High on sparsity: Interbin compensation of cardiac motion for improved assessment of left-ventricular function using 5D whole-heart MRI.

PURPOSE: Cardiac magnetic resonance is the gold standard for evaluating left-ventricular ejection fraction (LVEF). Standard protocols, however, can be inefficient, facing challenges due to significant operator and patient involvement. Although the free-running framework (FRF) addresses these challenges, the potential of the extensive data it collects remains underutilized. Therefore, we propose to leverage the large amount of data collected by incorporating interbin cardiac motion compensation into FRF (FRF-MC) to improve both image quality and LVEF measurement accuracy, while reducing the sensitivity to user-defined regularization parameters. METHODS: FRF-MC consists of several steps: data acquisition, self-gating signal extraction, deformation field estimations, and motion-resolved reconstruction with interbin cardiac motion compensation. FRF-MC was compared with the original 5D-FRF method using LVEF and several image-quality metrics. The cardiac regularization weight ( λ c $$ {\lambda}_c $$ ) was optimized for both methods by maximizing image quality without compromising LVEF measurement accuracy. Evaluations were performed in numerical simulations and in 9 healthy participants. In vivo images were assessed by blinded expert reviewers and compared with reference standard 2D-cine images. RESULTS: Both in silico and in vivo results revealed that FRF-MC outperformed FRF in terms of image quality and LVEF accuracy. FRF-MC reduced temporal blurring, preserving detailed anatomy even at higher cardiac regularization weights, and led to more accurate LVEF measurements. Optimized λ c $$ {\lambda}_c $$ produced accurate LVEF for both methods compared with the 2D-cine reference (FRF-MC: 0.59% [-7.2%, 6.0%], p = 0.47; FRF: 0.86% [-8.5%, 6.7%], p = 0.36), but FRF-MC resulted in superior image quality (FRF-MC: 2.89 ± 0.58, FRF: 2.11 ± 0.47; p < 10-3). CONCLUSION: Incorporating interbin cardiac motion compensation significantly improved image quality, supported higher cardiac regularization weights without compromising LVEF measurement accuracy, and reduced sensitivity to user-defined regularization parameters.

A Complex Quasi-Newton Proximal Method for Image Reconstruction in Compressed Sensing MRI.

Model-based methods are widely used for reconstruction in compressed sensing (CS) magnetic resonance imaging (MRI), using regularizers to describe the images of interest. The reconstruction process is equivalent to solving a composite optimization problem. Accelerated proximal methods (APMs) are very popular approaches for such problems. This paper proposes a complex quasi-Newton proximal method (CQNPM) for the wavelet and total variation based CS MRI reconstruction. Compared with APMs, CQNPM requires fewer iterations to converge but needs to compute a more challenging proximal mapping called weighted proximal mapping (WPM). To make CQNPM more practical, we propose efficient methods to solve the related WPM. Numerical experiments on reconstructing non-Cartesian MRI data demonstrate the effectiveness and efficiency of CQNPM.

A hybrid deep image prior and compressed sensing reconstruction method for highly accelerated 3D coronary magnetic resonance angiography.

Introduction: High-resolution whole-heart coronary magnetic resonance angiography (CMRA) often suffers from unreasonably long scan times, rendering imaging acceleration highly desirable. Traditional reconstruction methods used in CMRA rely on either hand-crafted priors or supervised learning models. Although the latter often yield superior reconstruction quality, they require a large amount of training data and memory resources, and may encounter generalization issues when dealing with out-of-distribution datasets. Methods: To address these challenges, we introduce an unsupervised reconstruction method that combines deep image prior (DIP) with compressed sensing (CS) to accelerate 3D CMRA. This method incorporates a slice-by-slice DIP reconstruction and 3D total variation (TV) regularization, enabling high-quality reconstruction under a significant acceleration while enforcing continuity in the slice direction. We evaluated our method by comparing it to iterative SENSE, CS-TV, CS-wavelet, and other DIP-based variants, using both retrospectively and prospectively undersampled datasets. Results: The results demonstrate the superiority of our 3D DIP-CS approach, which improved the reconstruction accuracy relative to the other approaches across both datasets. Ablation studies further reveal the benefits of combining DIP with 3D TV regularization, which leads to significant improvements of image quality over pure DIP-based methods. Evaluation of vessel sharpness and image quality scores shows that DIP-CS improves the quality of reformatted coronary arteries. Discussion: The proposed method enables scan-specific reconstruction of high-quality 3D CMRA from a five-minute acquisition, without relying on fully-sampled training data or placing a heavy burden on memory resources.

