Search

Purpose: To develop a neural network architecture for improved calibrationless reconstruction of radial data when no ground truth is available for training. Methods: NLINV‐Net is a model‐based neural network architecture that directly estimates images and coil sensitivities from (radial) k‐space data via nonlinear inversion (NLINV). Combined with a training strategy using self‐supervision via data undersampling (SSDU), it can be used for imaging problems where no ground truth reconstructions are available. We validated the method for (1) real‐time cardiac imaging and (2) single‐shot subspace‐based quantitative T1 mapping. Furthermore, region‐optimized virtual (ROVir) coils were used to suppress artifacts stemming from outside the field of view and to focus the k‐space‐based SSDU loss on the region of interest. NLINV‐Net‐based reconstructions were compared with conventional NLINV and PI‐CS (parallel imaging + compressed sensing) reconstruction and the effect of the region‐optimized virtual coils and the type of training loss was evaluated qualitatively. Results: NLINV‐Net‐based reconstructions contain significantly less noise than the NLINV‐based counterpart. ROVir coils effectively suppress streakings which are not suppressed by the neural networks while the ROVir‐based focused loss leads to visually sharper time series for the movement of the myocardial wall in cardiac real‐time imaging. For quantitative imaging, T1‐maps reconstructed using NLINV‐Net show similar quality as PI‐CS reconstructions, but NLINV‐Net does not require slice‐specific tuning of the regularization parameter. Conclusion: NLINV‐Net is a versatile tool for calibrationless imaging which can be used in challenging imaging scenarios where a ground truth is not available. [ABSTRACT FROM AUTHOR]

With a substantial growth in the use of musculoskeletal MRI, there has been a growing need to improve MRI workflow, and faster imaging has been suggested as one of the solutions for a more efficient examination process. Consequently, there have been considerable advances in accelerated MRI scanning methods. This article aims to review the basic principles and applications of accelerated musculoskeletal MRI techniques including widely used conventional acceleration methods, more advanced deep learning‐based techniques, and new approaches to reduce scan time. Specifically, conventional accelerated MRI techniques, including parallel imaging, compressed sensing, and simultaneous multislice imaging, and deep learning‐based accelerated MRI techniques, including undersampled MR image reconstruction, super‐resolution imaging, artifact correction, and generation of unacquired contrast images, are discussed. Finally, new approaches to reduce scan time, including synthetic MRI, novel sequences, and new coil setups and designs, are also reviewed. We believe that a deep understanding of these fast MRI techniques and proper use of combined acceleration methods will synergistically improve scan time and MRI workflow in daily practice. Evidence Level: 3 Technical Efficacy: Stage 1 [ABSTRACT FROM AUTHOR]

Purpose: This study leverages externally generated Pilot Tone (PT) signals to perform motion‐corrected brain MRI for sequences with arbitrary k‐space sampling and image contrast. Theory and Methods: PT signals are promising external motion sensors due to their cost‐effectiveness, easy workflow, and consistent performance across contrasts and sampling patterns. However, they lack robust calibration pipelines. This work calibrates PT signal to rigid motion parameters acquired during short blocks (˜4 s) of motion calibration (MC) acquisitions, which are short enough to unobstructively fit between acquisitions. MC acquisitions leverage self‐navigated trajectories that enable state‐of‐the‐art motion estimation methods for efficient calibration. To capture the range of patient motion occurring throughout the examination, distributed motion calibration (DMC) uses data acquired from MC scans distributed across the entire examination. After calibration, PT is used to retrospectively motion‐correct sequences with arbitrary k‐space sampling and image contrast. Additionally, a data‐driven calibration refinement is proposed to tailor calibration models to individual acquisitions. In vivo experiments involving 12 healthy volunteers tested the DMC protocol's ability to robustly correct subject motion. Results: The proposed calibration pipeline produces pose parameters consistent with reference values, even when distributing only six of these approximately 4‐s MC blocks, resulting in a total acquisition time of 22 s. In vivo motion experiments reveal significant (p<0.05$$ p<0.05 $$) improved motion correction with increased signal to residual ratio for both MPRAGE and SPACE sequences with standard k‐space acquisition, especially when motion is large. Additionally, results highlight the benefits of using a distributed calibration approach. Conclusions: This study presents a framework for performing motion‐corrected brain MRI in sequences with arbitrary k‐space encoding and contrast, using externally generated PT signals. The DMC protocol is introduced, promoting observation of patient motion occurring throughout the examination and providing a calibration pipeline suitable for clinical deployment. The method's application is demonstrated in standard volumetric MPRAGE and SPACE sequences. [ABSTRACT FROM AUTHOR]

Purpose: To investigate whether parallel imaging‐imposed geometric coil constraints can be relaxed when using a deep learning (DL)‐based image reconstruction method as opposed to a traditional non‐DL method. Theory and Methods: Traditional and DL‐based MR image reconstruction approaches operate in fundamentally different ways: Traditional methods solve a system of equations derived from the image data whereas DL methods use data/target pairs to learn a generalizable reconstruction model. Two sets of head coil profiles were evaluated: (1) 8‐channel and (2) 32‐channel geometries. A DL model was compared to conjugate gradient SENSE (CG‐SENSE) and L1‐wavelet compressed sensing (CS) through quantitative metrics and visual assessment as coil overlap was increased. Results: Results were generally consistent between experiments. As coil overlap increased, there was a significant (p < 0.001) decrease in performance in most cases for all methods. The decrease was most pronounced for CG‐SENSE, and the DL models significantly outperformed (p < 0.001) their non‐DL counterparts in all scenarios. CS showed improved robustness to coil overlap and signal‐to‐noise ratio (SNR) versus CG‐SENSE, but had quantitatively and visually poorer reconstructions characterized by blurriness as compared to DL. DL showed virtually no change in performance across SNR and very small changes across coil overlap. Conclusion: The DL image reconstruction method produced images that were robust to coil overlap and of higher quality than CG‐SENSE and CS. This suggests that geometric coil design constraints can be relaxed when using DL reconstruction methods. [ABSTRACT FROM AUTHOR]

Purpose: Toward pushing the boundaries of ultrahigh fields for human brain imaging, we wish to evaluate experimentally achievable SNR relative to ultimate intrinsic SNR (uiSNR) at 10.5T, develop design strategies toward approaching the latter, quantify magnetic field–dependent SNR gains, and demonstrate the feasibility of whole‐brain, high‐resolution human brain imaging at this uniquely high field strength. Methods: A dual row 16‐channel self‐decoupled transmit (Tx) and receive (Rx) array was developed for 10.5T using custom Tx/Rx switches. A 64‐channel receive‐only array was built to fit into the 16‐channel Tx/Rx array. Electromagnetic modeling and experiments were used to define safe operational power limits. Experimental SNR was evaluated relative to uiSNR at 10.5T and 7T. Results: The 64‐channel Rx array alone captured approximately 50% of the central uiSNR at 10.5T, while an identical array developed for 7T captured about 76% of uiSNR at 7T. The 16‐channel Tx/80‐channel Rx configuration brought the fraction of uiSNR captured at 10.5T to levels comparable to the 64‐channel Rx array at 7T. SNR data displayed an approximate B02$$ {\mathrm{B}}_0^2 $$ dependence over a large central region when evaluated in the context of uiSNR. Whole‐brain, high‐resolution T2*$$ {\mathrm{T}}_2^{\ast } $$‐weighted and T1‐weighted anatomical and gradient‐recalled‐echo BOLD‐EPI functional MRI images were obtained at 10.5T for the first time with such an advanced array. Conclusion: We demonstrated the ability to approach the uiSNR at 10.5T over the human brain, achieving large SNR gains over 7T, currently the most commonly used ultrahigh‐field platform. Whole‐brain, high‐resolution anatomical and EPI‐based functional MRI data were obtained at 10.5T, illustrating the promise of greater than 10T fields in studying the human brain. [ABSTRACT FROM AUTHOR]

