XD-GRASP: Golden-angle radial MRI with reconstruction of extra motion-state dimensions using compressed sensing

Focused navigation for respiratory-motion-corrected free-running radial 4D flow MRI

PURPOSE

To validate a respiratory motion correction method called focused navigation (fNAV) for free-running radial whole-heart 4D flow MRI.

METHODS

Using fNAV, respiratory signals derived from radial readouts are converted into three orthogonal displacements, which are then used to correct respiratory motion in 4D flow datasets. Hundred 4D flow acquisitions were simulated with non-rigid respiratory motion and used for validation. The difference between generated and fNAV displacement coefficients was calculated. Vessel area and flow measurements from 4D flow reconstructions with (fNAV) and without (uncorrected) motion correction were compared to the motion-free ground-truth. In 25 patients, the same measurements were compared between fNAV 4D flow, 2D flow, navigator-gated Cartesian 4D flow, and uncorrected 4D flow datasets.

RESULTS

For simulated data, the average difference between generated and fNAV displacement coefficients was 0.04± $$ \pm $$ 0.32 mm and 0.31± $$ \pm $$ 0.35 mm in the x and y directions, respectively. In the z direction, this difference was region-dependent (0.02± $$ \pm $$ 0.51 mm up to 5.85± $$ \pm $$ 3.41 mm). For all measurements (vessel area, net volume, and peak flow), the average difference from ground truth was higher for uncorrected 4D flow datasets (0.32± $$ \pm $$ 0.11 cm2 , 11.1± $$ \pm $$ 3.5 mL, and 22.3± $$ \pm $$ 6.0 mL/s) than for fNAV 4D flow datasets (0.10± $$ \pm $$ 0.03 cm2 , 2.6± $$ \pm $$ 0.7 mL, and 5.1± 0 $$ \pm 0 $$ .9 mL/s, p < 0.05). In vivo, average vessel area measurements were 4.92± $$ \pm $$ 2.95 cm2 , 5.06± $$ \pm $$ 2.64 cm2 , 4.87± $$ \pm $$ 2.57 cm2 , 4.87± $$ \pm $$ 2.69 cm2 , for 2D flow and fNAV, navigator-gated and uncorrected 4D flow datasets, respectively. In the ascending aorta, all 4D flow datasets except for the fNAV reconstruction had significantly different vessel area measurements from 2D flow. Overall, 2D flow datasets demonstrated the strongest correlation to fNAV 4D flow for both net volume (r2  = 0.92) and peak flow (r2  = 0.94), followed by navigator-gated 4D flow (r2  = 0.83 and r2  = 0.86, respectively), and uncorrected 4D flow (r2  = 0.69 and r2  = 0.86, respectively).

CONCLUSION

fNAV corrected respiratory motion in vitro and in vivo, resulting in fNAV 4D flow measurements that are comparable to those derived from 2D flow and navigator-gated Cartesian 4D flow datasets, with improvements over those from uncorrected 4D flow.

Deep learning-based left ventricular segmentation demonstrates improved performance on respiratory motion-resolved whole-heart reconstructions

Introduction

Deep learning (DL)-based segmentation has gained popularity for routine cardiac magnetic resonance (CMR) image analysis and in particular, delineation of left ventricular (LV) borders for LV volume determination. Free-breathing, self-navigated, whole-heart CMR exams provide high-resolution, isotropic coverage of the heart for assessment of cardiac anatomy including LV volume. The combination of whole-heart free-breathing CMR and DL-based LV segmentation has the potential to streamline the acquisition and analysis of clinical CMR exams. The purpose of this study was to compare the performance of a DL-based automatic LV segmentation network trained primarily on computed tomography (CT) images in two whole-heart CMR reconstruction methods: (1) an in-line respiratory motion-corrected (Mcorr) reconstruction and (2) an off-line, compressed sensing-based, multi-volume respiratory motion-resolved (Mres) reconstruction. Given that Mres images were shown to have greater image quality in previous studies than Mcorr images, we hypothesized that the LV volumes segmented from Mres images are closer to the manual expert-traced left ventricular endocardial border than the Mcorr images.

Method

This retrospective study used 15 patients who underwent clinically indicated 1.5 T CMR exams with a prototype ECG-gated 3D radial phyllotaxis balanced steady state free precession (bSSFP) sequence. For each reconstruction method, the absolute volume difference (AVD) of the automatically and manually segmented LV volumes was used as the primary quantity to investigate whether 3D DL-based LV segmentation generalized better on Mcorr or Mres 3D whole-heart images. Additionally, we assessed the 3D Dice similarity coefficient between the manual and automatic LV masks of each reconstructed 3D whole-heart image and the sharpness of the LV myocardium-blood pool interface. A two-tail paired Student's t-test (alpha = 0.05) was used to test the significance in this study.

Results & Discussion

The AVD in the respiratory Mres reconstruction was lower than the AVD in the respiratory Mcorr reconstruction: 7.73 ± 6.54 ml vs. 20.0 ± 22.4 ml, respectively (n = 15, p-value = 0.03). The 3D Dice coefficient between the DL-segmented masks and the manually segmented masks was higher for Mres images than for Mcorr images: 0.90 ± 0.02 vs. 0.87 ± 0.03 respectively, with a p-value = 0.02. Sharpness on Mres images was higher than on Mcorr images: 0.15 ± 0.05 vs. 0.12 ± 0.04, respectively, with a p-value of 0.014 (n = 15).

Conclusion

We conclude that the DL-based 3D automatic LV segmentation network trained on CT images and fine-tuned on MR images generalized better on Mres images than on Mcorr images for quantifying LV volumes.

Motion compensated self supervised deep learning for highly accelerated 3D ultrashort Echo time pulmonary MRI

PURPOSE

To investigate motion compensated, self-supervised, model based deep learning (MBDL) as a method to reconstruct free breathing, 3D pulmonary UTE acquisitions.

THEORY AND METHODS

A self-supervised eXtra dimension MBDL architecture (XD-MBDL) was developed that combined respiratory states to reconstruct a single high-quality 3D image. Non-rigid motion fields were incorporated into this architecture by estimating motion fields from a lower resolution motion resolved (XD-GRASP) reconstruction. Motion compensated XD-MBDL was evaluated on lung UTE datasets with and without contrast and compared to constrained reconstructions and variants of self-supervised MBDL that do not account for dynamic respiratory states or leverage motion correction.

RESULTS

Images reconstructed using XD-MBDL demonstrate improved image quality as measured by apparent SNR (aSNR), contrast to noise ratio (CNR), and visual assessment relative to self-supervised MBDL approaches that do not account for dynamic respiratory states, XD-GRASP and a recently proposed motion compensated iterative reconstruction strategy (iMoCo). Additionally, XD-MBDL reduced reconstruction time relative to both XD-GRASP and iMoCo.

CONCLUSION

A method was developed to allow self-supervised MBDL to combine multiple respiratory states to reconstruct a single image. This method was combined with graphics processing unit (GPU)-based image registration to further improve reconstruction quality. This approach showed promising results reconstructing a user-selected respiratory phase from free breathing 3D pulmonary UTE acquisitions.

Gaussian Processes for real-time 3D motion and uncertainty estimation during MR-guided radiotherapy

Respiratory motion during radiotherapy causes uncertainty in the tumor's location, which is typically addressed by an increased radiation area and a decreased dose. As a result, the treatments' efficacy is reduced. The recently proposed hybrid MR-linac scanner holds the promise to efficiently deal with such respiratory motion through real-time adaptive MR-guided radiotherapy (MRgRT). For MRgRT, motion-fields should be estimated from MR-data and the radiotherapy plan should be adapted in real-time according to the estimated motion-fields. All of this should be performed with a total latency of maximally 200 ms, including data acquisition and reconstruction. A measure of confidence in such estimated motion-fields is highly desirable, for instance to ensure the patient's safety in case of unexpected and undesirable motion. In this work, we propose a framework based on Gaussian Processes to infer 3D motion-fields and uncertainty maps in real-time from only three readouts of MR-data. We demonstrated an inference frame rate up to 69 Hz including data acquisition and reconstruction, thereby exploiting the limited amount of required MR-data. Additionally, we designed a rejection criterion based on the motion-field uncertainty maps to demonstrate the framework's potential for quality assurance. The framework was validated in silico and in vivo on healthy volunteer data (n=5) acquired using an MR-linac, thereby taking into account different breathing patterns and controlled bulk motion. Results indicate end-point-errors with a 75th percentile below 1 mm in silico, and a correct detection of erroneous motion estimates with the rejection criterion. Altogether, the results show the potential of the framework for application in real-time MR-guided radiotherapy with an MR-linac.

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

PURPOSE

To develop a respiratory-resolved motion-compensation method for free-breathing, high-resolution coronary magnetic resonance angiography (CMRA) using a 3D cones trajectory.

