Learning-Assisted Fast Determination of Regularization Parameter in Constrained Image Reconstruction.

OBJECTIVE: To leverage machine learning (ML) for fast selection of optimal regularization parameter in constrained image reconstruction. METHODS: Constrained image reconstruction is often formulated as a regularization problem and selecting a good regularization parameter value is an essential step. We solved this problem using an ML-based approach by leveraging the finding that for a specific constrained reconstruction problem defined for a fixed class of image functions, the optimal regularization parameter value is weakly subject-dependent and the dependence can be captured using few experimental data. The proposed method has four key steps: a) solution of a given constrained reconstruction problem for a few (say, 3) pre-selected regularization parameter values, b) extraction of multiple approximated quality metrics from the initial reconstructions, c) predicting the true quality metrics values from the approximated values using pre-trained neural networks, and d) determination of the optimal regularization parameter by fusing the predicted quality metrics. RESULTS: The effectiveness of the proposed method was demonstrated in two constrained reconstruction problems. Compared with L-curve-based method, the proposed method determined the regularization parameters much faster and produced substantially improved reconstructions. Our method also outperformed state-of-the-art learning-based methods when trained with limited experimental data. CONCLUSION: This paper demonstrates the feasibility and improved reconstruction quality by using machine learning to determine the regularization parameter in constrained reconstruction. SIGNIFICANCE: The proposed method substantially reduces the computational burden of the traditional methods (e.g., L-curve) or relaxes the requirement of large training data by modern learning-based methods, thus enhancing the practical utility of constrained reconstruction.

Simultaneous high-resolution whole-brain MR spectroscopy and [18F]FDG PET for temporal lobe epilepsy.

PURPOSE: Precise lateralizing the epileptogenic zone in patients with drug-resistant mesial temporal lobe epilepsy (mTLE) remains challenging, particularly when routine MRI scans are inconclusive (MRI-negative). This study aimed to investigate the synergy of fast, high-resolution, whole-brain MRSI in conjunction with simultaneous [18F]FDG PET for the lateralization of mTLE. METHODS: Forty-eight drug-resistant mTLE patients (M/F 31/17, age 12-58) underwent MRSI and [18F]FDG PET on a hybrid PET/MR scanner. Lateralization of mTLE was evaluated by visual inspection and statistical classifiers of metabolic mappings against routine MRI. Additionally, this study explored how disease status influences the associations between altered N-acetyl aspartate (NAA) and FDG uptake using hierarchical moderated multiple regression. RESULTS: The high-resolution whole-brain MRSI data offers metabolite maps at comparable resolution to [18F]FDG PET. Visual examinations of combined MRSI and [18F]FDG PET showed an mTLE lateralization accuracy rate of 91.7% in a 48-patient cohort, surpassing routine MRI (52.1%). Notably, out of 23 MRI-negative mTLE, combined MRSI and [18F]FDG PET helped detect 19 cases. Logistical regression models combining hippocampal NAA level and FDG uptake improved lateralization performance (AUC=0.856), while further incorporating extrahippocampal regions such as amygdala, thalamus, and superior temporal gyrus increased the AUC to 0.939. Concurrent MRSI/PET revealed a moderating influence of disease duration and hippocampal atrophy on the association between hippocampal NAA and glucose uptake, providing significant new insights into the disease's trajectory. CONCLUSION: This paper reports the first metabolic imaging study using simultaneous high-resolution MRSI and [18F]FDG PET, which help visualize MRI-unidentifiable lesions and may thus advance diagnostic tools and management strategies for drug-resistant mTLE.

Optimization of 3D dynamic speech MRI: Poisson-disc undersampling and locally higher-rank reconstruction through partial separability model with regional optimized temporal basis.

