Purpose
To enhance the visibility of nigrosome 1 in substantia nigra, which has recently been suggested as an imaging biomarker for Parkinson's disease (PD) at 3T magnetic resonance imaging (MRI).
...Materials and Methods
The substantia nigra structure was visualized at 3T MRI using multiecho susceptibility map‐weighted imaging (SMWI) in 15 healthy volunteers and 6 patients with Parkinson's disease (PD). The visibility of nigrosome 1 was further enhanced by acquiring data in an oblique‐coronal imaging plane at a high spatial resolution (0.5 × 0.5 × 1.0 mm3). To compare the visibility, the contrast‐to‐noise ratios (CNR) of the nigrosome 1 structure relative to the neighboring substantia nigra structure were evaluated in the SMWI and other conventional susceptibility contrast images (magnitude, frequency, quantitative susceptibility map QSM and susceptibility‐weighted image).
Results
In healthy volunteers, the CNRs of the nigrosome 1 structure were 1.04 ± 0.38, 0.84 ± 0.32, 1.04 ± 0.40, 0.86 ± 0.41, and 1.45 ± 0.48 for magnitude, frequency, quantitative susceptibility map, susceptibility‐weighted image, and SMWI, respectively. Compared to conventional susceptibility contrast images, the SMWI method significantly improved the CNR of nigrosome 1 (P = 0.014 for magnitude, P = 0.030 for QSM, and P < 0.001 for frequency and SWI, respectively). The magnetic susceptibility difference between nigrosome 1 and neighboring substantia nigra structures was 0.037 ± 0.016 ppm (measured in QSM, P < 0.001) in healthy volunteers. In the PD patients, the visibility of the nigrosome 1 structures was reduced.
Conclusion
The SMWI method enhances the visibility of nigrosome 1 structures at 3T MRI when compared to conventional susceptibility contrast images.
Level of Evidence: 3
Technical Efficacy: Stage 2
J. MAGN. RESON. IMAGING 2017;46:528–536
Background
FLAIR (fluid attenuated inversion recovery) imaging via synthetic MRI methods leads to artifacts in the brain, which can cause diagnostic limitations. The main sources of the artifacts are ...attributed to the partial volume effect and flow, which are difficult to correct by analytical modeling. In this study, a deep learning (DL)‐based synthetic FLAIR method was developed, which does not require analytical modeling of the signal.
Purpose
To correct artifacts in synthetic FLAIR using a DL method.
Study Type
Retrospective.
Subjects
A total of 80 subjects with clinical indications (60.6 ± 16.7 years, 38 males, 42 females) were divided into three groups: a training set (56 subjects, 62.1 ± 14.8 years, 25 males, 31 females), a validation set (1 subject, 62 years, male), and the testing set (23 subjects, 57.3 ± 20.4 years, 13 males, 10 females).
Field Strength/Sequence
3 T MRI using a multiple‐dynamic multiple‐echo acquisition (MDME) sequence for synthetic MRI and a conventional FLAIR sequence.
Assessment
Normalized root mean square (NRMSE) and structural similarity (SSIM) were computed for uncorrected synthetic FLAIR and DL‐corrected FLAIR. In addition, three neuroradiologists scored the three FLAIR datasets blindly, evaluating image quality and artifacts for sulci/periventricular and intraventricular/cistern space regions.
Statistical Tests
Pairwise Student's t‐tests and a Wilcoxon test were performed.
Results
For quantitative assessment, NRMSE improved from 4.2% to 2.9% (P < 0.0001) and SSIM improved from 0.85 to 0.93 (P < 0.0001). Additionally, NRMSE values significantly improved from 1.58% to 1.26% (P < 0.001), 3.1% to 1.5% (P < 0.0001), and 2.7% to 1.4% (P < 0.0001) in white matter, gray matter, and cerebral spinal fluid (CSF) regions, respectively, when using DL‐corrected FLAIR. For qualitative assessment, DL correction achieved improved overall quality, fewer artifacts in sulci and periventricular regions, and in intraventricular and cistern space regions.
