Whole brain multiparametric mapping in two minutes using a dual-flip-angle stack-of-stars blipped multi-gradient-echo acquisition.

A new MRI technique is presented for three-dimensional fast simultaneous whole brain mapping of myelin water fraction (MWF), T1, proton density (PD), R2*, magnetic susceptibility (QSM), and B1 transmit field (B1+). Phantom and human (N = 9) datasets were acquired using a dual-flip-angle blipped multi-gradient-echo (DFA-mGRE) sequence with a stack-of-stars (SOS) trajectory. Images were reconstructed using a subspace-based algorithm with a locally low-rank constraint. A novel joint-sparsity-constrained multicomponent T2*-T1 spectrum estimation (JMSE) algorithm is proposed to correct for the T1 saturation effect and B1+/B1- inhomogeneities in the quantification of MWF. A tissue-prior-based B1+ estimation algorithm was adapted for B1 correction in the mapping of T1 and PD. In the phantom study, measurements obtained at an acceleration factor (R) of 12 using prospectively under-sampled SOS showed good consistency (R2 > 0.997) with Cartesian reference for R2*/T1app/M0app. In the in vivo study, results of retrospectively under-sampled SOS with R = 6, 12, 18, showed good quality (structure similarity index measure > 0.95) compared with those of fully-sampled SOS. Besides, results of prospectively under-sampled SOS with R = 12 showed good consistency (intraclass correlation coefficient > 0.91) with Cartesian reference for T1/PD/B1+/MWF/QSM/R2*, and good reproducibility (coefficient of variation < 7.0 %) in the test-retest analysis for T1/PD/B1+/MWF/R2*. This study has demonstrated the feasibility of simultaneous whole brain multiparametric mapping with a two-minute scan using the DFA-mGRE SOS sequence, which may overcome a major obstacle for neurological applications of multiparametric MRI.

Reduction of ringing artifacts induced by diaphragm drifting in free-breathing dynamic pulmonary MRI using 3D koosh-ball acquisition.

PURPOSE: To reduce the ringing artifacts of the motion-resolved images in free-breathing dynamic pulmonary MRI. METHODS: A golden-step based interleaving (GSI) technique was proposed to reduce ringing artifacts induced by diaphragm drifting. The pulmonary MRI data were acquired using a superior-inferior navigated 3D radial UTE sequence in an interleaved manner during free breathing. Successive interleaves were acquired in an incoherent fashion along the polar direction. Four-dimensional images were reconstructed from the motion-resolved k-space data obtained by retrospectively binning. The reconstruction algorithms included standard nonuniform fast Fourier transform (NUFFT), Voronoi-density-compensated NUFFT, extra-dimensional UTE, and motion-state weighted motion-compensation reconstruction. The proposed interleaving technique was compared with a conventional sequential interleaving (SeqI) technique on a phantom and eight subjects. RESULTS: The quantified ringing artifacts level in the motion-resolved image is positively correlated with the quantified nonuniformity level of the corresponding k-space. The nonuniformity levels of the end-expiratory and end-inspiratory k-space binned from GSI data (0.34 ± 0.07, 0.33 ± 0.05) are significantly lower with statistical significance (p < 0.05) than that binned from SeqI data (0.44 ± 0.11, 0.42 ± 0.12). Ringing artifacts are substantially reduced in the dynamic images of eight subjects acquired using the proposed technique in comparison with that acquired using the conventional SeqI technique. CONCLUSION: Ringing artifacts in the motion-resolved images induced by diaphragm drifting can be reduced using the proposed GSI technique for free-breathing dynamic pulmonary MRI. This technique has the potential to reduce ringing artifacts in free-breathing liver and kidney MRI based on full-echo interleaved 3D radial acquisition.

Accelerating multi-echo chemical shift encoded water-fat MRI using model-guided deep learning.