METHODS

To achieve respiratory-resolved 0.98 mm resolution images in a clinically relevant scan time, we undersample the imaging data with a variable-density 3D cones trajectory. For retrospective motion compensation, translational estimates from 3D image-based navigators (3D iNAVs) are used to bin the imaging data into four phases from end-expiration to end-inspiration. To ensure pseudo-random undersampling within each respiratory phase, we devise a phyllotaxis readout ordering scheme mindful of eddy current artifacts in steady state free precession imaging. Following binning, residual 3D translational motion within each phase is computed using the 3D iNAVs and corrected for in the imaging data. The noise-like aliasing characteristic of the combined phyllotaxis and cones sampling pattern is leveraged in a compressed sensing reconstruction with spatial and temporal regularization to reduce aliasing in each of the respiratory phases.

RESULTS

In initial studies of six subjects, respiratory motion compensation using the proposed method yields improved image quality compared to non-respiratory-resolved approaches with no motion correction and with 3D translational correction. Qualitative assessment by two cardiologists and quantitative evaluation with the image edge profile acutance metric indicate the superior sharpness of coronary segments reconstructed with the proposed method (P < 0.01).

CONCLUSION

We have demonstrated a new method for free-breathing, high-resolution CMRA based on a variable-density 3D cones trajectory with modified phyllotaxis ordering and respiratory-resolved motion compensation with 3D iNAVs.

Single-spoke binning: Reducing motion artifacts in abdominal radial stack-of-stars imaging

PURPOSE

To increase the effectiveness of respiratory gating in radial stack-of-stars MRI, particularly when imaging at high spatial resolutions or with multiple echoes.

METHODS

Free induction decay (FID) navigators were integrated into a three-dimensional gradient echo radial stack-of-stars pulse sequence. These navigators provided a motion signal with a high temporal resolution, which allowed single-spoke binning (SSB): each spoke at each phase encode step was sorted individually to the corresponding motion state of the respiratory signal. SSB was compared with spoke-angle binning (SAB), in which all phase encode steps of one projection angle were sorted without the use of additional navigator data. To illustrate the benefit of SSB over SAB, images of a motion phantom and of six free-breathing volunteers were reconstructed after motion-gating using either method. Image sharpness was quantitatively compared using image gradient entropies.

RESULTS

The proposed method resulted in sharper images of the motion phantom and free-breathing volunteers. Differences in gradient entropy were statistically significant (p = 0.03) in favor of SSB. The increased accuracy of motion-gating led to a decrease of streaking artifacts in motion-gated four-dimensional reconstructions. To consistently estimate respiratory signals from the FID-navigator data, specific types of gradient spoiler waveforms were required.

CONCLUSION

SSB allowed high-resolution motion-corrected MR imaging, even when acquiring multiple gradient echo signals or large acquisition matrices, without sacrificing accuracy of motion-gating. SSB thus relieves restrictions on the choice of pulse sequence parameters, enabling the use of motion-gated radial stack-of-stars MRI in a broader domain of clinical applications.

Four-dimensional reconstruction and characterization of bladder deformations

BACKGROUND AND OBJECTIVE

Pelvic floor disorders are prevalent diseases and patient care remains difficult as the dynamics of the pelvic floor remains poorly understood. So far, only 2D dynamic observations of straining exercises at excretion are available in the clinics and 3D mechanical defects of pelvic organs are not well studied. In this context, we propose a complete methodology for the 3D representation of non-reversible bladder deformations during exercises, combined with a 3D representation of the location of the highest strain areas on the organ surface.

METHODS

Novel image segmentation and registration approaches have been combined with three geometrical configurations of up-to-date rapid dynamic multi-slice MRI acquisitions for the reconstruction of real-time dynamic bladder volumes.

RESULTS

For the first time, we proposed real-time 3D deformation fields of the bladder under strain from in-bore forced breathing exercises. The potential of our method was assessed on eight control subjects undergoing forced breathing exercises. We obtained average volume deviations of the reconstructed dynamic volume of bladders around 2.5% and high registration accuracy with mean distance values of 0.4 ± 0.3 mm and Hausdorff distance values of 2.2 ± 1.1 mm.

CONCLUSIONS

The proposed framework provides proper 3D+t spatial tracking of non-reversible bladder deformations. This has immediate applicability in clinical settings for a better understanding of pelvic organ prolapse pathophysiology. This work can be extended to patients with cavity filling or excretion problems to better characterize the severity of pelvic floor pathologies or to be used for preoperative surgical planning.

AI in MRI: Computational Frameworks for a Faster, Optimized, and Automated Imaging Workflow

Over the last decade, artificial intelligence (AI) has made an enormous impact on a wide range of fields, including science, engineering, informatics, finance, and transportation [...].

Free-breathing myocardial T1 mapping using inversion-recovery radial FLASH and motion-resolved model-based reconstruction

PURPOSE

To develop a free-breathing myocardialT 1 $$ {\mathrm{T}}_1 $$ mapping technique using inversion-recovery (IR) radial fast low-angle shot (FLASH) and calibrationless motion-resolved model-based reconstruction.

METHODS

Free-running (free-breathing, retrospective cardiac gating) IR radial FLASH is used for data acquisition at 3T. First, to reduce the waiting time between inversions, an analytical formula is derived that takes the incompleteT 1 $$ {\mathrm{T}}_1 $$ recovery into account for an accurateT 1 $$ {\mathrm{T}}_1 $$ calculation. Second, the respiratory motion signal is estimated from the k-space center of the contrast varying acquisition using an adapted singular spectrum analysis (SSA-FARY) technique. Third, a motion-resolved model-based reconstruction is used to estimate both parameter and coil sensitivity maps directly from the sorted k-space data. Thus, spatiotemporal total variation, in addition to the spatial sparsity constraints, can be directly applied to the parameter maps. Validations are performed on an experimental phantom, 11 human subjects, and a young landrace pig with myocardial infarction.

RESULTS

In comparison to an IR spin-echo reference, phantom results confirm goodT 1 $$ {\mathrm{T}}_1 $$ accuracy, when reducing the waiting time from 5 s to 1 s using the new correction. The motion-resolved model-based reconstruction further improvesT 1 $$ {\mathrm{T}}_1 $$ precision compared to the spatial regularization-only reconstruction. Aside from showing that a reliable respiratory motion signal can be estimated using modified SSA-FARY, in vivo studies demonstrate that dynamic myocardialT 1 $$ {\mathrm{T}}_1 $$ maps can be obtained within 2 min with good precision and repeatability.

CONCLUSION

Motion-resolved myocardialT 1 $$ {\mathrm{T}}_1 $$ mapping during free-breathing with good accuracy, precision and repeatability can be achieved by combining inversion-recovery radial FLASH, self-gating and a calibrationless motion-resolved model-based reconstruction.

Real-time radial reconstruction with domain transform manifold learning for MRI-guided radiotherapy

BACKGROUND

MRI-guidance techniques that dynamically adapt radiation beams to follow tumor motion in real time will lead to more accurate cancer treatments and reduced collateral healthy tissue damage. The gold-standard for reconstruction of undersampled MR data is compressed sensing (CS) which is computationally slow and limits the rate that images can be available for real-time adaptation.

PURPOSE

Once trained, neural networks can be used to accurately reconstruct raw MRI data with minimal latency. Here, we test the suitability of deep-learning-based image reconstruction for real-time tracking applications on MRI-Linacs.

METHODS

We use automated transform by manifold approximation (AUTOMAP), a generalized framework that maps raw MR signal to the target image domain, to rapidly reconstruct images from undersampled radial k-space data. The AUTOMAP neural network was trained to reconstruct images from a golden-angle radial acquisition, a benchmark for motion-sensitive imaging, on lung cancer patient data and generic images from ImageNet. Model training was subsequently augmented with motion-encoded k-space data derived from videos in the YouTube-8M dataset to encourage motion robust reconstruction.

RESULTS

AUTOMAP models fine-tuned on retrospectively acquired lung cancer patient data reconstructed radial k-space with equivalent accuracy to CS but with much shorter processing times. Validation of motion-trained models with a virtual dynamic lung tumor phantom showed that the generalized motion properties learned from YouTube lead to improved target tracking accuracy.

CONCLUSION

AUTOMAP can achieve real-time, accurate reconstruction of radial data. These findings imply that neural-network-based reconstruction is potentially superior to alternative approaches for real-time image guidance applications.

Uncertainty-aware physics-driven deep learning network for free-breathing liver fat and R2 * quantification using self-gated stack-of-radial MRI

PURPOSE

To develop a deep learning-based method for rapid liver proton-density fat fraction (PDFF) and R2 * quantification with built-in uncertainty estimation using self-gated free-breathing stack-of-radial MRI.

METHODS

This work developed an uncertainty-aware physics-driven deep learning network (UP-Net) to (1) suppress radial streaking artifacts because of undersampling after self-gating, (2) calculate accurate quantitative maps, and (3) provide pixel-wise uncertainty maps. UP-Net incorporated a phase augmentation strategy, generative adversarial network architecture, and an MRI physics loss term based on a fat-water and R2 * signal model. UP-Net was trained and tested using free-breathing multi-echo stack-of-radial MRI data from 105 subjects. UP-Net uncertainty scores were calibrated in a validation dataset and used to predict quantification errors for liver PDFF and R2 * in a testing dataset.