Data Conclusion
The DL approach provides a promising method to correct artifacts in synthetic FLAIR.
Level of Evidence: 4
Technical Efficacy: Stage 1
J. Magn. Reson. Imaging 2019;50:1413–1423.
To compare the
relaxation times acquired with synthetic MRI to those of multi-echo spin-echo sequences and to evaluate the usefulness of synthetic MRI in the clinical setting.
From January 2017 to ...May 2017, we included 51 patients with newly diagnosed breast cancer, who underwent additional synthetic MRI and multiecho spin echo (MESE)
mapping sequences. Synthetic MRI technique uses a multiecho and multidelay acquisition method for the simultaneous quantification of physical properties such as
and
relaxation times and proton density image map. A radiologist with 9 years of experience in breast imaging drew region of interests manually along the tumor margins on two consecutive axial sections including the center of tumor mass and in the fat tissue of contralateral breast on both synthetic
map and MESE
map images.
The mean
relaxation time of the cancer was 84.75 ms (± 15.54) by synthetic MRI and 90.35 ms (± 19.22) by MESE
mapping. The mean
relaxation time of the fat was 129.22 ms (± 9.53) and 102.11 ms (± 13.9), respectively. Bland-Altman analysis showed mean difference of 8.4 ms for the breast cancer and a larger mean difference of 27.8 ms for the fat tissue. Spearman's correlation test showed that there was significant positive correlation between synthetic MRI and MESE sequences for the cancer (
= 0.713,
< 0.001) and for the fat (
= 0.551,
< 0.001). The positive estrogen receptor and low histologic grade were associated with little differences between two methods (
= 0.02 and = 0.043, respectively).
relaxation times of breast cancer acquired with synthetic MRI showed positive correlation with those of MESE
mapping. Synthetic MRI could be useful for the evaluation of tissue characteristics by simultaneous acquisition of several quantitative physical properties.
Synthetic MRI is useful for the evaluation of
relaxation times of the breast cancers.
Gradient-echo MRI of resonance-frequency shift and T2* values exhibit unique tissue contrast and offer relevant physiological information. However, acquiring 3D-phase images and T2* maps with the ...standard spoiled gradient echo (SPGR) sequence is lengthy for routine imaging at high-spatial resolution and whole-brain coverage. In addition, with the standard SPGR sequence, optimal signal-to-noise ratio (SNR) cannot be achieved for every tissue type given their distributed resonance frequency and T2* value. To address these two issues, a SNR optimized multi-echo sequence with a stack-of-spiral acquisition is proposed and implemented for achieving fast and simultaneous acquisition of image phase and T2* maps. The analytical behavior of the phase SNR is derived as a function of resonance frequency, T2* and echo time. This relationship is utilized to achieve tissue optimized SNR by combining phase images with different echo times. Simulations and in vivo experiments were designed to verify the theoretical predictions. Using the multi-echo spiral acquisition, whole-brain coverage with 1mm isotropic resolution can be achieved within 2.5min, shortening the scan time by a factor of 8. The resulting multi-echo phase map shows similar SNR to that of the standard SPGR. The acquisition can be further accelerated with non-Cartesian parallel imaging. The technique can be readily extended to other multi-shot readout trajectories besides spiral. It may provide a practical acquisition strategy for high resolution and simultaneous 3D mapping of magnetic susceptibility and T2*.
► A multi-echo spiral acquisition is implemented achieving fast acquisition of image phase and T2* maps. ► The analytical behavior of phase SNR is derived and verified using simulation and experimental data. ► Scan time of whole-brain coverage was shorten by a factor of 8 compared to standard SPGR.
Purpose
Synthetic magnetic resonance imaging (MRI) requires the acquisition of multicontrast images to estimate quantitative parameter maps, such as T1, T2, and proton density (PD). The study aims to ...develop a multicontrast reconstruction method based on joint parallel imaging (JPI) and joint deep learning (JDL) to enable further acceleration of synthetic MRI.