Purpose: To develop an efficient navigator‐based motion and temporal B0‐shift correction technique for 3D multi‐echo gradient‐echo (ME‐GRE) MRI for quantitative susceptibility mapping (QSM) and R2*$$ {\mathrm{R}}_2^{\ast } $$ mapping. Theory and Methods: A dual‐echo 3D stack‐of‐spiral navigator was designed to interleave with the Cartesian multi‐echo gradient‐echo acquisitions, allowing the acquisition of both low‐echo and high‐echo time signals. We additionally designed a novel conjugate phase–based reconstruction method for the joint correction of motion and temporal B0 shifts. We performed numerical simulation, phantom scans, and in vivo human scans to assess the performance of the methods. Results: Numerical simulation and human brain scans demonstrated that the proposed technique successfully corrected artifacts induced by both head motions and temporal B0 changes. Efficient B0‐change correction with conjugate‐phase reconstruction can be performed on fewer than 10 clustered k‐space segments. In vivo scans showed that combining temporal B0 correction with motion correction further reduced artifacts and improved image quality in both R2*$$ {\mathrm{R}}_2^{\ast } $$ and QSM images. Conclusion: Our proposed approach of using 3D spiral navigators and a novel conjugate‐phase reconstruction method can improve susceptibility‐related measurements using MR. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) is crucial for accurately diagnosing a wide spectrum of musculoskeletal conditions due to its superior soft tissue contrast resolution. However, the long acquisition times of traditional two-dimensional (2D) and three-dimensional (3D) fast and turbo spin-echo (TSE) pulse sequences can limit patient access and comfort. Recent technical advancements have introduced acceleration techniques that significantly reduce MRI times for musculoskeletal examinations. Key acceleration methods include parallel imaging (PI), simultaneous multi-slice acquisition (SMS), and compressed sensing (CS), enabling up to eightfold faster scans while maintaining image quality, resolution, and safety standards. These innovations now allow for 3- to 6-fold accelerated clinical musculoskeletal MRI exams, reducing scan times to 4 to 6 min for joints and spine imaging. Evolving deep learning-based image reconstruction promises even faster scans without compromising quality. Current research indicates that combining acceleration techniques, deep learning image reconstruction, and superresolution algorithms will eventually facilitate tenfold accelerated musculoskeletal MRI in routine clinical practice. Such rapid MRI protocols can drastically reduce scan times by 80–90% compared to conventional methods. Implementing these rapid imaging protocols does impact workflow, indirect costs, and workload for MRI technologists and radiologists, which requires careful management. However, the shift from conventional to accelerated, deep learning-based MRI enhances the value of musculoskeletal MRI by improving patient access and comfort and promoting sustainable imaging practices. This article offers a comprehensive overview of the technical aspects, benefits, and challenges of modern accelerated musculoskeletal MRI, guiding radiologists and researchers in this evolving field. [ABSTRACT FROM AUTHOR]

Abstract We introduce three architecture modifications to enhance the performance of the end-to-end (E2E) variational network (VarNet) for undersampled MRI reconstructions. We first implemented the Feature VarNet, which propagates information throughout the cascades of the network in an N-channel feature-space instead of a 2-channel feature-space. Then, we add an attention layer that utilizes the spatial locations of Cartesian undersampling artifacts to further improve performance. Lastly, we combined the Feature and E2E VarNets into the Feature-Image (FI) VarNet, to facilitate cross-domain learning and boost accuracy. Reconstructions were evaluated on the fastMRI dataset using standard metrics and clinical scoring by three neuroradiologists. Feature and FI VarNets outperformed the E2E VarNet for 4 $$\times$$ × , 5 $$\times$$ × and 8 $$\times$$ × Cartesian undersampling in all studied metrics. FI VarNet secured second place in the public fastMRI leaderboard for 4 $$\times$$ × Cartesian undersampling, outperforming all open-source models in the leaderboard. Radiologists rated FI VarNet brain reconstructions with higher quality and sharpness than the E2E VarNet reconstructions. FI VarNet excelled in preserving anatomical details, including blood vessels, whereas E2E VarNet discarded or blurred them in some cases. The proposed FI VarNet enhances the reconstruction quality of undersampled MRI and could enable clinically acceptable reconstructions at higher acceleration factors than currently possible.

Background: Reducing Magnetic resonance imaging (MRI) scan time has been an important issue for clinical applications. In order to reduce MRI scan time, imaging acceleration was made possible by undersampling k‐space data. This is achieved by leveraging additional spatial information from multiple, independent receiver coils, thereby reducing the number of sampled k‐space lines. Purpose: The aim of this study is to develop a deep‐learning method for parallel imaging with a reduced number of auto‐calibration signals (ACS) lines in noisy environments. Methods: A cycle interpolator network is developed for robust reconstruction of parallel MRI with a small number of ACS lines in noisy environments. The network estimates missing (unsampled) lines of each coil data, and these estimated missing lines are then utilized to re‐estimate the sampled k‐space lines. In addition, a slice aware reconstruction technique is developed for noise‐robust reconstruction while reducing the number of ACS lines. We conducted an evaluation study using retrospectively subsampled data obtained from three healthy volunteers at 3T MRI, involving three different slice thicknesses (1.5, 3.0, and 4.5 mm) and three different image contrasts (T1w, T2w, and FLAIR). Results: Despite the challenges posed by substantial noise in cases with a limited number of ACS lines and thinner slices, the slice aware cycle interpolator network reconstructs the enhanced parallel images. It outperforms RAKI, effectively eliminating aliasing artifacts. Moreover, the proposed network outperforms GRAPPA and demonstrates the ability to successfully reconstruct brain images even under severe noisy conditions. Conclusions: The slice aware cycle interpolator network has the potential to improve reconstruction accuracy for a reduced number of ACS lines in noisy environments. [ABSTRACT FROM AUTHOR]

Parallel imaging is one of the key MRI technologies that allow reduction of image acquisition time. However, the parallel imaging reconstruction commonly leads to a signal‐to‐noise ratio (SNR) drop evaluated using a so‐called geometrical factor (g‐factor). The g‐factor is minimized by increasing the number of array elements and their spatial diversity. At the same time, increasing the element count requires a decrease in their size. This may lead to insufficient coil loading, an increase in the relative noise contribution from the RF coil itself, and hence SNR reduction. Previously, instead of increasing the channel number, we introduced the concept of electronically switchable time‐varying sensitivities, which was shown to improve parallel imaging performance. In this approach, each reconfigurable receive element supports two spatially distinct sensitivity profiles. In this work, we developed and evaluated a novel eight‐element human head receive‐only reconfigurable coaxial dipole array for human head imaging at 9.4 T. In contrast to the previously reported reconfigurable dipole array, the new design does not include direct current (DC) control wires connected directly to the dipoles. The coaxial cable itself is used to deliver DC voltage to the PIN diodes located at the ends of the antennas. Thus, the novel reconfigurable coaxial dipole design opens a way to scale the dynamic parallel imaging up to a realistic number of channels, that is, 32 and above. The novel array was optimized and tested experimentally, including in vivo studies. It was found that dynamic sensitivity switching provided an 8% lower mean and 33% lower maximum g‐factor (for Ry × Rz = 2 × 2 acceleration) compared with conventional static sensitivities. [ABSTRACT FROM AUTHOR]

We introduce three architecture modifications to enhance the performance of the end-to-end (E2E) variational network (VarNet) for undersampled MRI reconstructions. We first implemented the Feature VarNet, which propagates information throughout the cascades of the network in an N-channel feature-space instead of a 2-channel feature-space. Then, we add an attention layer that utilizes the spatial locations of Cartesian undersampling artifacts to further improve performance. Lastly, we combined the Feature and E2E VarNets into the Feature-Image (FI) VarNet, to facilitate cross-domain learning and boost accuracy. Reconstructions were evaluated on the fastMRI dataset using standard metrics and clinical scoring by three neuroradiologists. Feature and FI VarNets outperformed the E2E VarNet for 4 × , 5 × and 8 × Cartesian undersampling in all studied metrics. FI VarNet secured second place in the public fastMRI leaderboard for 4 × Cartesian undersampling, outperforming all open-source models in the leaderboard. Radiologists rated FI VarNet brain reconstructions with higher quality and sharpness than the E2E VarNet reconstructions. FI VarNet excelled in preserving anatomical details, including blood vessels, whereas E2E VarNet discarded or blurred them in some cases. The proposed FI VarNet enhances the reconstruction quality of undersampled MRI and could enable clinically acceptable reconstructions at higher acceleration factors than currently possible. [ABSTRACT FROM AUTHOR]

To improve the efficiency of multi-coil data compression and recover the compressed image reversibly, increasing the possibility of applying the proposed method to medical scenarios. A deep learning algorithm is employed for MR coil compression in the presented work. The approach introduces a variable augmentation network for invertible coil compression (VAN-ICC). This network utilizes the inherent reversibility of normalizing flow-based models. The aim is to enhance the readability of the sentence and clearly convey the key components of the algorithm. By applying the variable augmentation technology to image/k-space variables from multi-coils, VAN-ICC trains the invertible network by finding an invertible and bijective function, which can map the original data to the compressed counterpart and vice versa. Experiments conducted on both fully-sampled and under-sampled data verified the effectiveness and flexibility of VAN-ICC. Quantitative and qualitative comparisons with traditional non-deep learning-based approaches demonstrated that VAN-ICC carries much higher compression effects. The proposed method trains the invertible network by finding an invertible and bijective function, which improves the defects of traditional coil compression method by utilizing inherent reversibility of normalizing flow-based models. In addition, the application of variable augmentation technology ensures the implementation of reversible networks. In short, VAN-ICC offered a competitive advantage over other traditional coil compression algorithms. [ABSTRACT FROM AUTHOR]