RESULTS

Compared with images reconstructed using compressed sensing (CS), UP-Net achieved structural similarity index >0.87 and normalized root mean squared error <0.18. Compared with reference quantitative maps generated using CS and graph-cut (GC) algorithms, UP-Net achieved low mean differences (MD) for liver PDFF (-0.36%) and R2 * (-0.37 s-1 ). Compared with breath-holding Cartesian MRI results, UP-Net achieved low MD for liver PDFF (0.53%) and R2 * (6.75 s-1 ). UP-Net uncertainty scores predicted absolute liver PDFF and R2 * errors with low MD of 0.27% and 0.12 s-1 compared to CS + GC results. The computational time for UP-Net was 79 ms/slice, whereas CS + GC required 3.2 min/slice.

CONCLUSION

UP-Net rapidly calculates accurate liver PDFF and R2 * maps from self-gated free-breathing stack-of-radial MRI. The pixel-wise uncertainty maps from UP-Net predict quantification errors in the liver.

Region-focused multi-view transformer-based generative adversarial network for cardiac cine MRI reconstruction

Cardiac cine magnetic resonance imaging (MRI) reconstruction is challenging due to spatial and temporal resolution trade-offs. Temporal correlation in cardiac cine MRI is informative and vital for understanding cardiac dynamic motion. Exploiting the temporal correlations in cine reconstruction is crucial to resolve aliasing artifacts and maintaining the cardiac motion patterns. However, existing methods have the following shortcomings: (1) they simultaneously compute pairwise correlations along spatial and temporal dimensions to establish dependencies, ignoring that learning spatial contextual information first will benefit the temporal modeling. (2) most studies neglect to focus on reconstructing the local cardiac regions, resulting in insufficient reconstruction accuracy due to a relatively large field of view. To address these problems, we propose a region-focused multi-view transformer-based generative adversarial network for cardiac cine MRI reconstruction. The proposed transformer divides consecutive cardiac frames into multiple views for cross-view feature extraction, establishing long-distance dependencies among features and effectively learning the spatio-temporal information. We further design a cross-view attention for spatio-temporal information fusion, ensuring the interaction of different spatio-temporal information in each view and capturing more temporal correlations of the cardiac motion. In addition, we introduce a cardiac region detection loss for improving the reconstruction quality of the cardiac region. Experimental results demonstrated that our method outperforms state-of-the-art methods. Especially with an acceleration factor as high as 10×, our method can reconstruct images with better accuracy and perceptual quality.

Kz-accelerated variable-density stack-of-stars MRI

This work aimed to develop a modified stack-of-stars golden-angle radial sampling scheme with variable-density acceleration along the slice (kz) dimension (referred to as VD-stack-of-stars) and to test this new sampling trajectory with multi-coil compressed sensing reconstruction for rapid motion-robust 3D liver MRI. VD-stack-of-stars sampling implements additional variable-density undersampling along the kz dimension, so that slice resolution (or volumetric coverage) can be increased without prolonging scan time. The new sampling trajectory (with increased slice resolution) was compared with standard stack-of-stars sampling with fully sampled kz (with standard slice resolution) in both non-contrast-enhanced free-breathing liver MRI and dynamic contrast-enhanced MRI (DCE-MRI) of the liver in volunteers. For both sampling trajectories, respiratory motion was extracted from the acquired radial data, and images were reconstructed using motion-compensated (respiratory-resolved or respiratory-weighted) dynamic radial compressed sensing reconstruction techniques. Qualitative image quality assessment (visual assessment by experienced radiologists) and quantitative analysis (as a metric of image sharpness) were performed to compare images acquired using the new and standard stack-of-stars sampling trajectories. Compared to standard stack-of-stars sampling, both non-contrast-enhanced and DCE liver MR images acquired with VD-stack-of-stars sampling presented improved overall image quality, sharper liver edges and increased hepatic vessel clarity in all image planes. The results have suggested that the proposed VD-stack-of-stars sampling scheme can achieve improved performance (increased slice resolution or volumetric coverage with better image quality) over standard stack-of-stars sampling in free-breathing DCE-MRI without increasing scan time. The reformatted coronal and sagittal images with better slice resolution may provide added clinical value.

Single-heartbeat cardiac cine imaging via jointly regularized nonrigid motion-corrected reconstruction

The aim of the current study was to develop a novel approach for 2D breath-hold cardiac cine imaging from a single heartbeat, by combining cardiac motion-corrected reconstructions and nonrigidly aligned patch-based regularization. Conventional cardiac cine imaging is obtained via motion-resolved reconstructions of data acquired over multiple heartbeats. Here, we achieve single-heartbeat cine imaging by incorporating nonrigid cardiac motion correction into the reconstruction of each cardiac phase, in conjunction with a motion-aligned patch-based regularization. The proposed Motion-Corrected CINE (MC-CINE) incorporates all acquired data into the reconstruction of each (motion-corrected) cardiac phase, resulting in a better posed problem than motion-resolved approaches. MC-CINE was compared with iterative sensitivity encoding (itSENSE) and Extra-Dimensional Golden Angle Radial Sparse Parallel (XD-GRASP) in 14 healthy subjects in terms of image sharpness, reader scoring (range: 1-5) and reader ranking (range: 1-9) of image quality, and single-slice left ventricular assessment. MC-CINE was significantly superior to both itSENSE and XD-GRASP using 20 heartbeats, two heartbeats, and one heartbeat. Iterative SENSE, XD-GRASP, and MC-CINE achieved a sharpness of 74%, 74%, and 82% using 20 heartbeats, and 53%, 66%, and 82% with one heartbeat, respectively. The corresponding results for reader scoring were 4.0, 4.7, and 4.9 with 20 heartbeats, and 1.1, 3.0, and 3.9 with one heartbeat. The corresponding results for reader ranking were 5.3, 7.3, and 8.6 with 20 heartbeats, and 1.0, 3.2, and 5.4 with one heartbeat. MC-CINE using a single heartbeat presented nonsignificant differences in image quality to itSENSE with 20 heartbeats. MC-CINE and XD-GRASP at one heartbeat both presented a nonsignificant negative bias of less than 2% in ejection fraction relative to the reference itSENSE. It was concluded that the proposed MC-CINE significantly improves image quality relative to itSENSE and XD-GRASP, enabling 2D cine from a single heartbeat.

Joint Cardiac T1 Mapping and Cardiac Cine Using Manifold Modeling

The main focus of this work is to introduce a single free-breathing and ungated imaging protocol to jointly estimate cardiac function and myocardial T1 maps. We reconstruct a time series of images corresponding to k-space data from a free-breathing and ungated inversion recovery gradient echo sequence using a manifold algorithm. We model each image in the time series as a non-linear function of three variables: cardiac and respiratory phases and inversion time. The non-linear function is realized using a convolutional neural networks (CNN) generator, while the CNN parameters, as well as the phase information, are estimated from the measured k-t space data. We use a dense conditional auto-encoder to estimate the cardiac and respiratory phases from the central multi-channel k-space samples acquired at each frame. The latent vectors of the auto-encoder are constrained to be bandlimited functions with appropriate frequency bands, which enables the disentanglement of the latent vectors into cardiac and respiratory phases, even when the data are acquired with intermittent inversion pulses. Once the phases are estimated, we pose the image recovery as the learning of the parameters of the CNN generator from the measured k-t space data. The learned CNN generator is used to generate synthetic data on demand by feeding it with appropriate latent vectors. The proposed approach capitalizes on the synergies between cine MRI and T1 mapping to reduce the scan time and improve patient comfort. The framework also enables the generation of synthetic breath-held cine movies with different inversion contrasts, which improves the visualization of the myocardium. In addition, the approach also enables the estimation of the T1 maps with specific phases, which is challenging with breath-held approaches.

Free-breathing 2D radial cine MRI with respiratory auto-calibrated motion correction (RAMCO)

PURPOSE

To develop a free-breathing (FB) 2D radial balanced steady-state free precession cine cardiac MRI method with 100% respiratory gating efficiency using respiratory auto-calibrated motion correction (RAMCO) based on a motion-sensing camera.

METHODS

The signal from a respiratory motion-sensing camera was recorded during a FB retrospectively electrocardiogram triggered 2D radial balanced steady-state free precession acquisition using pseudo-tiny-golden-angle ordering. With RAMCO, for each acquisition the respiratory signal was retrospectively auto-calibrated by applying different linear translations, using the resulting in-plane image sharpness as a criterium. The auto-calibration determines the optimal magnitude of the linear translations for each of the in-plane directions to minimize motion blurring caused by bulk respiratory motion. Additionally, motion-weighted density compensation was applied during radial gridding to minimize through-plane and non-bulk motion blurring. Left ventricular functional parameters and sharpness scores of FB radial cine were compared with and without RAMCO, and additionally with conventional breath-hold Cartesian cine on 9 volunteers.

RESULTS

FB radial cine with RAMCO had similar sharpness scores as conventional breath-hold Cartesian cine and the left ventricular functional parameters agreed. For FB radial cine, RAMCO reduced respiratory motion artifacts with a statistically significant difference in sharpness scores (P < 0.05) compared to reconstructions without motion correction.

