Recurrent neural network-based simultaneous cardiac T1, T2, and T1ρ mapping.

The purpose of the current study was to explore the feasibility of training a deep neural network to accelerate the process of generating T1, T2, and T1ρ maps for a recently proposed free-breathing cardiac multiparametric mapping technique, where a recurrent neural network (RNN) was utilized to exploit the temporal correlation among the multicontrast images. The RNN-based model was developed for rapid and accurate T1, T2, and T1ρ estimation. Bloch simulation was performed to simulate a dataset of more than 10 million signals and time correspondences with different noise levels for network training. The proposed RNN-based method was compared with a dictionary-matching method and a conventional mapping method to evaluate the model's effectiveness in phantom and in vivo studies at 3 T, respectively. In phantom studies, the RNN-based method and the dictionary-matching method achieved similar accuracy and precision in T1, T2, and T1ρ estimations. In in vivo studies, the estimated T1, T2, and T1ρ values obtained by the two methods achieved similar accuracy and precision for 10 healthy volunteers (T1: 1228.70 ± 53.80 vs. 1228.34 ± 52.91 ms, p > 0.1; T2: 40.70 ± 2.89 vs. 41.19 ± 2.91 ms, p > 0.1; T1ρ: 45.09 ± 4.47 vs. 45.23 ± 4.65 ms, p > 0.1). The RNN-based method can generate cardiac multiparameter quantitative maps simultaneously in just 2 s, achieving 60-fold acceleration compared with the dictionary-matching method. The RNN-accelerated method offers an almost instantaneous approach for reconstructing accurate T1, T2, and T1ρ maps, being much more efficient than the dictionary-matching method for the free-breathing multiparametric cardiac mapping technique, which may pave the way for inline mapping in clinical applications.

Free-Breathing Non-Contrast T1ρ Dispersion MRI of Myocardial Interstitial Fibrosis in Comparison with Extracellular Volume Fraction.

BACKGROUND: Myocardial fibrosis is a common feature in various cardiac diseases. It causes adverse cardiac remodeling and is associated with poor clinical outcomes. Late gadolinium enhancement (LGE) and extracellular volume fraction (ECV) are the standard MRI techniques for detecting focal and diffuse myocardial fibrosis. However, these contrast-enhanced techniques require the administration of gadolinium contrast agents, which is not applicable to patients with gadolinium contraindications. To eliminate the need of contrast agents, we develop and apply an endogenous free-breathing T1ρ dispersion imaging technique (FB-MultiMap) for diagnosing diffuse myocardial fibrosis in a cohort with suspected cardiomyopathies. METHODS: The proposed FB-MultiMap technique, enabling T2, T1ρ and their difference (myocardial fibrosis index, mFI) quantification in a single scan was developed in phantoms and 15 healthy subjects. In the clinical study, 55 patients with suspected cardiomyopathies were imaged using FB-MultiMap, conventional native T1 mapping, LGE, and ECV imaging. The accuracy of the endogenous parameters for predicting increased ECV was evaluated using receiver operating characteristic (ROC) curve analysis. In addition, the correlation of native T1, T1ρ, and mFI with ECV was respectively assessed using Pearson correlation coefficients. RESULTS: FB-MultiMap showed a good agreement with conventional separate breath-hold mapping techniques in phantoms and healthy subjects. Considering all the patients, T1ρ was more accurate than mFI and native T1 for predicting increased ECV, with area under the curve (AUC) values of 0.91, 0.79 and 0.75, respectively, and showed stronger correlation with ECV (correlation coefficient r: 0.72 vs. 0.52 vs. 0.40). In the subset of 47 patients with normal T2 values, the diagnostic performance of mFI was significantly strengthened (AUC=0.90, r=0.83), outperforming T1ρ and native T1. CONCLUSION: The proposed free-breathing T1ρ dispersion imaging technique enabling simultaneous quantification of T2, T1ρ and mFI in a single scan has shown great potential for diagnosing diffuse myocardial fibrosis in patients with complex cardiomyopathies without contrast agents.

A motion-corrected deep-learning reconstruction framework for accelerating whole-heart magnetic resonance imaging in patients with congenital heart disease.

