Motion artifacts reduction in brain MRI by means of a deep residual network with densely connected multi-resolution blocks (DRN-DCMB)

Liu, Junchi; Koçak, Mehmet; Supanich, Mark; Deng, Jie

doi:10.1016/j.mri.2020.05.002

Cited by 40 publications

(27 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our unique two-stage network model aimed to solve this problem by reducing major motion artifact in stage-I and then recovering structural details in stage-II. The stage-I model adopted the architecture of DRN-DCMB network, which was previously used in brain MRI and led to the best performance of motion reduction among other state-of-the-art models (16). The DRN-DCMB network utilized multi-resolution blocks to extract motion details and meanwhile maintain desirable image contrast.…”

Section: Discussionmentioning

confidence: 99%

“…To simulate periodic human respiratory cycles, sinusoidal motion patterns were generated by changing the duration, frequency and phase of the simulated sinusoidal wave (16,19,24). The new k-space [ F ( Y )] sin (i.e., [ F ( Y )] sim in Eq.1) was generated by altering the signal phase of the original K-space F ( Y ), defined as follows: , where ∅( k ) denotes the phase shift error added to a given K-space line k along the phase-encoding direction, and ∅( k ) is defined as: , where k max is the range of center K-space lines that were preserved without adding phase shift errors, and k max was randomly chosen from π /10 to π /2.…”

Section: Methodsmentioning

confidence: 99%

“…In this study, a two-stage deep CNN model was developed to reduce motion artifacts of the liver DCE-MRI images. The stage-I model was adapted from the DRN-DCMB network originally proposed by Liu et al to reduce the major patterns of motion artifacts (16) ( Fig. 3 ).…”

Section: Methodsmentioning

confidence: 99%

“…In this study, we developed a two-stage DL model to reduce motion artifacts on liver DCE-MRI. Stage-I utilized a deep residual network with densely connected multi-resolution blocks (DRN-DCMB) to remove the major artifacts of the image (16). Stage-II exploited the perceptual similarity in a high-dimensional feature space exacted by a VGG-16 network to preserve imaging details (21).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Image-based Motion Artifact Reduction on Liver Dynamic Contrast Enhanced MRI

Liu

White

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Liver MRI images often suffer degraded quality from ghosting or blurring artifact caused by patient respiratory or bulk motion. In this study, we developed a two-stage deep learning model to reduce motion artifact on dynamic contrast enhanced (DCE) liver MRIs. The stage-I network utilized a deep residual network with a densely connected multi-resolution block (DRN-DCMB) network to remove the majority of motion artifacts. The stage-II network applied the perceptual loss to preserve image structural features by updating the parameters of the stage-I network via backpropagation. The stage-I network was trained using small image patches simulated with five types of motion, i.e., rotational, sinusoidal, random, elastic deformation and through-plane, to mimic actual liver motion patterns. The stage-II network training used full-size images with the same types of motion as the stage-I network. The motion reduction deep learning model was testing using simulated motion images and images with real motion artifacts. The resulted images after two-stage processing demonstrated substantially reduced motion artifacts while preserved anatomic details without image blurriness. This model outperformed existing methods of motion reduction artifact on liver DCE-MRI.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Image-based Motion Artifact Reduction on Liver Dynamic Contrast Enhanced MRI

Liu

White

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…A U‐Net employs feature maps with different resolution levels to characterize the information in an input image 30 . Such multi‐resolution structure is found to be effective for suppression of imaging noise and artifacts in medical images 23,31 . In this study, 3D volumes are used in the DL model, rather than 2D slices as in conventional U‐Nets, in order to better exploit the 3D spatial correlation among the voxels in the heart volume.…”

Section: Methodsmentioning

confidence: 99%

Deep learning with noise‐to‐noise training for denoising in SPECT myocardial perfusion imaging

