Self-navigation with compressed sensing for 2D translational motion correction in free-breathing coronary MRI: a feasibility study

A review of deep learning-based reconstruction methods for accelerated MRI using spatiotemporal and multi-contrast redundancies

Accelerated magnetic resonance imaging (MRI) has played an essential role in reducing data acquisition time for MRI. Acceleration can be achieved by acquiring fewer data points in k-space, which results in various artifacts in the image domain. Conventional reconstruction methods have resolved the artifacts by utilizing multi-coil information, but with limited robustness. Recently, numerous deep learning-based reconstruction methods have been developed, enabling outstanding reconstruction performances with higher acceleration. Advances in hardware and developments of specialized network architectures have produced such achievements. Besides, MRI signals contain various redundant information including multi-coil redundancy, multi-contrast redundancy, and spatiotemporal redundancy. Utilization of the redundant information combined with deep learning approaches allow not only higher acceleration, but also well-preserved details in the reconstructed images. Consequently, this review paper introduces the basic concepts of deep learning and conventional accelerated MRI reconstruction methods, followed by review of recent deep learning-based reconstruction methods that exploit various redundancies. Lastly, the paper concludes by discussing the challenges, limitations, and potential directions of future developments.

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

PURPOSE

Three-dimensional UTE MRI has shown the ability to provide simultaneous structural and functional lung imaging, but it is limited by respiratory motion and relatively low lung parenchyma SNR. The purpose of this paper is to improve this imaging by using a respiratory phase-resolved reconstruction approach, named motion-compensated low-rank reconstruction (MoCoLoR), which directly incorporates motion compensation into a low-rank constrained reconstruction model for highly efficient use of the acquired data.

THEORY AND METHODS

The MoCoLoR reconstruction is formulated as an optimization problem that includes a low-rank constraint using estimated motion fields to reduce the rank, optimizing over both the motion fields and reconstructed images. The proposed reconstruction along with XD and motion state-weighted motion-compensation (MostMoCo) methods were applied to 18 lung MRI scans of pediatric and young adult patients. The data sets were acquired under free-breathing and without sedation with 3D radial UTE sequences in approximately 5 min. After reconstruction, they went through ventilation analyses. Performance across reconstruction regularization and motion-state parameters were also investigated.

RESULTS

The in vivo experiments results showed that MoCoLoR made efficient use of the data, provided higher apparent SNR compared with state-of-the-art XD reconstruction and MostMoCo reconstructions, and yielded high-quality respiratory phase-resolved images for ventilation mapping. The method was effective across the range of patients scanned.

CONCLUSION

The motion-compensated low-rank regularized reconstruction approach makes efficient use of acquired data and can improve simultaneous structural and functional lung imaging with 3D-UTE MRI. It enables the scanning of pediatric patients under free-breathing and without sedation.

Accelerated free-breathing 3D whole-heart magnetic resonance angiography with a radial phyllotaxis trajectory, compressed sensing, and curvelet transform

PURPOSE

To develop and validate an accelerated free-breathing 3D whole-heart magnetic resonance angiography (MRA) technique using a radial k-space trajectory with compressed sensing and curvelet transform.

METHOD

A 3D radial phyllotaxis trajectory was implemented to traverse the centerline of k-space immediately before the segmented whole-heart MRA data acquisition at each cardiac cycle. The k-space centerlines were used to correct the respiratory-induced heart motion in the acquired MRA data. The corrected MRA data were then reconstructed by a novel compressed sensing algorithm using curvelets as the sparsifying domain. The proposed 3D whole-heart MRA technique (radial CS curvelet) was then prospectively validated against compressed sensing with a conventional wavelet transform (radial CS wavelet) and a standard Cartesian acquisition in terms of scan time and border sharpness.

RESULTS

Fifteen patients (females 10, median age 34-year-old) underwent 3D whole-heart MRA imaging using a standard Cartesian trajectory and our proposed radial phyllotaxis trajectory. Scan time for radial phyllotaxis was significantly shorter than Cartesian (4.88 ± 0.86 min. vs. 6.84 ± 1.79 min., P-value = 0.004). Radial CS curvelet border sharpness was slightly lower than Cartesian and, for the majority of vessels, was significantly better than radial CS wavelet (P-value < 0.050).

CONCLUSION

The proposed technique of 3D whole-heart MRA acquisition with a radial CS curvelet has a shorter scan time and slightly lower vessel sharpness compared to the Cartesian acquisition with radial profile ordering, and has slightly better sharpness than radial CS wavelet. Future work on this technique includes additional clinical trials and extending this technique to 3D cine imaging.