PURPOSE: To accelerate chemical shift encoded (CSE) water-fat imaging by applying a model-guided deep learning water-fat separation (MGDL-WF) framework to the undersampled k-space data. METHODS: A model-guided deep learning water-fat separation framework is proposed for the acceleration using Cartesian/radial undersampling data. The proposed MGDL-WF combines the power of CSE water-fat imaging model and data-driven deep learning by jointly using a multi-peak fat model and a modified residual U-net network. The model is used to guide the image reconstruction, and the network is used to capture the artifacts induced by the undersampling. A data consistency layer is used in MGDL-WF to ensure the output images to be consistent with the k-space measurements. A Gauss-Newton iteration algorithm is adapted for the gradient updating of the networks. RESULTS: Compared with the compressed sensing water-fat separation (CS-WF) algorithm/2-step procedure algorithm, the MGDL-WF increased peak signal-to-noise ratio (PSNR) by 5.31/5.23, 6.11/4.54, and 4.75 dB/1.88 dB with Cartesian sampling, and by 4.13/6.53, 2.90/4.68, and 1.68 dB/3.48 dB with radial sampling, at acceleration rates (R) of 4, 6, and 8, respectively. By using MGDL-WF, radial sampling increased the PSNR by 2.07 dB at R = 8, compared with Cartesian sampling. CONCLUSIONS: The proposed MGDL-WF enables exploiting features of the water images and fat images from the undersampled multi-echo data, leading to improved performance in the accelerated CSE water-fat imaging. By using MGDL-WF, radial sampling can further improve the image quality with comparable scan time in comparison with Cartesian sampling.

Dynamic pulmonary MRI using motion-state weighted motion-compensation (MostMoCo) reconstruction with ultrashort TE: A structural and functional study.

PURPOSE: To improve the quality of structural images and the quantification of ventilation in free-breathing dynamic pulmonary MRI. METHODS: A 3D radial ultrashort TE (UTE) sequence with superior-inferior navigators was used to acquire pulmonary data during free breathing. All acquired data were binned into different motion states according to the respiratory signal extracted from superior-inferior navigators. Motion-resolved images were reconstructed using eXtra-Dimensional (XD) UTE reconstruction. The initial motion fields were generated by registering images at each motion state to other motion states in motion-resolved images. A motion-state weighted motion-compensation (MostMoCo) reconstruction algorithm was proposed to reconstruct the dynamic UTE images. This technique, termed as MostMoCo-UTE, was compared with XD-UTE and iterative motion-compensation (iMoCo) on a porcine lung and 10 subjects. RESULTS: MostMoCo reconstruction provides higher peak SNR (37.0 vs. 35.4 and 34.2) and structural similarity (0.964 vs. 0.931 and 0.947) compared to XD-UTE and iMoCo in the porcine lung experiment. Higher apparent SNR and contrast-to-noise ratio are achieved using MostMoCo in the human experiment. MostMoCo reconstruction better preserves the temporal variations of signal intensity of parenchyma compared to iMoCo, shows reduced random noise and improved sharpness of anatomical structures compared to XD-UTE. In the porcine lung experiment, the quantification of ventilation using MostMoCo images is more accurate than that using XD-UTE and iMoCo images. CONCLUSION: The proposed MostMoCo-UTE provides improved quality of structural images and quantification of ventilation for free-breathing pulmonary MRI. It has the potential for the detection of structural and functional disorders of the lung in clinical settings.

Dynamic MRI of the abdomen using parallel non-Cartesian convolutional recurrent neural networks.

