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.

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.

Thermo-acoustic ultrasound for noninvasive temperature monitoring at lead tips during MRI.

PURPOSE: We explore the use of thermo-acoustic ultrasound (TAUS) to monitor temperature at the tips of conductive device leads during MRI. THEORY: In TAUS, rapid radiofrequency (RF) power deposition excites an acoustic signal via thermoelastic expansion. Coupling of the MRI RF transmit to device leads causes SAR amplification at lead tips, allowing MRI RF transmitters to excite significant lead tip TAUS signals. Because the amplitude of the TAUS signal depends on temperature, it becomes feasible to monitor the lead tip temperature during MRI by tracking the TAUS amplitude. METHODS: The TAUS temperature dependence was characterized in a phantom and in tissue. To perform TAUS acquisitions in an MRI scanner, amplitude modulated RF chirps were transmitted by the body coil, and the lead tip TAUS signal was detected by an ultrasonic transducer. The TAUS signal level was correlated with the RF current induced on the lead and the associated B1 artifacts in MRI. TAUS signals acquired during RF-induced heating were used to estimate the lead tip temperature. RESULTS: The TAUS signal exhibited strong dependence on temperature, increasing over 30% with 10∘ C of heating both in the phantom and in tissue. A lead tip TAUS signal was observed for a 100 mA rms current induced on a lead. During RF-induced heating, the TAUS signal appeared to accurately approximate the peak lead tip temperature. CONCLUSIONS: TAUS allows for noninvasive monitoring of lead tip temperature in an MRI environment. With further development, TAUS opens new avenues to improve RF device safety during MRI scans.

Two-dimensional UTE overview imaging for dental application.

PURPOSE: To investigate the applicability of a 2D-UTE half-pulse sequence for dental overview imaging and the detection of signal from mineralized dental tissue and caries lesions with ultra-short T2∗ as an efficient alternative to 3D sequences. METHODS: A modified 2D-UTE sequence using 240-µs half-pulses for excitation and a reduction of the coil tune delay from the manufacturer preset value allowed for the acquisition of in vivo dental images with a TE of 35 µs at 1.5T. The common occurrence of out-of-slice signal for half-pulse sequences was avoided by applying a quadratic-phase saturation pulse before each half-RF excitation. A conventional 2D-UTE sequence with a TE of 750 µs, using slice selection rephasing, was used for comparison. RESULTS: Quadratic phase saturation pulses adequately improve the slice profile of half-pulse excitations for dental imaging with a surface coil. In vivo images and SNR measurements show a distinct increase in signal in ultrashort T2∗ tissues for the proposed 2D-UTE half-pulse sequence compared with a 2D-UTE sequence using conventional slice selection, leading to an improved detection of caries lesions. CONCLUSION: The proposed pulse sequence enables the acquisition of in vivo images of a comprehensive overview of bone structures and teeth of a single side of the upper and lower jaw and signal detection from mineralized dental tissues in clinically acceptable scan times.

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.

Rosette Trajectories Enable Ungated, Motion-Robust, Simultaneous Cardiac and Liver T2 * Iron Assessment.

BACKGROUND: Quantitative T2 * MRI is the standard of care for the assessment of iron overload. However, patient motion corrupts T2 * estimates. PURPOSE: To develop and evaluate a motion-robust, simultaneous cardiac and liver T2 * imaging approach using non-Cartesian, rosette sampling and a model-based reconstruction as compared to clinical-standard Cartesian MRI. STUDY TYPE: Prospective. PHANTOM/POPULATION: Six ferumoxytol-containing phantoms (26-288 µg/mL). Eight healthy subjects and 18 patients referred for clinically indicated iron overload assessment. FIELD STRENGTH/SEQUENCE: 1.5T, 2D Cartesian and rosette gradient echo (GRE) ASSESSMENT: GRE T2 * values were validated in ferumoxytol phantoms. In healthy subjects, test-retest and spatial coefficient of variation (CoV) analysis was performed during three breathing conditions. Cartesian and rosette T2 * were compared using correlation and Bland-Altman analysis. Images were rated by three experienced radiologists on a 5-point scale. STATISTICAL TESTS: Linear regression, analysis of variance (ANOVA), and paired Student's t-testing were used to compare reproducibility and variability metrics in Cartesian and rosette scans. The Wilcoxon rank test was used to assess reader score comparisons and reader reliability was measured using intraclass correlation analysis. RESULTS: Rosette R2* (1/T2 *) was linearly correlated with ferumoxytol concentration (r2 = 1.00) and not significantly different than Cartesian values (P = 0.16). During breath-holding, ungated rosette liver and heart T2 * had lower spatial CoV (liver: 18.4 ± 9.3% Cartesian, 8.8% ± 3.4% rosette, P = 0.02, heart: 37.7% ± 14.3% Cartesian, 13.4% ± 1.7% rosette, P = 0.001) and higher-quality scores (liver: 3.3 [3.0-3.6] Cartesian, 4.7 [4.1-4.9] rosette, P = 0.005, heart: 3.0 [2.3-3] Cartesian, 4.5 [3.8-5.0] rosette, P = 0.005) compared to Cartesian values. During free-breathing and failed breath-holding, Cartesian images had very poor to average image quality with significant artifacts, whereas rosette remained very good, with minimal artifacts (P = 0.001). DATA CONCLUSION: Rosette k-sampling with a model-based reconstruction offers a clinically useful motion-robust T2 * mapping approach for iron quantification. J. MAGN. RESON. IMAGING 2020;52:1688-1698.