Purpose: To develop a framework that jointly estimates rigid motion and polarizing magnetic field (B0) perturbations (δB0$$ \delta {\mathbf{B}}_{\mathbf{0}} $$) for brain MRI using a single navigator of a few milliseconds in duration, and to additionally allow for navigator acquisition at arbitrary timings within any type of sequence to obtain high‐temporal resolution estimates. Theory and Methods: Methods exist that match navigator data to a low‐resolution single‐contrast image (scout) to estimate either motion orδB0$$ \delta {\mathbf{B}}_{\mathbf{0}} $$. In this work, called QUEEN (QUantitatively Enhanced parameter Estimation from Navigators), we propose combined motion and δB0$$ \delta {\mathbf{B}}_{\mathbf{0}} $$ estimation from a fast, tailored trajectory with arbitrary‐contrast navigator data. To this end, the concept of a quantitative scout (Q‐Scout) acquisition is proposed from which contrast‐matched scout data is predicted for each navigator. Finally, navigator trajectories, contrast‐matched scout, and δB0$$ \delta {\mathbf{B}}_{\mathbf{0}} $$ are integrated into a motion‐informed parallel‐imaging framework. Results: Simulations and in vivo experiments show the need to model δB0$$ \delta {\mathbf{B}}_{\mathbf{0}} $$ to obtain accurate motion parameters estimated in the presence of strong δB0$$ \delta {\mathbf{B}}_{\mathbf{0}} $$. Simulations confirm that tailored navigator trajectories are needed to robustly estimate both motion and δB0$$ \delta {\mathbf{B}}_{\mathbf{0}} $$. Furthermore, experiments show that a contrast‐matched scout is needed for parameter estimation from multicontrast navigator data. A retrospective, in vivo reconstruction experiment shows improved image quality when using the proposed Q‐Scout and QUEEN estimation. Conclusions: We developed a framework to jointly estimate rigid motion parameters and δB0$$ \delta {\mathbf{B}}_{\mathbf{0}} $$ from navigators. Combing a contrast‐matched scout with the proposed trajectory allows for navigator deployment in almost any sequence and/or timing, which allows for higher temporal‐resolution motion and δB0$$ \delta {\mathbf{B}}_{\mathbf{0}} $$ estimates. [ABSTRACT FROM AUTHOR]

Abstract Background This study aimed to determine the optimal scan time for high temporal resolution magnetic resonance (MR) imaging of the liver with gadoxetate disodium injection in combination with compressed sensing (CS) and parallel imaging (PI) techniques under single breath-holding using a 1.5-T MR system. Methods Sixty-two participants underwent multiple arterial phases of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) of the liver with gadoxetate disodium using fat-suppressed GRE T1-weighted imaging—liver acquisition with volume acceleration (LAVA)—in combination with CS and PI using a 1.5-T MR system. Forty-six and 22 participants underwent 6-s and 10-s scans, respectively. Pre-contrast, multiple arterial, portal venous, and hepatobiliary phase images were acquired. Two radiologists evaluated the visual scores for the outline of the liver, inferior right hepatic vein (IRHV), right portal vein, right hepatic artery, appropriateness of the arterial phase, and overall image quality using a 4- or 5-point scale. Results The overall image quality and the image quality of the outline of the liver in the pre-contrast and arterial phases and IRHV in the pre-contrast phase were significantly better (P

Incoherent k-space sampling plays a critical role in Compressed Sensing MRI (CS-MRI) by facilitating efficient utilization of the limited number of acquired samples to reconstruct high-quality images with reduced acquisition time and improved signal-to-noise ratio. Non-Cartesian sampling like radial, spiral, or randomly sampled trajectories are faster and provide more incoherent k-space compared to Cartesian sampling. However, maintaining the reconstruction quality at high acceleration factors is still challenging with non-Cartesian acquisitions. Addressing these challenges typically involves the use of a GeneRalized Autocalibrating Partially Parallel Acquisitions (GRAPPA) operator generated Bunched Phase Encoding data together with a conjugate gradient (CG) reconstruction algorithm, that mimics the functionality of the oscillating gradients required for bunched phase encoding sampling. However, the CG reconstruction method using GRAPPA Operator Gridding (GROG)-generated bunched points is limited to lower acceleration factors ( $AF= 2\sim 6 $ ). In this paper, a novel CS-based reconstruction framework is proposed leveraging enhanced incoherence along with added redundancy of GROG-generated BPE data, to generate artifact-free images from highly undersampled radial acquisitions. In the proposed framework, GRAPPA operator gridding is applied as a first step, on multi-coil undersampled radial data to generate randomly blipped BPE points. The GROG-generated BPE points (non-Cartesian data) are mapped to the Cartesian grid using self-calibrating GRAPPA operator gridding prior to CS-based image reconstruction. To better understand how the GROG-generated bunched points affect the reconstruction quality, sensitivity maps are not explicitly estimated during the CS reconstruction as a first choice. However, incorporating sensitivity maps of multiple channels helps balance data fidelity and regularization; therefore, the performance of the proposed method using coil sensitivity maps has also been investigated. The proposed methods have been validated with both the simulated and in-vivo multi-coil radial datasets. A comparison between the proposed methods and contemporary CS-based reconstruction methods is performed using quantifying parameters such as Artifact Power, Signal-to-Noise ratio, and Root Mean Square Error. The reconstructed images of the proposed method are also subjectively evaluated by expert radiologists. Experimental results show that the proposed methods yield superior performance, both quantitatively and qualitatively at higher acceleration factors ( $ upto~AF= 14$ ) in comparison with the contemporary CS-based image reconstruction techniques.

Magnetic Resonance Spin TomogrAphy in Time‐domain (MR‐STAT) is a multiparametric quantitative MR framework, which allows for simultaneously acquiring quantitative tissue parameters such as T1, T2, and proton density from one single short scan. A typical two‐dimensional (2D) MR‐STAT acquisition uses a gradient‐spoiled, gradient‐echo sequence with a slowly varying RF flip‐angle train and Cartesian readouts, and the quantitative tissue maps are reconstructed by an iterative, model‐based optimization algorithm. In this work, we design a three‐dimensional (3D) MR‐STAT framework based on previous 2D work, in order to achieve better image signal‐to‐noise ratio, higher though‐plane resolution, and better tissue characterization. Specifically, we design a 7‐min, high‐resolution 3D MR‐STAT sequence, and the corresponding two‐step reconstruction algorithm for the large‐scale dataset. To reduce the long acquisition time, Cartesian undersampling strategies such as SENSE are adopted in our transient‐state quantitative framework. To reduce the computational burden, a data‐splitting scheme is designed for decoupling the 3D reconstruction problem into independent 2D reconstructions. The proposed 3D framework is validated by numerical simulations, phantom experiments, and in vivo experiments. High‐quality knee quantitative maps with 0.8 × 0.8 × 1.5 mm3 resolution and bilateral lower leg maps with 1.6 mm isotropic resolution can be acquired using the proposed 7‐min acquisition sequence and the 3‐min‐per‐slice decoupled reconstruction algorithm. The proposed 3D MR‐STAT framework could have wide clinical applications in the future. [ABSTRACT FROM AUTHOR]

Purpose: Parallel imaging and compressed sensing reconstructions of large MRI datasets often have a prohibitive computational cost that bottlenecks clinical deployment, especially for three‐dimensional (3D) non‐Cartesian acquisitions. One common approach is to reduce the number of coil channels actively used during reconstruction as in coil compression. While effective for Cartesian imaging, coil compression inherently loses signal energy, producing shading artifacts that compromise image quality for 3D non‐Cartesian imaging. We propose coil sketching, a general and versatile method for computationally‐efficient iterative MR image reconstruction. Theory and Methods: We based our method on randomized sketching algorithms, a type of large‐scale optimization algorithms well established in the fields of machine learning and big data analysis. We adapt the sketching theory to the MRI reconstruction problem via a structured sketching matrix that, similar to coil compression, considers high‐energy virtual coils obtained from principal component analysis. But, unlike coil compression, it also considers random linear combinations of the remaining low‐energy coils, effectively leveraging information from all coils. Results: First, we performed ablation experiments to validate the sketching matrix design on both Cartesian and non‐Cartesian datasets. The resulting design yielded both improved computatioanal efficiency and preserved signal‐to‐noise ratio (SNR) as measured by the inverse g‐factor. Then, we verified the efficacy of our approach on high‐dimensional non‐Cartesian 3D cones datasets, where coil sketching yielded up to three‐fold faster reconstructions with equivalent image quality. Conclusion: Coil sketching is a general and versatile reconstruction framework for computationally fast and memory‐efficient reconstruction. [ABSTRACT FROM AUTHOR]