PURPOSE: To improve the image quality and reduce computational time for the reconstruction of undersampled non-Cartesian abdominal dynamic parallel MR data using the deep learning approach. METHODS: An algorithm of parallel non-Cartesian convolutional recurrent neural networks (PNCRNNs) was developed to enable the use of the redundant information in both spatial and temporal domains, and achieve data fidelity for the reconstruction of non-Cartesian parallel MR data. The performance of PNCRNNs was evaluated for various acceleration rates, motion patterns, and imaging applications in comparison with that of the state-of-the-art algorithms of dynamic imaging, including extra-dimensional golden-angle radial sparse parallel MRI (XD-GRASP), low-rank plus sparse matrix decomposition (L+S), blind compressive sensing (BCS), and 3D convolutional neural networks (3D CNNs). RESULTS: PNCRNNs increased the peak SNR of 9.07 dB compared with XD-GRASP, 9.26 dB compared with L+S, 3.48 dB compared with BCS, and 3.14 dB compared with 3D CNN at R = 16. The reconstruction time was 18 ms for each bin, which was two orders faster than that of XD-GRASP, L+S, and BCS. PNCRNNs provided good reconstruction for various motion patterns, k-space trajectories, and imaging applications. CONCLUSION: The proposed PNCRNN provides substantial improvement of the image quality for dynamic golden-angle radial imaging of the abdomen in comparison with XD-GRASP, L+S, BCS, and 3D CNN. The reconstruction time of PNCRNN can be as fast as 50 bins per second, due to the use of the highly computational efficient Toeplitz approach.

Center-out EPI (COEPI): A fast single-shot imaging technique with a short TE.

PURPOSE: To develop a center-out echo planar imaging (COEPI) acquisition technique to increase SNR through minimizing the TE. METHODS: In single-shot COEPI, the phase-encoding starts from the center (ky = 0) toward both sides of k-space to substantially shorten the TE compared to the conventional single-shot EPI. The phase-encoding gradient waveform is partially overlapped with the frequency-encoding gradient waveform to keep the echo spacing constant during the echo train readout. A reconstruction pipeline was developed to correct for phase and off-resonance errors in COEPI. Gradient-recalled echo (GRE), spin echo (SE), and DWI COEPI were obtained in phantoms and healthy brains at 1.5 tesla (T) and 3.0T. The SNR in COEPI and single-shot partial ky EPI was compared. RESULTS: Acquisition matrix of 128 × 80 (16 overscan lines) was obtained in both COEPI and EPI. At 1.5T/3.0T, a minimum TE of 3 ms/4 ms in GRE-COEPI, 11 ms/12 ms in SE-COEPI, and 40 ms in DWI-COEPI (3.0T only, maximum b value = 2000 s/mm2 ) was achieved, compared to a minimum TE of 18 ms/16 ms in GRE-EPI, 37 ms/34 ms in SE-EPI, and 66 ms in DWI-EPI, respectively. Image blurring and Nyquist ghost appear in COEPI and were substantially reduced after corrections. At 1.5T/3.0T, a SNR increase of 27.7% ± 6.9%/20.7% ± 7.0% in GRE-COEPI and 37.7% ± 5.7%/28.2% ± 1.3% in SE-COEPI was observed in white matter of human brains, compared to GRE-EPI and SE-EPI, respectively. At 3.0T, a SNR increase of 41.2% ± 4.1% in DWI-COEPI was observed in white matter of 5 subjects at 5 b values (0~2000 s/mm2 ), compared to DWI-EPI. CONCLUSION: The feasibility of COEPI and its SNR benefit were demonstrated in this study.

Improved quantification of myelin water fraction using joint sparsity of T2 * distribution.

