High-resolution, respiratory-resolved coronary MRA using a Phyllotaxis-reordered variable-density 3D cones trajectory.

PURPOSE: To develop a respiratory-resolved motion-compensation method for free-breathing, high-resolution coronary magnetic resonance angiography (CMRA) using a 3D cones trajectory. METHODS: To achieve respiratory-resolved 0.98 mm resolution images in a clinically relevant scan time, we undersample the imaging data with a variable-density 3D cones trajectory. For retrospective motion compensation, translational estimates from 3D image-based navigators (3D iNAVs) are used to bin the imaging data into four phases from end-expiration to end-inspiration. To ensure pseudo-random undersampling within each respiratory phase, we devise a phyllotaxis readout ordering scheme mindful of eddy current artifacts in steady state free precession imaging. Following binning, residual 3D translational motion within each phase is computed using the 3D iNAVs and corrected for in the imaging data. The noise-like aliasing characteristic of the combined phyllotaxis and cones sampling pattern is leveraged in a compressed sensing reconstruction with spatial and temporal regularization to reduce aliasing in each of the respiratory phases. RESULTS: In initial studies of six subjects, respiratory motion compensation using the proposed method yields improved image quality compared to non-respiratory-resolved approaches with no motion correction and with 3D translational correction. Qualitative assessment by two cardiologists and quantitative evaluation with the image edge profile acutance metric indicate the superior sharpness of coronary segments reconstructed with the proposed method (P < 0.01). CONCLUSION: We have demonstrated a new method for free-breathing, high-resolution CMRA based on a variable-density 3D cones trajectory with modified phyllotaxis ordering and respiratory-resolved motion compensation with 3D iNAVs.

Free-breathing R2∗ mapping of hepatic iron overload in children using 3D multi-echo UTE cones MRI.

PURPOSE: To enable motion-robust, ungated, free-breathing R2∗ mapping of hepatic iron overload in children with 3D multi-echo UTE cones MRI. METHODS: A golden-ratio re-ordered 3D multi-echo UTE cones acquisition was developed with chemical-shift encoding (CSE). Multi-echo complex-valued source images were reconstructed via gridding and coil combination, followed by confounder-corrected R2∗ (=1/ T2∗ ) mapping. A phantom containing 15 different concentrations of gadolinium solution (0-300 mM) was imaged at 3T. 3D multi-echo UTE cones with an initial TE of 0.036 ms and Cartesian CSE-MRI (IDEAL-IQ) sequences were performed. With institutional review board approval, 85 subjects (81 pediatric patients with iron overload + 4 healthy volunteers) were imaged at 3T using 3D multi-echo UTE cones with free breathing (FB cones), IDEAL-IQ with breath holding (BH Cartesian), and free breathing (FB Cartesian). Overall image quality of R2∗ maps was scored by 2 blinded experts and compared by a Wilcoxon rank-sum test. For each pediatric subject, the paired R2∗ maps were assessed to determine if a corresponding artifact-free 15 mm region-of-interest (ROI) could be identified at a mid-liver level on both images. Agreement between resulting R2∗ quantification from FB cones and BH/FB Cartesian was assessed with Bland-Altman and linear correlation analyses. RESULTS: ROI-based regression analysis showed a linear relationship between gadolinium concentration and R2∗ in IDEAL-IQ (y = 8.83x - 52.10, R2 = 0.995) as well as in cones (y = 9.19x - 64.16, R2 = 0.992). ROI-based Bland-Altman analysis showed that the mean difference (MD) was 0.15% and the SD was 5.78%. However, IDEAL-IQ R2∗ measurements beyond 200 mM substantially deviated from a linear relationship for IDEAL-IQ (y = 5.85x + 127.61, R2 = 0.827), as opposed to cones (y = 10.87x - 166.96, R2 = 0.984). In vivo, FB cones R2∗ had similar image quality with BH and FB Cartesian in 15 and 42 cases, respectively. FB cones R2∗ had better image quality scores than BH and FB Cartesian in 3 and 21 cases, respectively, where BH/FB Cartesian exhibited severe ghosting artifacts. ROI-based Bland-Altman analyses were 2.23% (MD) and 6.59% (SD) between FB cones and BH Cartesian and were 0.21% (MD) and 7.02% (SD) between FB cones and FB Cartesian, suggesting a good agreement between FB cones and BH (FB) Cartesian R2∗ . Strong linear relationships were observed between BH Cartesian and FB cones (y = 1.00x + 1.07, R2 = 0.996) and FB Cartesian and FB cones (y = 0.98x + 1.68, R2 = 0.999). CONCLUSION: Golden-ratio re-ordered 3D multi-echo UTE Cones MRI enabled motion-robust, ungated, and free-breathing R2∗ mapping of hepatic iron overload, with comparable R2∗ measurements and image quality to BH Cartesian, and better image quality than FB Cartesian.