BACKGROUND: Cardiovascular magnetic resonance (CMR) is an important imaging modality for the assessment and management of adult patients with congenital heart disease (CHD). However, conventional techniques for three-dimensional (3D) whole-heart acquisition involve long and unpredictable scan times and methods that accelerate scans via k-space undersampling often rely on long iterative reconstructions. Deep-learning-based reconstruction methods have recently attracted much interest due to their capacity to provide fast reconstructions while often outperforming existing state-of-the-art methods. In this study, we sought to adapt and validate a non-rigid motion-corrected model-based deep learning (MoCo-MoDL) reconstruction framework for 3D whole-heart MRI in a CHD patient cohort. METHODS: The previously proposed deep-learning reconstruction framework MoCo-MoDL, which incorporates a non-rigid motion-estimation network and a denoising regularization network within an unrolled iterative reconstruction, was trained in an end-to-end manner using 39 CHD patient datasets. Once trained, the framework was evaluated in eight CHD patient datasets acquired with seven-fold prospective undersampling. Reconstruction quality was compared with the state-of-the-art non-rigid motion-corrected patch-based low-rank reconstruction method (NR-PROST) and against reference images (acquired with three-or-four-fold undersampling and reconstructed with NR-PROST). RESULTS: Seven-fold undersampled scan times were 2.1 ± 0.3 minutes and reconstruction times were ∼30 seconds, approximately 240 times faster than an NR-PROST reconstruction. Image quality comparable to the reference images was achieved using the proposed MoCo-MoDL framework, with no statistically significant differences found in any of the assessed quantitative or qualitative image quality measures. Additionally, expert image quality scores indicated the MoCo-MoDL reconstructions were consistently of a higher quality than the NR-PROST reconstructions of the same data, with the differences in 12 of the 22 scores measured for individual vascular structures found to be statistically significant. CONCLUSION: The MoCo-MoDL framework was applied to an adult CHD patient cohort, achieving good quality 3D whole-heart images from ∼2-minute scans with reconstruction times of ∼30 seconds.

Stop moving: MR motion correction as an opportunity for artificial intelligence.

Subject motion is a long-standing problem of magnetic resonance imaging (MRI), which can seriously deteriorate the image quality. Various prospective and retrospective methods have been proposed for MRI motion correction, among which deep learning approaches have achieved state-of-the-art motion correction performance. This survey paper aims to provide a comprehensive review of deep learning-based MRI motion correction methods. Neural networks used for motion artifacts reduction and motion estimation in the image domain or frequency domain are detailed. Furthermore, besides motion-corrected MRI reconstruction, how estimated motion is applied in other downstream tasks is briefly introduced, aiming to strengthen the interaction between different research areas. Finally, we identify current limitations and point out future directions of deep learning-based MRI motion correction.

Simultaneous T1, T2, and T2* Mapping of Carotid Plaque: The SIMPLE* Technique.

Background Quantitative T1, T2, and T2* measurements of carotid atherosclerotic plaque are important in evaluating plaque vulnerability and monitoring its progression. Purpose To develop a sequence to simultaneously quantify T1, T2, and T2* of carotid plaque. Materials and Methods The simultaneous T1, T2, and T2* mapping of carotid plaque (SIMPLE*) sequence is composed of three modules with different T2 preparation pulses, inversion-recovery pulses, and acquisition schemas. Single-echo data were used for T1 and T2 quantification, while the multiecho (ME) data were used for T2* quantification. The quantitative accuracy of SIMPLE* was tested in a phantom study by comparing its measurements with those of reference standard sequences. In vivo feasibility of the technique was prospectively evaluated between November 2020 and February 2022 in healthy volunteers and participants with carotid atherosclerotic plaque. The Pearson or Spearman correlation test, Student t test, and Wilcoxon rank-sum test were used. Results T1, T2, and T2* estimated with SIMPLE* strongly correlated with inversion-recovery spin-echo (SE) (correlation coefficient [r] = 0.99), ME-SE (r = 0.99), and ME gradient-echo (r = 0.99) sequences in the phantom study. In five healthy volunteers (mean age, 25 years ± 3 [SD]; three women), measurements were similar between SIMPLE* and modified Look-Locker inversion recovery, or MOLLI (1151 msec ± 71 vs 1098 msec ± 64; P = .14), ME turbo SE (31 msec ± 1 vs 31 msec ± 1; P = .32), and ME turbo field echo (24 msec ± 2 vs 25 msec ± 2; P = .19). In 18 participants with carotid plaque (mean age, 65 years ± 9; 16 men), quantitative T1, T2, and T2* of plaque components were consistent with their signal characteristics on multicontrast images. Conclusion A quantitative technique for simultaneous T1, T2, and T2* mapping of carotid plaque with 100-mm3 coverage and 0.8-mm3 resolution was developed using the proposed SIMPLE* sequence and demonstrated high accuracy and in vivo feasibility. © RSNA, 2023 Supplemental material is available for this article.

Free-running 3D whole-heart T1 and T2 mapping and cine MRI using low-rank reconstruction with non-rigid cardiac motion correction.