Purpose: In MRI, the magnetization of nuclear spins is spatially encoded with linear gradients and radiofrequency receivers sensitivity profiles to produce images, which inherently leads to a long scan time. Cartesian MRI, as widely adopted for clinical scans, can be accelerated with parallel imaging and rapid magnetic field modulation during signal readout. Here, by using an 8‐channel local B0$$ {\mathrm{B}}_0 $$ coil array, the modulation scheme optimized for sampling efficiency is investigated to speed up 2D Cartesian scans. Theory and Methods: An 8‐channel local B0$$ {\mathrm{B}}_0 $$ coil array is made to carry sinusoidal currents during signal readout to accelerate 2D Cartesian scans. An MRI sampling theory based on reproducing kernel Hilbert space is exploited to visualize the efficiency of nonlinear encoding in arbitrary sampling duration. A field calibration method using current monitors for local B0$$ {\mathrm{B}}_0 $$ coils and the ESPIRiT algorithm is proposed to facilitate image reconstruction. Image acceleration with various modulation field shapes, aliasing control, and distinct modulation frequencies are scrutinized to find an optimized modulation scheme. A safety evaluation is conducted. In vivo 2D Cartesian scans are accelerated by the local B0$$ {\mathrm{B}}_0 $$ coils. Results: For 2D Cartesian MRI, the optimal modulation field by this local B0$$ {\mathrm{B}}_0 $$ array converges to a nearly linear gradient field. With the field calibration technique, it accelerates the in vivo scans (i.e., proved safe) by threefold and eightfold free of visible artifacts, without and with SENSE, respectively. Conclusion: The nonlinear encoding analysis tool, the field calibration method, the safety evaluation procedures, and the in vivo reconstructed scans make significant steps to push MRI speed further with the local B0$$ {\mathrm{B}}_0 $$ coil array. [ABSTRACT FROM AUTHOR]

Background: Wave gradient encoding can adequately utilize coil sensitivity profiles to facilitate higher accelerations in parallel magnetic resonance imaging (pMRI). However, there are limitations in mainstream pMRI and a few deep learning (DL) methods for recovering missing data under wave encoding framework: the former is prone to introduce errors from the auto‐calibration signals (ACS) signal acquisition and is time‐consuming, while the latter requires a large amount of training data. Purpose: To tackle the above issues, an untrained neural network (UNN) model incorporating wave‐encoded physical properties and deep generative model, named WDGM, was proposed with additional ACS‐ and training data‐free. Methods: Generally, the proposed method can provide powerful missing data interpolation capability using the wave physical encoding framework and designed UNN to characterize the MR image (k‐space data) priors. Specifically, the MRI reconstruction combining physical wave encoding and elaborate UNN is modeled as a generalized minimization problem. The designation of UNN is driven by the coil sensitivity maps (CSM) smoothness and k‐space linear predictability. And then, the iterative paradigm to recover the full k‐space signal is determined by the projected gradient descent, and the complex computation is unrolled to the network with optimized parameters by the optimizer. Simulated wave encoding and in vivo experiments are exploited to demonstrate the feasibility of the proposed method. The best quantitative metrics RMSE/SSIM/PSNR of 0.0413, 0.9514, and 37.4862 gave competitive results in all experiments with at least six‐fold acceleration, respectively. Results: In vivo experiments of human brains and knees showed that the proposed method can achieve comparable reconstruction quality and even has superiority relative to the comparison, especially at a high resolution of 0.67 mm and fewer ACS. In addition, the proposed method has a higher computational efficiency achieving a computation time of 9.6 s/per slice. Conclusions: The model proposed in this work addresses two limitations of MRI reconstruction in the wave encoding framework. The first is to eliminate the need for ACS signal acquisition to perform the time‐consuming calibration process and to avoid errors such as motion during the acquisition procedure. Furthermore, the proposed method has clinical application friendly without the need to prepare large training datasets, which is difficult in the clinical. All results of the proposed method demonstrate more confidence in both quantitative and qualitative metrics. In addition, the proposed method can achieve higher computational efficiency. [ABSTRACT FROM AUTHOR]

Purpose: A 128‐channel receive‐only array for brain imaging at 7 T was simulated, designed, constructed, and tested within a high‐performance head gradient designed for high‐resolution functional imaging. Methods: The coil used a tight‐fitting helmet geometry populated with 128 loop elements and preamplifiers to fit into a 39 cm diameter space inside a built‐in gradient. The signal‐to‐noise ratio (SNR) and parallel imaging performance (1/g) were measured in vivo and simulated using electromagnetic modeling. The histogram of 1/g factors was analyzed to assess the range of performance. The array's performance was compared to the industry‐standard 32‐channel receive array and a 64‐channel research array. Results: It was possible to construct the 128‐channel array with body noise–dominated loops producing an average noise correlation of 5.4%. Measurements showed increased sensitivity compared with the 32‐channel and 64‐channel array through a combination of higher intrinsic SNR and g‐factor improvements. For unaccelerated imaging, the 128‐channel array showed SNR gains of 17.6% and 9.3% compared to the 32‐channel and 64‐channel array, respectively, at the center of the brain and 42% and 18% higher SNR in the peripheral brain regions including the cortex. For R = 5 accelerated imaging, these gains were 44.2% and 24.3% at the brain center and 86.7% and 48.7% in the cortex. The 1/g‐factor histograms show both an improved mean and a tighter distribution by increasing the channel count, with both effects becoming more pronounced at higher accelerations. Conclusion: The experimental results confirm that increasing the channel count to 128 channels is beneficial for 7T brain imaging, both for increasing SNR in peripheral brain regions and for accelerated imaging. [ABSTRACT FROM AUTHOR]

Objective: To compare examination time and image quality between artificial intelligence (AI)–assisted compressed sensing (ACS) technique and parallel imaging (PI) technique in MRI of patients with nasopharyngeal carcinoma (NPC). Methods: Sixty-six patients with pathologically confirmed NPC underwent nasopharynx and neck examination using a 3.0-T MRI system. Transverse T2-weighted fast spin-echo (FSE) sequence, transverse T1-weighted FSE sequence, post-contrast transverse T1-weighted FSE sequence, and post-contrast coronal T1-weighted FSE were obtained by both ACS and PI techniques, respectively. The signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and duration of scanning of both sets of images analyzed by ACS and PI techniques were compared. The images from the ACS and PI techniques were scored for lesion detection, margin sharpness of lesions, artifacts, and overall image quality using the 5-point Likert scale. Results: The examination time with ACS technique was significantly shorter than that with PI technique (p < 0.0001). The comparison of SNR and CNR showed that ACS technique was significantly superior with PI technique (p < 0.005). Qualitative image analysis showed that the scores of lesion detection, margin sharpness of lesions, artifacts, and overall image quality were higher in the ACS sequences than those in the PI sequences (p < 0.0001). Inter-observer agreement was evaluated for all qualitative indicators for each method, in which the results showed satisfactory-to-excellent agreement (p < 0.0001). Conclusion: Compared with the PI technique, the ACS technique for MR examination of NPC can not only shorten scanning time but also improve image quality. Clinical relevance statement: The artificial intelligence (AI)–assisted compressed sensing (ACS) technique shortens examination time for patients with nasopharyngeal carcinoma, while improving the image quality and examination success rate, which will benefit more patients. Key Points: • Compared with the parallel imaging (PI) technique, the artificial intelligence (AI)–assisted compressed sensing (ACS) technique not only reduced examination time, but also improved image quality. • Artificial intelligence (AI)–assisted compressed sensing (ACS) pulls the state-of-the-art deep learning technique into the reconstruction procedure and helps find an optimal balance of imaging speed and image quality. [ABSTRACT FROM AUTHOR]

Deep learning based parallel imaging (PI) has made great progress in recent years to accelerate MRI. Nevertheless, it still has some limitations: for example, the robustness and flexibility of existing methods are greatly deficient. In this work, we propose a method to explore the k‐space domain learning via robust generative modeling for flexible calibrationless PI reconstruction, coined the weighted k‐space generative model (WKGM). Specifically, WKGM is a generalized k‐space domain model, where the k‐space weighting technology and high‐dimensional space augmentation design are efficiently incorporated for score‐based generative model training, resulting in good and robust reconstructions. In addition, WKGM is flexible and thus can be synergistically combined with various traditional k‐space PI models, which can make full use of the correlation between multi‐coil data and realize calibrationless PI. Even though our model was trained on only 500 images, experimental results with varying sampling patterns and acceleration factors demonstrate that WKGM can attain state‐of‐the‐art reconstruction results with the well learned k‐space generative prior. [ABSTRACT FROM AUTHOR]

Purpose: The combination of SENSE and spiral imaging with fat/water separation enables high temporal efficiency. However, the corresponding computation increases due to the blurring/deblurring operation across the multi‐channel data. This study presents two alternative models to simplify computational complexity in the original full model (model 1). The performances of the models are evaluated in terms of the computation time and reconstruction error. Methods: Two approximated spiral MRI reconstruction models were proposed: the comprehensive blurring before coil operation (model 2) and the regional blurring before coil operation (model 3), respectively, by altering the order of coil‐sensitivity encoding process to distribute signals among the multi‐channel coils. Four subjects were recruited for scanning both fully sampled T1‐ and T2‐weighted brain image data with simulated undersampling for testing the computational efficiency and accuracy on the approximation models. Results: Based on the examples, the computation time can be reduced to 31%–47% using model 2, and to 39%–56% using model 3. The quality of the water image remains unchanged among the three models, whereas the primary difference in image quality is in the fat channel. The fat images from model 3 are consistent with those from model 1, but those from model 2 have higher normalized error, differing by up to 4.8%. Conclusion: Model 2 provides the fastest computation but exhibits higher error in the fat channel, particularly in the high field and with long acquisition window. Model 3, an abridged alternative, is also faster than the full model and can maintain high accuracy in reconstruction. [ABSTRACT FROM AUTHOR]