BACKGROUND: Myelin water fraction (MWF) can be quantified with analysis of the T2 * distribution, whereas deducing the T2 * spectrum from several echoes is an underdetermined and ill-posed problem. PURPOSE: To improve the quantification of myelin water content by using nonnegative jointly sparse (NNJS) optimization. STUDY TYPE: Prospective. SUBJECTS: Nine healthy subjects. FIELD STRENGTH/SEQUENCE: 3T, multiecho gradient echo. ASSESSMENT: The results of NNJS were compared with that of the nonnegative least square (NNLS)-based algorithms. Simulated models with varied MWF at different noise levels were used to evaluate the accuracy of estimations. In human data, the MWF values of different regions were compared with previous studies and the coefficient of variation (COV) was used to assess the spatial coherence. STATISTICAL TEST: Paired t-test. RESULTS: In simulation, the relative errors of MWF obtained from synthesized data with signal-to-noise ratio (SNR) at 500, 200, 150, and 100 were 0.08, 0.09, 0.10, and 0.12 for NNJS, 0.29, 0.43, 0.48, and 0.53 for regularized NNLS (rNNLS), and 0.19, 0.24, 0.25, and 0.26 for spatially-regularized NNLS (srNNLS). In human data, the mean values of MWF produced by NNJS in different regions were consistent with previous studies. Compared with the NNLS-based algorithms, lower COVs generated by NNJS were observed in genu, forceps minor, forceps major, and internal capsule, which were 0.44 ± 0.08, 0.48 ± 0.07, 0.46 ± 0.03, and 0.48 ± 0.09 in NNJS, 0.88 ± 0.28, 0.96 ± 0.18, 0.72 ± 0.03, and 0.85 ± 0.15 in rNNLS, and 0.56 ± 0.17, 0.64 ± 0.14, 0.50 ± 0.04 and 0.58 ± 0.13 in srNNLS. DATA CONCLUSION: Quantitative results of both simulated and human data show that NNJS provides more plausible estimation than the NNLS-based algorithms. Visual advantages of NNJS in spatial consistency can be confirmed by the comparative COV index. The proposed algorithm might improve the quantification of myelin water content. LEVEL OF EVIDENCE: 2 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2020;52:146-158.

Simultaneous multislice magnetic resonance fingerprinting (SMS-MRF) with direct-spiral slice-GRAPPA (ds-SG) reconstruction.

PURPOSE: To develop a reconstruction method to improve SMS-MRF, in which slice acceleration is used in conjunction with highly undersampled in-plane acceleration to speed up MRF acquisition. METHODS: In this work two methods are employed to efficiently perform the simultaneous multislice magnetic resonance fingerprinting (SMS-MRF) data acquisition and the direct-spiral slice-GRAPPA (ds-SG) reconstruction. First, the lengthy training data acquisition is shortened by employing the through-time/through-k-space approach, in which similar k-space locations within and across spiral interleaves are grouped and are associated with a single set of kernel. Second, inversion recovery preparation (IR prepped), variable flip angle (FA), and repetition time (TR) are used for the acquisition of the training data, to increase signal variation and to improve the conditioning of the kernel fitting. RESULTS: The grouping of k-space locations enables a large reduction in the number of kernels required, and the IR-prepped training data with variable FA and TR provide improved ds-SG kernels and reconstruction performance. With direct-spiral slice-GRAPPA, tissue parameter maps comparable to that of conventional MRF were obtained at multiband (MB) = 3 acceleration using t-blipped SMS-MRF acquisition with 32-channel head coil at 3 Tesla (T). CONCLUSIONS: The proposed reconstruction scheme allows MB = 3 accelerated SMS-MRF imaging with high-quality T1 , T2 , and off-resonance maps, and can be used to significantly shorten MRF acquisition and aid in its adoption in neuro-scientific and clinical settings. Magn Reson Med 77:1966-1974, 2017. © 2016 International Society for Magnetic Resonance in Medicine.

Improving image quality for skipped phase encoding and edge deghosting (SPEED) by exploiting several sparsifying transforms.

PURPOSE: To improve the image quality of skipped phase encoding and edge deghosting (SPEED) by exploiting several sparsifying transforms. METHODS: The SPEED technique uses a skipped phase encoding (PE) step to accelerate MRI scan. Previously, a difference transform (DT) along PE direction is used to obtain sparse ghosted-edge maps, which were modeled by a double layer ghost model and was then deghosted by a least square error solution. In this work, it is hypothesized that enhanced sparsity, and thus improved image quality may be achievable with other sparsifying transforms, including discrete wavelet transform (DWT), discrete cosine transform (DCT), DWT combined with DT, and DCT combined with DT. RESULTS: For images of human subjects, SPEED with DWT or DCT can yield higher image quality than DT only, especially for those images with low contrast. Reconstruction error can be further reduced if DWT or DCT are combined with DT. CONCLUSION: Image sparsity can be enhanced with more advanced transforms, leading to higher reconstruction quality in SPEED imaging that is desirable for practical MRI applications.

