Accelerated motion correction with deep generative diffusion models.

PURPOSE: The aim of this work is to develop a method to solve the ill-posed inverse problem of accelerated image reconstruction while correcting forward model imperfections in the context of subject motion during MRI examinations. METHODS: The proposed solution uses a Bayesian framework based on deep generative diffusion models to jointly estimate a motion-free image and rigid motion estimates from subsampled and motion-corrupt two-dimensional (2D) k-space data. RESULTS: We demonstrate the ability to reconstruct motion-free images from accelerated two-dimensional (2D) Cartesian and non-Cartesian scans without any external reference signal. We show that our method improves over existing correction techniques on both simulated and prospectively accelerated data. CONCLUSION: We propose a flexible framework for retrospective motion correction of accelerated MRI based on deep generative diffusion models, with potential application to other forward model corruptions.

Correcting synthetic MRI contrast-weighted images using deep learning.

Synthetic magnetic resonance imaging (MRI) offers a scanning paradigm where a fast multi-contrast sequence can be used to estimate underlying quantitative tissue parameter maps, which are then used to synthesize any desirable clinical contrast by retrospectively changing scan parameters in silico. Two benefits of this approach are the reduced exam time and the ability to generate arbitrary contrasts offline. However, synthetically generated contrasts are known to deviate from the contrast of experimental scans. The reason for contrast mismatch is the necessary exclusion of some unmodeled physical effects such as partial voluming, diffusion, flow, susceptibility, magnetization transfer, and more. The inclusion of these effects in signal encoding would improve the synthetic images, but would make the quantitative imaging protocol impractical due to long scan times. Therefore, in this work, we propose a novel deep learning approach that generates a multiplicative correction term to capture unmodeled effects and correct the synthetic contrast images to better match experimental contrasts for arbitrary scan parameters. The physics inspired deep learning model implicitly accounts for some unmodeled physical effects occurring during the scan. As a proof of principle, we validate our approach on synthesizing arbitrary inversion recovery fast spin-echo scans using a commercially available 2D multi-contrast sequence. We observe that the proposed correction visually and numerically reduces the mismatch with experimentally collected contrasts compared to conventional synthetic MRI. Finally, we show results of a preliminary reader study and find that the proposed method statistically significantly improves in contrast and SNR as compared to synthetic MR images.

High-fidelity direct contrast synthesis from magnetic resonance fingerprinting.

PURPOSE: This work was aimed at proposing a supervised learning-based method that directly synthesizes contrast-weighted images from the Magnetic Resonance Fingerprinting (MRF) data without performing quantitative mapping and spin-dynamics simulations. METHODS: To implement our direct contrast synthesis (DCS) method, we deploy a conditional generative adversarial network (GAN) framework with a multi-branch U-Net as the generator and a multilayer CNN (PatchGAN) as the discriminator. We refer to our proposed approach as N-DCSNet. The input MRF data are used to directly synthesize T1-weighted, T2-weighted, and fluid-attenuated inversion recovery (FLAIR) images through supervised training on paired MRF and target spin echo-based contrast-weighted scans. The performance of our proposed method is demonstrated on in vivo MRF scans from healthy volunteers. Quantitative metrics, including normalized root mean square error (nRMSE), peak signal-to-noise ratio (PSNR), structural similarity (SSIM), learned perceptual image patch similarity (LPIPS), and Fréchet inception distance (FID), were used to evaluate the performance of the proposed method and compare it with others. RESULTS: In-vivo experiments demonstrated excellent image quality with respect to that of simulation-based contrast synthesis and previous DCS methods, both visually and according to quantitative metrics. We also demonstrate cases in which our trained model is able to mitigate the in-flow and spiral off-resonance artifacts typically seen in MRF reconstructions, and thus more faithfully represent conventional spin echo-based contrast-weighted images. CONCLUSION: We present N-DCSNet to directly synthesize high-fidelity multicontrast MR images from a single MRF acquisition. This method can significantly decrease examination time. By directly training a network to generate contrast-weighted images, our method does not require any model-based simulation and therefore can avoid reconstruction errors due to dictionary matching and contrast simulation (code available at:https://github.com/mikgroup/DCSNet).

Federated End-to-End Unrolled Models for Magnetic Resonance Image Reconstruction.