Purpose: To show that the acoustic noise of spiral MRI can be reduced by derating the gradients with minimal penalty to image quality and scan time, and to illustrate an algorithm for optimal choice of derating parameters. Theory and Methods: Acoustic noise level was measured and compared for various values of maximum gradient amplitude and slew rate for T1‐weighted spin‐echo spiral scans while maintaining image contrast, FOV and resolution, and readout time. A full gradient trajectory and a derated gradient (undersampled) trajectory were chosen for a volunteer scan followed by parallel imaging‐aided reconstruction to illustrate comparable image SNR. Two auto‐derating methods, which prioritize slew rate and gradient amplitude, respectively, were derived using analytical results from the WHIRLED PEAS variant of spiral waveforms and compared in their acoustic noise level under test use cases. Results: Derating the gradients made the scan quieter by 16.6 dB(A) on average than a full gradient trajectory and required an undersampling factor R = 2 in order to maintain scan time, with no appreciable penalty in image SNR. Prioritizing reduced slew rate resulted in maximal loudness reduction. Conclusion: Scanner gradients can often be derated to reduce the acoustic noise for spiral MRI with minimal penalty in scan time and image quality with the help of parallel imaging. An automatic slew‐priority derating method that maximizes loudness reduction is given. [ABSTRACT FROM AUTHOR]

Purpose: To extend the concept of 3D dynamic parallel imaging, we developed a prototype of an electronically reconfigurable dipole array that provides sensitivity alteration along the dipole length. Methods: We developed a radiofrequency array coil consisting of eight reconfigurable elevated‐end dipole antennas. The receive sensitivity profile of each dipole can be electronically shifted toward one or the other end by electrical shortening or lengthening the dipole arms using positive‐intrinsic‐negative‐diode lump‐element switching units. Based on the results of electromagnetic simulations, we built the prototype and tested it at 9.4 T on phantom and healthy volunteer. A modified 3D SENSE reconstruction was used, and geometry factor (g‐factor) calculations were performed to assess the new array coil. Results: Electromagnetic simulations showed that the new array coil was capable of alteration of its receive sensitivity profile along the dipole length. Electromagnetic and g‐factor simulations showed closely agreeing predictions when compared to the measurements. The new dynamically reconfigurable dipole array provided significant improvement in geometry factor compared to static dipoles. We obtained up to 220% improvement for 3 × 2 (Ry × Rz) acceleration compared to the static configuration case in terms of maximum g‐factor and up to 54% in terms of mean g‐factor for the same acceleration. Conclusion: We presented an 8‐element prototype of a novel electronically reconfigurable dipole receive array that permits rapid sensitivity modulations along the dipole axes. Applying dynamic sensitivity modulation during image acquisition emulates two virtual rows of receive elements along the z‐direction, and therefore improves parallel imaging performance for 3D acquisitions. [ABSTRACT FROM AUTHOR]

Purpose: Image quality in accelerated MRI rests on careful selection of various reconstruction parameters. A common yet tedious and error-prone practice is to hand-tune each parameter to attain visually appealing reconstructions. Here, we propose a parameter tuning strategy to automate hybrid parallel imaging (PI) – compressed sensing (CS) reconstructions via low-rank modeling of local k-space neighborhoods (LORAKS) supplemented with sparsity regularization in wavelet and total variation (TV) domains. Methods: For low-rank regularization, we leverage a soft-thresholding operation based on singular values for matrix rank selection in LORAKS. For sparsity regularization, we employ Stein's unbiased risk estimate criterion to select the wavelet regularization parameter and local standard deviation of reconstructions to select the TV regularization parameter. Comprehensive demonstrations are presented on a numerical brain phantom and in vivo brain and knee acquisitions. Quantitative assessments are performed via PSNR, SSIM and NMSE metrics. Results: The proposed hybrid PI-CS method improves reconstruction quality compared to PI-only techniques, and it achieves on par image quality to reconstructions with brute-force optimization of reconstruction parameters. These results are prominent across several different datasets and the range of examined acceleration rates. Conclusion: A data-driven parameter tuning strategy to automate hybrid PI-CS reconstructions is presented. The proposed method achieves reliable reconstructions of accelerated multi-coil MRI datasets without the need for exhaustive hand-tuning of reconstruction parameters.

IntroductionCurrent practice to obtain left ventricular (LV) native and post-contrast T1 and T2 comprises single-slice readouts with multiple breath-holds (BHs). We propose a multi-slice parallel-imaging approach with a 72-channel receive-array to reduce BHs and demonstrate this in healthy subjects and hypertrophic cardiomyopathy (HCM) patients.MethodsA T1/T2 phantom was scanned at 3 T using a 16-channel and a novel 72-channel coil to assess the impact of different coils and acceleration factors on relaxation times. 16–18 healthy participants (8 female, age 28.4 ± 5.1 years) and 3 HCM patients (3 male, age 55.3 ± 4.2 years) underwent cardiac-MRI with the 72-channel coil, using a Modified Look-Locker scan with a shared inversion pulse across 3 slices and a Gradient-Spin-Echo scan. Acceleration was done by sensitivity encoding (SENSE) with accelerations 2, 4, and 6. LV T1 and T2 values were analyzed globally, per slice, and in 16 segments, with SENSE = 2 as the reference.ResultsThe phantom scans revealed no bias between coils and acceleration factors for T1 or T2, except for T2 with SENSE = 2, which resulted in a bias of 8.0 ± 6.7 ms (p

Purpose: MRI is increasingly utilized for image‐guided radiotherapy due to its outstanding soft‐tissue contrast and lack of ionizing radiation. However, geometric distortions caused by gradient nonlinearities (GNLs) limit anatomical accuracy, potentially compromising the quality of tumor treatments. In addition, slow MR acquisition and reconstruction limit the potential for effective image guidance. Here, we demonstrate a deep learning‐based method that rapidly reconstructs distortion‐corrected images from raw k‐space data for MR‐guided radiotherapy applications. Methods: We leverage recent advances in interpretable unrolling networks to develop a Distortion‐Corrected Reconstruction Network (DCReconNet) that applies convolutional neural networks (CNNs) to learn effective regularizations and nonuniform fast Fourier transforms for GNL‐encoding. DCReconNet was trained on a public MR brain dataset from 11 healthy volunteers for fully sampled and accelerated techniques, including parallel imaging (PI) and compressed sensing (CS). The performance of DCReconNet was tested on phantom, brain, pelvis, and lung images acquired on a 1.0T MRI‐Linac. The DCReconNet, CS‐, PI‐and UNet‐based reconstructed image quality was measured by structural similarity (SSIM) and RMS error (RMSE) for numerical comparisons. The computation time and residual distortion for each method were also reported. Results: Imaging results demonstrated that DCReconNet better preserves image structures compared to CS‐ and PI‐based reconstruction methods. DCReconNet resulted in the highest SSIM (0.95 median value) and lowest RMSE (<0.04) on simulated brain images with four times acceleration. DCReconNet is over 10‐times faster than iterative, regularized reconstruction methods. Conclusions: DCReconNet provides fast and geometrically accurate image reconstruction and has the potential for MRI‐guided radiotherapy applications. [ABSTRACT FROM AUTHOR]

Infants and toddlers are a challenging population upon which to perform magnetic resonance imaging (MRI) of the brain, both in research and clinical settings. Because of the large range in head size during the early years of development, paediatric neuro‐MRI requires a radiofrequency (RF) coil, or set of coils, that is tailored to head size to provide the highest image quality. Mitigating techniques must also be employed to reduce and correct for subject motion. This manuscript describes an RF coil with a tailored mechanical–electrical design that can adapt to the head size of 3‐month‐old infants to 3‐year‐old toddlers. The RF coil was designed with tight‐fitting coil elements to improve the signal‐to‐noise ratio (SNR) in comparison with commercially available adult head coils, while simultaneously aiding in immobilization. The coil was designed without visual obstruction to facilitate an unimpeded view of the child's face and the potential application of camera or motion‐tracking systems. Despite the lack of elements over the face, the paediatric coil produced higher SNR over most of the brain compared with adult coils, including more than twofold in the periphery. Acceleration rates of fourfold in each Cartesian direction could be achieved. High SNR allowed for short acquisition times through accelerated imaging protocols and reduced the probability of motion during a scan. Modification of the acquisition protocol, with immobilization of the head through the adjustable coil geometry, and subsequently being combined with a motion‐tracking system, provides a compelling platform for scanning paediatric populations without sedation and with improved image quality. [ABSTRACT FROM AUTHOR]

