Learning MRI k-Space Subsampling Pattern Using Progressive Weight Pruning

Xuan, Kai; Sun, Shanhui; Zhang, Xue; Wang, Qian; Liao, Shu

doi:10.1007/978-3-030-59713-9_18

Cited by 14 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dataset Description: We use two datasets for our experiments: 1) fastMRI [190] -following [189], we filter out 227 and 24 pairs of proton density (PD) and fat suppressed proton density weighted images (FS-PDWI) volumes for training and validation.…”

Section: Experiments and Resultsmentioning

confidence: 99%

Improved Super Resolution of MR Images Using CNNs and Vision Transformers

Mahapatra¹

2022

Preprint

View full text Add to dashboard Cite

State of the art magnetic resonance (MR) image super-resolution methods (ISR) using convolutional neural networks (CNNs) leverage limited contextual information due to the limited spatial coverage of CNNs. Vision transformers (ViT) learn better global context that is helpful in generating superior quality HR images. We combine local information of CNNs and global information from ViTs for image super resolution and output super resolved images that have superior quality than those produced by state of the art methods. We include extra constraints through multiple novel loss functions that preserve structure and texture information from the low resolution to high resolution images.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Improved Super Resolution of MR Images Using CNNs and Vision Transformers

Mahapatra¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Datasets and Baselines 1) Datasets: We use two raw MR image datasets to evaluate our method: (1) fastMRI [50] is the largest open-access raw MR image dataset, officially provided at https:// fastmri.med.nyu.edu/. Following [9], we filter out 227 and 24 pairs of PDWI and FS-PDWI knee volumes for training and validation. PDWIs are used to guide the restoration of the FS-PDWI modality.…”

Section: Methodsmentioning

confidence: 99%

“…1, (a) and (b) are a pair of T1W and T2W brain MR images from the same subject of a real-world clinical dataset, where (a) provides morphological and structural information, and (b) shows edema and inflammation. Following [9], we filter out pairs of PDW and FS-PDW images from fastMRI (currently the largest available database for raw MR images), as shown in Fig. 1 (c) and (d).…”

Section: Introductionmentioning

confidence: 99%

Multi-Modal Transformer for Accelerated MR Imaging

Feng¹,

Yan²,

Chen³

et al. 2021

Preprint

View full text Add to dashboard Cite

Accelerated multi-modal magnetic resonance (MR) imaging is a new and effective solution for fast MR imaging, providing superior performance in restoring the target modality from its undersampled counterpart with guidance from an auxiliary modality. However, existing works simply combine the auxiliary modality as prior information, lacking in-depth investigations on the potential mechanisms for fusing different modalities. Further, they usually rely on the convolutional neural networks (CNNs), which is limited by the intrinsic locality in capturing the long-distance dependency. To this end, we propose a multimodal transformer (MTrans), which is capable of transferring multi-scale features from the target modality to the auxiliary modality, for accelerated MR imaging. To capture deep multi-modal information, our MTrans utilizes an improved multi-head attention mechanism, named cross attention module, which absorbs features from the auxiliary modality that contribute to the target modality. Our framework provides three appealing benefits: (i) Our MTrans is the first attempt at using improved transformers for multimodal MR imaging, affording more global information compared with existing CNN-based methods. (ii) A new cross attention module is proposed to exploit the useful information in each modality at different scales. It affords both distinct structural information and subtle pixel-level information, which supplement the target modality effectively. (iii) We evaluate MTrans with various accelerated multimodal MR imaging tasks, e.g., MR image reconstruction and super-resolution, where MTrans outperforms state-ofthe-art methods on fastMRI and real-world clinical datasets.

show abstract

“…We evaluate our approach on three datasets: 1) fastMRI [20] is the largest open-access MRI dataset. Following [19], we filter out 227 and 24 pairs of PD and FS-PDWI volumes for training and validation.…”

Section: Methodsmentioning

confidence: 99%

Multi-Contrast MRI Super-Resolution via a Multi-Stage Integration Network

Feng¹,

Fu²,

Yuan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Super-resolution (SR) plays a crucial role in improving the image quality of magnetic resonance imaging (MRI). MRI produces multicontrast images and can provide a clear display of soft tissues. However, current super-resolution methods only employ a single contrast, or use a simple multi-contrast fusion mechanism, ignoring the rich relations among different contrasts, which are valuable for improving SR. In this work, we propose a multi-stage integration network (i.e., MINet) for multi-contrast MRI SR, which explicitly models the dependencies between multi-contrast images at different stages to guide image SR. In particular, our MINet first learns a hierarchical feature representation from multiple convolutional stages for each of different-contrast image. Subsequently, we introduce a multi-stage integration module to mine the comprehensive relations between the representations of the multicontrast images. Specifically, the module matches each representation with all other features, which are integrated in terms of their similarities to obtain an enriched representation. Extensive experiments on fastMRI and real-world clinical datasets demonstrate that 1) our MINet outperforms state-of-the-art multi-contrast SR methods in terms of various metrics and 2) our multi-stage integration module is able to excavate complex interactions among multi-contrast features at different stages, leading to improved target-image quality.

show abstract

Learning MRI k-Space Subsampling Pattern Using Progressive Weight Pruning

Cited by 14 publications

References 19 publications

Improved Super Resolution of MR Images Using CNNs and Vision Transformers

Improved Super Resolution of MR Images Using CNNs and Vision Transformers

Multi-Modal Transformer for Accelerated MR Imaging

Multi-Contrast MRI Super-Resolution via a Multi-Stage Integration Network

Contact Info

Product

Resources

About