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.

Ultra-Low-Dose 18F-Florbetaben Amyloid PET Imaging Using Deep Learning with Multi-Contrast MRI Inputs.

Purpose To reduce radiotracer requirements for amyloid PET/MRI without sacrificing diagnostic quality by using deep learning methods. Materials and Methods Forty data sets from 39 patients (mean age ± standard deviation [SD], 67 years ± 8), including 16 male patients and 23 female patients (mean age, 66 years ± 6 and 68 years ± 9, respectively), who underwent simultaneous amyloid (fluorine 18 [18F]-florbetaben) PET/MRI examinations were acquired from March 2016 through October 2017 and retrospectively analyzed. One hundredth of the raw list-mode PET data were randomly chosen to simulate a low-dose (1%) acquisition. Convolutional neural networks were implemented with low-dose PET and multiple MR images (PET-plus-MR model) or with low-dose PET alone (PET-only) as inputs to predict full-dose PET images. Quality of the synthesized images was evaluated while Bland-Altman plots assessed the agreement of regional standard uptake value ratios (SUVRs) between image types. Two readers scored image quality on a five-point scale (5 = excellent) and determined amyloid status (positive or negative). Statistical analyses were carried out to assess the difference of image quality metrics and reader agreement and to determine confidence intervals (CIs) for reading results. Results The synthesized images (especially from the PET-plus-MR model) showed marked improvement on all quality metrics compared with the low-dose image. All PET-plus-MR images scored 3 or higher, with proportions of images rated greater than 3 similar to those for the full-dose images (-10% difference [eight of 80 readings], 95% CI: -15%, -5%). Accuracy for amyloid status was high (71 of 80 readings [89%]) and similar to intrareader reproducibility of full-dose images (73 of 80 [91%]). The PET-plus-MR model also had the smallest mean and variance for SUVR difference to full-dose images. Conclusion Simultaneously acquired MRI and ultra-low-dose PET data can be used to synthesize full-dose-like amyloid PET images. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Catana in this issue.

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.

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.

Rapid compressed sensing reconstruction of 3D non-Cartesian MRI.

PURPOSE: Conventional non-Cartesian compressed sensing requires multiple nonuniform Fourier transforms every iteration, which is computationally expensive. Accordingly, time-consuming reconstructions have slowed the adoption of undersampled 3D non-Cartesian acquisitions into clinical protocols. In this work we investigate several approaches to minimize reconstruction times without sacrificing accuracy. METHODS: The reconstruction problem can be reformatted to exploit the Toeplitz structure of matrices that are evaluated every iteration, but it requires larger oversampling than what is strictly required by nonuniform Fourier transforms. Accordingly, we investigate relative speeds of the two approaches for various nonuniform Fourier transform kernel sizes and oversampling for both GPU and CPU implementations. Second, we introduce a method to minimize matrix sizes by estimating the image support. Finally, density compensation weights have been used as a preconditioning matrix to improve convergence, but this increases noise. We propose a more general approach to preconditioning that allows a trade-off between accuracy and convergence speed. RESULTS: When using a GPU, the Toeplitz approach was faster for all practical parameters. Second, it was found that properly accounting for image support can prevent aliasing errors with minimal impact on reconstruction time. Third, the proposed preconditioning scheme improved convergence rates by an order of magnitude with negligible impact on noise. CONCLUSION: With the proposed methods, 3D non-Cartesian compressed sensing with clinically relevant reconstruction times (<2 min) is feasible using practical computer resources. Magn Reson Med 79:2685-2692, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Body diffusion-weighted imaging using magnetization prepared single-shot fast spin echo and extended parallel imaging signal averaging.

