SR) methods can synthesize high-resolution (HR) images from their low-resolution (LR) counterparts in the hard-to-obtain modality.

2023年10月1日 · Trained within minutes on a single commodity GPU, our model provides realistic super-resolution across different pairs of contrasts in our experiments with three datasets. Using Mutual Information (MI) as a metric, we find that our model converges to an optimum MI amongst sequences, achieving anatomically faithful reconstruction.

2021年9月21日 · We have proposed a multi-stage integration network for multi-contrast MRI super-resolution, with the aim of effectively restoring the target-contrast image with guidance from a complementary contrast.