DIMENSION: Dynamic MR imaging with both k‐space and spatial prior knowledge obtained via multi‐supervised network training

Wang, Rongpin; Ke, Ziwen; Cheng, Huitao; Jia, Sen; Ying, Leslie; Zheng, Hairong; Liang, Dong

doi:10.1002/nbm.4131

Cited by 94 publications

(84 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, a technique that combines DL for k-space interpolation and image dealiazing for retrospectively undersampled 2D cardiac cine MRI has been proposed (81). This approach consists of a first frequency domain network architecture for k-space data interpolation followed by a concatenated image domain network architecture for image dealiazing.…”

Section: Techniques For K-space Based Cmr Reconstructionmentioning

confidence: 99%

From Compressed-Sensing to Artificial Intelligence-Based Cardiac MRI Reconstruction

Bustin

Fuin

Botnar

et al. 2020

Front. Cardiovasc. Med.

102

View full text Add to dashboard Cite

Cardiac magnetic resonance (CMR) imaging is an important tool for the non-invasive assessment of cardiovascular disease. However, CMR suffers from long acquisition times due to the need of obtaining images with high temporal and spatial resolution, different contrasts, and/or whole-heart coverage. In addition, both cardiac and respiratory-induced motion of the heart during the acquisition need to be accounted for, further increasing the scan time. Several undersampling reconstruction techniques have been proposed during the last decades to speed up CMR acquisition. These techniques rely on acquiring less data than needed and estimating the non-acquired data exploiting some sort of prior information. Parallel imaging and compressed sensing undersampling reconstruction techniques have revolutionized the field, enabling 2-to 3-fold scan time accelerations to become standard in clinical practice. Recent scientific advances in CMR reconstruction hinge on the thriving field of artificial intelligence. Machine learning reconstruction approaches have been recently proposed to learn the non-linear optimization process employed in CMR reconstruction. Unlike analytical methods for which the reconstruction problem is explicitly defined into the optimization process, machine learning techniques make use of large data sets to learn the key reconstruction parameters and priors. In particular, deep learning techniques promise to use deep neural networks (DNN) to learn the reconstruction process from existing datasets in advance, providing a fast and efficient reconstruction that can be applied to all newly acquired data. However, before machine learning and DNN can realize their full potentials and enter widespread clinical routine for CMR image reconstruction, there are several technical hurdles that need to be addressed. In this article, we provide an overview of the recent developments in the area of artificial intelligence for CMR image reconstruction. The underlying assumptions of established techniques such as compressed sensing and low-rank reconstruction are briefly summarized, while a greater focus is given to recent advances in dictionary learning and deep learning based CMR reconstruction. In particular, approaches that exploit neural networks as implicit or explicit priors are discussed for 2D dynamic cardiac imaging and 3D whole-heart CMR imaging. Current limitations, challenges, and potential future directions of these techniques are also discussed.

show abstract

Section: Techniques For K-space Based Cmr Reconstructionmentioning

confidence: 99%

From Compressed-Sensing to Artificial Intelligence-Based Cardiac MRI Reconstruction

Bustin

Fuin

Botnar

et al. 2020

Front. Cardiovasc. Med.

102

View full text Add to dashboard Cite

show abstract

“…Compared with traditional methods, DL-based methods do not require enormous amounts of prior information. The DL-based method for fast MRI acquisition can be classified into four categories 23 : (1) Denoising acquired MRI images in the image domain 24,25 , (2) Updating both k-space domain and image domain using cascaded DL [26][27][28][29] , (3) Direct conversion of k-space data to image domain data through DL 30 , and (4) Interpolation of missing k-space data through DL and obtaining images through inverse Fourier transform 23 . Our study falls under category (1), which attempts to denoise the images in the post-processing steps.…”

Section: Related Workmentioning

confidence: 99%

Deep-learning-based image quality enhancement of compressed sensing magnetic resonance imaging of vessel wall: comparison of self-supervised and unsupervised approaches

Eun

Jang

et al. 2020

Sci Rep

View full text Add to dashboard Cite

While high-resolution proton density-weighted magnetic resonance imaging (MRI) of intracranial vessel walls is significant for a precise diagnosis of intracranial artery disease, its long acquisition time is a clinical burden. Compressed sensing MRI is a prospective technology with acceleration factors that could potentially reduce the scan time. However, high acceleration factors result in degraded image quality. Although recent advances in deep-learning-based image restoration algorithms can alleviate this problem, clinical image pairs used in deep learning training typically do not align pixel-wise. Therefore, in this study, two different deep-learning-based denoising algorithms-self-supervised learning and unsupervised learning-are proposed; these algorithms are applicable to clinical datasets that are not aligned pixel-wise. The two approaches are compared quantitatively and qualitatively. Both methods produced promising results in terms of image denoising and visual grading. While the image noise and signal-to-noise ratio of self-supervised learning were superior to those of unsupervised learning, unsupervised learning was preferable over self-supervised learning in terms of radiomic feature reproducibility.

show abstract

“…For zero-padded MNIST, CIFAR-10, and zero-padded Fashion-MNIST, which has image size of 32 × 32, the numbers of CS measurements selected for training are: for 4-MR training, m = [10,51,102,256], for 6-MR training, m = [10,20,51,102,150,256]; for 10-MR training, m = [10,18,26,34,42,51,75,102,180,256]; for 50-MR training, m starts from 10 with an increment of 5 until 250, plus 256. For COIL-100 which has 128 × 128 images, the same corresponding MRs are selected.…”

Section: B Training Detailsmentioning

confidence: 99%

Compressed Domain Image Classification Using a Dynamic-Rate Neural Network

Liu

Kelly

2020

IEEE Access

View full text Add to dashboard Cite

Compressed domain image classification performs classification directly on compressive measurements acquired from the single-pixel camera, bypassing the image reconstruction step. It is of great importance for extending high-speed object detection and classification beyond the visible spectrum in a cost-effective manner especially for resource-limited platforms. Previous neural network methods require training a dedicated neural network for each different measurement rate (MR), which is costly in computation and storage. In this work, we develop an efficient training scheme that provides a neural network with dynamic-rate property, where a single neural network is capable of classifying over any MR within the range of interest with a given sensing matrix. This training scheme uses only a few selected MRs for training and the trained neural network is valid over the full range of MRs of interest. We demonstrate the performance of the dynamic-rate neural network on datasets of MNIST, CIFAR-10, Fashion-MNIST, COIL-100, and show that it generates approximately equal performance at each MR as that of a single-rate neural network valid only for one MR. Robustness to noise of the dynamic-rate model is also demonstrated. The dynamic-rate training scheme can be regarded as a general approach compatible with different types of sensing matrices, various neural network architectures, and is a valuable step towards wider adoption of compressive inference techniques and other compressive sensing related tasks via neural networks.

show abstract

DIMENSION: Dynamic MR imaging with both k‐space and spatial prior knowledge obtained via multi‐supervised network training

Cited by 94 publications

References 38 publications

From Compressed-Sensing to Artificial Intelligence-Based Cardiac MRI Reconstruction

From Compressed-Sensing to Artificial Intelligence-Based Cardiac MRI Reconstruction

Deep-learning-based image quality enhancement of compressed sensing magnetic resonance imaging of vessel wall: comparison of self-supervised and unsupervised approaches

Compressed Domain Image Classification Using a Dynamic-Rate Neural Network

Contact Info

Product

Resources

About