PURPOSE: To improve the spatiotemporal qualities of images and dynamics of speech MRI through an improved data sampling and image reconstruction approach. METHODS: For data acquisition, we used a Poisson-disc random under sampling scheme that reduced the undersampling coherence. For image reconstruction, we proposed a novel locally higher-rank partial separability model. This reconstruction model represented the oral and static regions using separate low-rank subspaces, therefore, preserving their distinct temporal signal characteristics. Regional optimized temporal basis was determined from the regional-optimized virtual coil approach. Overall, we achieved a better spatiotemporal image reconstruction quality with the potential of reducing total acquisition time by 50%. RESULTS: The proposed method was demonstrated through several 2-mm isotropic, 64 mm total thickness, dynamic acquisitions with 40 frames per second and compared to the previous approach using a global subspace model along with other k-space sampling patterns. Individual timeframe images and temporal profiles of speech samples were shown to illustrate the ability of the Poisson-disc under sampling pattern in reducing total acquisition time. Temporal information of sagittal and coronal directions was also shown to illustrate the effectiveness of the locally higher-rank operator and regional optimized temporal basis. To compare the reconstruction qualities of different regions, voxel-wise temporal SNR analysis were performed. CONCLUSION: Poisson-disc sampling combined with a locally higher-rank model and a regional-optimized temporal basis can drastically improve the spatiotemporal image quality and provide a 50% reduction in overall acquisition time.

Subspace Model-Assisted Deep Learning for Improved Image Reconstruction.

Image reconstruction from limited and/or sparse data is known to be an ill-posed problem and a priori information/constraints have played an important role in solving the problem. Early constrained image reconstruction methods utilize image priors based on general image properties such as sparsity, low-rank structures, spatial support bound, etc. Recent deep learning-based reconstruction methods promise to produce even higher quality reconstructions by utilizing more specific image priors learned from training data. However, learning high-dimensional image priors requires huge amounts of training data that are currently not available in medical imaging applications. As a result, deep learning-based reconstructions often suffer from two known practical issues: a) sensitivity to data perturbations (e.g., changes in data sampling scheme), and b) limited generalization capability (e.g., biased reconstruction of lesions). This paper proposes a new method to address these issues. The proposed method synergistically integrates model-based and data-driven learning in three key components. The first component uses the linear vector space framework to capture global dependence of image features; the second exploits a deep network to learn the mapping from a linear vector space to a nonlinear manifold; the third is an unrolling-based deep network that captures local residual features with the aid of a sparsity model. The proposed method has been evaluated with magnetic resonance imaging data, demonstrating improved reconstruction in the presence of data perturbation and/or novel image features. The method may enhance the practical utility of deep learning-based image reconstruction.

High-Dimensional MR Spatiospectral Imaging by Integrating Physics-Based Modeling and Data-Driven Machine Learning: Current progress and future directions.

Magnetic resonance spectroscopic imaging (MRSI) offers a unique molecular window into the physiological and pathological processes in the human body. However, the applications of MRSI have been limited by a number of long-standing technical challenges due to high dimensionality and low signal-to-noise ratio (SNR). Recent technological developments integrating physics-based modeling and data-driven machine learning that exploit unique physical and mathematical properties of MRSI signals have demonstrated impressive performance in addressing these challenges for rapid, high-resolution, quantitative MRSI. This paper provides a systematic review of these progresses in the context of MRSI physics and offers perspectives on promising future directions.

Preliminary Development of an MRI Atlas for Application to Cleft Care: Findings and Future Recommendations.

OBJECTIVE: To introduce a highly innovative imaging method to study the complex velopharyngeal (VP) system and introduce the potential future clinical applications of a VP atlas in cleft care. DESIGN: Four healthy adults participated in a 20-min dynamic magnetic resonance imaging scan that included a high-resolution T2-weighted turbo-spin-echo 3D structural scan and five custom dynamic speech imaging scans. Subjects repeated a variety of phrases when in the scanner as real-time audio was captured. SETTING: Multisite institution and clinical setting. PARTICIPANTS: Four adult subjects with normal anatomy were recruited for this study. MAIN OUTCOME: Establishment of 4-D atlas constructed from dynamic VP MRI data. RESULTS: Three-dimensional dynamic magnetic resonance imaging was successfully used to obtain high quality dynamic speech scans in an adult population. Scans were able to be re-sliced in various imaging planes. Subject-specific MR data were then reconstructed and time-aligned to create a velopharyngeal atlas representing the averaged physiological movements across the four subjects. CONCLUSIONS: The current preliminary study examined the feasibility of developing a VP atlas for potential clinical applications in cleft care. Our results indicate excellent potential for the development and use of a VP atlas for assessing VP physiology during speech.

