Distortionless, free-breathing, and respiratory resolved 3D diffusion weighted imaging of the abdomen.

PURPOSE: Abdominal imaging is frequently performed with breath holds or respiratory triggering to reduce the effects of respiratory motion. Diffusion weighted sequences provide a useful clinical contrast but have prolonged scan times due to low signal-to-noise ratio (SNR), and cannot be completed in a single breath hold. Echo-planar imaging (EPI) is the most commonly used trajectory for diffusion weighted imaging but it is susceptible to off-resonance artifacts. A respiratory resolved, three-dimensional (3D) diffusion prepared sequence that obtains distortionless diffusion weighted images during free-breathing is presented. Techniques to address the myriad of challenges including: 3D shot-to-shot phase correction, respiratory binning, diffusion encoding during free-breathing, and robustness to off-resonance are described. METHODS: A twice-refocused, M1-nulled diffusion preparation was combined with an RF-spoiled gradient echo readout and respiratory resolved reconstruction to obtain free-breathing diffusion weighted images in the abdomen. Cartesian sampling permits a sampling density that enables 3D shot-to-shot phase navigation and reduction of transient fat artifacts. Theoretical properties of a region-based shot rejection are described. The region-based shot rejection method was evaluated with free-breathing (normal and exaggerated breathing), and respiratory triggering. The proposed sequence was compared in vivo with multishot DW-EPI. RESULTS: The proposed sequence exhibits no evident distortion in vivo when compared to multishot DW-EPI, robustness to B0 and B1 field inhomogeneities, and robustness to motion from different respiratory patterns. CONCLUSION: Acquisition of distortionless, diffusion weighted images is feasible during free-breathing with a b-value of 500 s/mm2, scan time of 6 min, and a clinically viable reconstruction time.

Accelerating High b-Value Diffusion-Weighted MRI Using a Convolutional Recurrent Neural Network (CRNN-DWI).

PURPOSE: To develop a novel convolutional recurrent neural network (CRNN-DWI) and apply it to reconstruct a highly undersampled (up to six-fold) multi-b-value, multi-direction diffusion-weighted imaging (DWI) dataset. METHODS: A deep neural network that combines a convolutional neural network (CNN) and recurrent neural network (RNN) was first developed by using a set of diffusion images as input. The network was then used to reconstruct a DWI dataset consisting of 14 b-values, each with three diffusion directions. For comparison, the dataset was also reconstructed with zero-padding and 3D-CNN. The experiments were performed with undersampling rates (R) of 4 and 6. Standard image quality metrics (SSIM and PSNR) were employed to provide quantitative assessments of the reconstructed image quality. Additionally, an advanced non-Gaussian diffusion model was employed to fit the reconstructed images from the different approaches, thereby generating a set of diffusion parameter maps. These diffusion parameter maps from the different approaches were then compared using SSIM as a metric. RESULTS: Both the reconstructed diffusion images and diffusion parameter maps from CRNN-DWI were better than those from zero-padding or 3D-CNN. Specifically, the average SSIM and PSNR of CRNN-DWI were 0.750 ± 0.016 and 28.32 ± 0.69 (R = 4), and 0.675 ± 0.023 and 24.16 ± 0.77 (R = 6), respectively, both of which were substantially higher than those of zero-padding or 3D-CNN reconstructions. The diffusion parameter maps from CRNN-DWI also yielded higher SSIM values for R = 4 (>0.8) and for R = 6 (>0.7) than the other two approaches (for R = 4, <0.7, and for R = 6, <0.65). CONCLUSIONS: CRNN-DWI is a viable approach for reconstructing highly undersampled DWI data, providing opportunities to reduce the data acquisition burden.

Motion-compensated low-rank reconstruction for simultaneous structural and functional UTE lung MRI.

