Dataset Information

Network Accelerated Motion Estimation and Reduction (NAMER): Convolutional neural network guided retrospective motion correction using a separable motion model.

ABSTRACT: PURPOSE:We introduce and validate a scalable retrospective motion correction technique for brain imaging that incorporates a machine learning component into a model-based motion minimization. METHODS:A convolutional neural network (CNN) trained to remove motion artifacts from 2D T2 -weighted rapid acquisition with refocused echoes (RARE) images is introduced into a model-based data-consistency optimization to jointly search for 2D motion parameters and the uncorrupted image. Our separable motion model allows for efficient intrashot (line-by-line) motion correction of highly corrupted shots, as opposed to previous methods which do not scale well with this refinement of the motion model. Final image generation incorporates the motion parameters within a model-based image reconstruction. The method is tested in simulations and in vivo motion experiments of in-plane motion corruption. RESULTS:While the convolutional neural network alone provides some motion mitigation (at the expense of introduced blurring), allowing it to guide the iterative joint-optimization both improves the search convergence and renders the joint-optimization separable. This enables rapid mitigation within shots in addition to between shots. For 2D in-plane motion correction experiments, the result is a significant reduction of both image space root mean square error in simulations, and a reduction of motion artifacts in the in vivo motion tests. CONCLUSION:The separability and convergence improvements afforded by the combined convolutional neural network+model-based method shows the potential for meaningful postacquisition motion mitigation in clinical MRI.

SUBMITTER: Haskell MW

PROVIDER: S-EPMC6626557 | biostudies-literature | 2019 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Network Accelerated Motion Estimation and Reduction (NAMER): Convolutional neural network guided retrospective motion correction using a separable motion model.

Haskell Melissa W MW Cauley Stephen F SF Bilgic Berkin B Hossbach Julian J Splitthoff Daniel N DN Pfeuffer Josef J Setsompop Kawin K Wald Lawrence L LL

Magnetic resonance in medicine 20190502 4

<h4>Purpose</h4>We introduce and validate a scalable retrospective motion correction technique for brain imaging that incorporates a machine learning component into a model-based motion minimization.<h4>Methods</h4>A convolutional neural network (CNN) trained to remove motion artifacts from 2D T<sub>2</sub> -weighted rapid acquisition with refocused echoes (RARE) images is introduced into a model-based data-consistency optimization to jointly search for 2D motion parameters and the uncorrupted i ...[more]

PMID: 31045278

Similar Datasets

Project description:PurposeTo investigate the feasibility of accelerating prostate diffusion-weighted imaging (DWI) by reducing the number of acquired averages and denoising the resulting image using a proposed guided denoising convolutional neural network (DnCNN).Materials and methodsRaw data from the prostate DWI scans were retrospectively gathered between July 2018 and July 2019 from six single-vendor MRI scanners. There were 103 datasets used for training (median age, 64 years; interquartile range [IQR], 11), 15 for validation (median age, 68 years; IQR, 12), and 37 for testing (median age, 64 years; IQR, 12). High b-value diffusion-weighted (hb DW) data were reconstructed into noisy images using two averages and reference images using all 16 averages. A conventional DnCNN was modified into a guided DnCNN, which uses the low b-value DW image as a guidance input. Quantitative and qualitative reader evaluations were performed on the denoised hb DW images. A cumulative link mixed regression model was used to compare the readers' scores. The agreement between the apparent diffusion coefficient (ADC) maps (denoised vs reference) was analyzed using Bland-Altman analysis.ResultsCompared with the original DnCNN, the guided DnCNN produced denoised hb DW images with higher peak signal-to-noise ratio (32.79 ± 3.64 [standard deviation] vs 33.74 ± 3.64), higher structural similarity index (0.92 ± 0.05 vs 0.93 ± 0.04), and lower normalized mean square error (3.9% ± 10 vs 1.6% ± 1.5) (P < .001 for all). Compared with the reference images, the denoised images received higher image quality scores from the readers (P < .0001). The ADC values based on the denoised hb DW images were in good agreement with the reference ADC values (mean ADC difference ranged from -0.04 to 0.02 × 10-3 mm2/sec).ConclusionAccelerating prostate DWI by reducing the number of acquired averages and denoising the resulting image using the proposed guided DnCNN is technically feasible. Supplemental material is available for this article. © RSNA, 2020.

Project description:Magnetic resonance imaging (MRI) can potentially be used for non-invasive screening of patients with stable angina pectoris to identify probable obstructive coronary artery disease. MRI-based coronary blood flow quantification has to date only been performed in a 2D fashion, limiting its clinical applicability. In this study, we propose a framework for coronary blood flow quantification using accelerated 4D flow MRI with respiratory motion correction and compressed sensing image reconstruction. We investigate its feasibility and repeatability in healthy subjects at rest. Fourteen healthy subjects received 8 times-accelerated 4D flow MRI covering the left coronary artery (LCA) with an isotropic spatial resolution of 1.0 mm3. Respiratory motion correction was performed based on 1) lung-liver navigator signal, 2) real-time monitoring of foot-head motion of the liver and LCA by a separate acquisition, and 3) rigid image registration to correct for anterior-posterior motion. Time-averaged diastolic LCA flow was determined, as well as time-averaged diastolic maximal velocity (VMAX) and diastolic peak velocity (VPEAK). 2D flow MRI scans of the LCA were acquired for reference. Scan-rescan repeatability and agreement between 4D flow MRI and 2D flow MRI were assessed in terms of concordance correlation coefficient (CCC) and coefficient of variation (CV). The protocol resulted in good visibility of the LCA in 11 out of 14 subjects (six female, five male, aged 28 ± 4 years). The other 3 subjects were excluded from analysis. Time-averaged diastolic LCA flow measured by 4D flow MRI was 1.30 ± 0.39 ml/s and demonstrated good scan-rescan repeatability (CCC/CV = 0.79/20.4%). Time-averaged diastolic VMAX (17.2 ± 3.0 cm/s) and diastolic VPEAK (24.4 ± 6.5 cm/s) demonstrated moderate repeatability (CCC/CV = 0.52/19.0% and 0.68/23.0%, respectively). 4D flow- and 2D flow-based diastolic LCA flow agreed well (CCC/CV = 0.75/20.1%). Agreement between 4D flow MRI and 2D flow MRI was moderate for both diastolic VMAX and VPEAK (CCC/CV = 0.68/20.3% and 0.53/27.0%, respectively). In conclusion, the proposed framework of accelerated 4D flow MRI equipped with respiratory motion correction and compressed sensing image reconstruction enables repeatable diastolic LCA flow quantification that agrees well with 2D flow MRI.

Dataset Information

Network Accelerated Motion Estimation and Reduction (NAMER): Convolutional neural network guided retrospective motion correction using a separable motion model.

Publications

Network Accelerated Motion Estimation and Reduction (NAMER): Convolutional neural network guided retrospective motion correction using a separable motion model.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets