68Ga-RM2 PET-MRI versus MRI alone for evaluation of patients with biochemical recurrence of prostate cancer: a single-centre, single-arm, phase 2/3 imaging trial.

BACKGROUND: National Comprehensive Cancer Network guidelines include prostate-specific membrane antigen (PSMA)-targeted PET for detection of biochemical recurrence of prostate cancer. However, targeting a single tumour characteristic might not be sufficient to reflect the full extent of disease. Gastrin releasing peptide receptors (GRPR) have been shown to be overexpressed in prostate cancer. In this study, we aimed to evaluate the diagnostic performance of the GRPR-targeting radiopharmaceutical 68Ga-RM2 in patients with biochemical recurrence of prostate cancer. METHODS: This single-centre, single-arm, phase 2/3 trial was done at Stanford University (USA). Adult patients (aged ≥18 years) with biochemical recurrence of prostate cancer, a Karnofsky performance status of 50 or higher, increasing prostate-specific antigen concentration 0·2 ng/mL or more after prostatectomy or 2 ng/mL or more above nadir after radiotherapy, and non-contributory conventional imaging (negative CT or MRI, and bone scan) were eligible. All participants underwent 68Ga-RM2 PET-MRI. The primary outcome was the proportion of patients with PET-positive findings on 68Ga-RM2 PET-MRI compared with MRI alone after initial therapy, at a per-patient and per-lesion level. The primary outcome would be considered met if at least 30% of patients had one or more lesions detected by 68Ga-RM2 PET-MRI and the detection by 68Ga-RM2 PET-MRI was significantly greater than for MRI. Each PET scan was interpreted by three independent masked readers using a standardised evaluation criteria. This study is registered with ClinicalTrials.gov, NCT02624518, and is complete. FINDINGS: Between Dec 12, 2015, and July 27, 2021, 209 men were screened for eligibility, of whom 100 were included in analyses. Median follow-up was 49·3 months (IQR 36·7-59·2). The primary endpoint was met; 68Ga-RM2 PET-MRI was positive in 69 (69%) patients and MRI alone was positive in 40 (40%) patients (p<0·0001). In the per-lesion analysis 68Ga-RM2 PET-MRI showed significantly higher detection rates than MRI alone (143 vs 96 lesions; p<0·0001). No grade 1 or worse events were reported. INTERPRETATION: 68Ga-RM2 PET-MRI showed better diagnostic performance than MRI alone in patients with biochemical recurrence of prostate cancer. Further prospective comparative studies with PSMA-targeted PET are needed to gain a better understanding of GRPR and PSMA expression patterns in these patients. FUNDING: The US Department of Defense.

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.

Practical Application of Multivendor MRI-Based R2* Mapping for Liver Iron Quantification at 1.5 T and 3.0 T.

BACKGROUND: Recent multicenter, multivendor MRI-based R2* vs. liver iron concentration (LIC) calibrations (i.e., MCMV calibrations) may facilitate broad clinical dissemination of R2*-based LIC quantification. However, these calibrations are based on a centralized offline R2* reconstruction, and their applicability with vendor-provided R2* maps is unclear. PURPOSE: To determine R2* ranges of agreement between the centralized and three MRI vendors' R2* reconstructions. STUDY TYPE: Prospective. SUBJECTS: Two hundred and seven subjects (mean age 37.6 ± 19.6 years; 117 male) with known or suspected iron overload from four academic medical centers. FIELD STRENGTH/SEQUENCE: Standardized multiecho spoiled gradient echo sequence at 1.5 T and 3.0 T for R2* mapping and a multiple spin-echo sequence at 1.5 T for LIC quantification. MRI vendors: GE Healthcare, Philips Healthcare, and Siemens Healthineers. ASSESSMENT: R2* maps were generated using both the centralized and vendor reconstructions, and ranges of agreement were determined. R2*-LIC linear calibrations were determined for each site, field strength, and reconstruction and compared with the MCMV calibrations. STATISTICAL TESTS: Bland-Altman analysis to determine ranges of agreement. Linear regression, analysis of covariance F tests, and Tukey's multiple comparison testing to assess reproducibility of calibrations across sites and vendors. A P value <0.05 was considered significant. RESULTS: The upper limits of R2* ranges of agreement were approximately 500, 375, and 330 s-1 for GE, Philips, and Siemens reconstructions, respectively, at 1.5 T and approximately 700 and 800 s-1 for GE and Philips, respectively, at 3.0 T. Within the R2* ranges of agreement, vendor R2*-LIC calibrations demonstrated high reproducibility (no significant differences between slopes or intercepts; P ≥ 0.06) and agreed with the MCMV calibrations (overlapping 95% confidence intervals). DATA CONCLUSION: Based on the determined upper limits, R2* measurements obtained from vendor-provided R2* maps may be reliably and practically used to quantify LIC less than approximately 8-13 mg/g using the MCMV calibrations and similar acquisition parameters as this study. EVIDENCE LEVEL: 1 TECHNICAL EFFICACY: Stage 3.

Multicenter Reproducibility of Liver Iron Quantification with 1.5-T and 3.0-T MRI.

Background MRI is a standard of care tool to measure liver iron concentration (LIC). Compared with regulatory-approved R2 MRI, R2* MRI has superior speed and is available in most MRI scanners; however, the cross-vendor reproducibility of R2*-based LIC estimation remains unknown. Purpose To evaluate the reproducibility of LIC via single-breath-hold R2* MRI at both 1.5 T and 3.0 T with use of a multicenter, multivendor study. Materials and Methods Four academic medical centers using MRI scanners from three different vendors (three 1.5-T scanners, one 2.89-T scanner, and two 3.0-T scanners) participated in this prospective cross-sectional study. Participants with known or suspected liver iron overload were recruited to undergo multiecho gradient-echo MRI for R2* mapping at 1.5 T and 3.0 T (2.89 T or 3.0 T) on the same day. R2* maps were reconstructed from the multiecho images and analyzed at a single center. Reference LIC measurements were obtained with a commercial R2 MRI method performed using standardized 1.5-T spin-echo imaging. R2*-versus-LIC calibrations were generated across centers and field strengths using linear regression and compared using F tests. Receiver operating characteristic (ROC) curve analysis was used to determine the diagnostic performance of R2* MRI in the detection of clinically relevant LIC thresholds. Results A total of 207 participants (mean age, 38 years ± 20 [SD]; 117 male participants) were evaluated between March 2015 and September 2019. A linear relationship was confirmed between R2* and LIC. All calibrations within the same field strength were highly reproducible, showing no evidence of statistically significant center-specific differences (P > .43 across all comparisons). Calibrations for 1.5 T and 3.0 T were generated, as follows: for 1.5 T, LIC (in milligrams per gram [dry weight]) = -0.16 + 2.603 × 10-2 R2* (in seconds-1); for 2.89 T, LIC (in milligrams per gram) = -0.03 + 1.400 × 10-2 R2* (in seconds-1); for 3.0 T, LIC (in milligrams per gram) = -0.03 + 1.349 × 10-2 R2* (in seconds-1). Liver R2* had high diagnostic performance in the detection of clinically relevant LIC thresholds (area under the ROC curve, >0.98). Conclusion R2* MRI enabled accurate and reproducible quantification of liver iron overload over clinically relevant ranges of liver iron concentration (LIC). The data generated in this study provide the necessary calibrations for broad clinical dissemination of R2*-based LIC quantification. ClinicalTrials.gov registration no.: NCT02025543 © RSNA, 2022 Online supplemental material is available for this article.

Validation of liver quantitative susceptibility mapping across imaging parameters at 1.5 T and 3.0 T using SQUID susceptometry as reference.

PURPOSE: To validate QSM-based biomagnetic liver susceptometry (BLS) to measure liver iron overload at 1.5 T and 3.0 T using superconducting quantum interference devices (SQUID)-based BLS as reference. METHODS: Subjects with known or suspected iron overload were recruited for QSM-BLS at 1.5 T and 3.0 T using eight different protocols. SQUID-BLS was also obtained in each subject to provide susceptibility reference. A recent QSM method based on data-adaptive regularization was used to obtain susceptibility and R 2 * $$ {\mathrm{R}}_2^{\ast } $$ maps. Measurements of susceptibility and R 2 * $$ {\mathrm{R}}_2^{\ast } $$ were obtained in the right liver lobe. Linear mixed-effects analysis was used to estimate the contribution of specific acquisition parameters to QSM-BLS. Linear regression and Bland-Altman analyses were used to assess the relationship between QSM-BLS and SQUID-BLS/ R 2 * $$ {\mathrm{R}}_2^{\ast } $$ . RESULTS: Susceptibility maps showed high subjective quality for each acquisition protocol across different iron levels. High linear correlation was observed between QSM-BLS and SQUID-BLS at 1.5 T (r2 range, [0.82, 0.84]) and 3.0 T (r2 range, [0.77, 0.85]) across different acquisition protocols. QSM-BLS and R 2 * $$ {\mathrm{R}}_2^{\ast } $$ were highly correlated at both field strengths (r2 range at 1.5 T, [0.94, 0.99]; 3.0 T, [0.93, 0.99]). High correlation (r2  = 0.99) between 1.5 T and 3.0 T QSM-BLS, with narrow reproducibility coefficients (range, [0.13, 0.21] ppm) were observed for each protocol. CONCLUSION: This work evaluated the feasibility and performance of liver QSM-BLS across iron levels and acquisition protocols at 1.5 T and 3.0 T. High correlation and reproducibility were observed between QSM-BLS and SQUID-BLS across protocols and field strengths. In summary, QSM-BLS may enable reliable and reproducible quantification of liver iron concentration.

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.

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.

Noise2Recon: Enabling SNR-robust MRI reconstruction with semi-supervised and self-supervised learning.

PURPOSE: To develop a method for building MRI reconstruction neural networks robust to changes in signal-to-noise ratio (SNR) and trainable with a limited number of fully sampled scans. METHODS: We propose Noise2Recon, a consistency training method for SNR-robust accelerated MRI reconstruction that can use both fully sampled (labeled) and undersampled (unlabeled) scans. Noise2Recon uses unlabeled data by enforcing consistency between model reconstructions of undersampled scans and their noise-augmented counterparts. Noise2Recon was compared to compressed sensing and both supervised and self-supervised deep learning baselines. Experiments were conducted using retrospectively accelerated data from the mridata three-dimensional fast-spin-echo knee and two-dimensional fastMRI brain datasets. All methods were evaluated in label-limited settings and among out-of-distribution (OOD) shifts, including changes in SNR, acceleration factors, and datasets. An extensive ablation study was conducted to characterize the sensitivity of Noise2Recon to hyperparameter choices. RESULTS: In label-limited settings, Noise2Recon achieved better structural similarity, peak signal-to-noise ratio, and normalized-RMS error than all baselines and matched performance of supervised models, which were trained with 14 × $$ 14\times $$ more fully sampled scans. Noise2Recon outperformed all baselines, including state-of-the-art fine-tuning and augmentation techniques, among low-SNR scans and when generalizing to OOD acceleration factors. Augmentation extent and loss weighting hyperparameters had negligible impact on Noise2Recon compared to supervised methods, which may indicate increased training stability. CONCLUSION: Noise2Recon is a label-efficient reconstruction method that is robust to distribution shifts, such as changes in SNR, acceleration factors, and others, with limited or no fully sampled training data.

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.

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.

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.

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.

Practical protocol for lung magnetic resonance imaging and common clinical indications.

Imaging speed, spatial resolution and availability have made CT the favored cross-sectional imaging modality for evaluating various respiratory diseases of children - but only for the price of a radiation exposure. MRI is increasingly being appreciated as an alternative to CT, not only for offering three-dimensional (3-D) imaging without radiation exposure at only slightly inferior spatial resolution, but also for its superior soft-tissue contrast and exclusive morpho-functional imaging capacities beyond the scope of CT. Continuing technical improvements and experience with this so far under-utilized modality contribute to a growing acceptance of MRI for an increasing number of indications, in particular for pediatric patients. This review article provides the reader with practical easy-to-use protocols for common clinical indications in children. This is intended to encourage pediatric radiologists to appreciate the new horizons for applications of this rapidly evolving technique in the field of pediatric respiratory diseases.