PURPOSE: Three-dimensional UTE MRI has shown the ability to provide simultaneous structural and functional lung imaging, but it is limited by respiratory motion and relatively low lung parenchyma SNR. The purpose of this paper is to improve this imaging by using a respiratory phase-resolved reconstruction approach, named motion-compensated low-rank reconstruction (MoCoLoR), which directly incorporates motion compensation into a low-rank constrained reconstruction model for highly efficient use of the acquired data. THEORY AND METHODS: The MoCoLoR reconstruction is formulated as an optimization problem that includes a low-rank constraint using estimated motion fields to reduce the rank, optimizing over both the motion fields and reconstructed images. The proposed reconstruction along with XD and motion state-weighted motion-compensation (MostMoCo) methods were applied to 18 lung MRI scans of pediatric and young adult patients. The data sets were acquired under free-breathing and without sedation with 3D radial UTE sequences in approximately 5 min. After reconstruction, they went through ventilation analyses. Performance across reconstruction regularization and motion-state parameters were also investigated. RESULTS: The in vivo experiments results showed that MoCoLoR made efficient use of the data, provided higher apparent SNR compared with state-of-the-art XD reconstruction and MostMoCo reconstructions, and yielded high-quality respiratory phase-resolved images for ventilation mapping. The method was effective across the range of patients scanned. CONCLUSION: The motion-compensated low-rank regularized reconstruction approach makes efficient use of acquired data and can improve simultaneous structural and functional lung imaging with 3D-UTE MRI. It enables the scanning of pediatric patients under free-breathing and without sedation.

SLfRank: Shinnar-Le-Roux Pulse Design With Reduced Energy and Accurate Phase Profiles Using Rank Factorization.

The Shinnar-Le-Roux (SLR) algorithm is widely used to design frequency selective pulses with large flip angles. We improve its design process to generate pulses with lower energy (by as much as 26%) and more accurate phase profiles. Concretely, the SLR algorithm consists of two steps: (1) an invertible transform between frequency selective pulses and polynomial pairs that represent Cayley-Klein (CK) parameters and (2) the design of the CK polynomial pair to match the desired magnetization profiles. Because the CK polynomial pair is bi-linearly coupled, the original algorithm sequentially solves for each polynomial instead of jointly. This results in sub-optimal pulses. Instead, we leverage a convex relaxation technique, commonly used for low rank matrix recovery, to address the bi-linearity. Our numerical experiments show that the resulting pulses are almost always globally optimal in practice. For slice excitation, the proposed algorithm results in more accurate linear phase profiles. And in general the improved pulses have lower energy than the original SLR pulses.

Deep Learning-Based Reconstruction for Cardiac MRI: A Review.

Cardiac magnetic resonance (CMR) is an essential clinical tool for the assessment of cardiovascular disease. Deep learning (DL) has recently revolutionized the field through image reconstruction techniques that allow unprecedented data undersampling rates. These fast acquisitions have the potential to considerably impact the diagnosis and treatment of cardiovascular disease. Herein, we provide a comprehensive review of DL-based reconstruction methods for CMR. We place special emphasis on state-of-the-art unrolled networks, which are heavily based on a conventional image reconstruction framework. We review the main DL-based methods and connect them to the relevant conventional reconstruction theory. Next, we review several methods developed to tackle specific challenges that arise from the characteristics of CMR data. Then, we focus on DL-based methods developed for specific CMR applications, including flow imaging, late gadolinium enhancement, and quantitative tissue characterization. Finally, we discuss the pitfalls and future outlook of DL-based reconstructions in CMR, focusing on the robustness, interpretability, clinical deployment, and potential for new methods.

Accelerated two-dimensional phase-contrast for cardiovascular MRI using deep learning-based reconstruction with complex difference estimation.