CONCLUSION

2D radial cine imaging with RAMCO allows evaluation of left ventricular functional parameters in FB with 100% respiratory efficiency. It eliminates the need for breath-holds, which is especially valuable for patients with no or impaired breath-holding capacity. Validation of the proposed method on patients is warranted.

High-fidelity Database-free Deep Learning Reconstruction for Real-time Cine Cardiac MRI

Real-time cine cardiac MRI provides an ECG-free free-breathing alternative to clinical gold-standard ECG-gated breath-hold segmented cine MRI for evaluation of heart function. Real-time cine MRI data acquisition during free breathing snapshot imaging enables imaging of patient cohorts that cannot be imaged with segmented or breath-hold acquisitions, but requires rapid imaging to achieve sufficient spatial-temporal resolutions. However, at high acceleration rates, conventional reconstruction techniques suffer from residual aliasing and temporal blurring, including advanced methods such as compressed sensing with radial trajectories. Recently, deep learning (DL) reconstruction has emerged as a powerful tool in MRI. However, its utility for free-breathing real-time cine MRI has been limited, as database-learning of spatio-temporal correlations with varying breathing and cardiac motion patterns across subjects has been challenging. Zero-shot self-supervised physics-guided deep learning (PG-DL) reconstruction has been proposed to overcome such challenges of database training by enabling subject-specific training. In this work, we adapt zero-shot PG-DL for real-time cine MRI with a spatio-temporal regularization. We compare our method to TGRAPPA, locally low-rank (LLR) regularized reconstruction and database-trained PG-DL reconstruction, both for retrospectively and prospectively accelerated datasets. Results on highly accelerated real-time Cartesian cine MRI show that the proposed method outperforms other reconstruction methods, both visibly in terms of noise and aliasing, and quantitatively.

MP-RAVE: IR-Prepared T1 -Weighted Radial Stack-of-Stars 3D GRE imaging with retrospective motion correction

PURPOSE

To describe an inversion-recovery T₁ -weighted radial stack-of-stars 3D gradient echo (GRE) sequence with comparable image quality to conventional MP-RAGE and to demonstrate how the radial acquisition scheme can be utilized for additional retrospective motion correction to improve robustness to head motion.

METHODS

The proposed sequence, named MP-RAVE, has been derived from a previously described radial stack-of-stars 3D GRE sequence (RAVE) and includes a 180° inversion recovery pulse that is generated once for every stack of radial views. The sequence is combined with retrospective 3D motion correction to improve robustness. The effectiveness has been evaluated in phantoms and healthy volunteers and compared to conventional MP-RAGE acquisition.

RESULTS

MP-RAGE and MP-RAVE anatomical images were rated "good" to "excellent" in overall image quality, with artifact level between "mild" and "no artifacts", and with no statistically significant difference between methods. During head motion, MP-RAVE showed higher inherent robustness with artifacts confined to local brain regions. In combination with motion correction, MP-RAVE provided noticeably improved image quality during different head motion and showed statistically significant improvement in image sharpness.

CONCLUSION

MP-RAVE provides comparable image quality and contrast to conventional MP-RAGE with improved robustness to head motion. In combination with retrospective 3D motion correction, MP-RAVE can be a useful alternative to MP-RAGE, especially in non-cooperative or pediatric patients.

Latest Advances in Image Acceleration: All Dimensions are Fair Game

Magnetic resonance imaging (MRI) is a versatile modality that can generate high-resolution images with a variety of tissue contrasts. However, MRI is a slow technique and requires long acquisition times, which increase with higher temporal and spatial resolution and/or when multiple contrasts and large volumetric coverage is required. In order to speedup MR data acquisition, several approaches have been introduced in the literature. Most of these techniques acquire less data than required and exploit intrinsic redundancies in the MR images to recover the information that was not sampled. This article presents a review of MR acquisition and reconstruction methods that have exploited redundancies in the temporal, spatial, and contrast/parametric dimensions to accelerate image data acquisition, focusing on cardiac and abdominal MR imaging applications. The review describes how each of these dimensions has been separately exploited for speeding up MR acquisition to then discuss more advanced techniques where multiple dimensions are exploited together for further reducing scan times. Finally, future directions for multidimensional image acceleration and remaining technical challenges are discussed. EVIDENCE LEVEL: 5 TECHNICAL EFFICACY: 1.

4D Golden-Angle Radial MRI at Subsecond Temporal Resolution

Intraframe motion blurring, as a major challenge in free-breathing dynamic MRI, can be reduced if high temporal resolution can be achieved. To address this challenge, this work proposes a highly accelerated 4D (3D + time) dynamic MRI framework with subsecond temporal resolution that does not require explicit motion compensation. The method combines standard stack-of-stars golden-angle radial sampling and tailored GRASP-Pro (Golden-angle RAdial Sparse Parallel imaging with imProved performance) reconstruction. Specifically, 4D dynamic MRI acquisition is performed continuously without motion gating or sorting. The k-space centers in stack-of-stars radial data are organized to guide estimation of a temporal basis, with which GRASP-Pro reconstruction is employed to enforce joint low-rank subspace and sparsity constraints. This new basis estimation strategy is the new feature proposed for subspace-based reconstruction in this work to achieve high temporal resolution (e.g., subsecond/3D volume). It does not require sequence modification to acquire additional navigation data, it is compatible with commercially available stack-of-stars sequences, and it does not need an intermediate reconstruction step. The proposed 4D dynamic MRI approach was tested in abdominal motion phantom, free-breathing abdominal MRI, and dynamic contrast-enhanced MRI (DCE-MRI). Our results have shown that GRASP-Pro reconstruction with the new basis estimation strategy enables highly-accelerated 4D dynamic imaging at subsecond temporal resolution (with five spokes or less for each dynamic frame per image slice) for both free-breathing non-DCE-MRI and DCE-MRI. In the abdominal phantom, better image quality with lower root mean square error and higher structural similarity index was achieved using GRASP-Pro compared with standard GRASP. With the ability to acquire each 3D image in less than 1 s, intraframe respiratory blurring can be intrinsically reduced for body applications with our approach, which eliminates the need for explicit motion detection and motion compensation.

Parallel non-Cartesian spatial-temporal dictionary learning neural networks (stDLNN) for accelerating 4D-MRI

Dynamic magnetic resonance imaging (MRI) acquisitions are relatively slow due to physical and physiological limitations. The spatial-temporal dictionary learning (DL) approach accelerates dynamic MRI by learning spatial-temporal correlations, but the regularization parameters need to be manually adjusted, the performance at high acceleration rate is limited, and the reconstruction can be time-consuming. Deep learning techniques have shown good performance in accelerating MRI due to the powerful representational capabilities of neural networks. In this work, we propose a parallel non-Cartesian spatial-temporal dictionary learning neural networks (stDLNN) framework that combines dictionary learning with deep learning algorithms and utilizes the spatial-temporal prior information of dynamic MRI data to achieve better reconstruction quality and efficiency. The coefficient estimation modules (CEM) are designed in the framework to adaptively adjust the regularization coefficients. Experimental results show that combining dictionary learning with deep neural networks and using spatial-temporal dictionaries can obviously improve the image quality and computational efficiency compared with the state-of-the-art non-Cartesian imaging methods for accelerating the 4D-MRI especially at high acceleration rate.

Fetal 3D cardiovascular cine image acquisition using radial sampling and compressed sensing

PURPOSE

To explore a fetal 3D cardiovascular cine acquisition using a radial image acquisition and compressed-sensing reconstruction and compare image quality and scan time with conventional multislice 2D imaging.

METHODS

Volumetric fetal cardiac data were acquired in 26 volunteers using a radial 3D balanced SSFP pulse sequence. Cardiac gating was performed using a Doppler ultrasound device. Images were reconstructed using a parallel-imaging and compressed-sensing algorithm. Multiplanar reformatting to standard cardiac views was performed before image analysis. Clinical 2D images were used for comparison. Qualitative and quantitative image evaluation were performed by two experienced observers (scale: 1-4). Volumes, mass, and function were assessed.

RESULTS

Average scan time for the 3D imaging was 6 min, including one localizer. A 2D imaging stack covering the entire heart including localizer sequences took at least 6.5 min, depending on planning complexity. The 3D acquisition was successful in 7 of 26 subjects (27%). Overall image contrast and perceived resolution were lower in the 3D images. Nonetheless, the 3D images had, on average, a moderate cardiac diagnostic quality (median [range]: 3 [1-4]). Standard clinical 2D acquisitions had a high cardiac diagnostic quality (median [range]: 4 [3, 4]). Cardiac measurements were not different between 2D and 3D images (all p > 0.16).

CONCLUSION

The presented free-breathing whole-heart fetal 3D radial cine MRI acquisition and reconstruction method enables retrospective visualization of all cardiac views while keeping examination times short. This proof-of-concept work produced images with diagnostic quality, while at the same time reducing the planning complexity to a single localizer.