PURPOSE: To introduce non-rigid cardiac motion correction into a novel free-running framework for the simultaneous acquisition of 3D whole-heart myocardial T 1 $$ {T}_1 $$ and T 2 $$ {T}_2 $$ maps and cine images, enabling a ∼ $$ \sim $$ 3-min scan. METHODS: Data were acquired using a free-running 3D golden-angle radial readout interleaved with inversion recovery and T 2 $$ {T}_2 $$ -preparation pulses. After correction for translational respiratory motion, non-rigid cardiac-motion-corrected reconstruction with dictionary-based low-rank compression and patch-based regularization enabled 3D whole-heart T 1 $$ {T}_1 $$ and T 2 $$ {T}_2 $$ mapping at any given cardiac phase as well as whole-heart cardiac cine imaging. The framework was validated and compared with established methods in 11 healthy subjects. RESULTS: Good quality 3D T 1 $$ {T}_1 $$ and T 2 $$ {T}_2 $$ maps and cine images were reconstructed for all subjects. Septal T 1 $$ {T}_1 $$ values using the proposed approach ( 1200 ± 50 $$ 1200\pm 50 $$ ms) were higher than those from a 2D MOLLI sequence ( 1063 ± 33 $$ 1063\pm 33 $$ ms), which is known to underestimate T 1 $$ {T}_1 $$ , while T 2 $$ {T}_2 $$ values from the proposed approach ( 51 ± 4 $$ 51\pm 4 $$ ms) were in good agreement with those from a 2D GraSE sequence ( 51 ± 2 $$ 51\pm 2 $$ ms). CONCLUSION: The proposed technique provides 3D T 1 $$ {T}_1 $$ and T 2 $$ {T}_2 $$ maps and cine images with isotropic spatial resolution in a single ∼ $$ \sim $$ 3.3-min scan.

Free-breathing simultaneous native myocardial T1, T2 and T1ρ mapping with Cartesian acquisition and dictionary matching.

BACKGROUND: T1, T2 and T1ρ are well-recognized parameters for quantitative cardiac MRI. Simultaneous estimation of these parameters allows for comprehensive myocardial tissue characterization, such as myocardial fibrosis and edema. However, conventional techniques either quantify the parameters individually with separate breath-hold acquisitions, which may result in unregistered parameter maps, or estimate multiple parameters in a prolonged breath-hold acquisition, which may be intolerable to patients. We propose a free-breathing multi-parametric mapping (FB-MultiMap) technique that provides co-registered myocardial T1, T2 and T1ρ maps in a single efficient acquisition. METHODS: The proposed FB-MultiMap performs electrocardiogram-triggered single-shot Cartesian acquisition over 16 consecutive cardiac cycles, where inversion, T2 and T1ρ preparations are introduced for varying contrasts. A diaphragmatic navigator was used for prospective through-plane motion correction and the in-plane motion was corrected retrospectively with a group-wise image registration method. Quantitative mapping was conducted through dictionary matching of the motion corrected images, where the subject-specific dictionary was created using Bloch simulations for a range of T1, T2 and T1ρ values, as well as B1 factors to account for B1 inhomogeneities. The FB-MultiMap was optimized and validated in numerical simulations, phantom experiments, and in vivo imaging of 15 healthy subjects and six patients with suspected cardiac diseases. RESULTS: The phantom T1, T2 and T1ρ values estimated with FB-MultiMap agreed well with reference measurements with no dependency on heart rate. In healthy subjects, FB-MultiMap T1 was higher than MOLLI T1 mapping (1218 ± 50 ms vs. 1166 ± 38 ms, p < 0.001). The myocardial T2 and T1ρ estimated with FB-MultiMap were lower compared to the mapping with T2- or T1ρ-prepared 2D balanced steady-state free precession (T2: 41.2 ± 2.8 ms vs. 42.5 ± 3.1 ms, p = 0.06; T1ρ: 45.3 ± 4.4 ms vs. 50.2 ± 4.0, p < 0.001). The pathological changes in myocardial parameters measured with FB-MultiMap were consistent with conventional techniques in all patients. CONCLUSION: The proposed free-breathing multi-parametric mapping technique provides co-registered myocardial T1, T2 and T1ρ maps in 16 heartbeats, achieving similar mapping quality to conventional breath-hold mapping methods.

Generalized low-rank nonrigid motion-corrected reconstruction for MR fingerprinting.