Methods
The JPI and JDL methods are extended and combined to improve reconstruction for better‐quality, synthesized images. JPI is performed as a first step to estimate the missing k‐space lines, and JDL is then performed to correct and refine the previous estimate with a trained neural network. For the JDL architecture, the original variable splitting network (VS‐Net) is modified and extended to form a joint variable splitting network (JVS‐Net) to apply to multicontrast reconstructions. The proposed method is designed and tested for multidynamic multiecho (MDME) images with Cartesian uniform under‐sampling using acceleration factors between 4 and 8.
Results
It is demonstrated that the normalized root‐mean‐square error (nRMSE) is lower and the structural similarity index measure (SSIM) values are higher with the proposed method compared to both the JPI and JDL methods individually. The method also demonstrates the potential to produce a set of synthesized contrast‐weighted images that closely resemble those from the fully sampled acquisition without erroneous artifacts.
Conclusion
Combining JPI and JDL enables the reconstruction of highly accelerated synthetic MRIs.
Magnetic Resonance Imaging (MRI) is sensitive to motion caused by patient movement due to the relatively long data acquisition time. This could cause severe degradation of image quality and therefore ...affect the overall diagnosis. In this paper, we develop an efficient retrospective 2D deep learning method called stacked U-Nets with self-assisted priors to address the problem of rigid motion artifacts in 3D brain MRI. The proposed work exploits the usage of additional knowledge priors from the corrupted images themselves without the need for additional contrast data. The proposed network learns the missed structural details through sharing auxiliary information from the contiguous slices of the same distorted subject. We further design a refinement stacked U-Nets that facilitates preserving the spatial image details and improves the pixel-to-pixel dependency. To perform network training, simulation of MRI motion artifacts is inevitable. The proposed network is optimized by minimizing the loss of structural similarity (SSIM) using the synthesized motion-corrupted images from 83 real motion-free subjects. We present an intensive analysis using various types of image priors: the proposed self-assisted priors and priors from other image contrast of the same subject. The experimental analysis proves the effectiveness and feasibility of our self-assisted priors since it does not require any further data scans. The overall image quality of the motion-corrected images via the proposed motion correction network significantly improves SSIM from 71.66% to 95.03% and declines the mean square error from 99.25 to 29.76. These results indicate the high similarity of the brain's anatomical structure in the corrected images compared to the motion-free data. The motion-corrected results of both the simulated and real motion data showed the potential of the proposed motion correction network to be feasible and applicable in clinical practices.
Display omitted
Patient movement during Magnetic Resonance Imaging (MRI) scan can cause severe degradation of image quality. In Susceptibility Weighted Imaging (SWI), several echoes are typically measured during a ...single repetition period, where the earliest echoes show less contrast between various tissues, while the later echoes are more susceptible to artifacts and signal dropout. In this paper, we propose a knowledge interaction paradigm that jointly learns feature details from multiple distorted echoes by sharing their knowledge with unified training parameters, thereby simultaneously reducing motion artifacts of all echoes. This is accomplished by developing a new scheme that boosts a Single Encoder with Multiple Decoders (SEMD), which assures that the generated features not only get fused but also learned together. We called the proposed method Knowledge Interaction Learning between Multi-Echo data (KIL-ME-based SEMD). The proposed KIL-ME-based SEMD allows to share information and gain an understanding of the correlations between the multiple echoes. The main purpose of this work is to correct the motion artifacts and maintain image quality and structure details of all motion-corrupted echoes towards generating high-resolution susceptibility enhanced contrast images, i.e., SWI, using a weighted average of multi-echo motion-corrected acquisitions. We also compare various potential strategies that might be used to address the problem of reducing artifacts in multi-echoes data. The experimental results demonstrate the feasibility and effectiveness of the proposed method, reducing the severity of motion artifacts and improving the overall clinical image quality of all echoes with their associated SWI maps. Significant improvement of image quality is observed using both motion-simulated test data and actual volunteer data with various motion severity strengths. Eventually, by enhancing the overall image quality, the proposed network can increase the effectiveness of the physicians' capability to evaluate and correctly diagnose brain MR images.