Image reconstruction is the process of recovering an image from raw, under-sampled signal measurements, and is a critical step in diagnostic medical imaging, such as magnetic resonance imaging (MRI). Recently, data-driven methods have led to improved image quality in MRI reconstruction using a limited number of measurements, but these methods typically rely on the existence of a large, centralized database of fully sampled scans for training. In this work, we investigate federated learning for MRI reconstruction using end-to-end unrolled deep learning models as a means of training global models across multiple clients (data sites), while keeping individual scans local. We empirically identify a low-data regime across a large number of heterogeneous scans, where a small number of training samples per client are available and non-collaborative models lead to performance drops. In this regime, we investigate the performance of adaptive federated optimization algorithms as a function of client data distribution and communication budget. Experimental results show that adaptive optimization algorithms are well suited for the federated learning of unrolled models, even in a limited-data regime (50 slices per data site), and that client-sided personalization can improve reconstruction quality for clients that did not participate in training.

An untrained deep learning method for reconstructing dynamic MR images from accelerated model-based data.

PURPOSE: To implement physics-based regularization as a stopping condition in tuning an untrained deep neural network for reconstructing MR images from accelerated data. METHODS: The ConvDecoder (CD) neural network was trained with a physics-based regularization term incorporating the spoiled gradient echo equation that describes variable-flip angle data. Fully-sampled variable-flip angle k-space data were retrospectively accelerated by factors of R = {8, 12, 18, 36} and reconstructed with CD, CD with the proposed regularization (CD + r), locally low-rank (LR) reconstruction, and compressed sensing with L1-wavelet regularization (L1). Final images from CD + r training were evaluated at the "argmin" of the regularization loss; whereas the CD, LR, and L1 reconstructions were chosen optimally based on ground truth data. The performance measures used were the normalized RMS error, the concordance correlation coefficient, and the structural similarity index. RESULTS: The CD + r reconstructions, chosen using the stopping condition, yielded structural similarity indexs that were similar to the CD (p = 0.47) and LR structural similarity indexs (p = 0.95) across R and that were significantly higher than the L1 structural similarity indexs (p = 0.04). The concordance correlation coefficient values for the CD + r T1 maps across all R and subjects were greater than those corresponding to the L1 (p = 0.15) and LR (p = 0.13) T1 maps, respectively. For R ≥ 12 (≤4.2 min scan time), L1 and LR T1 maps exhibit a loss of spatially refined details compared to CD + r. CONCLUSION: The use of an untrained neural network together with a physics-based regularization loss shows promise as a measure for determining the optimal stopping point in training without relying on fully-sampled ground truth data.

High fidelity deep learning-based MRI reconstruction with instance-wise discriminative feature matching loss.

PURPOSE: To improve reconstruction fidelity of fine structures and textures in deep learning- (DL) based reconstructions. METHODS: A novel patch-based Unsupervised Feature Loss (UFLoss) is proposed and incorporated into the training of DL-based reconstruction frameworks in order to preserve perceptual similarity and high-order statistics. The UFLoss provides instance-level discrimination by mapping similar instances to similar low-dimensional feature vectors and is trained without any human annotation. By adding an additional loss function on the low-dimensional feature space during training, the reconstruction frameworks from under-sampled or corrupted data can reproduce more realistic images that are closer to the original with finer textures, sharper edges, and improved overall image quality. The performance of the proposed UFLoss is demonstrated on unrolled networks for accelerated two- (2D) and three-dimensional (3D) knee MRI reconstruction with retrospective under-sampling. Quantitative metrics including normalized root mean squared error (NRMSE), structural similarity index (SSIM), and our proposed UFLoss were used to evaluate the performance of the proposed method and compare it with others. RESULTS: In vivo experiments indicate that adding the UFLoss encourages sharper edges and more faithful contrasts compared to traditional and learning-based methods with pure ℓ2$$ {\ell}_2 $$ loss. More detailed textures can be seen in both 2D and 3D knee MR images. Quantitative results indicate that reconstruction with UFLoss can provide comparable NRMSE and a higher SSIM while achieving a much lower UFLoss value. CONCLUSION: We present UFLoss, a patch-based unsupervised learned feature loss, which allows the training of DL-based reconstruction to obtain more detailed texture, finer features, and sharper edges with higher overall image quality under DL-based reconstruction frameworks. (Code available at: https://github.com/mikgroup/UFLoss).