PURPOSE: To develop and validate a deep learning-based reconstruction framework for highly accelerated two-dimensional (2D) phase contrast (PC-MRI) data with accurate and precise quantitative measurements. METHODS: We propose a modified DL-ESPIRiT reconstruction framework for 2D PC-MRI, comprised of an unrolled neural network architecture with a Complex Difference estimation (CD-DL). CD-DL was trained on 155 fully sampled 2D PC-MRI pediatric clinical datasets. The fully sampled data ( n = 29 $$ n=29 $$ ) was retrospectively undersampled (6-11 × $$ \times $$ ) and reconstructed using CD-DL and a parallel imaging and compressed sensing method (PICS). Measurements of peak velocity and total flow were compared to determine the highest acceleration rate that provided accuracy and precision within ± 5 % $$ \pm 5\% $$ . Feasibility of CD-DL was demonstrated on prospectively undersampled datasets acquired in pediatric clinical patients ( n = 5 $$ n=5 $$ ) and compared to traditional parallel imaging (PI) and PICS. RESULTS: The retrospective evaluation showed that 9 × $$ \times $$ accelerated 2D PC-MRI images reconstructed with CD-DL provided accuracy and precision (bias, [95 % $$ \% $$ confidence intervals]) within ± 5 % $$ \pm 5\% $$ . CD-DL showed higher accuracy and precision compared to PICS for measurements of peak velocity (2.8 % $$ \% $$ [ - 2 . 9 $$ -2.9 $$ , 4.5] vs. 3.9 % $$ \% $$ [ - 11 . 0 $$ -11.0 $$ , 4.9]) and total flow (1.8 % $$ \% $$ [ - 3 . 9 $$ -3.9 $$ , 3.4] vs. 2.9 % $$ \% $$ [ - 7 . 1 $$ -7.1 $$ , 6.9]). The prospective feasibility study showed that CD-DL provided higher accuracy and precision than PICS for measurements of peak velocity and total flow. CONCLUSION: In a retrospective evaluation, CD-DL produced quantitative measurements of 2D PC-MRI peak velocity and total flow with ≤ 5 % $$ \le 5\% $$ error in both accuracy and precision for up to 9 × $$ \times $$ acceleration. Clinical feasibility was demonstrated using a prospective clinical deployment of our 8 × $$ \times $$ undersampled acquisition and CD-DL reconstruction in a cohort of pediatric patients.

Rapid fat-water separated T1 mapping using a single-shot radial inversion-recovery spoiled gradient recalled pulse sequence.

T1 mapping is increasingly used in clinical practice and research studies. With limited scan time, existing techniques often have limited spatial resolution, contrast resolution and slice coverage. High fat concentrations yield complex errors in Look-Locker T1 methods. In this study, a dual-echo 2D radial inversion-recovery T1 (DEradIR-T1) technique was developed for fast fat-water separated T1 mapping. The DEradIR-T1 technique was tested in phantoms, 5 volunteers and 28 patients using a 3 T clinical MRI scanner. In our study, simulations were performed to analyze the composite (fat + water) and water-only T1 under different echo times (TE). In standardized phantoms, an inversion-recovery spin echo (IR-SE) sequence with and without fat saturation pulses served as a T1 reference. Parameter mapping with DEradIR-T1 was also assessed in vivo, and values were compared with modified Look-Locker inversion recovery (MOLLI). Bland-Altman analysis and two-tailed paired t-tests were used to compare the parameter maps from DEradIR-T1 with the references. Simulations of the composite and water-only T1 under different TE values and levels of fat matched the in vivo studies. T1 maps from DEradIR-T1 on a NIST phantom (Pcomp = 0.97) and a Calimetrix fat-water phantom (Pwater = 0.56) matched with the references. In vivo T1 was compared with that of MOLLI: R comp 2 = 0.77 ; R water 2 = 0.72 . In this work, intravoxel fat is found to have a variable, echo-time-dependent effect on measured T1 values, and this effect may be mitigated using the proposed DRradIR-T1.

Improving high frequency image features of deep learning reconstructions via k-space refinement with null-space kernel.