PURPOSE: This work demonstrates a magnetization prepared diffusion-weighted single-shot fast spin echo (SS-FSE) pulse sequence for the application of body imaging to improve robustness to geometric distortion. This work also proposes a scan averaging technique that is superior to magnitude averaging and is not subject to artifacts due to object phase. THEORY AND METHODS: This single-shot sequence is robust against violation of the Carr-Purcell-Meiboom-Gill (CPMG) condition. This is achieved by dephasing the signal after diffusion weighting and tipping the MG component of the signal onto the longitudinal axis while the non-MG component is spoiled. The MG signal component is then excited and captured using a traditional SS-FSE sequence, although the echo needs to be recalled prior to each echo. Extended Parallel Imaging (ExtPI) averaging is used where coil sensitivities from the multiple acquisitions are concatenated into one large parallel imaging (PI) problem. The size of the PI problem is reduced by SVD-based coil compression which also provides background noise suppression. This sequence and reconstruction are evaluated in simulation, phantom scans, and in vivo abdominal clinical cases. RESULTS: Simulations show that the sequence generates a stable signal throughout the echo train which leads to good image quality. This sequence is inherently low-SNR, but much of the SNR can be regained through scan averaging and the proposed ExtPI reconstruction. In vivo results show that the proposed method is able to provide diffusion encoded images while mitigating geometric distortion artifacts compared to EPI. CONCLUSION: This work presents a diffusion-prepared SS-FSE sequence that is robust against the violation of the CPMG condition while providing diffusion contrast in clinical cases. Magn Reson Med 79:3032-3044, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Slice profile effects on nCPMG SS-FSE.

PURPOSE: To determine the effects of the RF refocusing pulse profile on the magnitude of the transverse signal smoothness throughout the echo train in non-Carr-Purcell-Meiboom-Gill (nCPMG) single-shot fast spin echo (SS-FSE) imaging and to design an RF refocusing pulse that provides improved signal stability. THEORY AND METHODS: nCPMG SS-FSE quadratic phase modulation requires sufficiently high and uniform refocusing flip angle to achieve a stable signal. Typically, refocusing pulses used in SS-FSE sequences are designed for minimum duration to minimize echo spacing and as a consequence have poor selectivity. However, delay-insensitive variable rate excitation Shinnar-Le Roux (DV-SLR) refocusing pulses can achieve both improved selectivity as well as a short duration. This class of RF pulse is compared against a traditional low time-bandwidth refocusing pulse in a nCPMG SS-FSE in simulation, phantom, and in vivo. RESULTS: DV-SLR pulses achieve a more stable signal in simulation, phantom, and in vivo cases while maintaining an appropriately short duration as well as not dramatically increasing specific absorption rate (SAR) accumulation. CONCLUSION: The nCPMG SS-FSE method demonstrates improved robustness when a more selective refocusing pulse is used. Refocusing pulses that use a time-varying excitation gradient can achieve this selectivity while maintaining short echo spacing. Magn Reson Med 79:430-438, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Technique development of 3D dynamic CS-EPSI for hyperpolarized 13 C pyruvate MR molecular imaging of human prostate cancer.

PURPOSE: The purpose of this study was to develop a new 3D dynamic carbon-13 compressed sensing echoplanar spectroscopic imaging (EPSI) MR sequence and test it in phantoms, animal models, and then in prostate cancer patients to image the metabolic conversion of hyperpolarized [1-13 C]pyruvate to [1-13 C]lactate with whole gland coverage at high spatial and temporal resolution. METHODS: A 3D dynamic compressed sensing (CS)-EPSI sequence with spectral-spatial excitation was designed to meet the required spatial coverage, time and spatial resolution, and RF limitations of the 3T MR scanner for its clinical translation for prostate cancer patient imaging. After phantom testing, animal studies were performed in rats and transgenic mice with prostate cancers. For patient studies, a GE SPINlab polarizer (GE Healthcare, Waukesha, WI) was used to produce hyperpolarized sterile GMP [1-13 C]pyruvate. 3D dynamic 13 C CS-EPSI data were acquired starting 5 s after injection throughout the gland with a spatial resolution of 0.5 cm3 , 18 time frames, 2-s temporal resolution, and 36 s total acquisition time. RESULTS: Through preclinical testing, the 3D CS-EPSI sequence developed in this project was shown to provide the desired spectral, temporal, and spatial 5D HP 13 C MR data. In human studies, the 3D dynamic HP CS-EPSI approach provided first-ever simultaneously volumetric and dynamic images of the LDH-catalyzed conversion of [1-13 C]pyruvate to [1-13 C]lactate in a biopsy-proven prostate cancer patient with full gland coverage. CONCLUSION: The results demonstrate the feasibility to characterize prostate cancer metabolism in animals, and now patients using this new 3D dynamic HP MR technique to measure kPL , the kinetic rate constant of [1-13 C]pyruvate to [1-13 C]lactate conversion.

Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI.

BACKGROUND: There are concerns over gadolinium deposition from gadolinium-based contrast agents (GBCA) administration. PURPOSE: To reduce gadolinium dose in contrast-enhanced brain MRI using a deep learning method. STUDY TYPE: Retrospective, crossover. POPULATION: Sixty patients receiving clinically indicated contrast-enhanced brain MRI. SEQUENCE: 3D T1 -weighted inversion-recovery prepped fast-spoiled-gradient-echo (IR-FSPGR) imaging was acquired at both 1.5T and 3T. In 60 brain MRI exams, the IR-FSPGR sequence was obtained under three conditions: precontrast, postcontrast images with 10% low-dose (0.01mmol/kg) and 100% full-dose (0.1 mmol/kg) of gadobenate dimeglumine. We trained a deep learning model using the first 10 cases (with mixed indications) to approximate full-dose images from the precontrast and low-dose images. Synthesized full-dose images were created using the trained model in two test sets: 20 patients with mixed indications and 30 patients with glioma. ASSESSMENT: For both test sets, low-dose, true full-dose, and the synthesized full-dose postcontrast image sets were compared quantitatively using peak-signal-to-noise-ratios (PSNR) and structural-similarity-index (SSIM). For the test set comprised of 20 patients with mixed indications, two neuroradiologists scored blindly and independently for the three postcontrast image sets, evaluating image quality, motion-artifact suppression, and contrast enhancement compared with precontrast images. STATISTICAL ANALYSIS: Results were assessed using paired t-tests and noninferiority tests. RESULTS: The proposed deep learning method yielded significant (n = 50, P < 0.001) improvements over the low-dose images (>5 dB PSNR gains and >11.0% SSIM). Ratings on image quality (n = 20, P = 0.003) and contrast enhancement (n = 20, P < 0.001) were significantly increased. Compared to true full-dose images, the synthesized full-dose images have a slight but not significant reduction in image quality (n = 20, P = 0.083) and contrast enhancement (n = 20, P = 0.068). Slightly better (n = 20, P = 0.039) motion-artifact suppression was noted in the synthesized images. The noninferiority test rejects the inferiority of the synthesized to true full-dose images for image quality (95% CI: -14-9%), artifacts suppression (95% CI: -5-20%), and contrast enhancement (95% CI: -13-6%). DATA CONCLUSION: With the proposed deep learning method, gadolinium dose can be reduced 10-fold while preserving contrast information and avoiding significant image quality degradation. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 5 J. MAGN. RESON. IMAGING 2018;48:330-340.

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

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

Improved cortical bone specificity in UTE MR Imaging.

PURPOSE: Methods for direct visualization of compact bone using MRI have application in several "MR-informed" technologies, such as MR-guided focused ultrasound, MR-PET reconstruction and MR-guided radiation therapy. The specificity of bone imaging can be improved by manipulating image sensitivity to Bloch relaxation phenomena, facilitating distinction of bone from other tissues detected by MRI. METHODS: From Bloch equation dynamics, excitation pulses suitable for creating specific sensitivity to short-T2 magnetization from cortical bone are identified. These pulses are used with UTE subtraction demonstrate feasibility of MR imaging of compact bone with positive contrast. RESULTS: MR images of bone structures are acquired with contrast similar to that observed in x-ray CT images. Through comparison of MR signal intensities with CT Hounsfield units of the skull, the similarity of contrast is quantified. The MR technique is also demonstrated in other regions of the body that are relevant for interventional procedures, such as the shoulder, pelvis and leg. CONCLUSION: Matching RF excitation pulses to relaxation rates improves the specificity to bone of short-T2 contrast. It is demonstrated with a UTE sequence to acquire images of cortical bone with positive contrast, and the contrast is verified by comparison with x-ray CT. Magn Reson Med 77:684-695, 2017. © 2016 International Society for Magnetic Resonance in Medicine.