Implicit data crimes: Machine learning bias arising from misuse of public data.

SignificancePublic databases are an important resource for machine learning research, but their growing availability sometimes leads to "off-label" usage, where data published for one task are used for another. This work reveals that such off-label usage could lead to biased, overly optimistic results of machine-learning algorithms. The underlying cause is that public data are processed with hidden processing pipelines that alter the data features. Here we study three well-known algorithms developed for image reconstruction from magnetic resonance imaging measurements and show they could produce biased results with up to 48% artificial improvement when applied to public databases. We relate to the publication of such results as implicit "data crimes" to raise community awareness of this growing big data problem.

A generic deep learning model for reduced gadolinium dose in contrast-enhanced brain MRI.

PURPOSE: With rising safety concerns over the use of gadolinium-based contrast agents (GBCAs) in contrast-enhanced MRI, there is a need for dose reduction while maintaining diagnostic capability. This work proposes comprehensive technical solutions for a deep learning (DL) model that predicts contrast-enhanced images of the brain with approximately 10% of the standard dose, across different sites and scanners. METHODS: The proposed DL model consists of a set of methods that improve the model robustness and generalizability. The steps include multi-planar reconstruction, 2.5D model, enhancement-weighted L1, perceptual, and adversarial losses. The proposed model predicts contrast-enhanced images from corresponding pre-contrast and low-dose images. With IRB approval and informed consent, 640 heterogeneous patient scans (56 train, 13 validation, and 571 test) from 3 institutions consisting of 3D T1-weighted brain images were used. Quantitative metrics were computed and 50 randomly sampled test cases were evaluated by 2 board-certified radiologists. Quantitative tumor segmentation was performed on cases with abnormal enhancements. Ablation study was performed for systematic evaluation of proposed technical solutions. RESULTS: The average peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) between full-dose and model prediction were 35.07±3.84 dB and 0.92±0.02 , respectively. Radiologists found the same enhancing pattern in 45/50 (90%) cases; discrepancies were minor differences in contrast intensity and artifacts, with no effect on diagnosis. The average segmentation Dice score between full-dose and synthesized images was 0.88±0.06 (median = 0.91). CONCLUSIONS: We have proposed a DL model with technical solutions for low-dose contrast-enhanced brain MRI with potential generalizability under diverse clinical settings.

Quantitative anatomy mimicking slice phantoms.

PURPOSE: To present a reproducible methodology for building an anatomy mimicking phantom with targeted T1 and T2 contrast for use in quantitative magnetic resonance imaging. METHODS: We propose a reproducible method for creating high-resolution, quantitative slice phantoms. The phantoms are created using gels with different concentrations of NiCl2 and MnCl2 to achieve targeted T1 and T2 values. We describe a calibration method for accurately targeting anatomically realistic relaxation pairs. In addition, we developed a method of fabricating slice phantoms by extruding 3D printed walls on acrylic sheets. These procedures are combined to create a physical analog of the Brainweb digital phantom. RESULTS: With our method, we are able to target specific T1 /T2 values with less than 10% error. Additionally, our slice phantoms look realistic since their geometries are derived from anatomical data. CONCLUSION: Standardized and accurate tools for validating new techniques across sequences, platforms, and different imaging sites are important. Anatomy mimicking, multi-contrast phantoms designed with our procedures could be used for evaluating, testing, and verifying model-based methods.

Deep J-Sense: Accelerated MRI Reconstruction via Unrolled Alternating Optimization.

Accelerated multi-coil magnetic resonance imaging reconstruction has seen a substantial recent improvement combining compressed sensing with deep learning. However, most of these methods rely on estimates of the coil sensitivity profiles, or on calibration data for estimating model parameters. Prior work has shown that these methods degrade in performance when the quality of these estimators are poor or when the scan parameters differ from the training conditions. Here we introduce Deep J-Sense as a deep learning approach that builds on unrolled alternating minimization and increases robustness: our algorithm refines both the magnetization (image) kernel and the coil sensitivity maps. Experimental results on a subset of the knee fastMRI dataset show that this increases reconstruction performance and provides a significant degree of robustness to varying acceleration factors and calibration region sizes.

Computational MRI with Physics-based Constraints: Application to Multi-contrast and Quantitative Imaging.