PURPOSE: Deep learning (DL) based reconstruction using unrolled neural networks has shown great potential in accelerating MRI. However, one of the major drawbacks is the loss of high-frequency details and textures in the output. The purpose of the study is to propose a novel refinement method that uses null-space kernel to refine k-space and improve blurred image details and textures. METHODS: The proposed method constrains the output of the DL to comply to the linear neighborhood relationship calibrated in the auto-calibration lines. To demonstrate efficacy, we tested our refinement method on the DL reconstruction under a variety of conditions (i.e., dataset, unrolled neural networks, and under-sampling scheme). Specifically, the method was tested on three large-scale public datasets (knee and brain) from fastMRI's multi-coil track. RESULTS: The proposed scheme visually reduces the structural error in the k-space domain, enhance the homogeneity of the k-space intensity. Consequently, reconstructed image shows sharper images with enhanced details and textures. The proposed method is also successful in improving high-frequency image details (SSIM, GMSD) without sacrificing overall image error (PSNR). CONCLUSION: Our findings imply that refining DL output using the proposed method may generally improve DL reconstruction as tested with various large-scale dataset and networks.

Artifact- and content-specific quality assessment for MRI with image rulers.

In clinical practice MR images are often first seen by radiologists long after the scan. If image quality is inadequate either patients have to return for an additional scan, or a suboptimal interpretation is rendered. An automatic image quality assessment (IQA) would enable real-time remediation. Existing IQA works for MRI give only a general quality score, agnostic to the cause of and solution to low-quality scans. Furthermore, radiologists' image quality requirements vary with the scan type and diagnostic task. Therefore, the same score may have different implications for different scans. We propose a framework with multi-task CNN model trained with calibrated labels and inferenced with image rulers. Labels calibrated by human inputs follow a well-defined and efficient labeling task. Image rulers address varying quality standards and provide a concrete way of interpreting raw scores from the CNN. The model supports assessments of two of the most common artifacts in MRI: noise and motion. It achieves accuracies of around 90%, 6% better than the best previous method examined, and 3% better than human experts on noise assessment. Our experiments show that label calibration, image rulers, and multi-task training improve the model's performance and generalizability.

Volumetric and multispectral DWI near metallic implants using a non-linear phase Carr-Purcell-Meiboom-Gill diffusion preparation.

PURPOSE: DWI near metal implants has not been widely explored due to substantial challenges associated with through-slice and in-plane distortions, the increased encoding requirement of different spectral bins, and limited SNR. There is no widely adopted clinical protocol for DWI near metal since the commonly used EPI trajectory fails completely due to distortion from extreme off-resonance ranging from 2 to 20 kHz. We present a sequence that achieves DWI near metal with moderate b-values (400-500 s/mm2 ) and volumetric coverage in clinically feasible scan times. THEORY AND METHODS: Multispectral excitation with Cartesian sampling, view angle tilting, and kz phase encoding reduce in-plane and through-plane off-resonance artifacts, and Carr-Purcell-Meiboom-Gill (CPMG) spin-echo refocusing trains counteract T2* effects. The effect of random phase on the refocusing train is eliminated using a stimulated echo diffusion preparation. Root-flipped Shinnar-Le Roux refocusing pulses permits preparation of a high spectral bandwidth, which improves imaging times by reducing the number of excitations required to cover the desired spectral range. B1 sensitivity is reduced by using an excitation that satisfies the CPMG condition in the preparation. A method for ADC quantification insensitive to background gradients is presented. RESULTS: Non-linear phase refocusing pulses reduces the peak B1 by 46% which allows RF bandwidth to be doubled. Simulations and phantom experiments show that a non-linear phase CPMG pulse pair reduces B1 sensitivity. Application in vivo demonstrates complementary contrast to conventional multispectral acquisitions and improved visualization compared to DW-EPI. CONCLUSION: Volumetric and multispectral DW imaging near metal can be achieved with a 3D encoded sequence.

Deep Learning Automated Background Phase Error Correction for Abdominopelvic 4D Flow MRI.