Free-breathing simultaneous water-fat separation and T1 mapping of the whole liver (SWALI) with isotropic resolution using 3D golden-angle radial trajectory

Background

Conventional liver T1 mapping techniques are typically performed under breath-holding conditions; they have limited slice coverage and often rely on multiple acquisitions. Furthermore, liver fat affects the accuracy of T1 quantification. Therefore, we aim to propose a free-breathing technique for simultaneous water-fat separation and T1 mapping of the whole liver (SWALI) in a single scan.

Methods

The proposed SWALI sequence included an inversion recovery (IR) preparation pulse followed by a series of multiecho three-dimensional (3D) golden-angle radial acquisitions. For each echo time (TE), a series of images containing a mix of water and fat were reconstructed using a sliding window method. For each inversion time (TI), water and fat were separated, and then water and fat T1 estimation was conducted. The fat fraction (FF) was calculated based on the last TI image. The FF and water T1 quantification accuracy were compared with the gold standard sequences in the phantom. The in vivo feasibility was tested in 9 healthy volunteers, 2 patients with fatty liver, and 3 patients with hepatocellular carcinoma (HCC). The reproducibility was evaluated in the patients with fatty liver and in the healthy volunteers.

Results

The mean FF and the mean water T1 values obtained by the SWALI sequence showed good agreements with chemical shift-encoded magnetic resonance imaging (CSE-MRI; r=0.998; P<0.001) and fat-suppressed (FS) IR-spin echo (SE; r=0.997; P<0.001) in the phantom. For the patients with fatty liver and the healthy volunteers, the SWALI sequence showed no significant difference with CSE-MRI in FF quantification (P=0.53). In T1 quantification, comparable T1 values were obtained with the SWALI sequence and modified Look-Locker inversion recovery (MOLLI; P=0.10) in healthy volunteers, while the water T1 estimated by the SWALI sequence was significantly lower than the water-fat compound T1 estimated by MOLLI (P<0.001) in patients with fatty liver. In the reproducibility study, the intraclass correlation coefficients (ICCs) for the estimated FF and water T1 were 0.997 and 0.943, respectively. Water T1 of the patients with HCC calculated using the SWALI sequence showed a significant reduction after the contrast administration (P<0.001).

Conclusions

Free-breathing water-fat separation and T1 mapping of the whole liver with 2.5 mm isotropic spatial resolution were achieved simultaneously using the SWALI sequence in a 5-min scan.

4D lung MRI with high-isotropic-resolution using half-spoke (UTE) and full-spoke 3D radial acquisition and temporal compressed sensing reconstruction

Objective. To develop a respiratory motion-resolved four-dimensional (4D) magnetic resonance imaging (MRI) technique with high-isotropic-resolution (1.1 mm) using 3D radial sampling, camera-based respiratory motion sensing, and temporal compressed sensing reconstruction for lung cancer imaging.Approach. Free-breathing half- and full-spoke 3D golden-angle radial acquisitions were performed on eight healthy volunteers and eight patients with lung tumors of varying size. A back-and-forth k-space ordering between consecutive interleaves of the 3D radial acquisition was performed to minimize eddy current-related artifacts. Data were sorted into respiratory motion states using camera-based motion navigation and 4D images were reconstructed using temporal compressed sensing to reduce scan time. Normalized sharpness indices of the diaphragm, apparent signal-to-noise ratio (aSNR) and contrast-to-noise ratio (CNR) of the lung tumor (patients only), liver, and aortic arch were compared between half- and full-spoke 4D MRI images to evaluate the impact of respiratory motion and image contrast on 4D MRI image quality. Respiration-induced changes in lung volumes and center of mass shifts were compared between half- and full-spoke 4D MRI measurements. In addition, the motion measurements from 4D MRI and the same-day 4D CT were presented in one of the lung tumor patients.Main results. Half-spoke 4D MRI provides better visualization of the lung parenchyma, while full-spoke 4D MRI presents sharper diaphragm images and higher aSNR and CNR in the lung tumor, liver, and aortic arch. Lung volume changes and center of mass shifts measured by half- and full-spoke 4D MRI were not statistically different. For the patient with 4D MRI and same-day 4D CT, lung volume changes and center of mass shifts were generally comparable.Significance. This work demonstrates the feasibility of a motion-resolved 4D MRI technique with high-isotropic-resolution using 3D radial acquisition, camera-based respiratory motion sensing, and temporal compressed sensing reconstruction for treatment planning and motion monitoring in radiotherapy of lung cancer.

Correlation of MRI premature ventricular contraction activation pattern in bigeminy with electrophysiology study-confirmed site of origin

Although PVCs commonly lead to degraded cine cardiac MRI (CMR), patients with PVCs may have relatively sharp cine images of both normal and ectopic beats ("double beats") when the rhythm during CMR is ventricular bigeminy, and only one beat of the pair is detected for gating. MRI methods for directly imaging premature ventricular contractions (PVCs) are not yet widely available. Localization of PVC site of origin with images may be helpful in planning ablations. The contraction pattern of the PVCs in bigeminy provides a "natural experiment" for investigating the potential utility of PVC imaging for localization. The purpose of this study was to evaluate the correlation of the visually assessed site of the initial contraction of the ectopic beats with the site of origin found by electroanatomic mapping. Images from 7 of 86 consecutive patients who underwent CMR prior to PVC ablation were found to include clear cine images of bigeminy. The visually apparent site of origin of the ectopic contraction was determined by three experienced, blinded CMR readers and correlated with each other, and with PVC site of origin determined by 3D electroanatomic mapping during catheter ablation. Blinded ascertainment of visually apparent initial contraction pattern for PVC localization was within 2 wall segments of PVC origin by 3D electroanatomic mapping 76% of the time. Our data from patients with PVCs with clear images of the ectopic beats when in bigeminy provide proof-of-concept that CMR ectopic beat contraction patterns analysis may provide a novel method for localizing PVC origin prior to ablation procedures. Direct imaging of PVCs with use of newer cardiac imaging methods, even without the presence of bigeminy, may thus provide valuable data for procedural planning.

Guanidinium and amide CEST mapping of human brain by high spectral resolution CEST at 3 T

PURPOSE

To extract guanidinium (Guan) and amide CEST on the human brain at 3 T MRI with the high spectral resolution (HSR) CEST combined with the polynomial Lorentzian line-shape fitting (PLOF).

METHODS

Continuous wave (cw) turbo spin-echo (TSE) CEST was implemented to obtain the optimum saturation parameters. Both Guan and amide CEST peaks were extracted and quantified using the PLOF method. The NMR spectra on the egg white phantoms were acquired to reveal the fitting range and the contributions to the amide and GuanCEST. Two types of CEST approaches, including cw gradient- and spin-echo (cwGRASE) and steady state EPI (ssEPI), were implemented to acquire multi-slice HSR-CEST.

RESULTS

GuanCEST can be extracted with the PLOF method at 3 T, and the optimumB 1 = 0.6 μ T $$ {\mathrm{B}}_1=0.6\kern0.2em \upmu \mathrm{T} $$ was determined for GuanCEST in white matter (WM) and 1.0 μT in gray matter (GM). The optimum B1  = 0.8-1 μT was found for amideCEST. AmideCEST is lower in both WM and GM collected with ssEPI compared to those by cwGRASE (ssEPI = [1.27-1.63]%; cwGRASE = [2.19-2.25]%). The coefficients of variation (COV) of the amide and Guan CEST in both WM and GM for ssEPI (COV: 28.6-33.4%) are significantly higher than those of cwGRASE (COV: 8.6-18.8%). Completely different WM/GM contrasts for Guan and amide CEST were observed between ssEPI and cwGRASE. The amideCEST was found to have originated from the unstructured amide protons as suggested by the NMR spectrum of the unfolded proteins in egg white.

CONCLUSION

Guan and amide CEST mapping can be achieved by the HSR-CEST at 3 T combing with the PLOF method.

Prospective motion correction in kidney MRI using FID navigators

PURPOSE

Abdominal MRI scans may require breath-holding to prevent image quality degradation, which can be challenging for patients, especially children. In this study, we evaluate whether FID navigators can be used to measure and correct for motion prospectively, in real-time.

METHODS

FID navigators were inserted into a 3D radial sequence with stack-of-stars sampling. MRI experiments were conducted on 6 healthy volunteers. A calibration scan was first acquired to create a linear motion model that estimates the kidney displacement due to respiration from the FID navigator signal. This model was then applied to predict and prospectively correct for motion in real time during deep and continuous deep breathing scans. Resultant images acquired with the proposed technique were compared with those acquired without motion correction. Dice scores were calculated between inhale/exhale motion states. Furthermore, images acquired using the proposed technique were compared with images from extra-dimensional golden-angle radial sparse parallel, a retrospective motion state binning technique.

RESULTS

Images reconstructed for each motion state show that the kidneys' position could be accurately tracked and corrected with the proposed method. The mean of Dice scores computed between the motion states were improved from 0.93 to 0.96 using the proposed technique. Depiction of the kidneys was improved in the combined images of all motion states. Comparing results of the proposed technique and extra-dimensional golden-angle radial sparse parallel, high-quality images can be reconstructed from a fraction of spokes using the proposed method.

CONCLUSION

The proposed technique reduces blurriness and motion artifacts in kidney imaging by prospectively correcting their position both in-plane and through-slice.