Accelerating cardiac cine MRI using a deep learning-based ESPIRiT reconstruction.

PURPOSE: To propose a novel combined parallel imaging and deep learning-based reconstruction framework for robust reconstruction of highly accelerated 2D cardiac cine MRI data. METHODS: We propose DL-ESPIRiT, an unrolled neural network architecture that utilizes an extended coil sensitivity model to address SENSE-related field-of-view (FOV) limitations in previously proposed deep learning-based reconstruction frameworks. Additionally, we propose a novel neural network design based on (2+1)D spatiotemporal convolutions to produce more accurate dynamic MRI reconstructions than conventional 3D convolutions. The network is trained on fully sampled 2D cardiac cine datasets collected from 11 healthy volunteers with IRB approval. DL-ESPIRiT is compared against a state-of-the-art parallel imaging and compressed sensing method known as l1 -ESPIRiT. The reconstruction accuracy of both methods is evaluated on retrospectively undersampled datasets (R = 12) with respect to standard image quality metrics as well as automatic deep learning-based segmentations of left ventricular volumes. Feasibility of DL-ESPIRiT is demonstrated on two prospectively undersampled datasets acquired in a single heartbeat per slice. RESULTS: The (2+1)D DL-ESPIRiT method produces higher fidelity image reconstructions when compared to l1 -ESPIRiT reconstructions with respect to standard image quality metrics (P < .001). As a result of improved image quality, segmentations made from (2+1)D DL-ESPIRiT images are also more accurate than segmentations from l1 -ESPIRiT images. CONCLUSIONS: DL-ESPIRiT synergistically combines a robust parallel imaging model and deep learning-based priors to produce high-fidelity reconstructions of retrospectively undersampled 2D cardiac cine data acquired with reduced FOV. Although a proof-of-concept is shown, further experiments are necessary to determine the efficacy of DL-ESPIRiT in prospectively undersampled data.

Diffusion-weighted double-echo steady-state with a three-dimensional cones trajectory for non-contrast-enhanced breast MRI.

The image quality limitations of echo-planar diffusion-weighted imaging (DWI) are an obstacle to its widespread adoption in the breast. Steady-state DWI is an alternative DWI method with more robust image quality but its contrast for imaging breast cancer is not well-understood. The aim of this study was to develop and evaluate diffusion-weighted double-echo steady-state imaging with a three-dimensional cones trajectory (DW-DESS-Cones) as an alternative to conventional DWI for non-contrast-enhanced MRI in the breast. This prospective study included 28 women undergoing clinically indicated breast MRI and six asymptomatic volunteers. In vivo studies were performed at 3 T and included DW-DESS-Cones, DW-DESS-Cartesian, DWI, and CE-MRI acquisitions. Phantom experiments (diffusion phantom, High Precision Devices) and simulations were performed to establish framework for contrast of DW-DESS-Cones in comparison to DWI in the breast. Motion artifacts of DW-DESS-Cones were measured with artifact-to-noise ratio in volunteers and patients. Lesion-to-fibroglandular tissue signal ratios were measured, lesions were categorized as hyperintense or hypointense, and an image quality observer study was performed in DW-DESS-Cones and DWI in patients. Effect of DW-DESS-Cones method on motion artifacts was tested by mixed-effects generalized linear model. Effect of DW-DESS-Cones on signal in phantom was tested by quadratic regression. Correlation was calculated between DW-DESS-Cones and DWI lesion-to-fibroglandular tissue signal ratios. Inter-observer agreement was assessed with Gwet's AC. Simulations predicted hyperintensity of lesions with DW-DESS-Cones but at a 3% to 67% lower degree than with DWI. Motion artifacts were reduced with DW-DESS-Cones versus DW-DESS-Cartesian (p < 0.05). Lesion-to-fibroglandular tissue signal ratios were not correlated between DW-DESS-Cones and DWI (r = 0.25, p = 0.38). Concordant hyperintensity/hypointensity was observed between DW-DESS-Cones and DWI in 11/14 lesions. DW-DESS-Cones improved sharpness, distortion, and overall image quality versus DWI. DW-DESS-Cones may be able to eliminate motion artifacts in the breast allowing for investigation of higher degrees of steady-state diffusion weighting. Malignant breast lesions in DW-DESS-Cones demonstrated hyperintensity with respect to surrounding tissue without an injection of contrast. LEVEL OF EVIDENCE: 2. TECHNICAL EFFICACY STAGE: 1.