Autocalibrating motion-corrected wave-encoding for highly accelerated free-breathing abdominal MRI.

PURPOSE: To develop a motion-robust wave-encoding technique for highly accelerated free-breathing abdominal MRI. METHODS: A comprehensive 3D wave-encoding-based method was developed to enable fast free-breathing abdominal imaging: (a) auto-calibration for wave-encoding was designed to avoid extra scan for coil sensitivity measurement; (b) intrinsic butterfly navigators were used to track respiratory motion; (c) variable-density sampling was included to enable compressed sensing; (d) golden-angle radial-Cartesian hybrid view-ordering was incorporated to improve motion robustness; and (e) localized rigid motion correction was combined with parallel imaging compressed sensing reconstruction to reconstruct the highly accelerated wave-encoded datasets. The proposed method was tested on six subjects and image quality was compared with standard accelerated Cartesian acquisition both with and without respiratory triggering. Inverse gradient entropy and normalized gradient squared metrics were calculated, testing whether image quality was improved using paired t-tests. RESULTS: For respiratory-triggered scans, wave-encoding significantly reduced residual aliasing and blurring compared with standard Cartesian acquisition (metrics suggesting P < 0.05). For non-respiratory-triggered scans, the proposed method yielded significantly better motion correction compared with standard motion-corrected Cartesian acquisition (metrics suggesting P < 0.01). CONCLUSION: The proposed methods can reduce motion artifacts and improve overall image quality of highly accelerated free-breathing abdominal MRI. Magn Reson Med 78:1757-1766, 2017. © 2016 International Society for Magnetic Resonance in Medicine.

Resolving phase ambiguity in dual-echo dixon imaging using a projected power method.

PURPOSE: To develop a fast and robust method to resolve phase ambiguity in dual-echo Dixon imaging. METHODS: A major challenge in dual-echo Dixon imaging is to estimate the phase error resulting from field inhomogeneity. In this work, a binary quadratic optimization program was formulated to resolve the phase ambiguity. A projected power method was developed to efficiently solve the optimization problem. Both the 1-peak fat model and 6-peak fat model were applied to three-dimensional (3D) datasets. Additionally, the proposed method was extended to dynamic magnetic resonance imaging (MRI) applications using the 6-peak fat model. With institutional review board (IRB) approval and patient consent/assent, the proposed method was evaluated and compared with region growing on 29 consecutive 3D high-resolution patient datasets. RESULTS: Fast and robust water/fat separation was achieved by the proposed method in different representative 3D datasets and dynamic 3D datasets. Superior water/fat separation was achieved using the 6-peak fat model compared with the 1-peak fat model. Compared to region growing, the proposed method reduced water/fat swaps from 76 to 7% of the patient cohort. CONCLUSION: The proposed method can achieve fast and robust phase error estimation in dual-echo Dixon imaging. Magn Reson Med 77:2066-2076, 2017. © 2016 International Society for Magnetic Resonance in Medicine.

Spectrally selective three-dimensional dynamic balanced steady-state free precession for hyperpolarized C-13 metabolic imaging with spectrally selective radiofrequency pulses.

PURPOSE: Balanced steady-state free precession (bSSFP) sequences can provide superior signal-to-noise ratio efficiency for hyperpolarized (HP) carbon-13 (13 C) magnetic resonance imaging by efficiently utilizing the nonrecoverable magnetization, but managing their spectral response is challenging in the context of metabolic imaging. A new spectrally selective bSSFP sequence was developed for fast imaging of multiple HP 13 C metabolites with high spatiotemporal resolution. THEORY AND METHODS: This novel approach for bSSFP spectral selectivity incorporates optimized short-duration spectrally selective radiofrequency pulses within a bSSFP pulse train and a carefully chosen repetition time to avoid banding artifacts. RESULTS: The sequence enabled subsecond 3D dynamic spectrally selective imaging of 13 C metabolites of copolarized [1-13 C]pyruvate and [13 C]urea at 2-mm isotropic resolution, with excellent spectral selectivity (∼100:1). The sequence was successfully tested in phantom studies and in vivo studies with normal mice. CONCLUSION: This sequence is expected to benefit applications requiring dynamic volumetric imaging of metabolically active 13 C compounds at high spatiotemporal resolution, including preclinical studies at high field and, potentially, clinical studies. Magn Reson Med 78:963-975, 2017. © 2016 International Society for Magnetic Resonance in Medicine.