Undersampling artifact reduction for free-breathing 3D stack-of-radial MRI based on a deep adversarial learning network

PURPOSE

Stack-of-radial MRI allows free-breathing abdominal scans, however, it requires relatively long acquisition time. Undersampling reduces scan time but can cause streaking artifacts and degrade image quality. This study developed deep learning networks with adversarial loss and evaluated the performance of reducing streaking artifacts and preserving perceptual image sharpness.

METHODS

A 3D generative adversarial network (GAN) was developed for reducing streaking artifacts in stack-of-radial abdominal scans. Training and validation datasets were self-gated to 5 respiratory states to reduce motion artifacts and to effectively augment the data. The network used a combination of three loss functions to constrain the anatomy and preserve image quality: adversarial loss, mean-squared-error loss and structural similarity index loss. The performance of the network was investigated for 3-5 times undersampled data from 2 institutions. The performance of the GAN for 5 times accelerated images was compared with a 3D U-Net and evaluated using quantitative NMSE, SSIM and region of interest (ROI) measurements as well as qualitative scores of radiologists.

RESULTS

The 3D GAN showed similar NMSE (0.0657 vs. 0.0559, p = 0.5217) and significantly higher SSIM (0.841 vs. 0.798, p < 0.0001) compared to U-Net. ROI analysis showed GAN removed streaks in both the background air and the tissue and was not significantly different from the reference mean and variations. Radiologists' scores showed GAN had a significant improvement of 1.6 point (p = 0.004) on a 4-point scale in streaking score while no significant difference in sharpness score compared to the input.

CONCLUSION

3D GAN removes streaking artifacts and preserves perceptual image details.

View-sharing for 4D magnetic resonance imaging with randomized projection-encoding enables improvements of respiratory motion imaging for treatment planning in abdominothoracic radiotherapy

Background and Purpose

The accuracy and precision of radiation therapy are dependent on the characterization of organ-at-risk and target motion. This work aims to demonstrate a 4D magnetic resonance imaging (MRI) method for improving spatial and temporal resolution in respiratory motion imaging for treatment planning in abdominothoracic radiotherapy.

Materials and Methods

The spatial and temporal resolution of phase-resolved respiratory imaging is improved by considering a novel sampling function based on quasi-random projection-encoding and peripheral k-space view-sharing. The respiratory signal is determined directly from k-space, obviating the need for an external surrogate marker. The average breathing curve is used to optimize spatial resolution and temporal blurring by limiting the extent of data sharing in the Fourier domain. Improvements in image quality are characterized by evaluating changes in signal-to-noise ratio (SNR), resolution, target detection, and level of artifact. The method is validated in simulations, in a dynamic phantom, and in-vivo imaging.

Results

Sharing of high-frequency k-space data, driven by the average breathing curve, improves spatial resolution and reduces artifacts. Although equal sharing of k-space data improves resolution and SNR in stationary features, phases with large temporal changes accumulate significant artifacts due to averaging of high frequency features. In the absence of view-sharing, no averaging and detection artifacts are observed while spatial resolution is degraded.

Conclusions

The use of a quasi-random sampling function, with view-sharing driven by the average breathing curve, provides a feasible method for self-navigated 4D-MRI at improved spatial resolution.

Respiratory Motion Management in Abdominal MRI: Radiology In Training

A 96-year-old woman had a suboptimal evaluation of liver observations at abdominal MRI due to significant respiratory motion. State-of-the-art strategies to minimize respiratory motion during clinical abdominal MRI are discussed.

Performance of free-breathing dynamic T1-weighted sequences in patients at risk of developing motion artifacts undergoing gadoxetic acid–enhanced liver MRI

OBJECTIVES

To evaluate the recall rate and performance of free-breathing T1W dynamic imaging in patients who underwent gadoxetic acid-enhanced liver MRI.

METHODS

We retrospectively reviewed patients who underwent free-breathing dynamic T1WI liver MRI using Cartesian (XD-VIBE) or self-gated radial (SG-GRASP) sequences at two institutions. Four radiologists independently reviewed the overall image quality, streak, and motion artifacts for precontrast, arterial, and portal venous phases on a 4-point scale. Hepatic observations were annotated and assessed according to LI-RADS v2018.

RESULTS

In total, 360 patients were included (XD-VIBE [n = 253], SG-GRASP [n = 107]). The overall image quality of free-breathing T1WI was 3.4 ± 0.4, 3.2 ± 0.4, and 3.5 ± 0.4 for precontrast, arterial, and portal venous phases, respectively. The actual recall rate was 0.6% (2/360). The SG-GRASP group showed fewer motion artifacts and more streak artifacts than the XD-VIBE group in all phases (p < 0.001 for all). The overall image quality was not significantly different between the two sequences in arterial (3.2 ± 0.4 in both, p = 0.607) and portal venous phases (3.5 ± 0.4 in XD-VIBE, 3.4 ± 0.4 in SG-GRASP, p = 0.214). Two sequences did not show significant differences in the lesion detection rate (figure of merit, FOM: 0.67 vs. 0.68, p = 0.876) or diagnostic performance for hepatocellular carcinoma (FOM: 0.55 vs. 0.62, p = 0.105).

CONCLUSIONS

Both XD-VIBE and SG-GRASP provided sufficient image quality for patients at risk of developing motion artifacts, without significant differences in image quality or the lesion detection rate between sequences.

KEY POINTS

• The overall image quality of free-breathing T1-weighted images using Cartesian or radial sequences was 3.4 ± 0.4, 3.2 ± 0.4, and 3.5 ± 0.4 for precontrast, arterial, and portal venous phases, respectively. • Only 0.3% (1/360) had undiagnostic exams and the actual recall rate was 0.6% (2/360) in patients who underwent free-breathing dynamic T1WI. • The overall lesion detection rate was 0.67 without a significant difference between Cartesian and radial sequences (figure of merit: 0.67 vs. 0.68, respectively, p = 0.876).

The future of MRI in radiation therapy: Challenges and opportunities for the MR community

Radiation therapy is a major component of cancer treatment pathways worldwide. The main aim of this treatment is to achieve tumor control through the delivery of ionizing radiation while preserving healthy tissues for minimal radiation toxicity. Because radiation therapy relies on accurate localization of the target and surrounding tissues, imaging plays a crucial role throughout the treatment chain. In the treatment planning phase, radiological images are essential for defining target volumes and organs-at-risk, as well as providing elemental composition (e.g., electron density) information for radiation dose calculations. At treatment, onboard imaging informs patient setup and could be used to guide radiation dose placement for sites affected by motion. Imaging is also an important tool for treatment response assessment and treatment plan adaptation. MRI, with its excellent soft tissue contrast and capacity to probe functional tissue properties, holds great untapped potential for transforming treatment paradigms in radiation therapy. The MR in Radiation Therapy ISMRM Study Group was established to provide a forum within the MR community to discuss the unmet needs and fuel opportunities for further advancement of MRI for radiation therapy applications. During the summer of 2021, the study group organized its first virtual workshop, attended by a diverse international group of clinicians, scientists, and clinical physicists, to explore our predictions for the future of MRI in radiation therapy for the next 25 years. This article reviews the main findings from the event and considers the opportunities and challenges of reaching our vision for the future in this expanding field.

Variational Manifold Learning From Incomplete Data: Application to Multislice Dynamic MRI

Current deep learning-based manifold learning algorithms such as the variational autoencoder (VAE) require fully sampled data to learn the probability density of real-world datasets. However, fully sampled data is often unavailable in a variety of problems, including the recovery of dynamic and high-resolution magnetic resonance imaging (MRI). We introduce a novel variational approach to learn a manifold from undersampled data. The VAE uses a decoder fed by latent vectors, drawn from a conditional density estimated from the fully sampled images using an encoder. Since fully sampled images are not available in our setting, we approximate the conditional density of the latent vectors by a parametric model whose parameters are estimated from the undersampled measurements using back-propagation. We use the framework for the joint alignment and recovery of multi-slice free breathing and ungated cardiac MRI data from highly undersampled measurements. Experimental results demonstrate the utility of the proposed scheme in dynamic imaging alignment and reconstructions.

Deep-learning synthesized pseudo-CT for MR high-resolution pediatric cranial bone imaging (MR-HiPCB)

PURPOSE

CT is routinely used to detect cranial abnormalities in pediatric patients with head trauma or craniosynostosis. This study aimed to develop a deep learning method to synthesize pseudo-CT (pCT) images for MR high-resolution pediatric cranial bone imaging to eliminating ionizing radiation from CT.

METHODS

3D golden-angle stack-of-stars MRI were obtained from 44 pediatric participants. Two patch-based residual UNets were trained using paired MR and CT patches randomly selected from the whole head (NetWH) or in the vicinity of bone, fractures/sutures, or air (NetBA) to synthesize pCT. A third residual UNet was trained to generate a binary brain mask using only MRI. The pCT images from NetWH (pCTNetWH ) in the brain area and NetBA (pCTNetBA ) in the nonbrain area were combined to generate pCTCom . A manual processing method using inverted MR images was also employed for comparison.