Iterative motion-compensation reconstruction ultra-short TE (iMoCo UTE) for high-resolution free-breathing pulmonary MRI

PURPOSE

To develop a high-scanning efficiency, motion-corrected imaging strategy for free-breathing pulmonary MRI by combining an iterative motion-compensation reconstruction with a ultrashort echo time (UTE) acquisition called iMoCo UTE.

METHODS

An optimized golden-angle ordering radial UTE sequence was used to continuously acquire data for 5 minutes. All readouts were grouped to different respiratory motion states based on self-navigator signals, and then motion-resolved data was reconstructed by XD golden-angle radial sparse parallel reconstruction. One state from the motion-resolved images was selected as a reference, and then motion fields from the other states to the reference were derived via nonrigid registration. Finally, all motion-resolved data and motion fields were reconstructed by using an iterative motion-compensation (MoCo) reconstruction with a total generalized variation sparse constraint.

RESULTS

The iMoCo UTE strategy was evaluated in volunteers and nonsedated pediatric patient (4-6 years old) studies. Images reconstructed with iMoCo UTE provided sharper anatomical lung structures and higher apparent SNR and contrast-to-noise ratio compared to using other motion-correction strategies, such as soft-gating, motion-resolved reconstruction, and nonrigid MoCo. iMoCo UTE also showed promising results in an infant study.

CONCLUSION

The proposed iMoCo UTE combines self-navigation, motion modeling, and a compressed sensing reconstruction to increase scan efficiency and SNR and to reduce respiratory motion in lung MRI. This proposed strategy shows improvements in free-breathing lung MRI scans, especially in very challenging application situations such as pediatric MRI studies.

Optimized respiratory-resolved motion-compensated 3D Cartesian coronary MR angiography

Purpose

To develop a robust and efficient reconstruction framework that provides high‐quality motion‐compensated respiratory‐resolved images from free‐breathing 3D whole‐heart Cartesian coronary magnetic resonance angiography (CMRA) acquisitions.

Methods

Recently, XD‐GRASP (eXtra‐Dimensional Golden‐angle RAdial Sparse Parallel MRI) was proposed to achieve 100% scan efficiency and provide respiratory‐resolved 3D radial CMRA images by exploiting sparsity in the respiratory dimension. Here, a reconstruction framework for Cartesian CMRA imaging is proposed, which provides respiratory‐resolved motion‐compensated images by incorporating 2D beat‐to‐beat translational motion information to increase sparsity in the respiratory dimension. The motion information is extracted from interleaved image navigators and is also used to compensate for 2D translational motion within each respiratory phase. The proposed Optimized Respiratory‐resolved Cartesian Coronary MR Angiography (XD‐ORCCA) method was tested on 10 healthy subjects and 2 patients with cardiovascular disease, and compared against XD‐GRASP.

Results

The proposed XD‐ORCCA provides high‐quality respiratory‐resolved images, allowing clear visualization of the right and left coronary arteries, even for irregular breathing patterns. Compared with XD‐GRASP, the proposed method improves the visibility and sharpness of both coronaries. Significant differences (p < .05) in visible vessel length and proximal vessel sharpness were found between the 2 methods. The XD‐GRASP method provides good‐quality images in the absence of intraphase motion. However, motion blurring is observed in XD‐GRASP images for respiratory phases with larger motion amplitudes and subjects with irregular breathing patterns.

Conclusion

A robust respiratory‐resolved motion‐compensated framework for Cartesian CMRA has been proposed and tested in healthy subjects and patients. The proposed XD‐ORCCA provides high‐quality images for all respiratory phases, independently of the regularity of the breathing pattern.

Improved respiratory self-navigation for 3D radial acquisitions through the use of a pencil-beam 2D-T2 -prep for free-breathing, whole-heart coronary MRA

PURPOSE

In respiratory self-navigation (SN), signal from static structures, such as the chest wall, may complicate motion detection or introduce post-correction artefacts. Suppressing signal from superfluous tissues may therefore improve image quality. We thus test the hypothesis that SN whole-heart coronary magnetic resonance angiography (MRA) will benefit from an outer-volume suppressing 2D-T2 -Prep and present both phantom and in vivo results.

METHODS

A 2D-T2 -Prep and a conventional T2 -Prep were used prior to a free-breathing 3D-radial SN sequence. Both techniques were compared by imaging a home-built moving cardiac phantom and by performing coronary MRA in nine healthy volunteers. Reconstructions were performed using both a reference-based and a reference-independent approach to motion tracking, along with several coil combinations. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were compared, along with vessel sharpness (VS).