Compressed sensing takes advantage of low-dimensional signal structure to reduce sampling requirements far below the Nyquist rate. In magnetic resonance imaging (MRI), this often takes the form of sparsity through wavelet transform, finite differences, and low rank extensions. Though powerful, these image priors are phenomenological in nature and do not account for the mechanism behind the image formation. On the other hand, MRI signal dynamics are governed by physical laws, which can be explicitly modeled and used as priors for reconstruction. These explicit and implicit signal priors can be synergistically combined in an inverse problem framework to recover sharp, multi-contrast images from highly accelerated scans. Furthermore, the physics-based constraints provide a recipe for recovering quantitative, bio-physical parameters from the data. This article introduces physics-based modeling constraints in MRI and shows how they can be used in conjunction with compressed sensing for image reconstruction and quantitative imaging. We describe model-based quantitative MRI, as well as its linear subspace approximation. We also discuss approaches to selecting user-controllable scan parameters given knowledge of the physical model. We present several MRI applications that take advantage of this framework for the purpose of multi-contrast imaging and quantitative mapping.

Targeted rapid knee MRI exam using T2 shuffling.

BACKGROUND: MRI is commonly used to evaluate pediatric musculoskeletal pathologies, but same-day/near-term scheduling and short exams remain challenges. PURPOSE: To investigate the feasibility of a targeted rapid pediatric knee MRI exam, with the goal of reducing cost and enabling same-day MRI access. STUDY TYPE: A cost effectiveness study done prospectively. SUBJECTS: Forty-seven pediatric patients. FIELD STRENGTH/SEQUENCE: 3T. The 10-minute protocol was based on T2 Shuffling, a four-dimensional acquisition and reconstruction of images with variable T2 contrast, and a T1 2D fast spin-echo (FSE) sequence. A distributed, compressed sensing-based reconstruction was implemented on a four-node high-performance compute cluster and integrated into the clinical workflow. ASSESSMENT: In an Institutional Review Board-approved study with informed consent/assent, we implemented a targeted pediatric knee MRI exam for assessing pediatric knee pain. Pediatric patients were subselected for the exam based on insurance plan and clinical indication. Over a 2-year period, 47 subjects were recruited for the study and 49 MRIs were ordered. Date and time information was recorded for MRI referral, registration, and completion. Image quality was assessed from 0 (nondiagnostic) to 5 (outstanding) by two readers, and consensus was subsequently reached. STATISTICAL TESTS: A Wilcoxon rank-sum test assessed the null hypothesis that the targeted exam times compared with conventional knee exam times were unchanged. RESULTS: Of the 49 cases, 20 were completed on the same day as exam referral. Median time from registration to exam completion was 18.7 minutes. Median reconstruction time for T2 Shuffling was reduced from 18.9 minutes to 95 seconds using the distributed implementation. Technical fees charged for the targeted exam were one-third that of the routine clinical knee exam. No subject had to return for additional imaging. DATA CONCLUSION: The targeted knee MRI exam is feasible and reduces the imaging time, cost, and barrier to same-day MRI access for pediatric patients. LEVEL OF EVIDENCE: 2 Technical Efficacy: Stage 6 J. Magn. Reson. Imaging 2019.

Variable-Density Single-Shot Fast Spin-Echo MRI with Deep Learning Reconstruction by Using Variational Networks.

Purpose To develop a deep learning reconstruction approach to improve the reconstruction speed and quality of highly undersampled variable-density single-shot fast spin-echo imaging by using a variational network (VN), and to clinically evaluate the feasibility of this approach. Materials and Methods Imaging was performed with a 3.0-T imager with a coronal variable-density single-shot fast spin-echo sequence at 3.25 times acceleration in 157 patients referred for abdominal imaging (mean age, 11 years; range, 1-34 years; 72 males [mean age, 10 years; range, 1-26 years] and 85 females [mean age, 12 years; range, 1-34 years]) between March 2016 and April 2017. A VN was trained based on the parallel imaging and compressed sensing (PICS) reconstruction of 130 patients. The remaining 27 patients were used for evaluation. Image quality was evaluated in an independent blinded fashion by three radiologists in terms of overall image quality, perceived signal-to-noise ratio, image contrast, sharpness, and residual artifacts with scores ranging from 1 (nondiagnostic) to 5 (excellent). Wilcoxon tests were performed to test the hypothesis that there was no significant difference between VN and PICS. Results VN achieved improved perceived signal-to-noise ratio (P = .01) and improved sharpness (P < .001), with no difference in image contrast (P = .24) and residual artifacts (P = .07). In terms of overall image quality, VN performed better than did PICS (P = .02). Average reconstruction time ± standard deviation was 5.60 seconds ± 1.30 per section for PICS and 0.19 second ± 0.04 per section for VN. Conclusion Compared with the conventional parallel imaging and compressed sensing reconstruction (PICS), the variational network (VN) approach accelerates the reconstruction of variable-density single-shot fast spin-echo sequences and achieves improved overall image quality with higher perceived signal-to-noise ratio and sharpness. © RSNA, 2018 Online supplemental material is available for this article.