Background Four-dimensional (4D) flow MRI has the potential to provide hemodynamic insights for a variety of abdominopelvic vascular diseases, but its clinical utility is currently impaired by background phase error, which can be challenging to correct. Purpose To assess the feasibility of using deep learning to automatically perform image-based background phase error correction in 4D flow MRI and to compare its effectiveness relative to manual image-based correction. Materials and Methods A convenience sample of 139 abdominopelvic 4D flow MRI acquisitions performed between January 2016 and July 2020 was retrospectively collected. Manual phase error correction was performed using dedicated imaging software and served as the reference standard. After reserving 40 examinations for testing, the remaining examinations were randomly divided into training (86% [85 of 99]) and validation (14% [14 of 99]) data sets to train a multichannel three-dimensional U-Net convolutional neural network. Flow measurements were obtained for the infrarenal aorta, common iliac arteries, common iliac veins, and inferior vena cava. Statistical analyses included Pearson correlation, Bland-Altman analysis, and F tests with Bonferroni correction. Results A total of 139 patients (mean age, 47 years ± 14 [standard deviation]; 108 women) were included. Inflow-outflow correlation improved after manual correction (ρ = 0.94, P < .001) compared with that before correction (ρ = 0.50, P < .001). Automated correction showed similar results (ρ = 0.91, P < .001) and demonstrated very strong correlation with manual correction (ρ = 0.98, P < .001). Both correction methods reduced inflow-outflow variance, improving mean difference from -0.14 L/min (95% limits of agreement: -1.61, 1.32) (uncorrected) to 0.05 L/min (95% limits of agreement: -0.32, 0.42) (manually corrected) and 0.05 L/min (95% limits of agreement: -0.38, 0.49) (automatically corrected). There was no significant difference in inflow-outflow variance between manual and automated correction methods (P = .10). Conclusion Deep learning automated phase error correction reduced inflow-outflow bias and variance of volumetric flow measurements in four-dimensional flow MRI, achieving results comparable with manual image-based phase error correction. © RSNA, 2021 See also the editorial by Roldán-Alzate and Grist in this issue.

Upstream Machine Learning in Radiology.

Machine learning (ML) and Artificial intelligence (AI) has the potential to dramatically improve radiology practice at multiple stages of the imaging pipeline. Most of the attention has been garnered by applications focused on improving the end of the pipeline: image interpretation. However, this article reviews how AI/ML can be applied to improve upstream components of the imaging pipeline, including exam modality selection, hardware design, exam protocol selection, data acquisition, image reconstruction, and image processing. A breadth of applications and their potential for impact is shown across multiple imaging modalities, including ultrasound, computed tomography, and MRI.

Zero echo time pediatric musculoskeletal magnetic resonance imaging: initial experience.

BACKGROUND: Projection radiography (XR) is often supplemented by both CT (to evaluate osseous structures with ionizing radiation) and MRI (for marrow and soft-tissue assessment). Zero echo time (ZTE) MR imaging produces a "CT-like" osseous contrast that might obviate CT. OBJECTIVE: This study investigated our institution's initial experience in implementing an isotropic ZTE MR imaging sequence for pediatric musculoskeletal examinations. MATERIALS AND METHODS: Pediatric patients referred for extremity MRI at 3 tesla (T) underwent ZTE MR imaging to yield images with contrast similar to that of CT. A radiograph-like image was also created with ray-sum image processing. We assessed ZTE-CT/XR anatomical image quality (Sanat) from 0 (nondiagnostic) to 5 (outstanding). Further, we made image comparisons on a 5-point scale (Scomp) (range of -2 = conventional CT/XR greater anatomical delineation to +2 = ZTE-CT/XR greater anatomical delineation; 0=same) for three cohorts: (1) ZTE-XR to conventional radiography, (2) ZTE-CT to conventional CT and (3) pathological lesion assessment on ZTE-XR to conventional radiography. We measured cortical thickness of ZTE-XR and ZTE-CT and compared these with conventional imaging. We calculated confidence interval of proportions, Wilcoxon rank sum test and intraclass correlation coefficients for inter-reader agreement. RESULTS: Cohorts 1, 2 and 3 consisted of 40, 20 and 35 cases, respectively (age range 0.6-23.0 years). ZTE-CT versus CT and ZTE-XR versus radiography of cortical thicknesses were not significantly different (P=0.55 and P=0.31, respectively). Cortical delineation was rated diagnostic or better (score of 3, 4 or 5) in all cases (confidence interval of proportions = 100%) for ZTE-CT/XR. Similarly, intramedullary cavity delineation was rated diagnostic or better in all cases for ZTE-CT, and ZTE-XR was at least diagnostic in 58-63% of cases. For cohort 2, cortex and intramedullary cavity Scomp for ZTE-CT was comparable to those of conventional CT, with confidence interval of proportion (sum of score of -1 to +2) of 93-100% and 95%, respectively. Pathology visualized on ZTE-CT/XR was comparable; Scomp confidence interval of proportions was 95%/97-100%, with improved delineation of non-displaced fractures on ZTE-XR. Readers had moderate to near-perfect intraclass correlation coefficient (range=0.60-0.93). CONCLUSION: Implementation of a diagnostic-quality ZTE MRI sequence in the pediatric population is feasible and can be performed as a complementary pulse sequence to enhance musculoskeletal MRI studies. Compared to conventional CT, ZTE has comparable cortical delineation, intramedullary cavity and pathology visualization. While not intended as a replacement for conventional radiography, ZTE-XR provides similar visualization of pathology.