DIAGNOSTIC IMAGE QUALITY ASSESSMENT AND CLASSIFICATION IN MEDICAL IMAGING: OPPORTUNITIES AND CHALLENGES.

Magnetic Resonance Imaging (MRI) suffers from several artifacts, the most common of which are motion artifacts. These artifacts often yield images that are of non-diagnostic quality. To detect such artifacts, images are prospectively evaluated by experts for their diagnostic quality, which necessitates patient-revisits and rescans whenever non-diagnostic quality scans are encountered. This motivates the need to develop an automated framework capable of accessing medical image quality and detecting diagnostic and non-diagnostic images. In this paper, we explore several convolutional neural network-based frameworks for medical image quality assessment and investigate several challenges therein.

Multi-scale Unrolled Deep Learning Framework for Accelerated Magnetic Resonance Imaging.

Accelerating data acquisition in magnetic resonance imaging (MRI) has been of perennial interest due to its prohibitively slow data acquisition process. Recent trends in accelerating MRI employ data-centric deep learning frameworks due to its fast inference time and 'one-parameter-fit-all' principle unlike in traditional model-based acceleration techniques. Unrolled deep learning framework that combines the deep priors and model knowledge are robust compared to naive deep learning based framework. In this paper, we propose a novel multi-scale unrolled deep learning framework which learns deep image priors through multi-scale CNN and is combined with unrolled framework to enforce data-consistency and model knowledge. Essentially, this framework combines the best of both learning paradigms:model-based and data-centric learning paradigms. Proposed method is verified using several experiments on numerous data sets.

Compressed Sensing: From Research to Clinical Practice with Deep Neural Networks.

Compressed sensing (CS) reconstruction methods leverage sparse structure in underlying signals to recover high-resolution images from highly undersampled measurements. When applied to magnetic resonance imaging (MRI), CS has the potential to dramatically shorten MRI scan times, increase diagnostic value, and improve overall patient experience. However, CS has several shortcomings which limit its clinical translation such as: 1) artifacts arising from inaccurate sparse modelling assumptions, 2) extensive parameter tuning required for each clinical application, and 3) clinically infeasible reconstruction times. Recently, CS has been extended to incorporate deep neural networks as a way of learning complex image priors from historical exam data. Commonly referred to as unrolled neural networks, these techniques have proven to be a compelling and practical approach to address the challenges of sparse CS. In this tutorial, we will review the classical compressed sensing formulation and outline steps needed to transform this formulation into a deep learning-based reconstruction framework. Supplementary open source code in Python will be used to demonstrate this approach with open databases. Further, we will discuss considerations in applying unrolled neural networks in the clinical setting.

Direct measurement of atrioventricular valve regurgitant jets using 4D flow cardiovascular magnetic resonance is accurate and reliable for children with congenital heart disease: a retrospective cohort study.