B1 mapping using pre-learned subspaces for quantitative brain imaging.

PURPOSE: To develop a machine learning-based method for estimation of both transmitter and receiver B1 fields desired for correction of the B1 inhomogeneity effects in quantitative brain imaging. THEORY AND METHODS: A subspace model-based machine learning method was proposed for estimation of B1t and B1r fields. Probabilistic subspace models were used to capture scan-dependent variations in the B1 fields; the subspace basis and coefficient distributions were learned from pre-scanned training data. Estimation of the B1 fields for new experimental data was achieved by solving a linear optimization problem with prior distribution constraints. We evaluated the performance of the proposed method for B1 inhomogeneity correction in quantitative brain imaging scenarios, including T1 and proton density (PD) mapping from variable-flip-angle spoiled gradient-echo (SPGR) data as well as neurometabolic mapping from MRSI data, using phantom, healthy subject and brain tumor patient data. RESULTS: In both phantom and healthy subject data, the proposed method produced high-quality B1 maps. B1 correction on SPGR data using the estimated B1 maps produced significantly improved T1 and PD maps. In brain tumor patients, the proposed method produced more accurate and robust B1 estimation and correction results than conventional methods. The B1 maps were also applied to MRSI data from tumor patients and produced improved neurometabolite maps, with better separation between pathological and normal tissues. CONCLUSION: This work presents a novel method to estimate B1 variations using probabilistic subspace models and machine learning. The proposed method may make correction of B1 inhomogeneity effects more robust in practical applications.

Prediction of Stroke Onset Time With Combined Fast High-Resolution Magnetic Resonance Spectroscopic and Quantitative T2 Mapping.

OBJECTIVE: The purpose of this work is to develop a multispectral imaging approach that combines fast high-resolution 3D magnetic resonance spectroscopic imaging (MRSI) and fast quantitative T2 mapping to capture the multifactorial biochemical changes within stroke lesions and evaluate its potentials for stroke onset time prediction. METHODS: Special imaging sequences combining fast trajectories and sparse sampling were used to obtain whole-brain maps of both neurometabolites (2.0 × 3.0 × 3.0 mm3) and quantitative T2 values (1.9 × 1.9 × 3.0 mm3) within a 9-minute scan. Participants with ischemic stroke at hyperacute (0-24 h, n = 23) or acute (24 h-7d, n = 33) phase were recruited in this study. Lesion N-acetylaspartate (NAA), lactate, choline, creatine, and T2 signals were compared between groups and correlated with patient symptomatic duration. Bayesian regression analyses were employed to compare the predictive models of symptomatic duration using multispectral signals. RESULTS: In both groups, increased T2 and lactate levels, as well as decreased NAA and choline levels were detected within the lesion (all p < 0.001). Changes in T2, NAA, choline, and creatine signals were correlated with symptomatic duration for all patients (all p < 0.005). Predictive models of stroke onset time combining signals from MRSI and T2 mapping achieved the best performance (hyperacute: R2 = 0.438; all: R2 = 0.548). CONCLUSION: The proposed multispectral imaging approach provides a combination of biomarkers that index early pathological changes after stroke in a clinical-feasible time and improves the assessment of the duration of cerebral infarction. SIGNIFICANCE: Developing accurate and efficient neuroimaging techniques to provide sensitive biomarkers for prediction of stroke onset time is of great importance for maximizing the proportion of patients eligible for therapeutic intervention. The proposed method provides a clinically feasible tool for the assessment of symptom onset time post ischemic stroke, which will help guide time-sensitive clinical management.