Scan-specific Unsupervised Highly Accelerated Non-Cartesian CEST Imaging using Implicit Neural Representation and Explicit Sparse Prior.

OBJECTIVE: Chemical exchange saturation transfer (CEST) is a promising magnetic resonance imaging (MRI) technique. CEST imaging usually requires a long scan time, and reducing acquisition time is highly desirable for clinical applications. METHODS: A novel scan-specific unsupervised deep learning algorithm is proposed to accelerate steady-state pulsed CEST imaging with golden-angle stack-of-stars trajectory using hybrid-feature hash encoding implicit neural representation. Additionally, imaging quality is further improved by using the explicit prior knowledge of low rank and weighted joint sparsity in the spatial and Z-spectral domain of CEST data. RESULTS: In the retrospective acceleration experiment, the proposed method outperforms other state-of-the-art algorithms (TDDIP, LRTES, kt-SLR, NeRP, CRNN, and PBCS) for the in vivo human brain dataset under various acceleration rates. In the prospective acceleration experiment, the proposed algorithm can still obtain results close to the fully-sampled images. CONCLUSION AND SIGNIFICANCE: The hybrid-feature hash encoding implicit neural representation combined with explicit sparse prior (INRESP) can efficiently accelerate CEST imaging. The proposed algorithm achieves reduced error and improved image quality compared to several state-of-the-art algorithms at relatively high acceleration factors. The superior performance and the training database-free characteristic make the proposed algorithm promising for accelerating CEST imaging in various applications.

Accelerated four-dimensional free-breathing whole-liver water-fat magnetic resonance imaging with deep dictionary learning and chemical shift modeling.

Background: Multi-echo chemical-shift-encoded magnetic resonance imaging (MRI) has been widely used for fat quantification and fat suppression in clinical liver examinations. Clinical liver water-fat imaging typically requires breath-hold acquisitions, with the free-breathing acquisition method being more desirable for patient comfort. However, the acquisition for free-breathing imaging could take up to several minutes. The purpose of this study is to accelerate four-dimensional free-breathing whole-liver water-fat MRI by jointly using high-dimensional deep dictionary learning and model-guided (MG) reconstruction. Methods: A high-dimensional model-guided deep dictionary learning (HMDDL) algorithm is proposed for the acceleration. The HMDDL combines the powers of the high-dimensional dictionary learning neural network (hdDLNN) and the chemical shift model. The neural network utilizes the prior information of the dynamic multi-echo data in spatial respiratory motion, and echo dimensions to exploit the features of images. The chemical shift model is used to guide the reconstruction of field maps, R2∗ maps, water images, and fat images. Data acquired from ten healthy subjects and ten subjects with clinically diagnosed nonalcoholic fatty liver disease (NAFLD) were selected for training. Data acquired from one healthy subject and two NAFLD subjects were selected for validation. Data acquired from five healthy subjects and five NAFLD subjects were selected for testing. A three-dimensional (3D) blipped golden-angle stack-of-stars multi-gradient-echo pulse sequence was designed to accelerate the data acquisition. The retrospectively undersampled data were used for training, and the prospectively undersampled data were used for testing. The performance of the HMDDL was evaluated in comparison with the compressed sensing-based water-fat separation (CS-WF) algorithm and a parallel non-Cartesian recurrent neural network (PNCRNN) algorithm. Results: Four-dimensional water-fat images with ten motion states for whole-liver are demonstrated at several R values. In comparison with the CS-WF and PNCRNN, the HMDDL improved the mean peak signal-to-noise ratio (PSNR) of images by 9.93 and 2.20 dB, respectively, and improved the mean structure similarity (SSIM) of images by 0.058 and 0.009, respectively, at R=10. The paired t-test shows that there was no significant difference between HMDDL and ground truth for proton-density fat fraction (PDFF) and R2∗ values at R up to 10. Conclusions: The proposed HMDDL enables features of water images and fat images from the highly undersampled multi-echo data along spatial, respiratory motion, and echo dimensions, to improve the performance of accelerated four-dimensional (4D) free-breathing water-fat imaging.

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.

A tissue-relaxation-dependent neighboring method for robust mapping of the myelin water fraction.

Quantitative assessment of the myelin content in white matter (WM) using MRI has become a useful tool for investigating myelin-related diseases, such as multiple sclerosis (MS). Myelin water fraction (MWF) maps can be estimated pixel-by-pixel by a determination of the T2 or T2* spectrum from signal decay measurements at each individual image pixel. However, detection of parameters from the measured decay curve, assuming a combination of smooth multi-exponential curves, results in a nonlinear and seriously ill-posed problem. In this paper, we propose a new method to obtain a stable MWF map robust to the presence of noise while sustaining sufficient resolution, which uses weighted combinations of measured decay signals in a spatially independent neighborhood to combine tissues with similar relaxation parameters. To determine optimal weighting factors, we define a spatially independent neighborhood for each pixel and a distance with respect to decay rates that effectively includes pixels with similar decay characteristics, and which therefore have similar relaxation parameters. We recover the MWF values by using optimally weighted decay curves. We use numerical simulations and in vitro and in vivo experimental brain data scanned with a multi-gradient-echo sequence to demonstrate the feasibility of our proposed algorithm and to highlight its advantages compared to the conventional method.

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

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

Low-Rank Tensor Subspace Decomposition With Weighted Group Sparsity for the Acceleration of Non-Cartesian Dynamic MRI.

OBJECTIVE: Dynamic MR imaging often requires long scan time, and acceleration of data acquisition is highly desirable in clinical applications. METHODS: We proposed a Low-rank Tensor subspace decomposition with Weighted Group Sparsity (LTWGS) algorithm for non-Cartesian dynamic MRI. The proposed algorithm introduces the weighted group sparse constraints together with the subspace decomposition technique into the framework of low-rank tensor and sparse decomposition to better utilize the sparsity in the data. RESULTS: LTWGS increases the PSNR values by 1.97 dB, 2.03 dB, and 2.83 dB compared with PROST (patch-based reconstruction), SRTPCA (smooth robust tensor principal component analysis), and LRTES (low-rank tensor with "explicit subspace") in the dynamic abdominal imaging at an acceleration rate R = 25. LTWGS increases the PSNR values by 2.42 dB and 3.57 dB compared with PROST and LRTES in DCE liver imaging at R = 25. LTWGS increases the PSNR values by 1.40 dB and 1.96 dB compared with PROST and SRTPCA in cardiac cine imaging at R = 25. CONCLUSION AND SIGNIFICANCE: Jointly using group sparsity and sparsity can obtain better results than that using group sparsity alone, and weighted regularization can achieve better results than that without weighted regularization. The proposed algorithm results in reduced reconstruction error and improved image structural similarity in comparison with several state-of-the-art methods at relatively high acceleration factors. The proposed algorithm has the potential in various dynamic MRI application scenarios.

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.

Robust mapping of the myelin water fraction in the presence of noise: synergic combination of anisotropic diffusion filter and spatially regularized nonnegative least squares algorithm.

PURPOSE: To improve the mapping of myelin water fraction (MWF) despite the presence of measurement noise, and to increase the visibility of fine structures in MWF maps. MATERIALS AND METHODS: An anisotropic diffusion filter (ADF) was effectively combined with a spatially regularized nonnegative least squares algorithm (srNNLS) for robust MWF mapping. Synthetic data simulations were performed to assess the effectiveness of this new method. Experimental measurements of signal decay curves were obtained and MWF maps were estimated using the new method and compared with maps estimated using other methods. RESULTS: MWF mapping was substantially improved in both simulations and experimental data when ADF was combined with the srNNLS algorithm. MWF variability decreased with the use of the proposed method, which in turn resulted in increased visibility of small focal lesions and structures in the MWF maps. CONCLUSION: This study demonstrates that the benefits of ADF and srNNLS algorithms can be effectively combined in a synergic way for robust mapping of MWF in the presence of noise. Substantial improvements to MWF mapping can be made using the proposed method.