BACKGROUND: 3D-time resolved flow (4DF) cardiovascular magnetic resonance (CMR) with retrospective analysis of atrioventricular valve regurgitation (AVVR) allows for internal validation by multiple direct and indirect methods. Limited data exist on direct measurement of AVVR by 4DF CMR in pediatric congenital heart disease (CHD). We aimed to validate direct measurement of the AVVR jet as accurate and reliable compared to the volumetric method (clinical standard by 2D CMR) and as a superior method of internal validation than the annular inflow method. METHODS: We identified 44 consecutive patients with diverse CHD referred for evaluation of AVVR by CMR. 1.5 T or 3 T scanners, intravenous contrast, and a combination of parallel imaging and compressed sensing were used. Four methods of measuring AVVR volume (RVol) were used: volumetric method (VOL; the clinical standard) = stroke volume by 2D balanced steady-state free precession - semilunar valve forward flow (SLFF); annular inflow method (AIM) = atrioventricular valve forward flow [AVFF] - semilunar valve net flow (SLNF); and direct measurement (JET). AVFF was measured using static and retrospective valve tracking planes. SLFF, SLNF, AVFF, and JET were measured by 4DF phase contrast. Regurgitant fraction was calculated as [RVol/(RVol+SLNF)]× 100. Statistical methods included Spearman, Wilcoxon rank sum test/Student paired t-test, Bland Altman analysis, and intra-class coefficient (ICC), where appropriate. RESULTS: Regurgitant fraction by JET strongly correlated with the indirect methods (VOL and AIM) (ρ = 0.73-0.80, p < 0.001) and was similar to VOL with a median difference (interquartile range) of - 1.5% (- 8.3-7.2%; p = 0.624). VOL had weaker correlations with AIM and JET (ρ = 0.69-0.73, p < 0.001). AIM underestimated RF by 3.6-6.9% compared to VOL and JET, p < 0.03. Intra- and inter- observer reliability were excellent for all methods (ICC 0.94-0.99). The mean (±standard deviation) inter-observer difference for VOL was 2.4% (±5.1%), p < 0.05. CONCLUSIONS: In a diverse cohort of pediatric CHD, measurement of AVVR using JET is accurate and reliable to VOL and is a superior method of internal validation compared to AIM. This study supports use of 4DF CMR for measurement of AVVR, obviating need for expert prospective prescription during image acquisition by 2D CMR.

Extreme MRI: Large-scale volumetric dynamic imaging from continuous non-gated acquisitions.

PURPOSE: To develop a framework to reconstruct large-scale volumetric dynamic MRI from rapid continuous and non-gated acquisitions, with applications to pulmonary and dynamic contrast-enhanced (DCE) imaging. THEORY AND METHODS: The problem considered here requires recovering 100 gigabytes of dynamic volumetric image data from a few gigabytes of k-space data, acquired continuously over several minutes. This reconstruction is vastly under-determined, heavily stressing computing resources as well as memory management and storage. To overcome these challenges, we leverage intrinsic three-dimensional (3D) trajectories, such as 3D radial and 3D cones, with ordering that incoherently cover time and k-space over the entire acquisition. We then propose two innovations: (a) A compressed representation using multiscale low-rank matrix factorization that constrains the reconstruction problem, and reduces its memory footprint. (b) Stochastic optimization to reduce computation, improve memory locality, and minimize communications between threads and processors. We demonstrate the feasibility of the proposed method on DCE imaging acquired with a golden-angle ordered 3D cones trajectory and pulmonary imaging acquired with a bit-reversed ordered 3D radial trajectory. We compare it with "soft-gated" dynamic reconstruction for DCE and respiratory-resolved reconstruction for pulmonary imaging. RESULTS: The proposed technique shows transient dynamics that are not seen in gating-based methods. When applied to datasets with irregular, or non-repetitive motions, the proposed method displays sharper image features. CONCLUSIONS: We demonstrated a method that can reconstruct massive 3D dynamic image series in the extreme undersampling and extreme computation setting.

Reconstruction of undersampled 3D non-Cartesian image-based navigators for coronary MRA using an unrolled deep learning model.

PURPOSE: To rapidly reconstruct undersampled 3D non-Cartesian image-based navigators (iNAVs) using an unrolled deep learning (DL) model, enabling nonrigid motion correction in coronary magnetic resonance angiography (CMRA). METHODS: An end-to-end unrolled network is trained to reconstruct beat-to-beat 3D iNAVs acquired during a CMRA sequence. The unrolled model incorporates a nonuniform FFT operator in TensorFlow to perform the data-consistency operation, and the regularization term is learned by a convolutional neural network (CNN) based on the proximal gradient descent algorithm. The training set includes 6,000 3D iNAVs acquired from 7 different subjects and 11 scans using a variable-density (VD) cones trajectory. For testing, 3D iNAVs from 4 additional subjects are reconstructed using the unrolled model. To validate reconstruction accuracy, global and localized motion estimates from DL model-based 3D iNAVs are compared with those extracted from 3D iNAVs reconstructed with l1 -ESPIRiT. Then, the high-resolution coronary MRA images motion corrected with autofocusing using the l1 -ESPIRiT and DL model-based 3D iNAVs are assessed for differences. RESULTS: 3D iNAVs reconstructed using the DL model-based approach and conventional l1 -ESPIRiT generate similar global and localized motion estimates and provide equivalent coronary image quality. Reconstruction with the unrolled network completes in a fraction of the time compared to CPU and GPU implementations of l1 -ESPIRiT (20× and 3× speed increases, respectively). CONCLUSIONS: We have developed a deep neural network architecture to reconstruct undersampled 3D non-Cartesian VD cones iNAVs. Our approach decreases reconstruction time for 3D iNAVs, while preserving the accuracy of nonrigid motion information offered by them for correction.