PURPOSE: Develop a novel low-rank motion-corrected (LRMC) reconstruction for nonrigid motion-corrected MR fingerprinting (MRF). METHODS: Generalized motion-corrected (MC) reconstructions have been developed for steady-state imaging. Here we extend this framework to enable nonrigid MC for transient imaging applications with varying contrast, such as MRF. This is achieved by integrating low-rank dictionary-based compression into the generalized MC model to reconstruct MC singular images, reducing motion artifacts in the resulting parametric maps. The proposed LRMC reconstruction was applied for cardiac motion correction in 2D myocardial MRF (T1 and T2 ) with extended cardiac acquisition window (~450 ms) and for respiratory MC in free-breathing 3D myocardial and 3D liver MRF. Experiments were performed in phantom and 22 healthy subjects. The proposed approach was compared with reference spin echo (phantom) and with 2D electrocardiogram-triggered/breath-hold MOLLI and T2 gradient-and-spin echo conventional maps (in vivo 2D and 3D myocardial MRF). RESULTS: Phantom results were in general agreement with reference spin-echo measurements, presenting relative errors of approximately 5.4% and 5.5% for T1 and short T2 (<100 ms), respectively. The proposed LRMC MRF reduced residual blurring artifacts with respect to no MC for cardiac or respiratory motion in all cases (2D and 3D myocardial, 3D abdominal). In 2D myocardial MRF, left-ventricle T1 values were 1150 ± 41 ms for LRMC MRF and 1010 ± 56 ms for MOLLI; T2 values were 43.8 ± 2.3 ms for LRMC MRF and 49.5 ± 4.5 ms for T2 gradient and spin echo. Corresponding measurements for 3D myocardial MRF were 1085 ± 30 ms and 1062 ± 29 ms for T1 , and 43.5 ± 1.9 ms and 51.7 ± 1.7 ms for T2 . For 3D liver, LRMC MRF measured liver T1 at 565 ± 44 ms and liver T2 at 35.4 ± 2.4 ms. CONCLUSION: The proposed LRMC reconstruction enabled generalized (nonrigid) MC for 2D and 3D MRF, both for cardiac and respiratory motion. The proposed approach reduced motion artifacts in the MRF maps with respect to no motion compensation and achieved good agreement with reference measurements.

Accelerated 3D free-breathing high-resolution myocardial T1ρ mapping at 3 Tesla.

PURPOSE: To develop a fast free-breathing whole-heart high-resolution myocardial T1ρ mapping technique with robust spin-lock preparation that can be performed at 3 Tesla. METHODS: An adiabatically excited continuous-wave spin-lock module, insensitive to field inhomogeneities, was implemented with an electrocardiogram-triggered low-flip angle spoiled gradient echo sequence with variable-density 3D Cartesian undersampling at a 3 Tesla whole-body scanner. A saturation pulse was performed at the beginning of each cardiac cycle to null the magnetization before T1ρ preparation. Multiple T1ρ -weighted images were acquired with T1ρ preparations with different spin-lock times in an interleaved fashion. Respiratory self-gating approach was adopted along with localized autofocus to enable 3D translational motion correction of the data acquired in each heartbeat. After motion correction, multi-contrast locally low-rank reconstruction was performed to reduce undersampling artifacts. The accuracy and feasibility of the 3D T1ρ mapping technique was investigated in phantoms and in vivo in 10 healthy subjects compared with the 2D T1ρ mapping. RESULTS: The 3D T1ρ mapping technique provided similar phantom T1ρ measurements in the range of 25-120 ms to the 2D T1ρ mapping reference over a wide range of simulated heart rates. With the robust adiabatically excited continuous-wave spin-lock preparation, good quality 2D and 3D in vivo T1ρ -weighted images and T1ρ maps were obtained. Myocardial T1ρ values with the 3D T1ρ mapping were slightly longer than 2D breath-hold measurements (septal T1ρ : 52.7 ± 1.4 ms vs. 50.2 ± 1.8 ms, P < 0.01). CONCLUSION: A fast 3D free-breathing whole-heart T1ρ mapping technique was proposed for T1ρ quantification at 3 T with isotropic spatial resolution (2 mm3 ) and short scan time of ∼4.5 min.

Quantification of changes in myocardial T1 * values with exercise cardiac MRI using a free-breathing non-electrocardiograph radial imaging.

PURPOSE: To develop and evaluate a free breathing non-electrocardiograph (ECG) myocardial T1 * mapping sequence using radial imaging to quantify the changes in myocardial T1 * between rest and exercise (T1 *reactivity ) in exercise cardiac MRI (Ex-CMR). METHODS: A free-running T1 * sequence was developed using a saturation pulse followed by three Look-Locker inversion-recovery experiments. Each Look-Locker continuously acquired data as radial trajectory using a low flip-angle spoiled gradient-echo readout. Self-navigation was performed with a temporal resolution of ∼100 ms for retrospectively extracting respiratory motion. The mid-diastole phase for every cardiac cycle was retrospectively detected on the recorded electrocardiogram signal using an empirical model. Multiple measurements were performed to obtain mean value to reduce effects from the free-breathing acquisition. Finally, data acquired at both mid-diastole and end-expiration are picked and reconstructed by a low-rank plus sparsity constraint algorithm. The performance of this sequence was evaluated by simulations, phantoms, and in vivo studies at rest and after physiological exercise. RESULTS: Numerical simulation demonstrated that changes in T1 * are related to the changes in T1 ; however, other factors such as breathing motion could influence T1 * measurements. Phantom T1 * values measured using free-running T1 * mapping sequence had good correlation with spin-echo T1 values and was insensitive to heart rate. In the Ex-CMR study, the measured T1 * reactivity was 10% immediately after exercise and declined over time. CONCLUSION: The free-running T1 * mapping sequence allows free-breathing non-ECG quantification of changes in myocardial T1 * with physiological exercise. Although, absolute myocardial T1 * value is sensitive to various confounders such as B1 and B0 inhomogeneity, quantification of its change may be useful in revealing myocardial tissue properties with exercise.