Predicting the Onset of Ischemic Stroke With Fast High-Resolution 3D MR Spectroscopic Imaging.

BACKGROUND: Neurometabolite concentrations provide a direct index of infarction progression in stroke. However, their relationship with stroke onset time remains unclear. PURPOSE: To assess the temporal dynamics of N-acetylaspartate (NAA), creatine, choline, and lactate and estimate their value in predicting early (<6 hours) vs. late (6-24 hours) hyperacute stroke groups. STUDY TYPE: Cross-sectional cohort. POPULATION: A total of 73 ischemic stroke patients scanned at 1.8-302.5 hours after symptom onset, including 25 patients with follow-up scans. FIELD STRENGTH/SEQUENCE: A 3 T/magnetization-prepared rapid acquisition gradient echo sequence for anatomical imaging, diffusion-weighted imaging and fluid-attenuated inversion recovery imaging for lesion delineation, and 3D MR spectroscopic imaging (MRSI) for neurometabolic mapping. ASSESSMENT: Patients were divided into hyperacute (0-24 hours), acute (24 hours to 1 week), and subacute (1-2 weeks) groups, and into early (<6 hours) and late (6-24 hours) hyperacute groups. Bayesian logistic regression was used to compare classification performance between early and late hyperacute groups by using different combinations of neurometabolites as inputs. STATISTICAL TESTS: Linear mixed effects modeling was applied for group-wise comparisons between NAA, creatine, choline, and lactate. Pearson's correlation analysis was used for neurometabolites vs. time. P < 0.05 was considered statistically significant. RESULTS: Lesional NAA and creatine were significantly lower in subacute than in acute stroke. The main effects of time were shown on NAA (F = 14.321) and creatine (F = 12.261). NAA was significantly lower in late than early hyperacute patients, and was inversely related to time from symptom onset across both groups (r = -0.440). The decrease of NAA and increase of lactate were correlated with lesion volume (NAA: r = -0.472; lactate: r = 0.366) in hyperacute stroke. Discrimination was improved by combining NAA, creatine, and choline signals (area under the curve [AUC] = 0.90). DATA CONCLUSION: High-resolution 3D MRSI effectively assessed the neurometabolite changes and discriminated early and late hyperacute stroke lesions. EVIDENCE LEVEL: 1. TECHNICAL EFFICACY: Stage 2.

Simultaneous Mapping of Water Diffusion Coefficients and Metabolite Distributions of the Brain Using MR Spectroscopic Imaging Without Water Suppression.

OBJECTIVE: To simultaneously map water diffusion coefficients and metabolite distributions of the brain in magnetic resonance spectroscopic imaging (MRSI) experiments within a clinically feasible time. METHODS: A diffusion-preparation module was introduced in water-unsuppressed MRSI acquisition sequence to generate diffusion weighting of the water signals. Fast spatiospectral encodings were achieved using echo-planar spectroscopic imaging readouts with blipped phase encodings for sparse sampling. Navigator signals were embedded in the data acquisition sequence, which were used for detection of data corrupted by physiological motion in the diffusion preparation period. In data processing, a novel model-based method was developed to effectively use sparse (k, t)-space spectroscopic signals for reconstruction of the spatial distributions of water diffusion coefficients and metabolite concentrations. RESULTS: Both phantom experiments and in vivo experiments were carried out to evaluate the feasibility and performance of the proposed method. In an 8-minute scan, diffusion weighted images and apparent diffusion coefficients map at 2.0×1.0×1.0 mm3 were obtained simultaneously with metabolite maps at 2.0×3.0×3.0 mm3 nominal resolution. CONCLUSION: We demonstrated the feasibility of using the unsuppressed water signals from MRSI experiments to map the water diffusion coefficients of brain tissues and proposed a novel method to achieve simultaneous mapping of water diffusion coefficients and metabolite distributions. SIGNIFICANCE: The proposed method provides a unique imaging tool for simultaneous diffusion and metabolic imaging. This method is expected to be useful for various brain imaging applications.