CRNN-Refined Spatiotemporal Transformer for Dynamic MRI reconstruction.

Magnetic Resonance Imaging (MRI) plays a pivotal role in modern clinical practice, providing detailed anatomical visualization with exceptional spatial resolution and soft tissue contrast. Dynamic MRI, aiming to capture both spatial and temporal characteristics, faces challenges related to prolonged acquisition times and susceptibility to motion artifacts. Balancing spatial and temporal resolutions becomes crucial in real-world clinical scenarios. In the realm of dynamic MRI reconstruction, while Convolutional Recurrent Neural Networks (CRNNs) struggle with long-range dependencies, CRNNs require extensive iterations, impacting efficiency. Transformers, known for their effectiveness in high-dimensional imaging, are underexplored in dynamic MRI reconstruction. Additionally, prevailing algorithms fall short of achieving superior results in demanding generative reconstructions at high acceleration rates. This research proposes a novel approach for dynamic MRI reconstruction, named CRNN-Refined Spatiotemporal Transformer Network (CST-Net). The spatiotemporal Transformer initiates reconstruction, modeling temporal and spatial correlations, followed by refinement using the CRNN. This integration mitigates inaccuracies caused by damaged frames and reduces CRNN iterations, enhancing computational efficiency without compromising reconstruction quality. Our study compares the performance of the proposed CST-Net at 6 × and 12 × undersampling rates, showcasing its superiority over existing algorithms. Particularly, in challenging 25× generative reconstructions, the CST-Net outperforms current methods. The comparison includes experiments under both radial and Cartesian undersampling patterns. In conclusion, CST-Net successfully addresses the limitations inherent in existing generative reconstruction algorithms, thereby paving the way for further exploration and optimization of Transformer-based approaches in dynamic MRI reconstruction. Code and Datasets can be available: https://github.com/XWangBin/CST-Net.

Accelerated model-based T1, T2* and proton density mapping using a Bayesian approach with automatic hyperparameter estimation.

PURPOSE: To achieve automatic hyperparameter estimation for the model-based recovery of quantitative MR maps from undersampled data, we propose a Bayesian formulation that incorporates the signal model and sparse priors among multiple image contrasts. THEORY: We introduce a novel approximate message passing framework "AMP-PE" that enables the automatic and simultaneous recovery of hyperparameters and quantitative maps. METHODS: We employed the variable-flip-angle method to acquire multi-echo measurements using gradient echo sequence. We explored undersampling schemes to incorporate complementary sampling patterns across different flip angles and echo times. We further compared AMP-PE with conventional compressed sensing approaches such as the l 1 $$ {l}_1 $$ -norm minimization, PICS and other model-based approaches such as GraSP, MOBA. RESULTS: Compared to conventional compressed sensing approaches such as the l 1 $$ {l}_1 $$ -norm minimization and PICS, AMP-PE achieved superior reconstruction performance with lower errors in T 2 ∗ $$ {\mathrm{T}}_2^{\ast } $$ mapping and comparable performance in T 1 $$ {\mathrm{T}}_1 $$ and proton density mappings. When compared to other model-based approaches including GraSP and MOBA, AMP-PE exhibited greater robustness and outperformed GraSP in reconstruction error. AMP-PE offers faster speed than MOBA. AMP-PE performed better than MOBA at higher sampling rates and worse than MOBA at a lower sampling rate. Notably, AMP-PE eliminates the need for hyperparameter tuning, which is a requisite for all the other approaches. CONCLUSION: AMP-PE offers the benefits of model-based recovery with the additional key advantage of automatic hyperparameter estimation. It works adeptly in situations where ground-truth is difficult to obtain and in clinical environments where it is desirable to automatically adapt hyperparameters to individual protocol, scanner and patient.