Motion correction for native myocardial T1 mapping using self-supervised deep learning registration with contrast separation.

In myocardial T1 mapping, undesirable motion poses significant challenges because uncorrected motion can affect T1 estimation accuracy and cause incorrect diagnosis. In this study, we propose and evaluate a motion correction method for myocardial T1 mapping using self-supervised deep learning based registration with contrast separation (SDRAP). A sparse coding based method was first proposed to separate the contrast component from T1 -weighted (T1w) images. Then, a self-supervised deep neural network with cross-correlation (SDRAP-CC) or mutual information as the registration similarity measurement was developed to register contrast separated images, after which signal fitting was performed on the motion corrected T1w images to generate motion corrected T1 maps. The registration network was trained and tested in 80 healthy volunteers with images acquired using the modified Look-Locker inversion recovery (MOLLI) sequence. The proposed SDRAP was compared with the free form deformation (FFD) registration method regarding (1) Dice similarity coefficient (DSC) and mean boundary error (MBE) of myocardium contours, (2) T1 value and standard deviation (SD) of T1 fitting, (3) subjective evaluation score for overall image quality and motion artifact level, and (4) computation time. Results showed that SDRAP-CC achieved the highest DSC of 85.0 ± 3.9% and the lowest MBE of 0.92 ± 0.25 mm among the methods compared. Additionally, SDRAP-CC performed the best by resulting in lower SD value (28.1 ± 17.6 ms) and higher subjective image quality scores (3.30 ± 0.79 for overall quality and 3.53 ± 0.68 for motion artifact) evaluated by a cardiologist. The proposed SDRAP took only 0.52 s to register one slice of MOLLI images, achieving about sevenfold acceleration over FFD (3.7 s/slice).

Optimization of the Contrast Agent Injection Protocol for Carotid Artery Dynamic Contrast-Enhanced Magnetic Resonance Imaging.

BACKGROUND: The injection protocol used in previous carotid artery dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) studies varied. PURPOSE: To investigate the effect of contrast injection protocol and optimize this protocol for carotid artery DCE-MRI. STUDY TYPE: Prospective. SUBJECTS: Digital phantom and seven patients with carotid atherosclerosis. FIELD STRENGTH/SEQUENCE: 3 T, spoiled gradient recalled echo sequence. ASSESSMENT: Different injection doses (0.01-0.3 mmol/kg) and effective injection rates (0.01-1 mmol/sec) were tested using a digital carotid plaque phantom considering the contrast pharmacokinetics, DCE-MRI imaging, contrast variation and flow-related imaging artifacts, random time delay between the contrast injection and image acquisition, and pharmacokinetic analysis process. For each injection protocol, combining the root mean square relative error (RMSRE) of the measured K trans and v P maps within the adventitial vasa vasorum from 10 tested time delays by the root mean square produced RMSREoverall-vv which was used to measure the overall accuracy of the pharmacokinetic parameters. In vivo validation was performed on seven patients with carotid atherosclerosis by imaging them twice using the traditional commonly used protocol and the recommended protocol found by simulation. STATISTICAL TEST: Student's t-test, chi-square test, and paired t-test, P < 0.05 was considered statistically significant. RESULTS: A low region of RMSREoverall-vv with the combination of medium injection dose and low effective injection rate was found. The protocol with injection dose of 0.07 mmol/kg and effective injection rate of 0.06 mmol/sec achieved the minimal RMSREoverall-vv (4.29%), thus was recommended, which showed more accurate arterial input function. Coinciding with the simulation results, this recommended protocol in in vivo experiments produced significantly fewer image artifacts, lower K trans and v P (P all <0.05) than traditional protocol which overestimated these parameters in simulation. DATA CONCLUSION: The contrast injection protocol influenced the accuracy of the pharmacokinetics parameter estimation in carotid artery DCE-MRI. The injection protocol with injection dose of 0.07 mmol/kg and effective injection rate of 0.06 mmol/sec was recommended. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY STAGE: 1.

End-to-end deep learning nonrigid motion-corrected reconstruction for highly accelerated free-breathing coronary MRA.