JSENSE-Pro: Joint sensitivity estimation and image reconstruction in parallel imaging using pre-learned subspaces of coil sensitivity functions.

PURPOSE: To improve calibrationless parallel imaging using pre-learned subspaces of coil sensitivity functions. THEORY AND METHODS: A subspace-based joint sensitivity estimation and image reconstruction method was developed for improved parallel imaging with no calibration data. Specifically, we proposed to use a probabilistic subspace model to capture prior information of the coil sensitivity functions from previous scans acquired using the same receiver system. Both the subspace basis and coefficient distributions were learned from a small set of training data. The learned subspace model was then incorporated into the regularized reconstruction formalism that includes a sparsity prior. The nonlinear optimization problem was solved using alternating minimization algorithm. Public fastMRI brain dataset was retrospectively undersampled by different schemes for performance evaluation of the proposed method. RESULTS: With no calibration data, the proposed method consistently produced the most accurate coil sensitivity estimation and highest quality image reconstructions at all acceleration factors tested in comparison with state-of-the-art methods including JSENSE, DeepSENSE, P-LORAKS, and Sparse BLIP. Our results are comparable to or even better than those from SparseSENSE, which used calibration data for sensitivity estimation. The work also demonstrated that the probabilistic subspace model learned from T2 w data can be generalized to aiding the reconstruction of FLAIR data acquired from the same receiver system. CONCLUSION: A subspace-based method named JSENSE-Pro has been proposed for accelerated parallel imaging without the acquisition of companion calibration data. The method is expected to further enhance the practical utility of parallel imaging, especially in applications where calibration data acquisition is not desirable or limited.

Enhancing linguistic research through 2-mm isotropic 3D dynamic speech MRI optimized by sparse temporal sampling and low-rank reconstruction.

PURPOSE: To enable a more comprehensive view of articulations during speech through near-isotropic 3D dynamic MRI with high spatiotemporal resolution and large vocal-tract coverage. METHODS: Using partial separability model-based low-rank reconstruction coupled with a sparse acquisition of both spatial and temporal models, we are able to achieve near-isotropic resolution 3D imaging with a high frame rate. The total acquisition time of the speech acquisition is shortened by introducing a sparse temporal sampling that interleaves one temporal navigator with four randomized phase and slice-encoded imaging samples. Memory and computation time are improved through compressing coils based on the region of interest for low-rank constrained reconstruction with an edge-preserving spatial penalty. RESULTS: The proposed method has been evaluated through experiments on several speech samples, including a standard reading passage. A near-isotropic 1.875 × 1.875 × 2 mm3 spatial resolution, 64-mm through-plane coverage, and a 35.6-fps temporal resolution are achieved. Investigations and analysis on specific speech samples support novel insights into nonsymmetric tongue movement, velum raising, and coarticulation events with adequate visualization of rapid articulatory movements. CONCLUSION: Three-dimensional dynamic images of the vocal tract structures during speech with high spatiotemporal resolution and axial coverage is capable of enhancing linguistic research, enabling visualization of soft tissue motions that are not possible with other modalities.

T 2 ' mapping of the brain from water-unsuppressed 1 H-MRSI and turbo spin-echo data.