et al. 2020

Self Cite

View full text Add to dashboard Cite

Purpose Post‐reconstruction filtering is often applied for noise suppression due to limited data counts in myocardial perfusion imaging (MPI) with single‐photon emission computed tomography (SPECT). We study a deep learning (DL) approach for denoising in conventional SPECT‐MPI acquisitions, and investigate whether it can be more effective for improving the detectability of perfusion defects compared to traditional postfiltering. Methods Owing to the lack of ground truth in clinical studies, we adopt a noise‐to‐noise (N2N) training approach for denoising in SPECT‐MPI images. We consider a coupled U‐Net (CU‐Net) structure which is designed to improve learning efficiency through feature map reuse. For network training we employ a bootstrap procedure to generate multiple noise realizations from list‐mode clinical acquisitions. In the experiments we demonstrated the proposed approach on a set of 895 clinical studies, where the iterative OSEM algorithm with three‐dimensional (3D) Gaussian postfiltering was used to reconstruct the images. We investigated the detection performance of perfusion defects in the reconstructed images using the non‐prewhitening matched filter (NPWMF), evaluated the uniformity of left ventricular (LV) wall in terms of image intensity, and quantified the effect of smoothing on the spatial resolution of the reconstructed LV wall by using its full‐width at half‐maximum (FWHM). Results Compared to OSEM with Gaussian postfiltering, the DL denoised images with CU‐Net significantly improved the detection performance of perfusion defects at all contrast levels (65%, 50%, 35%, and 20%). The signal‐to‐noise ratio (SNRD) in the NPWMF output was increased on average by 8% over optimal Gaussian smoothing (P < 10−4, paired t‐test), while the inter‐subject variability was greatly reduced. The CU‐Net also outperformed a 3D nonlocal means (NLM) filter and a convolutional autoencoder (CAE) denoising network in terms of SNRD. In addition, the FWHM of the LV wall in the reconstructed images was varied by less than 1%. Furthermore, CU‐Net also improved the detection performance when the images were processed with less post‐reconstruction smoothing (a trade‐off of increased noise for better LV resolution), with SNRD improved on average by 23%. Conclusions The proposed DL with N2N training approach can yield additional noise suppression in SPECT‐MPI images over conventional postfiltering. For perfusion defect detection, DL with CU‐Net could outperform conventional 3D Gaussian filtering with optimal setting as well as NLM and CAE.

show abstract

Fully automatic quantification of transient severe respiratory motion artifact of gadoxetate disodium–enhanced MRI during arterial phase

et al. 2022

View full text Add to dashboard Cite

Purpose It is important to fully automate the evaluation of gadoxetate disodium–enhanced arterial phase images because the efficient quantification of transient severe motion artifacts can be used in a variety of applications. Our study proposes a fully automatic evaluation method of motion artifacts during the arterial phase of gadoxetate disodium–enhanced MR imaging. Methods The proposed method was based on the construction of quality‐aware features to represent the motion artifact using MR image statistics and multidirectional filtered coefficients. Using the quality‐aware features, the method calculated quantitative quality scores of gadoxetate disodium–enhanced images fully automatically. The performance of our proposed method, as well as two other methods, was acquired by correlating scores against subjective scores from radiologists based on the 5‐point scale and binary evaluation. The subjective scores evaluated by two radiologists were severity scores of motion artifacts in the evaluation set on a scale of 1 (no motion artifacts) to 5 (severe motion artifacts). Results Pearson's linear correlation coefficient (PLCC) and Spearman's rank–ordered correlation coefficient (SROCC) values of our proposed method against the subjective scores were 0.9036 and 0.9057, respectively, whereas the PLCC values of two other methods were 0.6525 and 0.8243, and the SROCC values were 0.6070 and 0.8348. Also, in terms of binary quantification of transient severe respiratory motion, the proposed method achieved 0.9310 sensitivity, 0.9048 specificity, and 0.9200 accuracy, whereas the other two methods achieved 0.7586, 0.8996 sensitivities, 0.8098, 0.8905 specificities, and 0.9200, 0.9048 accuracies Conclusions This study demonstrated the high performance of the proposed automatic quantification method in evaluating transient severe motion artifacts in arterial phase images.

show abstract

Motion artifacts reduction in brain MRI by means of a deep residual network with densely connected multi-resolution blocks (DRN-DCMB)

Cited by 40 publications

References 31 publications

Image-based Motion Artifact Reduction on Liver Dynamic Contrast Enhanced MRI

Image-based Motion Artifact Reduction on Liver Dynamic Contrast Enhanced MRI

Deep learning with noise‐to‐noise training for denoising in SPECT myocardial perfusion imaging

Fully automatic quantification of transient severe respiratory motion artifact of gadoxetate disodium–enhanced MRI during arterial phase

Contact Info

Product

Resources

About