Purpose: To develop a robust parallel imaging reconstruction method using spatial nulling maps (SNMs). Methods: Parallel reconstruction using null operations (PRUNO) is a k‐space reconstruction method where a k‐space nulling system is derived using null‐subspace bases of the calibration matrix. ESPIRiT reconstruction extends the PRUNO subspace concept by exploiting the linear relationship between signal‐subspace bases and spatial coil sensitivity characteristics, yielding a hybrid‐domain approach. Yet it requires empirical eigenvalue thresholding to mask the coil sensitivity information and is sensitive to signal‐ and null‐subspace division. In this study, we combine the concepts of null‐subspace PRUNO and hybrid‐domain ESPIRiT to provide a more robust reconstruction method that extracts null‐subspace bases of calibration matrix to calculate image‐domain SNMs. Multi‐channel images are reconstructed by solving an image‐domain nulling system formed by SNMs that contain both coil sensitivity and finite image support information, therefore, circumventing the masking‐related procedure. The proposed method was evaluated with multi‐channel 2D brain and knee data and compared to ESPIRiT. Results: The proposed hybrid‐domain method produced quality reconstruction highly comparable to ESPIRiT with optimal manual masking. It involved no masking‐related manual procedure and was tolerant of the actual division of null‐ and signal‐subspace. Spatial regularization could be also readily incorporated to reduce noise amplification as in ESPIRiT. Conclusion: We provide an efficient hybrid‐domain reconstruction method using multi‐channel SNMs that are calculated from coil calibration data. It eliminates the need for coil sensitivity masking and is relatively insensitive to subspace separation, therefore, presenting a robust parallel imaging reconstruction procedure in practice. [ABSTRACT FROM AUTHOR]

Herein, we propose a novel model-based simultaneous multi-slice (SMS) reconstruction method by exploiting data-driven parameter modeling for highly accelerated T1 parameter quantification. We assume that the predefined slice-specific null space operator remains invariant along the parameter dimension. We incorporate the parameter dimension into SMS-HSL to exploit Hankel-structured and Casorati matrices. Given this consideration, the SMS signal is reformulated in k-p space as a constrained optimization problem that exploits rank deficiency for the Hankel-structured matrix and a finite-dimensional basis for a subspace containing slowly evolving signals in the parameter direction. The proposed model-based SMS reconstruction method is validated on in vivo data and compared with state-of-the-art methods with slice acceleration factors of 3 and 5, including an in-plane acceleration factor of 2. The experimental results demonstrate that the proposed method performs effective slice unfolding and signal recovery in reconstructed images and T1 maps with high precision as compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Longer examination time, need for anesthesia in smaller children and the inability of most children to hold their breath are major limitations of MRI in pediatric body imaging. Fortunately, with technical advances, many new and upcoming MRI sequences are overcoming these limitations. Advances in data acquisition and k-space sampling methods have enabled sequences with improved temporal and spatial resolution, and minimal artifacts. Sequences to minimize movement artifacts mainly utilize radial k-space filling, and examples include the stack-of-stars method for T1-weighted imaging and the periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER)/BLADE method for T2-weighted imaging. Similarly, the sequences with improved temporal resolution and the ability to obtain multiple phases in a single breath-hold in dynamic imaging mainly use some form of partial k-space filling method. New sequences use a variable combination of data sampling methods like compressed sensing, golden-angle radial k-space filling, parallel imaging and partial k-space filling to achieve free-breathing, faster sequences that could be useful for pediatric abdominal and thoracic imaging. Simultaneous multi-slice method has improved diffusion-weighted imaging (DWI) with reduction in scan time and artifacts. In this review, we provide an overview of data sampling methods like parallel imaging, compressed sensing, radial k-space sampling, partial k-space sampling and simultaneous multi-slice. This is followed by newer available and upcoming sequences for T1-, T2- and DWI based on these other advances. We also discuss the Dixon method and newer approaches to reducing metal artifacts. [ABSTRACT FROM AUTHOR]

Background: Satisfactory magnetic resonance imaging (MRI) of those patients with involuntary head motion due to brain diseases is essential in avoiding missed diagnosis and guiding treatment. Purpose: To investigate the clinical feasibility of artificial intelligence-assisted compressed sensing single-shot fluid-attenuated inversion recovery (ACS-SS-FLAIR) in evaluating patients with involuntary head motion due to brain diseases, compared with the conventional T2-FLAIR with parallel imaging (PI-FLAIR). Material and Methods: A total of 33 uncooperative patients with brain disease were prospectively enrolled. Two readers independently reviewed images acquired with ACS-SS-FLAIR and PI-FLAIR at a 3.0-T MR scanner. In the aspects of qualitative evaluation of image quality, overall image quality and lesion conspicuity of ACS-SS-FLAIR and PI-FLAIR were assessed and then statistically compared by paired Wilcoxon rank-sum test. For quantitative evaluation, the relative contrast of lesion-to-cerebral parenchyma were calculated and compared. Results: Overall image quality scores of ACS-SS-FLAIR evaluated by two readers were 2.94 ± 0.24 and 2.91 ± 0.29, respectively, both of which were significantly higher than that of PI-FLAIR, respectively (P < 0.001 and <0.001). Lesion conspicuity scores of were 2.74 ± 0.47 and 2.79 ± 0.44, both of which were significantly higher than that of PI-FLAIR, respectively (P < 0.001 and <0.001). In the quantitative evaluation for image quality, the relative contrast of lesion-to-cerebral parenchyma was 0.34 ± 0.09 in the ACS-SS-FLAIR sequence, significantly larger than that in the PI-FLAIR sequence (P = 0.001). Conclusion: The ACS-SS-FLAIR sequence is clinically feasible in the MRI workup of those patients with involuntary head motion due to brain diseases, showing shorter image acquisition time and better image quality compared with conventional PI-FLAIR. [ABSTRACT FROM AUTHOR]

Image quality in accelerated MRI rests on careful selection of various reconstruction parameters. A common yet tedious and error-prone practice is to hand-tune each parameter to attain visually appealing reconstructions. Here, we propose a parameter tuning strategy to automate hybrid parallel imaging (PI) – compressed sensing (CS) reconstructions via low-rank modeling of local k-space neighborhoods (LORAKS) supplemented with sparsity regularization in wavelet and total variation (TV) domains. For low-rank regularization, we leverage a soft-thresholding operation based on singular values for matrix rank selection in LORAKS. For sparsity regularization, we employ Stein's unbiased risk estimate criterion to select the wavelet regularization parameter and local standard deviation of reconstructions to select the TV regularization parameter. Comprehensive demonstrations are presented on a numerical brain phantom and in vivo brain and knee acquisitions. Quantitative assessments are performed via PSNR, SSIM and NMSE metrics. The proposed hybrid PI-CS method improves reconstruction quality compared to PI-only techniques, and it achieves on par image quality to reconstructions with brute-force optimization of reconstruction parameters. These results are prominent across several different datasets and the range of examined acceleration rates. A data-driven parameter tuning strategy to automate hybrid PI-CS reconstructions is presented. The proposed method achieves reliable reconstructions of accelerated multi-coil MRI datasets without the need for exhaustive hand-tuning of reconstruction parameters. [ABSTRACT FROM AUTHOR]

Purpose: To develop a new motion‐resolved real‐time four‐dimensional (4D) flow MRI method, which enables the quantification and visualization of blood flow velocities with three‐directional flow encodings and volumetric coverage without electrocardiogram (ECG) synchronization and respiration control. Methods: An integrated imaging method is presented for real‐time 4D flow MRI, which encompasses data acquisition, image reconstruction, and postprocessing. The proposed method features a specialized continuous (k,t)$$ \left(\mathbf{k},t\right) $$‐space acquisition scheme, which collects two sets of data (i.e., training data and imaging data) in an interleaved manner. By exploiting strong spatiotemporal correlation of 4D flow data, it reconstructs time‐series images from highly‐undersampled (k,t)$$ \left(\mathbf{k},t\right) $$‐space measurements with a low‐rank and subspace model. Through data‐binning‐based postprocessing, it constructs a five‐dimensional dataset (i.e., x‐y‐z‐cardiac‐respiratory), from which respiration‐dependent flow information is further analyzed. The proposed method was evaluated in aortic flow imaging experiments with ten healthy subjects and two patients with atrial fibrillation. Results: The proposed method achieves 2.4 mm isotropic spatial resolution and 34.4 ms temporal resolution for measuring the blood flow of the aorta. For the healthy subjects, it provides flow measurements in good agreement with those from the conventional 4D flow MRI technique. For the patients with atrial fibrillation, it is able to resolve beat‐by‐beat pathological flow variations, which cannot be obtained from the conventional technique. The postprocessing further provides respiration‐dependent flow information. Conclusion: The proposed method enables high‐resolution motion‐resolved real‐time 4D flow imaging without ECG gating and respiration control. It is able to resolve beat‐by‐beat blood flow variations as well as respiration‐dependent flow information. [ABSTRACT FROM AUTHOR]

Purpose: To develop a robust retrospective motion‐correction technique based on repeating k‐space guidance lines for improving motion correction in Cartesian 2D and 3D brain MRI. Methods: The motion guidance lines are inserted into the standard sequence orderings for 2D turbo spin echo and 3D MPRAGE to inform a data consistency–based motion estimation and reconstruction, which can be guided by a low‐resolution scout. The extremely limited number of required guidance lines are repeated during each echo train and discarded in the final image reconstruction. Thus, integration within a standard k‐space acquisition ordering ensures the expected image quality/contrast and motion sensitivity of that sequence. Results: Through simulation and in vivo 2D multislice and 3D motion experiments, we demonstrate that respectively 2 or 4 optimized motion guidance lines per shot enables accurate motion estimation and correction. Clinically acceptable reconstruction times are achieved through fully separable on‐the‐fly motion optimizations (˜1 s/shot) using standard scanner GPU hardware. Conclusion: The addition of guidance lines to scout accelerated motion estimation facilitates robust retrospective motion correction that can be effectively introduced without perturbing standard clinical protocols and workflows. [ABSTRACT FROM AUTHOR]