4D flow vs. 2D cardiac MRI for the evaluation of pulmonary regurgitation and ventricular volume in repaired tetralogy of Fallot: a retrospective case control study.

Lengthy exams and breath-holding limit the use of pediatric cardiac MRI (CMR). 3D time-resolved flow MRI (4DF) is a free-breathing, single-sequence exam that obtains magnitude (anatomic) and phase contrast (PC) data. We compare the accuracy of gadobenate dimeglumine-enhanced 4DF on a 1.5 T magnet to 2D CMR in children with repaired tetralogy of Fallot (rTOF) to measure pulmonary net flow (PNF) as a reflection of pulmonary regurgitation, forward flow (FF) and ventricular volumetry. Thirty-four consecutive cases were included. 2D PCs were obtained at the valve level. Using 4DF, we measured PNF at the valve and at the main and branch pulmonary arteries. PNF measured at the valve by 4DF demonstrated the strongest correlation (r = 0.87, p < 0.001) and lowest mean difference (3.5 ± 9.4 mL/beat) to aortic net flow (ANF). Semilunar FF and stroke volume of the respective ventricle demonstrated moderate-strong correlation by 4DF (r = 0.66-0.81, p < 0.001) and strong correlation by 2D (r = 0.81-0.84, p < 0.001) with similar correlations and mean differences between techniques (p > 0.05). Ventricular volumes correlated strongly between 2D and 4DF (r = 0.75-0.96, p < 0.001), though 4DF overestimated right ventricle volumes by 11.8-19.2 mL/beat. Inter-rater reliability was excellent for 2D and 4DF volumetry (ICC = 0.91-0.99). Ejection fraction moderately correlated (r = 0.60-0.75, p < 0.001) with better reliability by 4DF (ICC: 0.80-0.85) than 2D (ICC: 0.69-0.89). 4DF exams were shorter than 2D (9 vs. 71 min, p < 0.001). 4DF provides highly reproducible and accurate measurements of flow with slight overestimation of RV volumes compared to 2D in pediatric rTOF. 4DF offers important advantages in this population with long-term monitoring needs.

Data-driven self-calibration and reconstruction for non-cartesian wave-encoded single-shot fast spin echo using deep learning.

BACKGROUND: Current self-calibration and reconstruction methods for wave-encoded single-shot fast spin echo imaging (SSFSE) requires long computational time, especially when high accuracy is needed. PURPOSE: To develop and investigate the clinical feasibility of data-driven self-calibration and reconstruction of wave-encoded SSFSE imaging for computation time reduction and quality improvement. STUDY TYPE: Prospective controlled clinical trial. SUBJECTS: With Institutional Review Board approval, the proposed method was assessed on 29 consecutive adult patients (18 males, 11 females, range, 24-77 years). FIELD STRENGTH/SEQUENCE: A wave-encoded variable-density SSFSE sequence was developed for clinical 3.0T abdominal scans to enable 3.5× acceleration with full-Fourier acquisitions. Data-driven calibration of wave-encoding point-spread function (PSF) was developed using a trained deep neural network. Data-driven reconstruction was developed with another set of neural networks based on the calibrated wave-encoding PSF. Training of the calibration and reconstruction networks was performed on 15,783 2D wave-encoded SSFSE abdominal images. ASSESSMENT: Image quality of the proposed data-driven approach was compared independently and blindly with a conventional approach using iterative self-calibration and reconstruction with parallel imaging and compressed sensing by three radiologists on a scale from -2 to 2 for noise, contrast, sharpness, artifacts, and confidence. Computation time of these two approaches was also compared. STATISTICAL TESTS: Wilcoxon signed-rank tests were used to compare image quality and two-tailed t-tests were used to compare computation time with P values of under 0.05 considered statistically significant. RESULTS: An average 2.1-fold speedup in computation was achieved using the proposed method. The proposed data-driven self-calibration and reconstruction approach significantly reduced the perceived noise level (mean scores 0.82, P < 0.0001). DATA CONCLUSION: The proposed data-driven calibration and reconstruction achieved twice faster computation with reduced perceived noise, providing a fast and robust self-calibration and reconstruction for clinical abdominal SSFSE imaging. LEVEL OF EVIDENCE: 1 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2020;51:841-853.