RESULTS

In phantoms, using the 2D-T2 -Prep increased SNR by 16% to 53% and mean VS by 8%; improved motion tracking precision was also achieved. In volunteers, SNR increased by an average of 29% to 33% in the blood pool and by 15% to 25% in the myocardium, depending on the choice of reconstruction coils and algorithm, and VS increased by 34%.

CONCLUSION

A 2D-T2 -Prep significantly improves image quality in both phantoms and volunteers when performing SN coronary MRA. Magn Reson Med 79:1293-1303, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Advances in PET/MR instrumentation and image reconstruction

The combination of positron emission tomography (PET) and MRI has attracted the attention of researchers in the past approximately 20 years in small-animal imaging and more recently in clinical research. The combination of PET/MRI allows researchers to explore clinical and research questions in a wide number of fields, some of which are briefly mentioned here. An important number of groups have developed different concepts to tackle the problems that PET instrumentation poses to the exposition of electromagnetic fields. We have described most of these research developments in preclinical and clinical experiments, including the few commercial scanners available. From the software perspective, an important number of algorithms have been developed to address the attenuation correction issue and to exploit the possibility that MRI provides for motion correction and quantitative image reconstruction, especially parametric modelling of radiopharmaceutical kinetics. In this work, we give an overview of some exemplar applications of simultaneous PET/MRI, together with technological hardware and software developments.

5D whole-heart sparse MRI

PURPOSE

A 5D whole-heart sparse imaging framework is proposed for simultaneous assessment of myocardial function and high-resolution cardiac and respiratory motion-resolved whole-heart anatomy in a single continuous noncontrast MR scan.

METHODS

A non-electrocardiograph (ECG)-triggered 3D golden-angle radial balanced steady-state free precession sequence was used for data acquisition. The acquired 3D k-space data were sorted into a 5D dataset containing separated cardiac and respiratory dimensions using a self-extracted respiratory motion signal and a recorded ECG signal. Images were then reconstructed using XD-GRASP, a multidimensional compressed sensing technique exploiting correlations/sparsity along cardiac and respiratory dimensions. 5D whole-heart imaging was compared with respiratory motion-corrected 3D and 4D whole-heart imaging in nine volunteers for evaluation of the myocardium, great vessels, and coronary arteries. It was also compared with breath-held, ECG-gated 2D cardiac cine imaging for validation of cardiac function quantification.

RESULTS

5D whole-heart images received systematic higher quality scores in the myocardium, great vessels and coronary arteries. Quantitative coronary sharpness and length were always better for the 5D images. Good agreement was obtained for quantification of cardiac function compared with 2D cine imaging.

CONCLUSION

5D whole-heart sparse imaging represents a robust and promising framework for simplified comprehensive cardiac MRI without the need for breath-hold and motion correction. Magn Reson Med 79:826-838, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Nonrigid Motion Correction With 3D Image-Based Navigators for Coronary MR Angiography

PURPOSE

To develop a retrospective nonrigid motion-correction method based on 3D image-based navigators (iNAVs) for free-breathing whole-heart coronary magnetic resonance angiography (MRA).

METHODS

The proposed method detects global rigid-body motion and localized nonrigid motion from 3D iNAVs and compensates them with an autofocusing algorithm. To model the global motion, 3D rotation and translation are estimated from the 3D iNAVs. Two sets of localized nonrigid motions are obtained from deformation fields between 3D iNAVs and reconstructed binned images, respectively. A bank of motion-corrected images is generated and the final image is assembled pixel-by-pixel by selecting the best focused pixel from this bank. In vivo studies with six healthy volunteers were conducted to compare the performance of the proposed method with 3D translational motion correction and no correction.

RESULTS

In vivo studies showed that compared to no correction, 3D translational motion correction and the proposed method increased the vessel sharpness by 13% ± 13% and 19% ± 16%, respectively. Out of 90 vessel segments, 75 segments showed improvement with the proposed method compared to 3D translational correction.

CONCLUSION

We have developed a nonrigid motion-correction method based on 3D iNAVs and an autofocusing algorithm that improves the vessel sharpness of free-breathing whole-heart coronary MRA. Magn Reson Med 77:1884-1893, 2017. © 2016 International Society for Magnetic Resonance in Medicine.

Four-dimensional respiratory motion-resolved whole heart coronary MR angiography

PURPOSE

Free-breathing whole-heart coronary MR angiography (MRA) commonly uses navigators to gate respiratory motion, resulting in lengthy and unpredictable acquisition times. Conversely, self-navigation has 100% scan efficiency, but requires motion correction over a broad range of respiratory displacements, which may introduce image artifacts. We propose replacing navigators and self-navigation with a respiratory motion-resolved reconstruction approach.