PURPOSE: To develop an end-to-end deep learning technique for nonrigid motion-corrected (MoCo) reconstruction of ninefold undersampled free-breathing whole-heart coronary MRA (CMRA). METHODS: A novel deep learning framework was developed consisting of a diffeomorphic registration network and a motion-informed model-based deep learning (MoDL) reconstruction network. The registration network receives as input highly undersampled (~22×) respiratory-resolved images and outputs 3D nonrigid respiratory motion fields between the images. The motion-informed MoDL performs MoCo reconstruction from undersampled data using the predicted motion fields. The whole deep learning framework, termed as MoCo-MoDL, was trained end-to-end in a supervised manner for simultaneous 3D nonrigid motion estimation and MoCo reconstruction. MoCo-MoDL was compared with a state-of-the-art nonrigid MoCo CMRA reconstruction technique in 15 retrospectively undersampled datasets and 9 prospectively undersampled acquisitions. RESULTS: The acquisition time for ninefold accelerated CMRA was ~2.5 min. The reconstruction time was ~22 s for the proposed MoCo-MoDL and ~35 min for the conventional approach. MoCo-MoDL achieved higher peak SNR (27.86 ± 3.00 vs. 26.71 ± 2.79; P < .05) and structural similarity (0.78 ± 0.06 vs. 0.75 ± 0.06; P < .05) than the conventional approach. Similar vessel length and visual image quality score were obtained with the 2 methods, whereas improved vessel sharpness was observed with MoCo-MoDL. CONCLUSION: An end-to-end deep learning approach was introduced for simultaneous nonrigid motion estimation and MoCo reconstruction of highly undersampled free-breathing whole-heart CMRA. The rapid free-breathing CMRA acquisition together with the fast reconstruction of the proposed approach promises easy integration into clinical workflow.

A novel sequence for simultaneous measurement of whole-brain static and dynamic MRA, intracranial vessel wall image, and T1 -weighted structural brain MRI.

PURPOSE: To propose a highly time-efficient imaging technique named improved simultaneous noncontrast angiography and intraplaque hemorrhage (iSNAP) for simultaneous assessment of lumen, vessel wall, and blood flow in intracranial arteries. METHODS: iSNAP consists of pulsed arterial spin labeling preparations and 3D golden angle radial acquisition. Images were reconstructed by k-space weighted image contrast (KWIC) method with optimized data-sharing strategies. Dynamic MRA for blood flow assessment was obtained from iSNAP by reconstruction at multiple inversion times and image subtraction, static MRA by both image subtraction approach and phase-sensitive inversion recovery technique, and vessel wall images by both reconstruction at zero-crossing time-point of blood and phase-sensitive inversion recovery. A T1 -weighted brain MRI was also reconstructed from iSNAP. Preliminary comparison of iSNAP against the dedicated dynamic MRA sequence 4D-TRANCE, MRA/vessel wall imaging sequence SNAP, and vessel wall imaging sequence T1 -weighted VISTA was performed in healthy volunteers and patients. RESULTS: iSNAP has whole-brain coverage and takes ~6.5 min. The dedicated reconstruction strategies are feasible for each iSNAP image contrast and beneficial for image SNR. iSNAP-dynamic MRA yields similar dynamic flow information as 4D-TRANCE and allows more flexible temporal resolution. The 2 types of iSNAP static MRA images complement each other in characterizing both proximal large arteries and distal small arteries. Depiction of vessel wall lesions in iSNAP vessel wall images is better than SNAP and may be similar to T1 -weighted VISTA, although the images are slightly blurred. CONCLUSION: iSNAP provides a time-efficient evaluation of intracranial arteries and may have great potential for comprehensive assessment of intracranial vascular conditions using a single sequence.

Deep-learning based super-resolution for 3D isotropic coronary MR angiography in less than a minute.

PURPOSE: To develop and evaluate a novel and generalizable super-resolution (SR) deep-learning framework for motion-compensated isotropic 3D coronary MR angiography (CMRA), which allows free-breathing acquisitions in less than a minute. METHODS: Undersampled motion-corrected reconstructions have enabled free-breathing isotropic 3D CMRA in ~5-10 min acquisition times. In this work, we propose a deep-learning-based SR framework, combined with non-rigid respiratory motion compensation, to shorten the acquisition time to less than 1 min. A generative adversarial network (GAN) is proposed consisting of two cascaded Enhanced Deep Residual Network generator, a trainable discriminator, and a perceptual loss network. A 16-fold increase in spatial resolution is achieved by reconstructing a high-resolution (HR) isotropic CMRA (0.9 mm3 or 1.2 mm3 ) from a low-resolution (LR) anisotropic CMRA (0.9 × 3.6 × 3.6 mm3 or 1.2 × 4.8 × 4.8 mm3 ). The impact and generalization of the proposed SRGAN approach to different input resolutions and operation on image and patch-level is investigated. SRGAN was evaluated on a retrospective downsampled cohort of 50 patients and on 16 prospective patients that were scanned with LR-CMRA in ~50 s under free-breathing. Vessel sharpness and length of the coronary arteries from the SR-CMRA is compared against the HR-CMRA. RESULTS: SR-CMRA showed statistically significant (P < .001) improved vessel sharpness 34.1% ± 12.3% and length 41.5% ± 8.1% compared with LR-CMRA. Good generalization to input resolution and image/patch-level processing was found. SR-CMRA enabled recovery of coronary stenosis similar to HR-CMRA with comparable qualitative performance. CONCLUSION: The proposed SR-CMRA provides a 16-fold increase in spatial resolution with comparable image quality to HR-CMRA while reducing the predictable scan time to <1 min.