Deep residual network for off-resonance artifact correction with application to pediatric body MRA with 3D cones.

PURPOSE: To enable rapid imaging with a scan time-efficient 3D cones trajectory with a deep-learning off-resonance artifact correction technique. METHODS: A residual convolutional neural network to correct off-resonance artifacts (Off-ResNet) was trained with a prospective study of pediatric MRA exams. Each exam acquired a short readout scan (1.18 ms ± 0.38) and a long readout scan (3.35 ms ± 0.74) at 3 T. Short readout scans, with longer scan times but negligible off-resonance blurring, were used as reference images and augmented with additional off-resonance for supervised training examples. Long readout scans, with greater off-resonance artifacts but shorter scan time, were corrected by autofocus and Off-ResNet and compared with short readout scans by normalized RMS error, structural similarity index, and peak SNR. Scans were also compared by scoring on 8 anatomical features by two radiologists, using analysis of variance with post hoc Tukey's test and two one-sided t-tests. Reader agreement was determined with intraclass correlation. RESULTS: The total scan time for long readout scans was on average 59.3% shorter than short readout scans. Images from Off-ResNet had superior normalized RMS error, structural similarity index, and peak SNR compared with uncorrected images across ±1 kHz off-resonance (P < .01). The proposed method had superior normalized RMS error over -677 Hz to +1 kHz and superior structural similarity index and peak SNR over ±1 kHz compared with autofocus (P < .01). Radiologic scoring demonstrated that long readout scans corrected with Off-ResNet were noninferior to short readout scans (P < .05). CONCLUSION: The proposed method can correct off-resonance artifacts from rapid long-readout 3D cones scans to a noninferior image quality compared with diagnostically standard short readout scans.

Whole-heart coronary MR angiography using a 3D cones phyllotaxis trajectory.

PURPOSE: To develop a 3D cones steady-state free precession sequence with improved robustness to respiratory motion while mitigating eddy current artifacts for free-breathing whole-heart coronary magnetic resonance angiography. METHOD: The proposed sequence collects cone interleaves using a phyllotaxis pattern, which allows for more distributed k-space sampling for each heartbeat compared to a typical sequential collection pattern. A Fibonacci number of segments is chosen to minimize eddy current effects with the trade-off of an increased number of acquisition heartbeats. For verification, phyllotaxis-cones is compared to sequential-cones through simulations, phantom studies, and in vivo coronary scans with 8 subjects using 2D image-based navigators for retrospective motion correction. RESULTS: Simulated point spread functions and moving phantom results show less coherent motion artifacts for phyllotaxis-cones compared to sequential-cones. Assessment of the right and left coronary arteries using reader scores and the image edge profile acutance vessel sharpness metric indicate superior image quality and sharpness for phyllotaxis-cones. CONCLUSION: Phyllotaxis 3D cones results in improved qualitative image scores and coronary vessel sharpness for free-breathing whole-heart coronary magnetic resonance angiography compared to standard sequential ordering when using a steady-state free precession sequence.

Conical ultrashort echo time (UTE) MRI in the evaluation of pediatric acute appendicitis.

