Published on Sat Jun 12 2021

Task Transformer Network for Joint MRI Reconstruction and Super-Resolution

Chun-Mei Feng, Yunlu Yan, Huazhu Fu, Li Chen, Yong Xu

The core problem of Magnetic Resonance Imaging (MRI) is the trade off between accelerating and image quality. Current methods are designed to perform these tasks separately, ignoring the correlations between them. We propose an end-to-end task transformer network for joint MRI reconstruction and super-resolution.

0
0
0
Abstract

The core problem of Magnetic Resonance Imaging (MRI) is the trade off between acceleration and image quality. Image reconstruction and super-resolution are two crucial techniques in Magnetic Resonance Imaging (MRI). Current methods are designed to perform these tasks separately, ignoring the correlations between them. In this work, we propose an end-to-end task transformer network (TNet) for joint MRI reconstruction and super-resolution, which allows representations and feature transmission to be shared between multiple task to achieve higher-quality, super-resolved and motion-artifacts-free images from highly undersampled and degenerated MRI data. Our framework combines both reconstruction and super-resolution, divided into two sub-branches, whose features are expressed as queries and keys. Specifically, we encourage joint feature learning between the two tasks, thereby transferring accurate task information. We first use two separate CNN branches to extract task-specific features. Then, a task transformer module is designed to embed and synthesize the relevance between the two tasks. Experimental results show that our multi-task model significantly outperforms advanced sequential methods, both quantitatively and qualitatively.

Fri Jul 12 2019
Computer Vision
Coupled-Projection Residual Network for MRI Super-Resolution
Magnetic Resonance Imaging (MRI) has been widely used in clinical application and pathology research by helping doctors make more accurate diagnoses. Improving MRI image quality and resolution is a critically important task. This paper presents an innovative Coupled-Projection Residual Network (CPRN) for MRI super-resolution.
0
0
0
Sun Jun 27 2021
Computer Vision
MTrans: Multi-Modal Transformer for Accelerated MR Imaging
Accelerating multi-modal magnetic resonance (MR) imaging is a new solution for fast MR imaging, providing superior performance in restoring the target modality from its undersampled counterpart. However, existing works simply introduce the auxiliary modality as prior information, lacking in-depth investigations on the potential mechanisms for fusing two modalities.
0
0
0
Thu May 06 2021
Computer Vision
Deep Learning based Multi-modal Computing with Feature Disentanglement for MRI Image Synthesis
The proposed method could be effective in prediction of target MRI sequences, and useful for clinical diagnosis and treatment. The experimental results demonstrate our approach significantly outperforms the benchmark method and other state-of-the-art medical image synthesis methods.
0
0
0
Mon Aug 09 2021
Computer Vision
FA-GAN: Fused Attentive Generative Adversarial Networks for MRI Image Super-Resolution
A framework called the Fused Attentive Generative Adversarial Networks(FA-GAN) is proposed to generate the super-resolution MR image from low-resolution images. 40 sets of 3D magnetic resonance images are used to train the network.
0
0
0
Tue Sep 24 2019
Machine Learning
IFR-Net: Iterative Feature Refinement Network for Compressed Sensing MRI
The proposed IFR-CS still has some limitations, such as the selection of hyper-parameters, a lengthy reconstruction time, and the fixed sparsifying transform. To alleviate these issues, we unroll the iterative feature refinement procedures to a supervised model-driven network.
0
0
0
Mon Jun 22 2020
Computer Vision
Semantic Features Aided Multi-Scale Reconstruction of Inter-Modality Magnetic Resonance Images
Long acquisition time (AQT) due to series acquisition of multi-modality MR images is undesirable for disease diagnosis. We propose a deep network based solution to reconstruct T2W images from T1W images using an encoder-decoder architecture.
0
0
0
Wed Mar 28 2018
Computer Vision
End-to-End Multi-Task Learning with Attention
The Multi-Task Attention Network (MTAN) consists of a single shared network containing a global feature pool, together with a soft-attention module for each task. We show that our architecture is state-of-the-art in multi-task learning compared to existing methods.
1
3
13
Mon Jul 10 2017
Computer Vision
Enhanced Deep Residual Networks for Single Image Super-Resolution
The proposed methods show superior performance over the state-of-the-art methods on benchmark datasets. The proposed methods won the NTIRE2017 Super-Resolution Challenge.
0
0
0
Wed May 19 2021
Computer Vision
Multi-Contrast MRI Super-Resolution via a Multi-Stage Integration Network
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. Current super-resolution methods only employ a single contrast, ignoring the rich relations among different contrasts.
0
0
0
Wed May 12 2021
Computer Vision
DONet: Dual-Octave Network for Fast MR Image Reconstruction
0
0
0
Sat Jul 06 2019
Machine Learning
MRI Super-Resolution with Ensemble Learning and Complementary Priors
Magnetic resonance imaging (MRI) is a widely used medical imaging modality. It is often clinically challenging to obtain high-quality MR images. The super-resolution approach is potentially promising to improve MR image quality.
0
0
0
Fri Apr 28 2017
Computer Vision
Image reconstruction by domain transform manifold learning
Image reconstruction plays a critical role in the implementation of all contemporary imaging modalities includingoptical, MRI, CT, PET, and radio astronomy. We present a unified framework for image reconstruction, AUtomated TransfOrm by Manifold APproximation (AUTOMAP)
0
0
0