Deep learning-enhanced T1 mapping with spatial-temporal and physical constraint.

PURPOSE: To propose a reconstruction framework to generate accurate T1 maps for a fast MR T1 mapping sequence. METHODS: A deep learning-enhanced T1 mapping method with spatial-temporal and physical constraint (DAINTY) was proposed. This method explicitly imposed low-rank and sparsity constraints on the multiframe T1 -weighted images to exploit the spatial-temporal correlation. A deep neural network was used to efficiently perform T1 mapping as well as denoise and reduce undersampling artifacts. Additionally, the physical constraint was used to build a bridge between low-rank and sparsity constraint and deep learning prior, so the benefits of constrained reconstruction and deep learning can be both available. The DAINTY method was trained on simulated brain data sets, but tested on real acquired phantom, 6 healthy volunteers, and 7 atherosclerosis patients, compared with the narrow-band k-space-weighted image contrast filter conjugate-gradient SENSE (NK-CS) method, kt-sparse-SENSE (kt-SS) method, and low-rank plus sparsity (L+S) method with least-squares T1 fitting and direct deep learning mapping. RESULTS: The DAINTY method can generate more accurate T1 maps and higher-quality T1 -weighted images compared with other methods. For atherosclerosis patients, the intraplaque hemorrhage can be successfully detected. The computation speed of DAINTY was 10 times faster than traditional methods. Meanwhile, DAINTY can reconstruct images with comparable quality using only 50% of k-space data. CONCLUSION: The proposed method can provide accurate T1 maps and good-quality T1 -weighted images with high efficiency.

Synergistic multi-contrast cardiac magnetic resonance image reconstruction.

Cardiac magnetic resonance imaging (CMR) is an important tool for the non-invasive diagnosis of a variety of cardiovascular diseases. Parametric mapping with multi-contrast CMR is able to quantify tissue alterations in myocardial disease and promises to improve patient care. However, magnetic resonance imaging is an inherently slow imaging modality, resulting in long acquisition times for parametric mapping which acquires a series of cardiac images with different contrasts for signal fitting or dictionary matching. Furthermore, extra efforts to deal with respiratory and cardiac motion by triggering and gating further increase the scan time. Several techniques have been developed to speed up CMR acquisitions, which usually acquire less data than that required by the Nyquist-Shannon sampling theorem, followed by regularized reconstruction to mitigate undersampling artefacts. Recent advances in CMR parametric mapping speed up CMR by synergistically exploiting spatial-temporal and contrast redundancies. In this article, we will review the recent developments in multi-contrast CMR image reconstruction for parametric mapping with special focus on low-rank and model-based reconstructions. Deep learning-based multi-contrast reconstruction has recently been proposed in other magnetic resonance applications. These developments will be covered to introduce the general methodology. Current technical limitations and potential future directions are discussed. This article is part of the theme issue 'Synergistic tomographic image reconstruction: part 1'.

Deep learning-based MR fingerprinting ASL ReconStruction (DeepMARS).

PURPOSE: To develop a reproducible and fast method to reconstruct MR fingerprinting arterial spin labeling (MRF-ASL) perfusion maps using deep learning. METHOD: A fully connected neural network, denoted as DeepMARS, was trained using simulation data and added Gaussian noise. Two MRF-ASL models were used to generate the simulation data, specifically a single-compartment model with 4 unknowns parameters and a two-compartment model with 7 unknown parameters. The DeepMARS method was evaluated using MRF-ASL data from healthy subjects (N = 7) and patients with Moymoya disease (N = 3). Computation time, coefficient of determination (R2 ), and intraclass correlation coefficient (ICC) were compared between DeepMARS and conventional dictionary matching (DM). The relationship between DeepMARS and Look-Locker PASL was evaluated by a linear mixed model. RESULTS: Computation time per voxel was <0.5 ms for DeepMARS and >4 seconds for DM in the single-compartment model. Compared with DM, the DeepMARS showed higher R2 and significantly improved ICC for single-compartment derived bolus arrival time (BAT) and two-compartment derived cerebral blood flow (CBF) and higher or similar R2 /ICC for other parameters. In addition, the DeepMARS was significantly correlated with Look-Locker PASL for BAT (single-compartment) and CBF (two-compartment). Moreover, for Moyamoya patients, the location of diminished CBF and prolonged BAT shown in DeepMARS was consistent with the position of occluded arteries shown in time-of-flight MR angiography. CONCLUSION: Reconstruction of MRF-ASL with DeepMARS is faster and more reproducible than DM.