PURPOSE: To obtain high-quality T 2 ' $$ {\mathrm{T}}_2^{\prime } $$ maps of brain tissues from water-unsuppressed magnetic resonance spectroscopic imaging (MRSI) and turbo spin-echo (TSE) data. METHODS: T 2 ' $$ {\mathrm{T}}_2^{\prime } $$ mapping can be achieved using T 2 * $$ {\mathrm{T}}_2^{\ast } $$ mapping from water-unsuppressed MRSI data and T 2 $$ {\mathrm{T}}_2 $$ mapping from TSE data. However, T 2 * $$ {\mathrm{T}}_2^{\ast } $$ mapping often suffers from signal dephasing and distortions caused by B 0 $$ {\mathrm{B}}_0 $$ field inhomogeneity; T 2 $$ {\mathrm{T}}_2 $$ measurements may be biased due to system imperfections, especially for T 2 $$ {\mathrm{T}}_2 $$ -weighted image with small number of TEs. In this work, we corrected the B 0 $$ {\mathrm{B}}_0 $$ field inhomogeneity effect on T 2 * $$ {\mathrm{T}}_2^{\ast } $$ mapping using a subspace model-based method, incorporating pre-learned spectral basis functions of the water signals. T 2 $$ {\mathrm{T}}_2 $$ estimation bias was corrected using a TE-adjustment method, which modeled the deviation between measured and reference T 2 $$ {\mathrm{T}}_2 $$ decays as TE shifts. RESULTS: In vivo experiments were performed to evaluate the performance of the proposed method. High-quality T 2 * $$ {\mathrm{T}}_2^{\ast } $$ maps were obtained in the presence of large field inhomogeneity in the prefrontal cortex. Bias in T 2 $$ {\mathrm{T}}_2 $$ measurements obtained from TSE data was effectively reduced. Based on the T 2 * $$ {\mathrm{T}}_2^{\ast } $$ and T 2 $$ {\mathrm{T}}_2 $$ measurements produced by the proposed method, high-quality T 2 ' $$ {\mathrm{T}}_2^{\prime } $$ maps were obtained, along with neurometabolite maps, from MRSI and TSE data that were acquired in about 9 min. The results obtained from acute stroke and glioma patients demonstrated the feasibility of the proposed method in the clinical setting. CONCLUSIONS: High-quality T 2 ' $$ {\mathrm{T}}_2^{\prime } $$ maps can be obtained from water-unsuppressed 1 H-MRSI and TSE data using the proposed method. With further development, this method may lay a foundation for simultaneously imaging oxygenation and neurometabolic alterations of brain disorders.

Epigenetic MRI: Noninvasive imaging of DNA methylation in the brain.

Both neuronal and genetic mechanisms regulate brain function. While there are excellent methods to study neuronal activity in vivo, there are no nondestructive methods to measure global gene expression in living brains. Here, we present a method, epigenetic MRI (eMRI), that overcomes this limitation via direct imaging of DNA methylation, a major gene-expression regulator. eMRI exploits the methionine metabolic pathways for DNA methylation to label genomic DNA through 13C-enriched diets. A 13C magnetic resonance spectroscopic imaging method then maps the spatial distribution of labeled DNA. We validated eMRI using pigs, whose brains have stronger similarity to humans in volume and anatomy than rodents, and confirmed efficient 13C-labeling of brain DNA. We also discovered strong regional differences in global DNA methylation. Just as functional MRI measurements of regional neuronal activity have had a transformational effect on neuroscience, we expect that the eMRI signal, both as a measure of regional epigenetic activity and as a possible surrogate for regional gene expression, will enable many new investigations of human brain function, behavior, and disease.

DeepSENSE: Learning coil sensitivity functions for SENSE reconstruction using deep learning.

PURPOSE: To improve the estimation of coil sensitivity functions from limited auto-calibration signals (ACS) in SENSE-based reconstruction for brain imaging. METHODS: We propose to use deep learning to estimate coil sensitivity functions by leveraging information from previous scans obtained using the same RF receiver system. Specifically, deep convolutional neural networks were designed to learn an end-to-end mapping from the initial sensitivity to the high-resolution counterpart. Sensitivity alignment was further proposed to reduce the geometric variation caused by different subject positions and imaging FOVs. Cross-validation with a small set of datasets was performed to validate the learned neural network. Iterative SENSE reconstruction was adopted to evaluate the utility of the sensitivity functions from the proposed and conventional methods. RESULTS: The proposed method produced improved sensitivity estimates and SENSE reconstructions compared to the conventional methods in terms of aliasing and noise suppression with very limited ACS data. Cross-validation with a small set of data demonstrated the feasibility of learning coil sensitivity functions for brain imaging. The network learned on the spoiled GRE data can be applied to predict sensitivity functions for spin-echo and MPRAGE datasets. CONCLUSION: A deep learning-based method has been proposed for improving the estimation of coil sensitivity functions. Experimental results have demonstrated the feasibility and potential of the proposed method for improving SENSE-based reconstructions especially when the ACS data are limited.