PURPOSE: Magnetic resonance imaging (MRI) sequences with conical k-space trajectories are able to decrease motion artifacts while achieving ultrashort echo times (UTE). We assessed the performance of free-breathing conical UTE MRI in the evaluation of the pediatric pelvis for suspected appendicitis. METHODS: Our retrospective review of 84 pediatric patients who underwent MRI for suspected appendicitis compared three contrast-enhanced sequences: free-breathing conical UTE, breath-hold three-dimensional (3D) spoiled gradient echo (BH-SPGR), and free-breathing high-resolution 3D SPGR (FB-SPGR). Two radiologists performed blinded and independent evaluations of each sequence for image quality (four point scale), anatomic delineation (four point scale), and diagnostic confidence (five point scale). Subsequently, the three sequences were directly compared for overall image quality (- 3 to + 3 scale). Scores were compared using Kruskal-Wallis and Wilcoxon signed-rank tests. RESULTS: UTE demonstrated significantly better perceived signal-to-noise ratio (SNR) and fewer artifacts than BH-SPGR and FB-SPGR (means of 3.6 and 3.4, 3.4 and 3.2, 3.1 and 2.7, respectively; p < 0.0006). BH-SPGR and FB-SPGR demonstrated significantly better contrast than UTE (means of 3.6, 3.4, and 3.2, respectively; p < 0.03). In the remaining categories, UTE performed significantly better than FB-SPGR (p < 0.00001), while there was no statistical difference between UTE and BH-SPGR. Direct paired comparisons of overall image quality demonstrated the readers significantly preferred UTE over both BH-SPGR (mean + 0.5, p < 0.00001) and FB-SPGR (mean + 1.2, p < 0.00001). CONCLUSIONS: In the evaluation of suspected appendicitis, free-breathing conical UTE MRI performed better in the assessed metrics than FB-SPGR. When compared to BH-SPGR, UTE demonstrated superior perceived SNR and fewer artifacts.

Deep Generative Adversarial Neural Networks for Compressive Sensing MRI.

Undersampled magnetic resonance image (MRI) reconstruction is typically an ill-posed linear inverse task. The time and resource intensive computations require tradeoffs between accuracy and speed. In addition, state-of-the-art compressed sensing (CS) analytics are not cognizant of the image diagnostic quality. To address these challenges, we propose a novel CS framework that uses generative adversarial networks (GAN) to model the (low-dimensional) manifold of high-quality MR images. Leveraging a mixture of least-squares (LS) GANs and pixel-wise l1/l2 cost, a deep residual network with skip connections is trained as the generator that learns to remove the aliasing artifacts by projecting onto the image manifold. The LSGAN learns the texture details, while the l1/l2 cost suppresses high-frequency noise. A discriminator network, which is a multilayer convolutional neural network (CNN), plays the role of a perceptual cost that is then jointly trained based on high-quality MR images to score the quality of retrieved images. In the operational phase, an initial aliased estimate (e.g., simply obtained by zero-filling) is propagated into the trained generator to output the desired reconstruction. This demands a very low computational overhead. Extensive evaluations are performed on a large contrast-enhanced MR dataset of pediatric patients. Images rated by expert radiologists corroborate that GANCS retrieves higher quality images with improved fine texture details compared with conventional Wavelet-based and dictionary-learning-based CS schemes as well as with deep-learning-based schemes using pixel-wise training. In addition, it offers reconstruction times of under a few milliseconds, which are two orders of magnitude faster than the current state-of-the-art CS-MRI schemes.

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.

4D flow MRI quantification of mitral and tricuspid regurgitation: Reproducibility and consistency relative to conventional MRI.

BACKGROUND: In patients with mitral or tricuspid valve regurgitation, evaluation of regurgitant severity is essential for determining the need for surgery. While transthoracic echocardiography is widely accessible, it has limited reproducibility for grading inlet valve regurgitation. Multiplanar cardiac MRI is the quantitative standard but requires specialized local expertise, and is thus not widely available. Volumetric 4D flow MRI has potential for quantitatively grading the severity of inlet valve regurgitation in adult patients. PURPOSE: To evaluate the accuracy and reproducibility of volumetric 4D flow MRI for quantification of inlet valvular regurgitation compared to conventional multiplanar MRI, which may simplify and improve accessibility of cardiac MRI. STUDY TYPE: This retrospective, HIPAA-compliant imaging-based comparison study was conducted at a single institution. SUBJECTS: Twenty-one patients who underwent concurrent multiplanar and 4D flow cardiac MRI between April 2015 and January 2017. FIELD STRENGTH/SEQUENCES: 3T; steady-state free-precession (SSFP), 2D phase contrast (2D-PC), and postcontrast 4D flow. ASSESSMENT: We evaluated the intertechnique (4D flow vs. 2D-PC), intermethod (direct vs. indirect measurement), interobserver and intraobserver reproducibility of measurements of regurgitant flow volume (RFV), fraction (RF), and volume (RVol). STATISTICAL TESTS: Statistical analysis included Pearson correlation, Bland-Altman statistics, and intraclass correlation coefficients. RESULTS: There was high concordance between 4D flow and multiplanar MRI, whether using direct or indirect methods of quantifying regurgitation (r = 0.813-0.985). Direct interrogation of the regurgitant jet with 4D flow showed high intraobserver consistency (r = 0.976-0.999) and interobserver consistency (r = 0.861-0.992), and correlated well with traditional indirect measurements obtained as the difference between stroke volume and forward outlet valve flow. DATA CONCLUSION: 4D flow MRI provides highly reproducible measurements of mitral and tricuspid regurgitant volume, and may be used in place of conventional multiplanar MRI. LEVEL OF EVIDENCE: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;48:1147-1158.

