A Review of Deep Learning Methods for Compressed Sensing Image Reconstruction and Its Medical Applications

Xie, Yutong; Li, Quanzheng

doi:10.3390/electronics11040586

Cited by 19 publications

(13 citation statements)

References 155 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The appearance of some false-positive fibers, especially in the fornix, can partially be controlled by the addition of exclusion ROIs. For AF=4 and both CS approaches, further adjustment of tractography parameters, use of deep-learning-based versions of CS [43][44][45][46] , and possibly introducing priors 47,48 could help improve the reconstruction, but they have not yet been applied to preclinical data. To allow comparisons with other reconstruction methods, the data acquired in this study have been made available.…”

Section: Discussionmentioning

confidence: 99%

Evaluation of Kernel Low-Rank Compressed Sensing in preclinical Diffusion Magnetic Resonance Imaging

Souza

Mathieu

Deloulme

et al. 2023

Preprint

View full text Add to dashboard Cite

Compressed Sensing (CS) is widely used to accelerate clinical diffusion MRI acquisitions, but it remains under-utilized in preclinical settings. In this study, we optimized and compared several CS reconstruction methods for diffusion imaging. Different undersampling patterns and two reconstruction approaches were evaluated: conventional CS, based on Berkeley Advanced Reconstruction Toolbox (BART-CS) toolbox, and a new Kernel Low-Rank (KLR)-CS, based on Kernel Principal Component Analysis and low-resolution-phase maps. 3D CS acquisitions were performed at 9.4T using a 4-element cryocoil on mice (wild type and a MAP6 knockout). Comparison metrics were error and Structural Similarity Index Measure (SSIM) on fractional anisotropy (FA) and mean diffusivity (MD) as well as reconstructions of anterior commissure and fornix. Acceleration factors (AF) up to 6 were considered. In case of retrospective undersampling, the proposed KLR-CS outperformed BART-CS up to AF=6 for FA and MD maps and for tractography. For instance, for AF=4, the maximum errors were respectively 8.0% for BART-CS and 4.9% for KLR-CS, considering both FA and MD in the corpus callosum. In case of undersampled acquisitions, these maximum errors became respectively 10.5% for BART-CS and 7.0% for KLR-CS. This difference between simulations and acquisitions arose mainly from repetition noise, but also from differences in resonance frequency drift, signal-to-noise ratio, and in reconstruction noise. Despite this increased error, fully sampled and AF=2 yielded comparable results for FA, MD and tractography, and AF=4 showed minor faults. Altogether, KLR-CS based on low-resolution-phase maps seems a robust approach to accelerate preclinical diffusion MRI.

show abstract

Section: Discussionmentioning

confidence: 99%

Evaluation of Kernel Low-Rank Compressed Sensing in preclinical Diffusion Magnetic Resonance Imaging

Souza

Mathieu

Deloulme

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…(3) Machine learning is adopted to optimize the measurement matrix and reconstruction algorithm of CSSPI at the same time to achieve the best match, which is expected to strike a balance between measurement efficiency and imaging quality. There have been some efforts to use machine learning algorithms to improve the performance of CS, which shows the strong impact of machine learning on CS [ 87 , 171 , 172 , 173 , 174 ].…”

Section: Discussionmentioning

confidence: 99%

Comparison of Common Algorithms for Single-Pixel Imaging via Compressed Sensing

Zhao

Gao

Zhai

et al. 2023

Sensors

View full text Add to dashboard Cite

Single-pixel imaging (SPI) uses a single-pixel detector instead of a detector array with a lot of pixels in traditional imaging techniques to realize two-dimensional or even multi-dimensional imaging. For SPI using compressed sensing, the target to be imaged is illuminated by a series of patterns with spatial resolution, and then the reflected or transmitted intensity is compressively sampled by the single-pixel detector to reconstruct the target image while breaking the limitation of the Nyquist sampling theorem. Recently, in the area of signal processing using compressed sensing, many measurement matrices as well as reconstruction algorithms have been proposed. It is necessary to explore the application of these methods in SPI. Therefore, this paper reviews the concept of compressive sensing SPI and summarizes the main measurement matrices and reconstruction algorithms in compressive sensing. Further, the performance of their applications in SPI through simulations and experiments is explored in detail, and then their advantages and disadvantages are summarized. Finally, the prospect of compressive sensing with SPI is discussed.

show abstract

“…The appearance of some falsepositive fibers, especially in the fornix, can partially be controlled by the addition of exclusion ROIs. For AF = 4 and both CS approaches, further adjustment of tractography parameters, use of deep-learning-based versions of CS (Cao et al, 2020;Dar et al, 2020;Baul et al, 2021;Xie and Li, 2022), and possibly introducing priors (Güngör et al, 2022;Korkmaz et al, 2022) could help improve the reconstruction, but they have not yet been applied to preclinical data. To allow comparisons with other reconstruction methods, the data acquired in this study have been made available.…”

Section: Discussionmentioning

confidence: 99%

Evaluation of kernel low-rank compressed sensing in preclinical diffusion magnetic resonance imaging

et al. 2023

View full text Add to dashboard Cite

Compressed sensing (CS) is widely used to accelerate clinical diffusion MRI acquisitions, but it is not widely used in preclinical settings yet. In this study, we optimized and compared several CS reconstruction methods for diffusion imaging. Different undersampling patterns and two reconstruction approaches were evaluated: conventional CS, based on Berkeley Advanced Reconstruction Toolbox (BART-CS) toolbox, and a new kernel low-rank (KLR)-CS, based on kernel principal component analysis and low-resolution-phase (LRP) maps. 3D CS acquisitions were performed at 9.4T using a 4-element cryocoil on mice (wild type and a MAP6 knockout). Comparison metrics were error and structural similarity index measure (SSIM) on fractional anisotropy (FA) and mean diffusivity (MD), as well as reconstructions of the anterior commissure and fornix. Acceleration factors (AF) up to 6 were considered. In the case of retrospective undersampling, the proposed KLR-CS outperformed BART-CS up to AF = 6 for FA and MD maps and tractography. For instance, for AF = 4, the maximum errors were, respectively, 8.0% for BART-CS and 4.9% for KLR-CS, considering both FA and MD in the corpus callosum. Regarding undersampled acquisitions, these maximum errors became, respectively, 10.5% for BART-CS and 7.0% for KLR-CS. This difference between simulations and acquisitions arose mainly from repetition noise, but also from differences in resonance frequency drift, signal-to-noise ratio, and in reconstruction noise. Despite this increased error, fully sampled and AF = 2 yielded comparable results for FA, MD and tractography, and AF = 4 showed minor faults. Altogether, KLR-CS based on LRP maps seems a robust approach to accelerate preclinical diffusion MRI and thereby limit the effect of the frequency drift.

show abstract

A Review of Deep Learning Methods for Compressed Sensing Image Reconstruction and Its Medical Applications

Cited by 19 publications

References 155 publications

Evaluation of Kernel Low-Rank Compressed Sensing in preclinical Diffusion Magnetic Resonance Imaging

Evaluation of Kernel Low-Rank Compressed Sensing in preclinical Diffusion Magnetic Resonance Imaging

Comparison of Common Algorithms for Single-Pixel Imaging via Compressed Sensing

Evaluation of kernel low-rank compressed sensing in preclinical diffusion magnetic resonance imaging

Contact Info

Product

Resources

About