CS-GAN for High-Quality Diffusion Tensor Imaging

Cao, Ying; Wang, Lihui; Huang, Jianping; Cheng, Xinyu; Zhang, Jian; Yang, Feng; Zhang, Pengpeng; Yang, Jie; Yueming, Zhu

doi:10.21203/rs.3.rs-65572/v1

Cited by 4 publications

(4 citation statements)

References 36 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

“…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

“…Another approach involves reconstructing DW images or DTI parameter maps from undersampled k-space data using compressed sensing (CS) 12,13 or deep learning methods. [14][15][16][17][18][19][20][21] Wu et al 14 investigated the feasibility and effectiveness of distributed CS for accelerating DTI employing the joint sparse prior in DW images. Ma et al 15 integrated low-rank and sparsity constraints to accelerate cardiac diffusion tensor imaging.…”

Section: Introductionmentioning

confidence: 99%

“…Schlemper et al 19 conducted the first cDTI reconstruction study employing a CS-based deep cascaded CNN model. Cao et al 20 proposed a GAN-based approach to address the de-aliasing issue in CS-DTI with highly undersampled k-space data. In addition, Huang et al 21 In this study, we proposed a cDTI reconstruction method based on octave convolution (OctConv) 28 and Swin Transformer.…”

Section: Introductionmentioning

confidence: 99%

Accelerating cardiac diffusion tensor imaging using Swin transformer with octave convolution

Li,

Mo,

Wang

et al. 2024

Int J Imaging Syst Tech

Self Cite

View full text Add to dashboard Cite

Cardiac diffusion tensor imaging (cDTI) is a promising and noninvasive magnetic resonance imaging (MRI) technique for assessing myocardial fiber microstructure. However, its clinical application is hampered by lengthy scanning and susceptibility to motion artifacts. This study proposes a cDTI reconstruction model (OSDTI), which leverages octave convolution (OctConv) and Swin Transformer to reconstruct diffusion‐weighted (DW) images from undersampled k‐space data. Our model capitalizes on the strengths of both OctConv and Swin Transformers. Specifically, the OctConv module excels at capturing intricate details and texture information within DW images, while the residual‐connected Swin Transformer module facilitates information retention across various feature extraction stages, thereby enhancing overall image comprehension and reconstruction accuracy. The evaluation of OSDTI using a human ex vivo heart dataset robustly validated the generalization ability of the model. Comparative analyze against existing deep‐learning methods demonstrated OSDTI's superior performance in both DW image quality and diffusion tensor metrics.

show abstract

CS-GAN for High-Quality Diffusion Tensor Imaging

Cited by 4 publications

References 36 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

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

Accelerating cardiac diffusion tensor imaging using Swin transformer with octave convolution

Contact Info

Product

Resources

About