General phase regularized reconstruction using phase cycling.

PURPOSE: To develop a general phase regularized image reconstruction method, with applications to partial Fourier imaging, water-fat imaging and flow imaging. THEORY AND METHODS: The problem of enforcing phase constraints in reconstruction was studied under a regularized inverse problem framework. A general phase regularized reconstruction algorithm was proposed to enable various joint reconstruction of partial Fourier imaging, water-fat imaging and flow imaging, along with parallel imaging (PI) and compressed sensing (CS). Since phase regularized reconstruction is inherently non-convex and sensitive to phase wraps in the initial solution, a reconstruction technique, named phase cycling, was proposed to render the overall algorithm invariant to phase wraps. The proposed method was applied to retrospectively under-sampled in vivo datasets and compared with state of the art reconstruction methods. RESULTS: Phase cycling reconstructions showed reduction of artifacts compared to reconstructions without phase cycling and achieved similar performances as state of the art results in partial Fourier, water-fat and divergence-free regularized flow reconstruction. Joint reconstruction of partial Fourier + water-fat imaging + PI + CS, and partial Fourier + divergence-free regularized flow imaging + PI + CS were demonstrated. CONCLUSION: The proposed phase cycling reconstruction provides an alternative way to perform phase regularized reconstruction, without the need to perform phase unwrapping. It is robust to the choice of initial solutions and encourages the joint reconstruction of phase imaging applications. Magn Reson Med 80:112-125, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Free-breathing pediatric chest MRI: Performance of self-navigated golden-angle ordered conical ultrashort echo time acquisition.

PURPOSE: To assess the feasibility and performance of conical k-space trajectory free-breathing ultrashort echo time (UTE) chest magnetic resonance imaging (MRI) versus four-dimensional (4D) flow and effects of 50% data subsampling and soft-gated motion correction. MATERIALS AND METHODS: Thirty-two consecutive children who underwent both 4D flow and UTE ferumoxytol-enhanced chest MR (mean age: 5.4 years, range: 6 days to 15.7 years) in one 3T exam were recruited. From UTE k-space data, three image sets were reconstructed: 1) one with all data, 2) one using the first 50% of data, and 3) a final set with soft-gating motion correction, leveraging the signal magnitude immediately after each excitation. Two radiologists in blinded fashion independently scored image quality of anatomical landmarks on a 5-point scale. Ratings were compared using Wilcoxon rank-sum, Wilcoxon signed-ranks, and Kruskal-Wallis tests. Interobserver agreement was assessed with the intraclass correlation coefficient (ICC). RESULTS: For fully sampled UTE, mean scores for all structures were ≥4 (good-excellent). Full UTE surpassed 4D flow for lungs and airways (P < 0.001), with similar pulmonary artery (PA) quality (P = 0.62). 50% subsampling only slightly degraded all landmarks (P < 0.001), as did motion correction. Subsegmental PA visualization was possible in >93% scans for all techniques (P = 0.27). Interobserver agreement was excellent for combined scores (ICC = 0.83). CONCLUSION: High-quality free-breathing conical UTE chest MR is feasible, surpassing 4D flow for lungs and airways, with equivalent PA visualization. Data subsampling only mildly degraded images, favoring lesser scan times. Soft-gating motion correction overall did not improve image quality. LEVEL OF EVIDENCE: 2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;47:200-209.