Background: Echo planar imaging (EPI) suffers from Nyquist ghost caused by eddy currents and other non-ideal factors. Deep learning has received interest for EPI ghost correction.However,large datasets with qualified labels are usually unavailable, especially for the under-sampled EPI data due to the imperfection of traditional ghost correction algorithms. Purpose: To develop a multi-coil synthetic-data-based deep learning method for the Nyquist ghost correction and reconstruction of under-sampled EPI. Methods: Our network is trained purely with synthetic data. The labels of the training samples are generated by combining a public magnetic resonance imaging dataset and a few pre-collected coil sensitivity maps. The input is synthesized by under-sampling (for the accelerated case) and adding phase errors between the even and odd echoes of the label. To bridge the gap between synthetic data and data from real acquisition, linear and non-linear 2D phase errors are considered during the training data generation. Results: The proposed method outperformed the existing mainstream approaches in several experiments. The average ghost-to-signal ratios of our/3-line navigator-based methods were 0.51%/5.36% and 0.42%/8.64% in fully-sampled and under-sampled in vivo experiments, respectively. In the sagittal experiments, our method successfully corrected higher-order and 2D phase errors. Our method also outperformed other reference-based methods on motion-corrupted data. In the simulation experiments, the peak signal-to-noise ratios were 37.6/38.3 dB for 2D linear/non-linear simulated phase errors, indicating that our method was consistently reliable for different kinds of phase errors. Conclusion: Our method achieves superb ghost correction and parallel imaging reconstruction without any calibration information, and can be readily adapted to other EPI-based applications. [ABSTRACT FROM AUTHOR]

Objective: To compare standard (STD-DWI) single-shot echo-planar imaging DWI and simultaneous multislice (SMS) DWI during whole-body positron emission tomography (PET)/MRI regarding acquisition time, image quality, and lesion detection. Methods: Eighty-three adults (47 females, 57%), median age of 64 years (IQR 52–71), were prospectively enrolled from August 2018 to March 2020. Inclusion criteria were (a) abdominal or pelvic tumors and (b) PET/MRI referral from a clinician. Patients were excluded if whole-body acquisition of STD-DWI and SMS-DWI sequences was not completed. The evaluated sequences were axial STD-DWI at b-values 50–400–800 s/mm2 and the apparent diffusion coefficient (ADC), and axial SMS-DWI at b-values 50–300–800 s/mm2 and ADC, acquired with a 3-T PET/MRI scanner. Three radiologists rated each sequence's quality on a five-point scale. Lesion detection was quantified using the anatomic MRI sequences and PET as the reference standard. Regression models were constructed to quantify the association between all imaging outcomes/scores and sequence type. Results: The median whole-body STD-DWI acquisition time was 14.8 min (IQR 14.1–16.0) versus 7.0 min (IQR 6.7–7.2) for whole-body SMS-DWI, p < 0.001. SMS-DWI image quality scores were higher than STD-DWI in the abdomen (OR 5.31, 95% CI 2.76–10.22, p < 0.001), but lower in the cervicothoracic junction (OR 0.21, 95% CI 0.10–0.43, p < 0.001). There was no significant difference in the chest, mediastinum, pelvis, and rectum. STD-DWI detected 276/352 (78%) lesions while SMS-DWI located 296/352 (84%, OR 1.46, 95% CI 1.02–2.07, p = 0.038). Conclusions: In cancer staging and restaging, SMS-DWI abbreviates acquisition while maintaining or improving the diagnostic yield in most anatomic regions. Key Points: • Simultaneous multislice diffusion-weighted imaging enables faster whole-body image acquisition. • Simultaneous multislice diffusion-weighted imaging maintains or improves image quality when compared to single-shot echo-planar diffusion-weighted imaging in most anatomical regions. • Simultaneous multislice diffusion-weighted imaging leads to superior lesion detection. [ABSTRACT FROM AUTHOR]

Since its first observation in the 18th century, the diffusion phenomenon has been actively studied by many researchers. Diffusion-weighted imaging (DWI) is a technique to probe the diffusion of water molecules and create a MR image with contrast based on the local diffusion properties. The DWI pixel intensity is modulated by the hindrance the diffusing water molecules experience. This hindrance is caused by structures in the tissue and reflects the state of the tissue. This characteristic makes DWI a unique and effective tool to gain more insight into the tissue's pathophysiological condition. In the past decades, DWI has made dramatic technical progress, leading to greater acceptance in clinical practice. In the abdominal region, however, acquiring DWI with good quality is challenging because of several reasons, such as large imaging volume, respiratory and other types of motion, and difficulty in achieving homogeneous fat suppression. In this review, we discuss technical advancements from the past decades that help mitigate these problems common in abdominal imaging. We describe the use of scan acceleration techniques such as parallel imaging and compressed sensing to reduce image distortion in echo planar imaging. Then we compare techniques developed to mitigate issues due to respiratory motion, such as free-breathing, respiratory-triggering, and navigator-based approaches. Commonly used fat suppression techniques are also introduced, and their effectiveness is discussed. Additionally, the influence of the abovementioned techniques on image quality is demonstrated. Finally, we discuss the current and future clinical applications of abdominal DWI, such as whole-body DWI, simultaneous multiple-slice excitation, intravoxel incoherent motion, and the use of artificial intelligence. Abdominal DWI has the potential to develop further in the future, thanks to scan acceleration and image quality improvement driven by technological advancements. The accumulation of clinical proof will further drive clinical acceptance. [ABSTRACT FROM AUTHOR]

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 T2w 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. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) is an efficient, non-invasive diagnostic imaging tool for a variety of disorders. In modern MRI systems, the scanning procedure is time-consuming, which leads to problems with patient comfort and causes motion artifacts. Accelerated or parallel MRI has the potential to minimize patient stress as well as reduce scanning time and medical costs. In this paper, a new deep learning MR image reconstruction framework is proposed to provide more accurate reconstructed MR images when under-sampled or aliased images are generated. The proposed reconstruction model is designed based on the conditional generative adversarial networks (CGANs) where the generator network is designed in a form of an encoder–decoder U-Net network. A hybrid spatial and k-space loss function is also proposed to improve the reconstructed image quality by minimizing the L1-distance considering both spatial and frequency domains simultaneously. The proposed reconstruction framework is directly compared when CGAN and U-Net are adopted and used individually based on the proposed hybrid loss function against the conventional L1-norm. Finally, the proposed reconstruction framework with the extended loss function is evaluated and compared against the traditional SENSE reconstruction technique using the evaluation metrics of structural similarity (SSIM) and peak signal to noise ratio (PSNR). To fine-tune and evaluate the proposed methodology, the public Multi-Coil k-Space OCMR dataset for cardiovascular MR imaging is used. The proposed framework achieves a better image reconstruction quality compared to SENSE in terms of PSNR by 6.84 and 9.57 when U-Net and CGAN are used, respectively. Similarly, it demonstrates SSIM of the reconstructed MR images comparable to the one provided by the SENSE algorithm when U-Net and CGAN are used. Comparing cases where the proposed hybrid loss function is used against the cases with the simple L1-norm, the reconstruction performance can be noticed to improve by 6.84 and 9.57 for U-Net and CGAN, respectively. To conclude this, the proposed framework using CGAN provides the best reconstruction performance compared with U-Net or the conventional SENSE reconstruction techniques. The proposed framework seems to be useful for the practical reconstruction of cardiac images since it can provide better image quality in terms of SSIM and PSNR. [ABSTRACT FROM AUTHOR]

Although recent deep energy‐based generative models (EBMs) have shown encouraging results in many image‐generation tasks, how to take advantage of self‐adversarial cogitation in deep EBMs to boost the performance of magnetic resonance imaging (MRI) reconstruction is still desired. With the successful application of deep learning in a wide range of MRI reconstructions, a line of emerging research involves formulating an optimization‐based reconstruction method in the space of a generative model. Leveraging this, a novel regularization strategy is introduced in this article that takes advantage of self‐adversarial cogitation of the deep energy‐based model. More precisely, we advocate alternating learning by a more powerful energy‐based model with maximum likelihood estimation to obtain the deep energy‐based information, represented as a prior image. Simultaneously, implicit inference with Langevin dynamics is a unique property of reconstruction. In contrast to other generative models for reconstruction, the proposed method utilizes deep energy‐based information as the image prior in reconstruction to improve the quality of image. Experimental results imply the proposed technique can obtain remarkable performance in terms of high reconstruction accuracy that is competitive with state‐of‐the‐art methods, and which does not suffer from mode collapse. Algorithmically, an iterative approach is presented to strengthen EBM training with the gradient of energy network. The robustness and reproducibility of the algorithm were also experimentally validated. More importantly, the proposed reconstruction framework can be generalized for most MRI reconstruction scenarios. [ABSTRACT FROM AUTHOR]