Multi-angle speed-of-sound imaging with sparse sampling to characterize medical tissue properties.

Medical Speed-of-sound (SoS) imaging, which can characterize medical tissue properties better by quantifying their different SoS, is an effective imaging method compared with conventional B-mode ultrasound imaging. As a commonly used diagnostic instrument, a hand-held array probe features convenient and quick inspection. However, artifacts will occur in the single-angle SoS imaging, resulting in indistinguishable tissue boundaries. In order to build a high-quality SoS image, a number of raw data are needed, which will bring difficulties to data storage and processing. Compressed sensing (CS) theory offers theoretical support to the feasibility that a sparse signal can be rebuilt with random but less sampling data. In this study, we proposed an SoS reconstruction method based on CS theory to process signals obtained from a hand-held linear array probe with a passive reflector positioned on the opposite side. The SoS reconstruction method consists of three parts. Firstly, a sparse transform basis is selected appropriately for a sparse representation of the original signal. Then, considering the mathematical principles of SoS imaging, the ray-length matrix is used as a sparse measurement matrix to observe the original signal, which represents the length of the acoustic propagation path. Finally, the orthogonal matching pursuit algorithm is introduced for image reconstruction. The experimental result of the phantom proves that SoS imaging can clearly distinguish tissues that show similar echogenicity in B-mode ultrasound imaging. The simulation and experimental results show that our proposed method holds promising potential for reconstructing precision SoS images with fewer signal samplings, transmission, and storage.

Compressed sensing reconstruction for high-SNR, rapid dissolved 129Xe gas exchange MRI.

PURPOSE: Three-dimensional hyperpolarized 129Xe gas exchange imaging suffers from low SNR and long breath-holds, which could be improved using compressed sensing (CS). The purpose of this work was to assess whether gas exchange ratio maps are quantitatively preserved in CS-accelerated dissolved-phase 129Xe imaging and to investigate the feasibility of CS-dissolved 129Xe imaging with reduced-cost natural abundance (NA) xenon. METHODS: 129Xe gas exchange imaging was performed at 1.5 T with a multi-echo spectroscopic imaging sequence. A CS reconstruction with an acceleration factor of 2 was compared retrospectively with conventional gridding reconstruction in a cohort of 16 healthy volunteers, 5 chronic obstructive pulmonary disease patients, and 23 patients who were hospitalized following COVID-19 infection. Metrics of comparison included normalized mean absolute error, mean gas exchange ratio, and red blood cell (RBC) image SNR. Dissolved 129Xe CS imaging with NA xenon was assessed in 4 healthy volunteers. RESULTS: CS reconstruction enabled acquisition time to be halved, and it reduced background noise. Median RBC SNR increased from 6 (2-18) to 11 (2-100) with CS, and there was strong agreement between CS and gridding mean ratio map values (R2 = 0.99). Image fidelity was maintained for gridding RBC SNR > 5, but below this, normalized mean absolute error increased nonlinearly with decreasing SNR. CS increased the mean SNR of NA 129Xe images 3-fold. CONCLUSION: CS reconstruction of dissolved 129Xe imaging improved image quality with decreased scan time, while preserving key gas exchange metrics. This will benefit patients with breathlessness and/or low gas transfer and shows promise for NA-dissolved 129Xe imaging.

Impact of artificial intelligence assisted compressed sensing technique on scan time and image quality in musculoskeletal MRI - A systematic review.

