Retrospective 3D motion correction using spherical navigator echoes

Deep-learning-based motion correction using multichannel MRI data: a study using simulated artifacts in the fastMRI dataset

Deep learning presents a generalizable solution for motion correction requiring no pulse sequence modifications or additional hardware, but previous networks have all been applied to coil-combined data. Multichannel MRI data provide a degree of spatial encoding that may be useful for motion correction. We hypothesize that incorporating deep learning for motion correction prior to coil combination will improve results. A conditional generative adversarial network was trained using simulated rigid motion artifacts in brain images acquired at multiple sites with multiple contrasts (not limited to healthy subjects). We compared the performance of deep-learning-based motion correction on individual channel images (single-channel model) with that performed after coil combination (channel-combined model). We also investigate simultaneous motion correction of all channel data from an image volume (multichannel model). The single-channel model significantly (p < 0.0001) improved mean absolute error, with an average 50.9% improvement compared with the uncorrected images. This was significantly (p < 0.0001) better than the 36.3% improvement achieved by the channel-combined model (conventional approach). The multichannel model provided no significant improvement in quantitative measures of image quality compared with the uncorrected images. Results were independent of the presence of pathology, and generalizable to a new center unseen during training. Performing motion correction on single-channel images prior to coil combination provided an improvement in performance compared with conventional deep-learning-based motion correction. Improved deep learning methods for retrospective correction of motion-affected MR images could reduce the need for repeat scans if applied in a clinical setting.

Prospective motion correction for brain MRI using spherical navigators

PURPOSE

To demonstrate for the first time the feasibility of performing prospective motion correction using spherical navigators (SNAVs).

METHODS

SNAVs were interleaved in a 3D FLASH sequence with an additional short baseline scan (6.8 s) for fast rotation estimation. Assessment of SNAV-based prospective motion correction was performed in six volunteers. Participant motion was guided using randomly generated stepwise prompts as well as prompts derived from real motion cases. Experiments were performed on a 3 T MRI scanner using a 32-channel head coil.

RESULTS

When optimized for real-time application, SNAV-based motion estimates were computed in 25.8 ± 1.3 ms. Phantom-based quantification of rotation and translation accuracy indicated mean absolute errors of 0.10 ± 0.09° and 0.25 ± 0.14 mm, respectively. Implementing SNAV-based motion estimates for prospective motion correction led to a clear improvement in image quality with minimal increase in scan time (<5%).

CONCLUSION

Optimization of SNAV processing for real-time application enables prospective motion correction with low latency and minimal scan time requirements.

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.

Deep Learning for Image Enhancement and Correction in Magnetic Resonance Imaging-State-of-the-Art and Challenges

Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast for clinical diagnoses and research which underpin many recent breakthroughs in medicine and biology. The post-processing of reconstructed MR images is often automated for incorporation into MRI scanners by the manufacturers and increasingly plays a critical role in the final image quality for clinical reporting and interpretation. For image enhancement and correction, the post-processing steps include noise reduction, image artefact correction, and image resolution improvements. With the recent success of deep learning in many research fields, there is great potential to apply deep learning for MR image enhancement, and recent publications have demonstrated promising results. Motivated by the rapidly growing literature in this area, in this review paper, we provide a comprehensive overview of deep learning-based methods for post-processing MR images to enhance image quality and correct image artefacts. We aim to provide researchers in MRI or other research fields, including computer vision and image processing, a literature survey of deep learning approaches for MR image enhancement. We discuss the current limitations of the application of artificial intelligence in MRI and highlight possible directions for future developments. In the era of deep learning, we highlight the importance of a critical appraisal of the explanatory information provided and the generalizability of deep learning algorithms in medical imaging.

Suppressing motion artefacts in MRI using an Inception-ResNet network with motion simulation augmentation

The suppression of motion artefacts from MR images is a challenging task. The purpose of this paper was to develop a standalone novel technique to suppress motion artefacts in MR images using a data-driven deep learning approach. A simulation framework was developed to generate motion-corrupted images from motion-free images using randomly generated motion profiles. An Inception-ResNet deep learning network architecture was used as the encoder and was augmented with a stack of convolution and upsampling layers to form an encoder-decoder network. The network was trained on simulated motion-corrupted images to identify and suppress those artefacts attributable to motion. The network was validated on unseen simulated datasets and real-world experimental motion-corrupted in vivo brain datasets. The trained network was able to suppress the motion artefacts in the reconstructed images, and the mean structural similarity (SSIM) increased from 0.9058 to 0.9338. The network was also able to suppress the motion artefacts from the real-world experimental dataset, and the mean SSIM increased from 0.8671 to 0.9145. The motion correction of the experimental datasets demonstrated the effectiveness of the motion simulation generation process. The proposed method successfully removed motion artefacts and outperformed an iterative entropy minimization method in terms of the SSIM index and normalized root mean squared error, which were 5-10% better for the proposed method. In conclusion, a novel, data-driven motion correction technique has been developed that can suppress motion artefacts from motion-corrupted MR images. The proposed technique is a standalone, post-processing method that does not interfere with data acquisition or reconstruction parameters, thus making it suitable for routine clinical practice.