Free-breathing Accelerated Cardiac MRI Using Deep Learning: Validation in Children and Young Adults.

Background Obtaining ventricular volumetry and mass is key to most cardiac MRI but challenged by long multibreath-hold acquisitions. Purpose To assess the image quality and performance of a highly accelerated, free-breathing, two-dimensional cine cardiac MRI sequence incorporating deep learning (DL) reconstruction compared with reference standard balanced steady-state free precession (bSSFP). Materials and Methods A DL algorithm was developed to reconstruct custom 12-fold accelerated bSSFP cardiac MRI cine images from coil sensitivity maps using 15 iterations of separable three-dimensional convolutions and data consistency steps. The model was trained, validated, and internally tested in 10, two, and 10 adult human volunteers, respectively, based on vendor partner-supplied fully sampled bSSFP acquisitions. For prospective external clinical validation, consecutive children and young adults undergoing cardiac MRI from September through December 2019 at a single children's hospital underwent both conventional and highly accelerated short-axis bSSFP cine acquisitions in one MRI examination. Two radiologists scored overall and volumetric three-dimensional mesh image quality of all short-axis stacks on a five-point Likert scale and manually segmented endocardial and epicardial contours. Scan times and image quality were compared using the Wilcoxon rank sum test. Measurement agreement was assessed with intraclass correlation coefficient and Bland-Altman analysis. Results Fifty participants (mean age, 16 years ± 4 [standard deviation]; range, 5-30 years; 29 men) were evaluated. The mean prescribed acquisition times of accelerated scans (non-breath-held) and bSSFP (excluding breath-hold time) were 0.9 minute ± 0.3 versus 3.0 minutes ± 1.9 (P < .001). Overall and three-dimensional mesh image quality scores were, respectively, 3.8 ± 0.6 versus 4.3 ± 0.6 (P < .001) and 4.0 ± 1.0 versus 4.4 ± 0.8 (P < .001). Raters had strong agreement between all bSSFP and DL measurements, with intraclass correlation coefficients of 0.76 to 0.97, near-zero mean differences, and narrow limits of agreement. Conclusion With slightly lower image quality yet much faster speed, deep learning reconstruction may allow substantially shorter acquisition times of cardiac MRI compared with conventional balanced steady-state free precession MRI performed for ventricular volumetry. © RSNA, 2021 Online supplemental material is available for this article.

Quantification of the Hemodynamic Changes of Cirrhosis with Free-Breathing Self-Navigated MRI.