Self-Calibrating Wave-Encoded Variable-Density Single-Shot Fast Spin Echo Imaging.

BACKGROUND: It is highly desirable in clinical abdominal MR scans to accelerate single-shot fast spin echo (SSFSE) imaging and reduce blurring due to T2 decay and partial-Fourier acquisition. PURPOSE: To develop and investigate the clinical feasibility of wave-encoded variable-density SSFSE imaging for improved image quality and scan time reduction. STUDY TYPE: Prospective controlled clinical trial. SUBJECTS: With Institutional Review Board approval and informed consent, the proposed method was assessed on 20 consecutive adult patients (10 male, 10 female, range, 24-84 years). FIELD STRENGTH/SEQUENCE: A wave-encoded variable-density SSFSE sequence was developed for clinical 3.0T abdominal scans to enable high acceleration (3.5×) with full-Fourier acquisitions by: 1) introducing wave encoding with self-refocusing gradient waveforms to improve acquisition efficiency; 2) developing self-calibrated estimation of wave-encoding point-spread function and coil sensitivity to improve motion robustness; and 3) incorporating a parallel imaging and compressed sensing reconstruction to reconstruct highly accelerated datasets. ASSESSMENT: Image quality was compared pairwise with standard Cartesian acquisition independently and blindly by two radiologists on a scale from -2 to 2 for noise, contrast, confidence, sharpness, and artifacts. The average ratio of scan time between these two approaches was also compared. STATISTICAL TESTS: A Wilcoxon signed-rank tests with a P value under 0.05 considered statistically significant. RESULTS: Wave-encoded variable-density SSFSE significantly reduced the perceived noise level and improved the sharpness of the abdominal wall and the kidneys compared with standard acquisition (mean scores 0.8, 1.2, and 0.8, respectively, P < 0.003). No significant difference was observed in relation to other features (P = 0.11). An average of 21% decrease in scan time was achieved using the proposed method. DATA CONCLUSION: Wave-encoded variable-density sampling SSFSE achieves improved image quality with clinically relevant echo time and reduced scan time, thus providing a fast and robust approach for clinical SSFSE imaging. LEVEL OF EVIDENCE: 1 Technical Efficacy: Stage 6 J. Magn. Reson. Imaging 2018;47:954-966.

T2 shuffling: Sharp, multicontrast, volumetric fast spin-echo imaging.

PURPOSE: A new acquisition and reconstruction method called T2 Shuffling is presented for volumetric fast spin-echo (three-dimensional [3D] FSE) imaging. T2 Shuffling reduces blurring and recovers many images at multiple T2 contrasts from a single acquisition at clinically feasible scan times (6-7 min). THEORY AND METHODS: The parallel imaging forward model is modified to account for temporal signal relaxation during the echo train. Scan efficiency is improved by acquiring data during the transient signal decay and by increasing echo train lengths without loss in signal-to-noise ratio (SNR). By (1) randomly shuffling the phase encode view ordering, (2) constraining the temporal signal evolution to a low-dimensional subspace, and (3) promoting spatio-temporal correlations through locally low rank regularization, a time series of virtual echo time images is recovered from a single scan. A convex formulation is presented that is robust to partial voluming and radiofrequency field inhomogeneity. RESULTS: Retrospective undersampling and in vivo scans confirm the increase in sharpness afforded by T2 Shuffling. Multiple image contrasts are recovered and used to highlight pathology in pediatric patients. A proof-of-principle method is integrated into a clinical musculoskeletal imaging workflow. CONCLUSION: The proposed T2 Shuffling method improves the diagnostic utility of 3D FSE by reducing blurring and producing multiple image contrasts from a single scan. Magn Reson Med 77:180-195, 2017. © 2016 Wiley Periodicals, Inc.