Motion-corrected MRI with DISORDER: Distributed and incoherent sample orders for reconstruction deblurring using encoding redundancy

PURPOSE

To enable rigid body motion-tolerant parallel volumetric magnetic resonance imaging by retrospective head motion correction on a variety of spatiotemporal scales and imaging sequences.

THEORY AND METHODS

Tolerance against rigid body motion is based on distributed and incoherent sampling orders for boosting a joint retrospective motion estimation and reconstruction framework. Motion resilience stems from the encoding redundancy in the data, as generally provided by the coil array. Hence, it does not require external sensors, navigators or training data, so the methodology is readily applicable to sequences using 3D encodings.

RESULTS

Simulations are performed showing full inter-shot corrections for usual levels of in vivo motion, large number of shots, standard levels of noise and moderate acceleration factors. Feasibility of inter- and intra-shot corrections is shown under controlled motion in vivo. Practical efficacy is illustrated by high-quality results in most corrupted of 208 volumes from a series of 26 clinical pediatric examinations collected using standard protocols.

CONCLUSIONS

The proposed framework addresses the rigid motion problem in volumetric anatomical brain scans with sufficient encoding redundancy which has enabled reliable pediatric examinations without sedation.

3D rigid-body motion information from spherical Lissajous navigators at small k-space radii: A proof of concept

PURPOSE

To demonstrate, for the first time, the feasibility of obtaining low-latency 3D rigid-body motion information from spherical Lissajous navigators acquired at extremely small k-space radii, which has significant advantages compared with previous techniques.

THEORY AND METHODS

A spherical navigator concept is proposed in which the surface of a k-space sphere is sampled on a 3D Lissajous curve at a radius of 0.1/cm. The navigator only uses a single excitation and is acquired in less than 5 ms. Rotation estimations were calculated with an algorithm from computer vision that exploits a rotation theorem of the spherical harmonics transform and has minimal computational cost. The effectiveness of the concept was investigated with phantom and in vivo measurements on a commercial 3T MRI scanner.

RESULTS

Scanner-induced in vivo motion was measured with maximum absolute errors of 0.58° and 0.33 mm for rotations and translations, respectively. In the case of real, in vivo motion, the proposed method showed good agreement with motion information from FSL image registrations (mean/maximum deviations of 0.37°/1.24° and 0.44 mm/1.35 mm). In addition, phantom measurements indicated precisions of 0.014° and 0.013 mm. The computations for complete motion information took, on average, 24 ms on an ordinary laptop.

CONCLUSIONS

This work demonstrates a proof of concept for obtaining accurate motion information from small-radius spherical navigators. The method has the potential to overcome several previously reported problems and could help increase the utility of navigator-based motion correction both in research and in the clinic.

Conditional generative adversarial network for 3D rigid-body motion correction in MRI

PURPOSE

Subject motion in MRI remains an unsolved problem; motion during image acquisition may cause blurring and artifacts that severely degrade image quality. In this work, we approach motion correction as an image-to-image translation problem, which refers to the approach of training a deep neural network to predict an image in 1 domain from an image in another domain. Specifically, the purpose of this work was to develop and train a conditional generative adversarial network to predict artifact-free brain images from motion-corrupted data.

METHODS

An open source MRI data set comprising T₂ *-weighted, FLASH magnitude, and phase brain images for 53 patients was used to generate complex image data for motion simulation. To simulate rigid motion, rotations and translations were applied to the image data based on randomly generated motion profiles. A conditional generative adversarial network, comprising a generator and discriminator networks, was trained using the motion-corrupted and corresponding ground truth (original) images as training pairs.

RESULTS

The images predicted by the conditional generative adversarial network have improved image quality compared to the motion-corrupted images. The mean absolute error between the motion-corrupted and ground-truth images of the test set was 16.4% of the image mean value, whereas the mean absolute error between the conditional generative adversarial network-predicted and ground-truth images was 10.8% The network output also demonstrated improved peak SNR and structural similarity index for all test-set images.

CONCLUSION

The images predicted by the conditional generative adversarial network have quantitatively and qualitatively improved image quality compared to the motion-corrupted images.