BACKGROUND: Non-invasive assessment of the hemodynamic changes of cirrhosis might help guide management of patients with liver disease but are currently limited. PURPOSE: To determine whether free-breathing 4D flow MRI can be used to quantify the hemodynamic effects of cirrhosis and introduce hydraulic circuit indexes of severity. STUDY TYPE: Retrospective. POPULATION: Forty-seven patients including 26 with cirrhosis. FIELD STRENGTH/SEQUENCE: 3 T/free-breathing 4D flow MRI with soft gating and golden-angle view ordering. ASSESSMENT: Measurements of the supra-celiac abdominal aorta, supra-renal abdominal aorta (SRA), celiac trunk (CeT), superior mesenteric artery (SMA), splenic artery (SpA), common hepatic artery (CHA), portal vein (PV), and supra-renal inferior vena cava (IVC) were made by two radiologists. Measures of hepatic vascular resistance (hepatic arterial relative resistance [HARR]; portal resistive index [PRI]) were proposed and calculated. STATISTICAL ANALYSIS: Bland-Altman, Pearson's correlation, Tukey's multiple comparison, and Cohen's kappa. P < 0.05 was considered significant. RESULTS: Forty-four of 47 studies yielded adequate image quality for flow quantification (94%). Arterial structures showed high inter-reader concordance (range; ρ = 0.948-0.987) and the IVC (ρ = 0.972), with moderate concordance in the PV (ρ = 0.866). Conservation of mass analysis showed concordance between large vessels (SRA vs. IVC; ρ = 0.806), small vessels (celiac vs. CHA + SpA; ρ = 0.939), and across capillary beds (CeT + SMA vs. PV; ρ = 0.862). Splanchnic flow was increased in patients with portosystemic shunting (PSS) relative to control patients and patients with cirrhosis without PSS (P < 0.05, difference range 0.11-0.68 liter/m). HARR was elevated and PRI was decreased in patients with PSS (3.55 and 1.49, respectively) compared to both the control (2.11/3.18) and non-PSS (2.11/2.35) cohorts. DATA CONCLUSION: 4D flow MRI with self-navigation was technically feasible, showing promise in quantifying the hemodynamic effects of cirrhosis. Proposed quantitative metrics of hepatic vascular resistance correlated with PSS. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 2.

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.

Prospective Deployment of Deep Learning in MRI: A Framework for Important Considerations, Challenges, and Recommendations for Best Practices.

Artificial intelligence algorithms based on principles of deep learning (DL) have made a large impact on the acquisition, reconstruction, and interpretation of MRI data. Despite the large number of retrospective studies using DL, there are fewer applications of DL in the clinic on a routine basis. To address this large translational gap, we review the recent publications to determine three major use cases that DL can have in MRI, namely, that of model-free image synthesis, model-based image reconstruction, and image or pixel-level classification. For each of these three areas, we provide a framework for important considerations that consist of appropriate model training paradigms, evaluation of model robustness, downstream clinical utility, opportunities for future advances, as well recommendations for best current practices. We draw inspiration for this framework from advances in computer vision in natural imaging as well as additional healthcare fields. We further emphasize the need for reproducibility of research studies through the sharing of datasets and software. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY STAGE: 2.

Wasserstein GANs for MR Imaging: From Paired to Unpaired Training.

Lack of ground-truth MR images impedes the common supervised training of neural networks for image reconstruction. To cope with this challenge, this article leverages unpaired adversarial training for reconstruction networks, where the inputs are undersampled k-space and naively reconstructed images from one dataset, and the labels are high-quality images from another dataset. The reconstruction networks consist of a generator which suppresses the input image artifacts, and a discriminator using a pool of (unpaired) labels to adjust the reconstruction quality. The generator is an unrolled neural network - a cascade of convolutional and data consistency layers. The discriminator is also a multilayer CNN that plays the role of a critic scoring the quality of reconstructed images based on the Wasserstein distance. Our experiments with knee MRI datasets demonstrate that the proposed unpaired training enables diagnostic-quality reconstruction when high-quality image labels are not available for the input types of interest, or when the amount of labels is small. In addition, our adversarial training scheme can achieve better image quality (as rated by expert radiologists) compared with the paired training schemes with pixel-wise loss.

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.