METHODS

Using a respiratory signal extracted directly from the imaging data, individual signal-readouts are binned according to their respiratory states. The resultant series of undersampled images are reconstructed using an extradimensional golden-angle radial sparse parallel imaging (XD-GRASP) algorithm, which exploits sparsity along the respiratory dimension. Whole-heart coronary MRA was performed in 11 volunteers and four patients with the proposed methodology. Image quality was compared with that obtained with one-dimensional respiratory self-navigation.

RESULTS

Respiratory-resolved reconstruction effectively suppressed respiratory motion artifacts. The quality score for XD-GRASP reconstructions was greater than or equal to self-navigation in 80/88 coronary segments, reaching diagnostic quality in 61/88 segments versus 41/88. Coronary sharpness and length were always superior for the respiratory-resolved datasets, reaching statistical significance (P < 0.05) in most cases.

CONCLUSION

XD-GRASP represents an attractive alternative for handling respiratory motion in free-breathing whole heart MRI and provides an effective alternative to self-navigation. Magn Reson Med 77:1473-1484, 2017. © 2016 International Society for Magnetic Resonance in Medicine.

4D respiratory motion-compensated image reconstruction of free-breathing radial MR data with very high undersampling

PURPOSE

To develop four-dimensional (4D) respiratory time-resolved MRI based on free-breathing acquisition of radial MR data with very high undersampling.

METHODS

We propose the 4D joint motion-compensated high-dimensional total variation (4D joint MoCo-HDTV) algorithm, which alternates between motion-compensated image reconstruction and artifact-robust motion estimation at multiple resolution levels. The algorithm is applied to radial MR data of the thorax and upper abdomen of 12 free-breathing subjects with acquisition times between 37 and 41 s and undersampling factors of 16.8. Resulting images are compared with compressed sensing-based 4D motion-adaptive spatio-temporal regularization (MASTeR) and 4D high-dimensional total variation (HDTV) reconstructions.

RESULTS

For all subjects, 4D joint MoCo-HDTV achieves higher similarity in terms of normalized mutual information and cross-correlation than 4D MASTeR and 4D HDTV when compared with reference 4D gated gridding reconstructions with 8.4 ± 1.1 times longer acquisition times. In a qualitative assessment of artifact level and image sharpness by two radiologists, 4D joint MoCo-HDTV reveals higher scores (P < 0.05) than 4D HDTV and 4D MASTeR at the same undersampling factor and the reference 4D gated gridding reconstructions, respectively.

CONCLUSIONS

4D joint MoCo-HDTV enables time-resolved image reconstruction of free-breathing radial MR data with undersampling factors of 16.8 while achieving low-streak artifact levels and high image sharpness. Magn Reson Med 77:1170-1183, 2017. © 2016 International Society for Magnetic Resonance in Medicine.

Is there an optimal respiratory reference position for self-navigated whole-heart coronary MR angiography?

PURPOSE

To test the direct influence of the reference respiratory position on image quality for self-navigated whole-heart coronary MRI.

METHODS

Self-navigated whole-heart coronary MRI was performed in 11 healthy adult subjects. Respiratory motion was compensated for by using three different respiratory reference positions of the heart: end-inspiratory, end-expiratory, and the mean of the entire respiratory excursion. All datasets were reconstructed without motion compensation for comparison. Image quality was assessed in all reconstructions using signal-to-noise ratio (SNR) and contrst-to-noise ratio (CNR) measurements, as well as percentage vessel sharpness and visible length of the coronary arteries.

RESULTS

While SNR and CNR remained close to constant in all reconstructions, a clear and significant improvement in vessel sharpness was identified in all motion corrected datasets with respect to their uncorrected counterpart (e.g., percentage sharpness of the proximal right coronary artery (RCA): 61.6 ± 8.2% for end-inspiration, 64.1 ± 10.7% for end-expiration, and 63.3 ± 7.0% for the mean respiratory position versus 55.0 ± 10.4 for the uncorrected datasets; P < 0.05). Among all motion corrected reconstructions, the use of an end-expiratory reference position most consistently provided the highest image quality. In particular, some of the improvements in vessel sharpness and length measured for end-expiration were statistically significant with respect to the reconstructions performed at end-inspiration (e.g., percentage sharpness of the proximal left anterior descending coronary: 58.2 ± 7.4% versus 55.8 ± 8.4%; P < 0.05; and visible length of the RCA: 125.7 ± 25.9 mm versus 114.4 ± 27.4 mm; P < 0.05).

CONCLUSION

The use of end-expiration as a reference position for respiratory motion correction in free-breathing self-navigated whole heart coronary MRA significantly improves image quality. J