Display omitted
•We propose a knowledge interaction learning that learns representations of multi-echo MRI to reduce the motion artifacts.•This paper investigates how to take the benefit of learning multiple echoes simultaneously.•The proposed method shares the knowledge between corrupted echoes using a single encoder with unified training parameters.•The experimental analysis proves the feasibility of our knowledge interaction learning method.•The proposed network can increase the effectiveness of the physicians' capability to correctly diagnose brain MR images.
Background
Quantitative susceptibility mapping (QSM) is emerging as a technique that quantifies the paramagnetic nonheme iron in brain tissue. Brain iron quantification during early development ...provides insights into the underlying mechanism of brain maturation.
Purpose
To quantify the spatiotemporal variations of brain iron‐related magnetic susceptibility in deep gray matter nuclei during early development by using QSM.
Study Type
Retrospective.
Subjects
Eighty‐seven infants and children aged 1 month to 6 years.
Field Strength/Sequence
Enhanced T2*‐weighted angiography using a 3D gradient‐echo sequence at 3.0T.
Assessment
QSM was calculated by modified sophisticated harmonic artifact reduction for phase data and sparse linear equations and sparse least squares‐based algorithm. Means of susceptibility in deep gray matter nuclei (caudate nucleus, putamen, globus pallidus, thalamus) relative to that in splenium of corpus callosum were measured.
Statistical Tests
Relationships of mean susceptibility with age and referenced iron concentration were tested by Pearson correlation. Differences of mean susceptibility between the selected nuclei in each age group were compared by one‐way analysis of variance (ANOVA) and Fisher's Linear Significant Difference (LSD) test.
Results
Positive correlations of susceptibility with both referenced iron concentration and age were found (P < 0.0001); particularly, globus pallidus showed the highest correlation with age (correlation coefficient, 0.882; slope, 1.203; P < 0.001) and greatest susceptibility (P < 0.05) among the selected nuclei.
Data Conclusion
QSM allows the feasible quantification of iron deposition in deep gray matter nuclei in infants and young children, which exhibited gradual accumulation at different speeds. The fastest and highest iron accumulation was observed in the globus pallidus with increasing age during early development.
Level of Evidence: 4
Technical Efficacy:Stage 2
J. Magn. Reson. Imaging 2018.
•We develop harmonic background field extension based on physics-informed GAN.•Our method mitigates propagated error from background field removal in limited FOV.•Physics-informed loss shows improved ...results of extended harmonic field.•Outperforms conventional background field removal algorithms alone in limited FOV.•Overcomes susceptibility underestimation of QSM in limited FOV.
Quantitative susceptibility mapping (QSM) is frequently employed in investigating brain iron related to brain development and diseases within deep gray matter (DGM). Nonetheless, the acquisition of whole-brain QSM data is time-intensive. An alternative approach, focusing the QSM specifically on areas of interest such as the DGM by reducing the field-of-view (FOV), can significantly decrease scan times. However, severe susceptibility value underestimations have been reported during QSM reconstruction with a limited FOV, largely attributable to artifacts from incorrect background field removal in the boundary region. This presents a considerable barrier to the clinical use of QSM with small spatial coverages using conventional methods alone.
To mitigate the propagation of these errors, we proposed a harmonic field extension method based on a physics-informed generative adversarial network. Both quantitative and qualitative results demonstrate that our method outperforms conventional methods and delivers results comparable to those obtained with full FOV. Furthermore, we demonstrate the versatility of our method by applying it to data acquired prospectively with limited FOV and to data from patients with Parkinson's disease. The method has shown significant improvements in local field results, with QSM outcomes. In a clear illustration of its feasibility and effectiveness in real clinical environments, our proposed method addresses the prevalent issue of susceptibility underestimation in QSM with small spatial coverage.