INTRODUCTION: Magnetic Resonance Imaging (MRI) has revolutionized the diagnosis and treatment of musculoskeletal disorders. Parallel imaging (PI) and compressed sensing (CS) techniques reduce scan time, but higher acceleration factors decrease image quality. Artificial intelligence has enhanced MRI reconstructions by integrating deep learning algorithms. Therefore, the study aims to review the impact of Artificial intelligence-assisted compressed sensing (AI-CS) and acceleration factors on scan time and image quality in musculoskeletal MRI. METHODS: Database searches were completed across PubMed, Scopus, CINAHL, Web of Science, Cochrane Library, and Embase to identify relevant articles focusing on the application of AI-CS in musculoskeletal MRI between 2022 and 2024. We utilized the Preferred Reporting Items for Systematic Reviews and Meta-analysis guidelines to extract data from the selected studies. RESULTS: Nine articles were included for the final review, with a total sample size of 730 participants. Of these, seven articles were rated as high, while two articles were considered to be of moderate quality. MRI examination with AI-CS showed scan time reduction of 18.9-38.8% for lumbar spine, 38-40% for shoulder, 54-75% for knee and 53-63% for ankle. CONCLUSIONS: AI-CS showed a significant reduction in scan time and improved image quality for 2D and 3D sequences in musculoskeletal MRI compared with PI and CS. Determining the optimal acceleration factor necessary to achieve images with higher image quality compared to traditional PI techniques is required before clinical implementation. Higher acceleration factors currently lead to reduced image scores, although advancements in AI-CS are expected to address the limitation. IMPLICATIONS OF PRACTICE: AI-CS in MRI improves patient care by shortening scan times, reducing patient discomfort and anxiety, and produces high quality images for accurate diagnosis.

Radiomic feature reliability of amide proton transfer-weighted MR images acquired with compressed sensing at 3T.

Compressed sensing (CS) is a novel technique for MRI acceleration. The purpose of this paper was to assess the effects of CS on the radiomic features extracted from amide proton transfer-weighted (APTw) images. Brain tumor MRI data of 40 scans were studied. Standard images using sensitivity encoding (SENSE) with an acceleration factor (AF) of 2 were used as the gold standard, and APTw images using SENSE with CS (CS-SENSE) with an AF of 4 were assessed. Regions of interest (ROIs), including normal tissue, edema, liquefactive necrosis, and tumor, were manually drawn, and the effects of CS-SENSE on radiomics were assessed for each ROI category. An intraclass correlation coefficient (ICC) was first calculated for each feature extracted from APTw images with SENSE and CS-SENSE for all ROIs. Different filters were applied to the original images, and the effects of these filters on the ICCs were further compared between APTw images with SENSE and CS-SENSE. Feature deviations were also provided for a more comprehensive evaluation of the effects of CS-SENSE on radiomic features. The ROI-based comparison showed that most radiomic features extracted from CS-SENSE-APTw images and SENSE-APTw images had moderate or greater reliabilities (ICC ≥ 0.5) for all four ROIs and all eight image sets with different filters. Tumor showed significantly higher ICCs than normal tissue, edema, and liquefactive necrosis. Compared to the original images, filters (such as Exponential or Square) may improve the reliability of radiomic features extracted from CS-SENSE-APTw and SENSE-APTw images.

Dynamic contrast enhanced MRI of the head and neck region using a VIBE sequence with Cartesian undersampling and compressed sensing.

OBJECTIVES: Compressed sensing allows for image reconstruction from sparsely sampled k-space data, which is particularly useful in dynamic contrast enhanced MRI (DCE-MRI). The aim of the study was to assess the diagnostic value of a volume-interpolated 3D T1-weighted spoiled gradient-echo sequence with variable density Cartesian undersampling and compressed sensing (CS) for head and neck MRI. METHODS: Seventy-one patients with clinical indications for head and neck MRI were included in this study. DCE-MRI was performed at 3 Tesla magnet using CS-VIBE (variable density undersampling, temporal resolution 3.4 s, slice thickness 1 mm). Image quality was compared to standard Cartesian VIBE. Three experienced readers independently evaluated image quality and lesion conspicuity on a 5-point Likert scale and determined the DCE-derived time intensity curve (TIC) types. RESULTS: CS-VIBE demonstrated higher image quality scores compared to standard VIBE with respect to overall image quality (4.3 ± 0.6 vs. 4.2 ± 0.7, p = 0.682), vessel contour (4.6 ± 0.4 vs. 4.4 ± 0.6, p < 0.001), muscle contour (4.4 ± 0.5 vs. 4.5 ± 0.6, p = 0.302), lesion conspicuity (4.5 ± 0.7 vs. 4.3 ± 0.9, p = 0.024) and showed improved fat saturation (4.8 ± 0.3 vs. 3.8 ± 0.4, p < 0.001) and movement artifacts were significantly reduced (4.6 ± 0.6 vs. 3.7 ± 0.7, p < 0.001). Standard VIBE outperformed CS-VIBE in the delineation of pharyngeal mucosa (4.2 ± 0.5 vs. 4.6 ± 0.6, p < 0.001). Lesion size in cases where a focal lesion was identified was similar for all readers for CS-VIBE and standard VIBE (p = 0.101). TIC curve assessment showed good interobserver agreement (k=0.717). CONCLUSION: CS-VIBE with variable density Cartesian undersampling allows for DCE-MRI of the head and neck region with diagnostic, high image quality and high temporal resolution.