High-Resolution Label-Free Molecular Imaging of Brain Tumor.

Molecular imaging has long been recognized as an important tool for diagnosis, characterization, and monitoring of treatment responses of brain tumors. Magnetic resonance spectroscopic imaging (MRSI) is a label-free molecular imaging technique capable of mapping metabolite distributions non-invasively. Several metabolites detectable by MRSI, including Choline, Lactate and N-Acetyl Aspartate, have been proved useful biomarkers for brain tumor characterization. However, clinical application of MRSI has been limited by poor resolution, small spatial coverage, low signal-to-noise ratio and long scan time. This work presents a novel MRSI method for fast, high-resolution metabolic imaging of brain tumor. This method synergistically integrates fast acquisition sequence, sparse sampling, subspace modeling and machine learning to enable 3D mapping of brain metabolites with a spatial resolution of 2.0×3.0×3.0 mm3 in a 7-minute scan. Experimental results obtained from patients with diagnosed brain tumor showed great promise for capturing small-size tumors and revealing intra-tumor metabolic heterogeneities.Clinical Relevance - This paper presents a novel technique for label-free molecular imaging of brain tumor. With further development, this technology may enable many potential clinical applications, from tumor detection, characterization, to assessment of treatment efficacy.

Improved estimation of myelin water fractions with learned parameter distributions.

PURPOSE: To improve estimation of myelin water fraction (MWF) in the brain from multi-echo gradient-echo imaging data. METHODS: A systematic sensitivity analysis was first conducted to characterize the conventional exponential models used for MWF estimation. A new estimation method was then proposed for improved estimation of MWF from practical gradient-echo imaging data. The proposed method uses an extended signal model that includes a finite impulse response filter to compensate for practical signal variations. This new model also enables the use of prelearned parameter distributions as well as low-rank signal structures to improve parameter estimation. The resulting parameter estimation problem was solved optimally in the Bayesian sense. RESULTS: Our sensitivity analysis results showed that the conventional exponential models were very sensitive to measurement noise and modeling errors. Our simulation and experimental results showed that our proposed method provided a substantial improvement in reliability, reproducibility, and robustness of MWF estimates over the conventional methods. Clinical results obtained from stroke patients indicated that the proposed method, with its improved capability, could reveal the loss of myelin in lesions, demonstrating its translational potentials. CONCLUSION: This paper addressed the problem of robust MWF estimation from gradient-echo imaging data. A new method was proposed to provide improved MWF estimation in the presence of significant noise and modeling errors. The performance of the proposed method has been evaluated using both simulated and experimental data, showing significantly improved robustness over the existing methods. The proposed method may prove useful for quantitative myelin imaging in clinical applications.

Machine Learning-Enabled High-Resolution Dynamic Deuterium MR Spectroscopic Imaging.

Deuterium magnetic resonance spectroscopic imaging (DMRSI) has recently been recognized as a potentially powerful tool for noninvasive imaging of brain energy metabolism and tumor. However, the low sensitivity of DMRSI has significantly limited its utility for both research and clinical applications. This work presents a novel machine learning-based method to address this limitation. The proposed method synergistically integrates physics-based subspace modeling and data-driven deep learning for effective denoising, making high-resolution dynamic DMRSI possible. Specifically, a novel subspace model was used to represent the dynamic DMRSI signals; deep neural networks were trained to capture the low-dimensional manifolds of the spectral and temporal distributions of practical dynamic DMRSI data. The learned subspace and manifold structures were integrated via a regularization formulation to remove measurement noise. Theoretical analysis, computer simulations, and in vivo experiments have been conducted to demonstrate the denoising efficacy of the proposed method which enabled high-resolution imaging capability. The translational potential was demonstrated in tumor-bearing rats, where the Warburg effect associated with cancer metabolism and tumor heterogeneity were successfully captured. The new method may not only provide an effective tool to enhance the sensitivity of DMRSI for basic research and clinical applications but also provide a framework for denoising other spatiospectral data.