RESULTS

pCTCom (68.01 ± 14.83 HU) had significantly smaller mean absolute errors (MAEs) than pCTNetWH (82.58 ± 16.98 HU, P < 0.0001) and pCTNetBA (91.32 ± 17.2 HU, P < 0.0001) in the whole head. Within cranial bone, the MAE of pCTCom (227.92 ± 46.88 HU) was significantly lower than pCTNetWH (287.85 ± 59.46 HU, P < 0.0001) but similar to pCTNetBA (230.20 ± 46.17 HU). Dice similarity coefficient of the segmented bone was significantly higher in pCTCom (0.90 ± 0.02) than in pCTNetWH (0.86 ± 0.04, P < 0.0001), pCTNetBA (0.88 ± 0.03, P < 0.0001), and inverted MR (0.71 ± 0.09, P < 0.0001). Dice similarity coefficient from pCTCom demonstrated significantly reduced age dependence than inverted MRI. Furthermore, pCTCom provided excellent suture and fracture visibility comparable to CT.

CONCLUSION

MR high-resolution pediatric cranial bone imaging may facilitate the clinical translation of a radiation-free MR cranial bone imaging method for pediatric patients.

Pediatric magnetic resonance imaging: faster is better

Magnetic resonance imaging (MRI) has emerged as the preferred imaging modality for evaluating a wide range of pediatric medical conditions. Nevertheless, the long acquisition times associated with this technique can limit its widespread use in young children, resulting in motion-degraded or non-diagnostic studies. As a result, sedation or general anesthesia is often necessary to obtain diagnostic images, which has implications for the safety profile of MRI, the cost of the exam and the radiology department's clinical workflow. Over the last decade, several techniques have been developed to increase the speed of MRI, including parallel imaging, single-shot acquisition, controlled aliasing techniques, compressed sensing and artificial-intelligence-based reconstructions. These are advantageous because shorter examinations decrease the need for sedation and the severity of motion artifacts, increase scanner throughput, and improve system efficiency. In this review we discuss a framework for image acceleration in children that includes the synergistic use of state-of-the-art MRI hardware and optimized pulse sequences. The discussion is framed within the context of pediatric radiology and incorporates the authors' experience in deploying these techniques in routine clinical practice.

Simultaneous multi-parametric acquisition and reconstruction techniques in cardiac magnetic resonance imaging: Basic concepts and status of clinical development

Simultaneous multi-parametric acquisition and reconstruction techniques (SMART) are gaining attention for their potential to overcome some of cardiovascular magnetic resonance imaging's (CMR) clinical limitations. The major advantages of SMART lie within their ability to simultaneously capture multiple "features" such as cardiac motion, respiratory motion, T1/T2 relaxation. This review aims to summarize the overarching theory of SMART, describing key concepts that many of these techniques share to produce co-registered, high quality CMR images in less time and with less requirements for specialized personnel. Further, this review provides an overview of the recent developments in the field of SMART by describing how they work, the parameters they can acquire, their status of clinical testing and validation, and by providing examples for how their use can improve the current state of clinical CMR workflows. Many of the SMART are in early phases of development and testing, thus larger scale, controlled trials are needed to evaluate their use in clinical setting and with different cardiac pathologies.

Free-breathing motion-informed locally low-rank quantitative 3D myocardial perfusion imaging

PURPOSE

To propose respiratory motion-informed locally low-rank reconstruction (MI-LLR) for robust free-breathing single-bolus quantitative 3D myocardial perfusion CMR imaging. Simulation and in-vivo results are compared to locally low-rank (LLR) and compressed sensing reconstructions (CS) for reference.

METHODS

Data were acquired using a 3D Cartesian pseudo-spiral in-out k-t undersampling scheme (R = 10) and reconstructed using MI-LLR, which encompasses two stages. In the first stage, approximate displacement fields are derived from an initial LLR reconstruction to feed a motion-compensated reference system to a second reconstruction stage, which reduces the rank of the inverse problem. For comparison, data were also reconstructed with LLR and frame-by-frame CS using wavelets as sparsifying transform ( ℓ 1 $$ {\ell}_1 $$ -wavelet). Reconstruction accuracy relative to ground truth was assessed using synthetic data for realistic ranges of breathing motion, heart rates, and SNRs. In-vivo experiments were conducted in healthy subjects at rest and during adenosine stress. Myocardial blood flow (MBF) maps were derived using a Fermi model.

RESULTS

Improved uniformity of MBF maps with reduced local variations was achieved with MI-LLR. For rest and stress, intra-volunteer variation of absolute and relative MBF was lower in MI-LLR (±0.17 mL/g/min [26%] and ±1.07 mL/g/min [33%]) versus LLR (±0.19 mL/g/min [28%] and ±1.22 mL/g/min [36%]) and versus ℓ 1 $$ {\ell}_1 $$ -wavelet (±1.17 mL/g/min [113%] and ±6.87 mL/g/min [115%]). At rest, intra-subject MBF variation was reduced significantly with MI-LLR.

CONCLUSION

The combination of pseudo-spiral Cartesian undersampling and dual-stage MI-LLR reconstruction improves free-breathing quantitative 3D myocardial perfusion CMR imaging under rest and stress condition.

Dynamic Imaging Using Deep Bi-Linear Unsupervised Representation (DEBLUR)

Bilinear models such as low-rank and dictionary methods, which decompose dynamic data to spatial and temporal factor matrices are powerful and memory-efficient tools for the recovery of dynamic MRI data. Current bilinear methods rely on sparsity and energy compaction priors on the factor matrices to regularize the recovery. Motivated by deep image prior, we introduce a novel bilinear model, whose factor matrices are generated using convolutional neural networks (CNNs). The CNN parameters, and equivalently the factors, are learned from the undersampled data of the specific subject. Unlike current unrolled deep learning methods that require the storage of all the time frames in the dataset, the proposed approach only requires the storage of the factors or compressed representation; this approach allows the direct use of this scheme to large-scale dynamic applications, including free breathing cardiac MRI considered in this work. To reduce the run time and to improve performance, we initialize the CNN parameters using existing factor methods. We use sparsity regularization of the network parameters to minimize the overfitting of the network to measurement noise. Our experiments on free-breathing and ungated cardiac cine data acquired using a navigated golden-angle gradient-echo radial sequence show the ability of our method to provide reduced spatial blurring as compared to classical bilinear methods as well as a recent unsupervised deep-learning approach.

Non-contrast free-breathing whole-heart 3D cine cardiovascular magnetic resonance with a novel 3D radial leaf trajectory

PURPOSE

To develop and validate a non-contrast free-breathing whole-heart 3D cine steady-state free precession (SSFP) sequence with a novel 3D radial leaf trajectory.

METHODS

We used a respiratory navigator to trigger acquisition of 3D cine data at end-expiration to minimize respiratory motion in our 3D cine SSFP sequence. We developed a novel 3D radial leaf trajectory to reduce gradient jumps and associated eddy-current artifacts. We then reconstructed the 3D cine images with a resolution of 2.0mm³ using an iterative nonlinear optimization algorithm. Prospective validation was performed by comparing ventricular volumetric measurements from a conventional breath-hold 2D cine ventricular short-axis stack against the non-contrast free-breathing whole-heart 3D cine dataset in each patient (n = 13).

RESULTS

All 3D cine SSFP acquisitions were successful and mean scan time was 07:09 ± 01:31 min. End-diastolic ventricular volumes for left ventricle (LV) and right ventricle (RV) measured from the 3D datasets were smaller than those from 2D (LV: 159.99 ± 42.99 vs. 173.16 ± 47.42; RV: 180.35 ± 46.08 vs. 193.13 ± 49.38; p-value≤0.044; bias<8%), whereas ventricular end-systolic volumes were more comparable (LV: 79.12 ± 26.78 vs. 78.46 ± 25.35; RV: 97.18 ± 32.35 vs. 102.42 ± 32.53; p-value≥0.190, bias<6%). The 3D cine data had a lower subjective image quality score.

CONCLUSION

Our non-contrast free-breathing whole-heart 3D cine sequence with novel leaf trajectory was robust and yielded smaller ventricular end-diastolic volumes compared to 2D cine imaging. It has the potential to make examinations easier and more comfortable for patients.