MR venography of the brain with enhanced vessel contrast using image-domain high-pass filtering of the susceptibility phase shift.

PURPOSE: To develop a postprocessing algorithm that enhances the visibility of intracranial venous vasculature and reduces the artifacts in the display of susceptibility-weighted images (SWI). MATERIALS AND METHODS: Image-domain high-pass filters based on second-order phase difference were applied to the complex 3D SWI data to enhance the susceptibility phase shift of the veins and suppress background signal in SWI. A multivariant statistical parameter was used to suppress the noise in air. RESULTS: Magnetic resonance (MR) venography with enhanced susceptibility phase shift and reduced off-resonance artifacts was obtained using the proposed filters. The background signal in the 3D MR venography data was well suppressed. Venous vasculature in the peripheral regions of the brain was well depicted and the adverse effect of noise in air in the maximum-intensity projection display of the 3D SWI data was well suppressed. CONCLUSION: Image-domain high-pass filtering with second-order phase difference provides an alternative display of 3D SWI data with enhanced visibility of the venous vasculature and effective suppression of artifacts.

Whole Brain Myelin Water Mapping in One Minute Using Tensor Dictionary Learning With Low-Rank Plus Sparse Regularization.

The quantification of myelin water content in the brain can be obtained by the multi-echo [Formula: see text] weighted images ( [Formula: see text]WIs). To accelerate the long acquisition, a novel tensor dictionary learning algorithm with low-rank and sparse regularization (TDLLS) is proposed to reconstruct the [Formula: see text]WIs from the undersampled data. The proposed algorithm explores the local and nonlocal similarity and the global temporal redundancy in the real and imaginary parts of the complex relaxation signals. The joint application of the low-rank constraints on the dictionaries and the sparse constraints on the core coefficient tensors improves the performance of the tensor-based recovery. Parallel imaging is incorporated into the TDLLS algorithm (pTDLLS) for further acceleration. A pulse sequence is proposed to prospectively undersample the Ky-t space to obtain the whole brain high-quality myelin water fraction (MWF) maps within 1 minute at an undersampling rate (R) of 6.

In vivo multi-slice mapping of myelin water content using T2* decay.

Quantitative assessment of the myelin water content in the brain can substantially improve our understanding of white matter diseases such as multiple sclerosis. In this study, in vivo myelin water content was estimated using T(2)* relaxation with multi-slice acquisitions in magnetic resonance imaging (MRI). The main advantages of using T(2)* relaxation are (1) a low specific absorption rate (SAR), which is especially beneficial for imaging at high field strengths, (2) a short first-echo time (approximately 2 ms) and short echo spacing (approximately 1 ms), which allows for the acquisition of multiple sampling points during the fast decay of the myelin water signal, and (3) fast multi-slice acquisitions. High-resolution and multi-slice myelin water fraction (MWF) maps were obtained in a clinically acceptable scan time at 3T. Five healthy adults were scanned with a multi-gradient-echo sequence to acquire T(2)* signal decay data. Images with a dimension of 256x256 at eight slice locations were acquired in 8.5 min with a signal-to-noise ratio (SNR) of 94.8 in the first-echo images. The SNR was further increased by using an anisotropic diffusion filter. Local field gradients (LFG) were estimated from the acquired multi-slice data, and the LFG-induced signal decays were corrected with a first-order approximation of LFG using the sinc function. The corrected T(2)* signal decays were analyzed with a three-pool model to quantify MWF. Our results demonstrate the feasibility of in vivo multi-slice mapping of MWF using multi-compartmental analysis of the T(2)* signal decay.