High-resolution sodium imaging using anatomical and sparsity constraints for denoising and recovery of novel features.

PURPOSE: To develop and evaluate a novel method for reconstruction of high-quality sodium MR images from noisy, limited k-space data. THEORY AND METHODS: A novel reconstruction method was developed for reconstruction of high-quality sodium images from noisy, limited k-space data. This method is based on a novel image model that contains a motion-compensated generalized series model and a sparse model. The motion-compensated generalized series model enables effective use of anatomical information from a proton image for denoising and resolution enhancement of sodium data, whereas the sparse model enables high-resolution reconstruction of sodium-dependent novel features. The underlying model estimation problems were solved efficiently using convex optimization algorithms. RESULTS: The proposed method has been evaluated using both simulation and experimental data obtained from phantoms, healthy human volunteers, and tumor patients. Results showed a substantial improvement in spatial resolution and SNR over state-of-the-art reconstruction methods, including compressed sensing and anatomically constrained reconstruction methods. Quantitative tissue sodium concentration maps were obtained from both healthy volunteers and brain tumor patients. These tissue sodium concentration maps showed improved lesion fidelity and allowed accurate interrogation of small targets. CONCLUSION: A new method has been developed to obtain high-resolution sodium images with good SNR at 3 T. The proposed method makes effective use of anatomical prior information for denoising, while using a sparse model synergistically to recover sodium-dependent novel features. Experimental results have been obtained to demonstrate the feasibility of achieving high-quality tissue sodium concentration maps and their potential for improved detection of spatially heterogeneous responses of tumor to treatment.

Accelerated J-resolved 1 H-MRSI with limited and sparse sampling of ( k,t1,t2 -space.

PURPOSE: To accelerate the acquisition of J-resolved proton magnetic resonance spectroscopic imaging (1 H-MRSI) data for high-resolution mapping of brain metabolites and neurotransmitters. METHODS: The proposed method used a subspace model to represent multidimensional spatiospectral functions, which significantly reduced the number of parameters to be determined from J-resolved 1 H-MRSI data. A semi-LASER-based (Localization by Adiabatic SElective Refocusing) echo-planar spectroscopic imaging (EPSI) sequence was used for data acquisition. The proposed data acquisition scheme sampled k,t1,t2 -space in variable density, where t1 and t2 specify the J-coupling and chemical-shift encoding times, respectively. Selection of the J-coupling encoding times (or, echo time values) was based on a Cramer-Rao lower bound analysis, which were optimized for gamma-aminobutyric acid (GABA) detection. In image reconstruction, parameters of the subspace-based spatiospectral model were determined by solving a constrained optimization problem. RESULTS: Feasibility of the proposed method was evaluated using both simulated and experimental data from a spectroscopic phantom. The phantom experimental results showed that the proposed method, with a factor of 12 acceleration in data acquisition, could determine the distribution of J-coupled molecules with expected accuracy. In vivo study with healthy human subjects also showed that 3D maps of brain metabolites and neurotransmitters can be obtained with a nominal spatial resolution of 3.0 × 3.0 × 4.8 mm3 from J-resolved 1 H-MRSI data acquired in 19.4 min. CONCLUSIONS: This work demonstrated the feasibility of highly accelerated J-resolved 1 H-MRSI using limited and sparse sampling of k,t1,t2 -space and subspace modeling. With further development, the proposed method may enable high-resolution mapping of brain metabolites and neurotransmitters in clinical applications.