Rigid-body motion correction in hybrid PET/MRI using spherical navigator echoes

Integrated positron emission tomography and magnetic resonance imaging (PET/MRI) is an imaging technology that provides complementary anatomical and functional information for medical diagnostics. Both PET and MRI are highly susceptible to motion artifacts due, in part, to long acquisition times. The simultaneous acquisition of the two modalities presents the opportunity to use MRI navigator techniques for motion correction of both PET and MRI data. For this task, we propose spherical navigator echoes (SNAVs)-3D k-space navigators that can accurately and rapidly measure rigid body motion in all six degrees of freedom. SNAVs were incorporated into turbo FLASH (tfl)-a product fast gradient echo sequence-to create the tfl-SNAV pulse sequence. Acquiring in vivo brain images from a healthy volunteer with both sequences first compared the tfl-SNAV and product tfl sequences. It was observed that incorporation of the SNAVs into the image sequence did not have any detrimental impact on the image quality. The SNAV motion correction technique was evaluated using an anthropomorphic brain phantom. Following a stationary reference image where the tfl-SNAV sequence was acquired along with simultaneous list-mode PET, three identical PET/MRI scans were performed where the phantom was moved several times throughout each acquisition. This motion-up to 11° and 14 mm-resulted in motion artifacts in both PET and MR images. Following SNAV motion correction of the MRI and PET list-mode data, artifact reduction was achieved for both the PET and MR images in all three motion trials. The corrected images have improved image quality and are quantitatively more similar to the ground truth reference images.

From simultaneous to synergistic MR-PET brain imaging: A review of hybrid MR-PET imaging methodologies

Simultaneous Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) scanning is a recent major development in biomedical imaging. The full integration of the PET detector ring and electronics within the MR system has been a technologically challenging design to develop but provides capacity for simultaneous imaging and the potential for new diagnostic and research capability. This article reviews state-of-the-art MR-PET hardware and software, and discusses future developments focusing on neuroimaging methodologies for MR-PET scanning. We particularly focus on the methodologies that lead to an improved synergy between MRI and PET, including optimal data acquisition, PET attenuation and motion correction, and joint image reconstruction and processing methods based on the underlying complementary and mutual information. We further review the current and potential future applications of simultaneous MR-PET in both systems neuroscience and clinical neuroimaging research. We demonstrate a simultaneous data acquisition protocol to highlight new applications of MR-PET neuroimaging research studies.

Cardiac 4D phase-contrast CMR at 9.4 T using self-gated ultra-short echo time (UTE) imaging

BACKGROUND

Time resolved 4D phase contrast (PC) cardiovascular magnetic resonance (CMR) in mice is challenging due to long scan times, small animal ECG-gating and the rapid blood flow and cardiac motion of small rodents. To overcome several of these technical challenges we implemented a retrospectively self-gated 4D PC radial ultra-short echo-time (UTE) acquisition scheme and assessed its performance in healthy mice by comparing the results with those obtained with an ECG-triggered 4D PC fast low angle shot (FLASH) sequence.

METHODS

Cardiac 4D PC CMR images were acquired at 9.4 T in healthy mice using the proposed self-gated radial center-out UTE acquisition scheme (TE/TR of 0.5 ms/3.1 ms) and a standard Cartesian 4D PC imaging sequence (TE/TR of 2.1 ms/5.0 ms) with a four-point Hadamard flow encoding scheme. To validate the proposed UTE flow imaging technique, experiments on a flow phantom with variable pump rates were performed.

RESULTS

The anatomical images and flow velocity maps of the proposed 4D PC UTE technique showed reduced artifacts and an improved SNR (left ventricular cavity (LV): 8.9 ± 2.5, myocardium (MC): 15.7 ± 1.9) compared to those obtained using a typical Cartesian FLASH sequence (LV: 5.6 ± 1.2, MC: 10.1 ± 1.4) that was used as a reference. With both sequences comparable flow velocities were obtained in the flow phantom as well as in the ascending aorta (UTE: 132.8 ± 18.3 cm/s, FLASH: 134.7 ± 13.4 cm/s) and pulmonary artery (UTE: 78.5 ± 15.4 cm/s, FLASH: 86.6 ± 6.2 cm/s) of the animals. Self-gated navigator signals derived from information of the oversampled k-space center were successfully extracted for all animals with a higher gating efficiency of time spent on acquiring gated data versus total measurement time (UTE: 61.8 ± 11.5%, FLASH: 48.5 ± 4.9%).

CONCLUSIONS

The proposed self-gated 4D PC UTE sequence enables robust and accurate flow velocity mapping of the mouse heart in vivo at high magnetic fields. At the same time SNR, gating efficiency, flow artifacts and image quality all improved compared to the images obtained using the well-established, ECG-triggered, 4D PC FLASH sequence.