Fast comprehensive single-sequence four-dimensional pediatric knee MRI with T2 shuffling.

PURPOSE: To develop and clinically evaluate a pediatric knee magnetic resonance imaging (MRI) technique based on volumetric fast spin-echo (3DFSE) and compare its diagnostic performance, image quality, and imaging time to that of a conventional 2D protocol. MATERIALS AND METHODS: A 3DFSE sequence was modified and combined with a compressed sensing-based reconstruction resolving multiple image contrasts, a technique termed T2 Shuffling (T2 Sh). With Institutional Review Board (IRB) approval, 28 consecutive children referred for 3T knee MRI prospectively underwent a standard clinical knee protocol followed by T2 Sh. T2 Sh performance was assessed by two readers blinded to diagnostic reports. Interpretive discrepancies were resolved by medical record chart review and consensus between the readers and an orthopedic surgeon. Image quality was evaluated by rating anatomic delineation, with 95% confidence interval. A Wilcoxon rank-sum test assessed the null hypothesis that T2 Sh structure delineation compared to conventional 2D is unchanged. Intraclass correlation coefficients were calculated for interobserver agreement. Imaging time of the conventional protocol and T2 Sh was compared. RESULTS: There was 81% and 87% concordance between T2 Sh reports and diagnostic reports, respectively, for each reader. Upon consensus review, T2 Sh had 93% sensitivity and 100% specificity compared to clinical reports for detection of clinically relevant findings. The 95% confidence interval of diagnostic or better rating was 95-100%, with 34-80% interobserver agreement. There was no significant difference in structure delineation between T2 Sh and 2D, except for the retinaculum (P < 0.05), where 2D was preferred. Typical imaging time for T2 Sh and the conventional exam was 7 and 13 minutes, respectively. CONCLUSION: A single-sequence pediatric knee exam is feasible with T2 Sh, providing multiplanar, reformattable 4D images. LEVEL OF EVIDENCE: 2 J. MAGN. RESON. IMAGING 2017;45:1700-1711.

Comprehensive motion-compensated highly accelerated 4D flow MRI with ferumoxytol enhancement for pediatric congenital heart disease.

PURPOSE: To develop and evaluate motion-compensation and compressed-sensing techniques in 4D flow MRI for anatomical assessment in a comprehensive ferumoxytol-enhanced congenital heart disease (CHD) exam. MATERIALS AND METHODS: A Cartesian 4D flow sequence was developed to enable intrinsic navigation and two variable-density sampling schemes: VDPoisson and VDRad. Four compressed-sensing methods were developed: A) VDPoisson scan reconstructed using spatial wavelets; B) added temporal total variation to A; C) VDRad scan using the same reconstruction as in B; and D) added motion compensation to C. With Institutional Review Board (IRB) approval and Health Insurance Portability and Accountability Act (HIPAA) compliance, 23 consecutive patients (eight females, mean 6.3 years) referred for ferumoxytol-enhanced CHD 3T MRI were recruited. Images were acquired and reconstructed using methods A-D. Two cardiovascular radiologists independently scored the images on a 5-point scale. These readers performed a paired wall motion and functional assessment between method D and 2D balanced steady-state free precession (bSSFP) CINE for 16 cases. RESULTS: Method D had higher diagnostic image quality for most anatomical features (mean 3.8-4.8) compared to A (2.0-3.6), B (2.2-3.7), and C (2.9-3.9) with P < 0.05 with good interobserver agreement (κ ≥ 0.49). Method D had similar or better assessment of myocardial borders and cardiac motion compared to 2D bSSFP (P < 0.05, κ ≥ 0.77). All methods had good internal agreement in comparing aortic with pulmonic flow (BA mean < 0.02%, r > 0.85) and compared to method A (BA mean < 0.13%, r > 0.84) with P < 0.01. CONCLUSION: Flow, functional, and anatomical assessment in CHD with ferumoxytol-enhanced 4D flow is feasible and can be significantly improved using motion compensation and compressed sensing. J. Magn. Reson. Imaging 2016;43:1355-1368.