Objective. This study aimed at developing a simultaneous multi-segment (SMSeg) imaging technique using a two-dimensional (2D) RF pulse in conjunction with echo planar imaging (EPI) to image multiple focal regions. Approach. The SMSeg technique leveraged periodic replicates of the excitation profile of a 2D RF pulse to simultaneously excite multiple focal regions at different locations. These locations were controlled by rotating and scaling transmit k-space trajectories. The resulting multiple isolated focal regions were projected into a composite 'slice' for display. GRAPPA-based parallel imaging was incorporated into SMSeg by taking advantage of coil sensitivity variations in both the phase-encoded and slice-selection directions. The SMSeg technique was implemented at 3 T in a single-shot gradient-echo EPI sequence and demonstrated in a phantom and human brains for both anatomic imaging and functional imaging. Main results. In both the phantom and the human brain, SMSeg images from three focal regions were simultaneously acquired. SMSeg imaging enabled up to a six-fold acceleration in parallel imaging without causing appreciable residual aliasing artifacts when compared with a conventional gradient-echo EPI sequence with the same acceleration factor. In the functional imaging experiment, BOLD activations associated with a visuomotor task were simultaneously detected in two non-coplanar segments (each with a size of 240 × 30 mm2), corresponding to visual and motor cortices, respectively. Significance. Our study has demonstrated that SMSeg imaging can be a viable method for studying multiple focal regions simultaneously. [ABSTRACT FROM AUTHOR]

Background: High-resolution diffusion-weighted imaging (DWI) is usually achieved through multi-shot acquisitions and parallel imaging-based reconstructions. Multiple POCS (projections onto convex sets) based algorithms have been proposed for DWI reconstructions. However, the slow convergence of POCS and the suboptimal quality of the reconstructed images limit their applications. Purpose: In this study, a revised POCS algorithm for multi-shot DWI reconstruction is proposed based on FISTA (fast iterative shrinkage-thresholding algorithm) to achieve faster convergence and higher accuracy. Methods: In FISTA, the next iteration is computed based on two previous iterations, instead of only the previous one, to improve the convergence speed. This scheme is adopted into the relevant POCS-based algorithms, including POCSENSE (POCS-based sensitivity-encoding), POCSMUSE (POCS-based multiplexed sensitivity-encoding), iPOCSMUSE (iterative POCSMUSE), and POCS-ICE (POCS-enhanced inherent correction of motion-induced phase errors) to address the slow convergence problem. Simulations and in vivo experiments were performed to evaluate the performance of the proposed method. Results: Experimental results show that the proposed method enables faster convergence compared to the original POCS. For example, for a spiral DWI simulation using eight-shot interleaves and having SNR of 20 dB, the iteration number needed for the revised POCS-ICE decreases by about 70% to achieve approximately the same nRMSE level as POCS-ICE. Additionally, it improves image quality in terms of fewer artifacts compared with the original POCS. Conclusions: The revised DWI reconstruction methods can achieve higher convergence rates than the original POCS-based algorithms and higher image quality with the same iteration numbers. As such, the proposed method can serve as a practical and efficient reconstruction method for multi-shot DWI. [ABSTRACT FROM AUTHOR]

Purpose: To develop a deep‐learning‐based image reconstruction framework for reproducible research in MRI. Methods: The BART toolbox offers a rich set of implementations of calibration and reconstruction algorithms for parallel imaging and compressed sensing. In this work, BART was extended by a nonlinear operator framework that provides automatic differentiation to allow computation of gradients. Existing MRI‐specific operators of BART, such as the nonuniform fast Fourier transform, are directly integrated into this framework and are complemented by common building blocks used in neural networks. To evaluate the use of the framework for advanced deep‐learning‐based reconstruction, two state‐of‐the‐art unrolled reconstruction networks, namely the Variational Network and MoDL, were implemented. Results: State‐of‐the‐art deep image‐reconstruction networks can be constructed and trained using BART's gradient‐based optimization algorithms. The BART implementation achieves a similar performance in terms of training time and reconstruction quality compared to the original implementations based on TensorFlow. Conclusion: By integrating nonlinear operators and neural networks into BART, we provide a general framework for deep‐learning‐based reconstruction in MRI. [ABSTRACT FROM AUTHOR]

Purpose: To evaluate an iterative learning approach for enhanced performance of robust artificial‐neural‐networks for k‐space interpolation (RAKI), when only a limited amount of training data (auto‐calibration signals [ACS]) are available for accelerated standard 2D imaging. Methods: In a first step, the RAKI model was tailored for the case of limited training data amount. In the iterative learning approach (termed iterative RAKI [iRAKI]), the tailored RAKI model is initially trained using original and augmented ACS obtained from a linear parallel imaging reconstruction. Subsequently, the RAKI convolution filters are refined iteratively using original and augmented ACS extracted from the previous RAKI reconstruction. Evaluation was carried out on 200 retrospectively undersampled in vivo datasets from the fastMRI neuro database with different contrast settings. Results: For limited training data (18 and 22 ACS lines for R = 4 and R = 5, respectively), iRAKI outperforms standard RAKI by reducing residual artifacts and yields better noise suppression when compared to standard parallel imaging, underlined by quantitative reconstruction quality metrics. Additionally, iRAKI shows better performance than both GRAPPA and standard RAKI in case of pre‐scan calibration with varying contrast between training‐ and undersampled data. Conclusion: RAKI benefits from the iterative learning approach, which preserves the noise suppression feature, but requires less original training data for the accurate reconstruction of standard 2D images thereby improving net acceleration. [ABSTRACT FROM AUTHOR]

Purpose: Through‐time spiral GRAPPA is a real‐time imaging technique that enables ungated, free‐breathing evaluation of the left ventricle. However, it requires a separate fully‐sampled calibration scan to calculate GRAPPA weights. A self‐calibrated through‐time spiral GRAPPA method is proposed that uses a specially designed spiral trajectory with interleaved arm ordering such that consecutive undersampled frames can be merged to form calibration data, eliminating the separate fully‐sampled acquisition. Theory and Methods: The proposed method considers the time needed to acquire data at all points in a GRAPPA calibration kernel when using interleaved arm ordering. Using this metric, simulations were performed to design a spiral trajectory for self‐calibrated GRAPPA. Data were acquired in healthy volunteers using the proposed method and a comparison electrocardiogram‐gated and breath‐held cine scan. Left ventricular functional values and image quality are compared. Results: A 12‐arm spiral trajectory was designed with a temporal resolution of 32.72 ms/cardiac phase with an acceleration factor of 3. Functional values calculated using the proposed method and the gold‐standard method were not statistically significantly different (paired t‐test, p < 0.05). Image quality ratings were lower for the proposed method, with statistically significantly different ratings (Wilcoxon signed rank test, p < 0.05) for two of five image quality aspects rated (level of artifact, blood‐myocardium contrast). Conclusions: A self‐calibrated through‐time spiral GRAPPA reconstruction can enable ungated, free‐breathing evaluation of the left ventricle in 71 s. Functional values are equivalent to a gold‐standard cine technique, although some aspects of image quality may be inferior due to the real‐time nature of the data collection. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) is a widely used medical imaging modality. However, due to the limitations in hardware, scan time, and throughput, it is often clinically challenging to obtain high-quality MR images. In this article, we propose a method of using artificial intelligence to expand the coils to achieve the goal of generating the virtual coils. The main characteristic of our work is utilizing dummy variable technology to expand/extrapolate the receive coils in both image and k-space domains. The high-dimensional information formed by coil expansion is used as the prior information to improve the reconstruction performance of parallel imaging. Two main components are incorporated into the network design, namely variable augmentation technology and sum of squares (SOS) objective function. Variable augmentation provides the network with more high-dimensional prior information, which is helpful for the network to extract the deep feature information of the data. The SOS objective function is employed to solve the deficiency of k-space data training while speeding up convergence. Experimental results demonstrated its great potentials in accelerating parallel imaging reconstruction. [ABSTRACT FROM AUTHOR]

[Display omitted] • Investigating the relationship between parallel imaging and EMI elimination. • Exploring how parallel imaging inspires new methods for EMI elimination. • Demonstrating how tailored convolutional kernel can adapt to varying EMI coupling. Recent advances in ultra-low field MRI have attracted attention from both academic and industrial MR communities for its potential in democratizing MRI applications. One of the most striking features on those advances is shielding-free imaging by actively sensing and eliminating the electromagnetic interference (EMI). In this study, we review the analytical approaches for EMI estimation/elimination, and investigate their theoretical basis and relations with parallel imaging reconstruction. We provide further understanding of the existing approaches, formulating EMI estimation as convolution in k-space or multiplication in spectrum-space. We further propose to use tailored convolutional kernel to adaptively fit the varying EMI coupling across the acquisition window. These methods were evaluated with both simulation study and human brain imaging. The results show that using tailored convolutional kernel can achieve more robust performance against system and acquisition imperfections. [ABSTRACT FROM AUTHOR]