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.

Analysis of deep complex-valued convolutional neural networks for MRI reconstruction and phase-focused applications.

PURPOSE: Deep learning has had success with MRI reconstruction, but previously published works use real-valued networks. The few works which have tried complex-valued networks have not fully assessed their impact on phase. Therefore, the purpose of this work is to fully investigate end-to-end complex-valued convolutional neural networks (CNNs) for accelerated MRI reconstruction and in several phase-based applications in comparison to 2-channel real-valued networks. METHODS: Several complex-valued activation functions for MRI reconstruction were implemented, and their performance was compared. Complex-valued convolution was implemented and tested on an unrolled network architecture and a U-Net-based architecture over a wide range of network widths and depths with knee, body, and phase-contrast datasets. RESULTS: Quantitative and qualitative results demonstrated that complex-valued CNNs with complex-valued convolutions provided superior reconstructions compared to real-valued convolutions with the same number of trainable parameters for both an unrolled network architecture and a U-Net-based architecture, and for 3 different datasets. Complex-valued CNNs consistently had superior normalized RMS error, structural similarity index, and peak SNR compared to real-valued CNNs. CONCLUSION: Complex-valued CNNs can enable superior accelerated MRI reconstruction and phase-based applications such as fat-water separation, and flow quantification compared to real-valued convolutional neural networks.

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.

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.

Near-Silent and Distortion-Free Diffusion MRI in Pediatric Musculoskeletal Disorders: Comparison With Echo Planar Imaging Diffusion.

BACKGROUND: Diffusion-weighted imaging (DWI) is common for evaluating pediatric musculoskeletal lesions, but suffers from geometric distortion and intense acoustic noise. PURPOSE: To investigate the performance of a near-silent and distortion-free DWI sequence (DW-SD) relative to standard echo-planar DWI (DW-EPI) in pediatric extremity MRI. STUDY TYPE: Prospective validation study. SUBJECTS: Thirty-nine children referred for extremity MRI. FIELD STRENGTH/SEQUENCE: DW-EPI and DW-SD, based on a rotating ultrafast sequence modified with sinusoidal diffusion preparation gradients, at 3T. ASSESSMENT: DW-SD image quality (Sanat ) was assessed from 0 (nondiagnostic) to 5 (outstanding) and comparative image quality (Scomp ) (from -2 = DW-EPI more delineated to +2 = DW-SD more delineated, 0 = same). ADC measured by DW-SD and DW-EPI were compared in bone marrow, muscle, and lesions. STATISTICAL TESTS: Wilcoxon rank-sum test and confidence interval of proportions (CIOP) were calculated for Scomp , Student's t-test, coefficient of variation (COV), and Bland-Altman analysis for ADC values, and intraclass correlation coefficient (ICC) for interreader agreement. RESULTS: DW-SD and DW-EPI ADC values for bone marrow, muscle, and lesions were not significantly different (P = 0.3, P = 0.2, and P = 0.27, respectively) and had an overall ADC COV of 14.8% (95% confidence interval: 12.3%, 16.9%) and no significant proportional bias on Bland-Altman analysis. Sanat CIOP was rated diagnostic or better (score of 3, 4, or 5) in 72-98% of cases for bone marrow, muscle, and soft tissues. DW-SD was equivalent to or preferred over DW-EPI in muscles and soft tissues, with CIOP 86-93% and 93%, respectively. Lesions were equally visualized on DW-SD and DW-EPI in 40-51%, with DW-SD preferred in 44-56% of cases. DW-SD was rated significantly better than DW-EPI across all comparative variables that included bone marrow, muscle, soft tissue, cartilage, and lesions (P < 0.05). Readers had moderate to near-perfect (ICC range = 0.45-0.85). DATA CONCLUSION: DW-SD of the extremities provided similar ADC values and improved image quality compared with conventional DW-EPI. Level of Evidence 2 Technical Efficacy Stage 2 J. MAGN. RESON. IMAGING 2021;53:504-513.

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.

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.