Effects of CT/MRI Image Fusion on Cerebrovascular Protection, Postoperative Complications, and Limb Functional Recovery in Patients with Anterior and Middle Skull Base Tumors: Based on a Retrospective Cohort Study

Objective. To explore the effect of CT/MRI image fusion on cerebrovascular protection, postoperative complications and limb function recovery in patients with anterior and middle skull base tumors. Methods. During January 2019 to December 2021, a retrospective study was conducted on 50 patients who underwent anterior and middle skull base tumor resection in the same surgeon group in our hospital. According to the different surgical approaches, the patients were assigned to the fusion group (n = 29) and the routine group (n = 21). The routine group was operated with traditional operation, and the fusion group was operated with CT/MRI image fusion technique. The operation time, wound volume, resection rate and Karnofsky performance status (KPS), blood transfusion (vascular protection), tumor resection rate, and postoperative complications were compared. Results. The time of operation in the fusion group was shorter compared to the routine group, and the volume of the wound cavity in the fusion group was smaller compared to the routine group, and the difference was statistically significant ( $P<0.05$ ). Following treatment, the KPS score of the fusion group was remarkably higher compared to the routine group, and the difference was statistically significant ( $P<0.05$ ). The intraoperative blood transfusion rate in the fusion group was 17.24%, and the intraoperative blood transfusion rate in the routine group was 47.62%, and the difference was statistically significant ( $P<0.05$ ). The resection rate in the fusion group (89.66%) was remarkably higher compared to the routine group (61.90%, $P<0.05$ ). The incidence of postoperative complications in the fusion group (6.90%) was remarkably lower compared to the control group (33.33%, $P<0.05$ ). Conclusion. The application of CT/MRI image-fusion technology can effectively enhance the clinical symptoms of patients with tumors in the anterior and middle region of the skull base, which can promote the prognosis, shorten the operation time, reduce unnecessary cerebral neurovascular injuries, and retain more brain functions.

Interstitial fluid pressure as an emerging biomarker in solid tumors

The physical microenvironment of cancer is characterized by elevated stiffness and tissue pressure, the main component of which is the interstitial fluid pressure (IFP). Elevated IFP is an established negative predictive and prognostic parameter, directly affecting malignant behavior and therapy response. As such, measurement of the IFP would allow to develop strategies aimed at engineering the physical microenvironment of cancer. Traditionally, IFP measurement required the use of invasive methods. Recent progress in dynamic and functional imaging methods such as dynamic contrast enhanced (DCE) magnetic resonance imaging and elastography, combined with numerical models and simulation, allows to comprehensively assess the biomechanical landscape of cancer, and may help to overcome physical barriers to drug delivery and immune cell infiltration. Here, we provide a comprehensive overview of the origin of elevated IFP, and its role in the malignant phenotype. Also, we review the methods used to measure IFP using invasive and imaging based methods, and highlight remaining obstacles and potential areas of progress in order to implement IFP measurement in clinical practice.

Deformation-Compensated Learning for Image Reconstruction Without Ground Truth

Deep neural networks for medical image reconstruction are traditionally trained using high-quality ground-truth images as training targets. Recent work on Noise2Noise (N2N) has shown the potential of using multiple noisy measurements of the same object as an alternative to having a ground-truth. However, existing N2N-based methods are not suitable for learning from the measurements of an object undergoing nonrigid deformation. This paper addresses this issue by proposing the deformation-compensated learning (DeCoLearn) method for training deep reconstruction networks by compensating for object deformations. A key component of DeCoLearn is a deep registration module, which is jointly trained with the deep reconstruction network without any ground-truth supervision. We validate DeCoLearn on both simulated and experimentally collected magnetic resonance imaging (MRI) data and show that it significantly improves imaging quality.

Real time volumetric MRI for 3D motion tracking via geometry-informed deep learning

PURPOSE

To develop a geometry-informed deep learning framework for volumetric MRI with sub-second acquisition time in support of 3D motion tracking, which is highly desirable for improved radiotherapy precision but hindered by the long image acquisition time.

METHODS

A 2D-3D deep learning network with an explicitly defined geometry module that embeds geometric priors of the k-space encoding pattern was investigated, where a 2D generation network first augmented the sparsely sampled image dataset by generating new 2D representations of the underlying 3D subject. A geometry module then unfolded the 2D representations to the volumetric space. Finally, a 3D refinement network took the unfolded 3D data and outputted high-resolution volumetric images. Patient-specific models were trained for seven abdominal patients to reconstruct volumetric MRI from both orthogonal cine slices and sparse radial samples. To evaluate the robustness of the proposed method to longitudinal patient anatomy and position changes, we tested the trained model on separate datasets acquired more than one month later and evaluated 3D target motion tracking accuracy using the model-reconstructed images by deforming a reference MRI with gross tumor volume (GTV) contours to a 5-min time series of both ground truth and model-reconstructed volumetric images with a temporal resolution of 340 ms.

RESULTS

Across the seven patients evaluated, the median distances between model-predicted and ground truth GTV centroids in the superior-inferior direction were 0.4 ± 0.3 mm and 0.5 ± 0.4 mm for cine and radial acquisitions, respectively. The 95-percentile Hausdorff distances between model-predicted and ground truth GTV contours were 4.7 ± 1.1 mm and 3.2 ± 1.5 mm for cine and radial acquisitions, which are of the same scale as cross-plane image resolution.

CONCLUSION

Incorporating geometric priors into deep learning model enables volumetric imaging with high spatial and temporal resolution, which is particularly valuable for 3D motion tracking and has the potential of greatly improving MRI-guided radiotherapy precision.

Contrast-enhanced magnetic resonance imaging perfusion can predict microvascular invasion in patients with hepatocellular carcinoma (between 1 and 5 cm)

PURPOSE

To evaluate the role of perfusion parameters with MR imaging of the liver in diagnosing MVI in hepatocellular carcinoma (HCC) (between 1 and 5 cm).

MATERIALS AND METHODS

This retrospective study was approved by the institutional review board. In 80 patients with 43 MVI( +) and 42 MVI( -) HCC, whole-liver perfusion MR imaging with Cartesian k-space undersampling and compressed sensing reconstruction was performed after injection of 0.1 mmol/kg gadopentetate dimeglumine. Parameters derived from a dual-input single-compartment model of arterial flow (Fa), portal venous flow (Fp), total blood flow (Ft = Fa + Fp), arterial fraction (ART), distribution volume (DV), and mean transit time (MTT) were measured. The significant parameters between the two groups were included to correlate with the presence of MVI at simple and multiple regression analysis.

RESULTS

In MVI-positive HCC, Fp was significantly higher than in MVI-negative HCC, whereas the reverse was seen for ART (p < 0.001). Tumor size (β = 1.2, p = 0.004; odds ratio, 3.20; 95% CI 1.45, 7.06), Fp (β = 1.1, p = 0.004; odds ratio, 3.09; 95% CI 1.42, 6.72), and ART (β =  - 3.1, p = 0.001; odds ratio, 12.13; 95% CI 2.85, 51.49) were independent risk factors for MVI. The AUC value of the combination of all three metrics was 0.931 (95% CI 0.855, 0.975), with sensitivity of 97.6% and specificity of 76.2%.

CONCLUSION

The combination of Fp, ART, and tumor size demonstrated a higher diagnostic accuracy compared with each parameter used individually when evaluating MVI in HCC (between 1 and 5 cm).

Inflammatory Diseases of the Aorta: JACC Focus Seminar, Part 2

Inflammatory aortitis is most often caused by large vessel vasculitis (LVV), including giant cell arteritis, Takayasu's arteritis, immunoglobulin G4-related aortitis, and isolated aortitis. There are distinct differences in the clinical presentation, imaging findings, and natural history of LVV that are important for the cardiovascular provider to know. If possible, histopathologic specimens should be obtained to aide in accurate diagnosis and management of LVV. In most cases, corticosteroids are utilized in the acute phase, with the addition of steroid-sparing agents to achieve disease remission while sparing corticosteroid toxic effects. Endovascular and surgical procedures have been described with success but should be delayed until disease control is achieved whenever possible. Long-term management should include regular follow-up with rheumatology and surveillance imaging for sequelae of LVV.

MR-assisted PET respiratory motion correction using deep-learning based short-scan motion fields

PURPOSE

We evaluated the impact of PET respiratory motion correction (MoCo) in a phantom and patients. Moreover, we proposed and examined a PET MoCo approach using motion vector fields (MVFs) from a deep-learning reconstructed short MRI scan.

METHODS

The evaluation of PET MoCo was performed in a respiratory motion phantom study with varying lesion sizes and tumor to background ratios (TBRs) using a static scan as the ground truth. MRI-based MVFs were derived from either 2000 spokes (MoCo2000 , 5-6 min acquisition time) using a Fourier transform reconstruction or 200 spokes (MoCoP2P200 , 30-40 s acquisition time) using a deep-learning Phase2Phase (P2P) reconstruction and then incorporated into PET MoCo reconstruction. For six patients with hepatic lesions, the performance of PET MoCo was evaluated using quantitative metrics (SUVmax , SUVpeak , SUVmean , lesion volume) and a blinded radiological review on lesion conspicuity.

RESULTS

MRI-assisted PET MoCo methods provided similar results to static scans across most lesions with varying TBRs in the phantom. Both MoCo2000 and MoCoP2P200 PET images had significantly higher SUVmax , SUVpeak , SUVmean and significantly lower lesion volume than non-motion-corrected (non-MoCo) PET images. There was no statistical difference between MoCo2000 and MoCoP2P200 PET images for SUVmax , SUVpeak , SUVmean or lesion volume. Both radiological reviewers found that MoCo2000 and MoCoP2P200 PET significantly improved lesion conspicuity.

CONCLUSION

An MRI-assisted PET MoCo method was evaluated using the ground truth in a phantom study. In patients with hepatic lesions, PET MoCo images improved quantitative and qualitative metrics based on only 30-40 s of MRI motion modeling data.