3D free-breathing cardiac magnetic resonance fingerprinting.

PURPOSE: To develop a novel respiratory motion compensated three-dimensional (3D) cardiac magnetic resonance fingerprinting (cMRF) approach for whole-heart myocardial T1 and T2 mapping from a free-breathing scan. METHODS: Two-dimensional (2D) cMRF has been recently proposed for simultaneous, co-registered T1 and T2 mapping from a breath-hold scan; however, coverage is limited. Here we propose a novel respiratory motion compensated 3D cMRF approach for whole-heart myocardial T1 and T2 tissue characterization from a free-breathing scan. Variable inversion recovery and T2 preparation modules are used for parametric encoding, respiratory bellows driven localized autofocus is proposed for beat-to-beat translation motion correction and a subspace regularized reconstruction is employed to accelerate the scan. The proposed 3D cMRF approach was evaluated in a standardized T1 /T2 phantom in comparison with reference spin echo values and in 10 healthy subjects in comparison with standard 2D MOLLI, SASHA and T2 -GraSE mapping techniques at 1.5 T. RESULTS: 3D cMRF T1 and T2 measurements were generally in good agreement with reference spin echo values in the phantom experiments, with relative errors of 2.9% and 3.8% for T1 and T2 (T2 < 100 ms), respectively. in vivo left ventricle (LV) myocardial T1 values were 1054 ± 19 ms for MOLLI, 1146 ± 20 ms for SASHA and 1093 ± 24 ms for the proposed 3D cMRF; corresponding T2 values were 51.8 ± 1.6 ms for T2-GraSE and 44.6 ± 2.0 ms for 3D cMRF. LV coefficients of variation were 7.6 ± 1.6% for MOLLI, 12.1 ± 2.7% for SASHA and 5.8 ± 0.8% for 3D cMRF T1 , and 10.5 ± 1.4% for T2-GraSE and 11.7 ± 1.6% for 3D cMRF T2 . CONCLUSION: The proposed 3D cMRF can provide whole-heart, simultaneous and co-registered T1 and T2 maps with accuracy and precision comparable to those of clinical standards in a single free-breathing scan of about 7 min.

Respiratory motion-compensated high-resolution 3D whole-heart T1ρ mapping.

BACKGROUND: Cardiovascular magnetic resonance (CMR) T1ρ mapping can be used to detect ischemic or non-ischemic cardiomyopathy without the need of exogenous contrast agents. Current 2D myocardial T1ρ mapping requires multiple breath-holds and provides limited coverage. Respiratory gating by diaphragmatic navigation has recently been exploited to enable free-breathing 3D T1ρ mapping, which, however, has low acquisition efficiency and may result in unpredictable and long scan times. This study aims to develop a fast respiratory motion-compensated 3D whole-heart myocardial T1ρ mapping technique with high spatial resolution and predictable scan time. METHODS: The proposed electrocardiogram (ECG)-triggered T1ρ mapping sequence is performed under free-breathing using an undersampled variable-density 3D Cartesian sampling with spiral-like order. Preparation pulses with different T1ρ spin-lock times are employed to acquire multiple T1ρ-weighted images. A saturation prepulse is played at the start of each heartbeat to reset the magnetization before T1ρ preparation. Image navigators are employed to enable beat-to-beat 2D translational respiratory motion correction of the heart for each T1ρ-weighted dataset, after which, 3D translational registration is performed to align all T1ρ-weighted volumes. Undersampled reconstruction is performed using a multi-contrast 3D patch-based low-rank algorithm. The accuracy of the proposed technique was tested in phantoms and in vivo in 11 healthy subjects in comparison with 2D T1ρ mapping. The feasibility of the proposed technique was further investigated in 3 patients with suspected cardiovascular disease. Breath-hold late-gadolinium enhanced (LGE) images were acquired in patients as reference for scar detection. RESULTS: Phantoms results revealed that the proposed technique provided accurate T1ρ values over a wide range of simulated heart rates in comparison to a 2D T1ρ mapping reference. Homogeneous 3D T1ρ maps were obtained for healthy subjects, with septal T1ρ of 58.0 ± 4.1 ms which was comparable to 2D breath-hold measurements (57.6 ± 4.7 ms, P = 0.83). Myocardial scar was detected in 1 of the 3 patients, and increased T1ρ values (87.4 ± 5.7 ms) were observed in the infarcted region. CONCLUSIONS: An accelerated free-breathing 3D whole-heart T1ρ mapping technique was developed with high respiratory scan efficiency and near-isotropic spatial resolution (1.7 × 1.7 × 2 mm3) in a clinically feasible scan time of ~ 6 mins. Preliminary patient results suggest that the proposed technique may find applications in non-contrast myocardial tissue characterization.