LD-CSNet: A latent diffusion-based architecture for perceptual Compressed Sensing.

Compressed Sensing (CS) is a groundbreaking paradigm in image acquisition, challenging the constraints of the Nyquist-Shannon sampling theorem. This enables high-quality image reconstruction using a minimal number of measurements. Neural Networks' potent feature induction capabilities enable advanced data-driven CS methods to achieve high-fidelity image reconstruction. However, achieving satisfactory reconstruction performance, particularly in terms of perceptual quality, remains challenging at extremely low sampling rates. To tackle this challenge, we introduce a novel two-stage image CS framework based on latent diffusion, named LD-CSNet. In the first stage, we utilize an autoencoder pre-trained on a large dataset to represent natural images as low-dimensional latent vectors, establishing prior knowledge distinct from sparsity and effectively reducing the dimensionality of the solution space. In the second stage, we employ a conditional diffusion model for maximum likelihood estimates in the latent space. This is supported by a measurement embedding module designed to encode measurements, making them suitable for a denoising network. This guides the generation process in reconstructing low-dimensional latent vectors. Finally, the image is reconstructed using a pre-trained decoder. Experimental results across multiple public datasets demonstrate LD-CSNet's superior perceptual quality and robustness to noise. It maintains fidelity and visual quality at lower sampling rates. Research findings suggest the promising application of diffusion models in image CS. Future research can focus on developing more appropriate models for the first stage.

Fast and motion-robust saturation transfer MRI with inherent B0 correction using rosette trajectories and compressed sensing.

PURPOSE: To implement rosette readout trajectories with compressed sensing reconstruction for fast and motion-robust CEST and magnetization transfer contrast imaging with inherent correction of B0 inhomogeneity. METHODS: A pulse sequence was developed for fast saturation transfer imaging using a stack of rosette trajectories with a higher sampling density near the k-space center. Each rosette lobe was segmented into two halves to generate dual-echo images. B0 inhomogeneities were estimated using the phase difference between the images and corrected subsequently. The rosette-based imaging was evaluated in comparison to a fully sampled Cartesian trajectory and demonstrated on CEST phantoms (creatine solutions and egg white) and healthy volunteers at 3 T. RESULTS: Compared with the conventional Cartesian acquisition, compressed sensing reconstructed rosette images provided image quality with overall higher contrast-to-noise ratio and significantly faster readout time. Accurate B0 map estimation was achieved from the rosette acquisition with a negligible bias of 0.01 Hz between the rosette and dual-echo Cartesian gradient echo B0 maps, using the latter as ground truth. The water-saturation spectra (Z-spectra) and amide proton transfer weighted signals obtained from the rosette-based sequence were well preserved compared with the fully sampled data, both in the phantom and human studies. CONCLUSIONS: Fast, motion-robust, and inherent B0-corrected CEST and magnetization transfer contrast imaging using rosette trajectories could improve subject comfort and compliance, contrast-to-noise ratio, and provide inherent B0 homogeneity information. This work is expected to significantly accelerate the translation of CEST-MRI into a robust, clinically viable approach.

LUCMT: Learnable under-sampling and reconstructed network with cross multi-head attention transformer for accelerating MR image reconstruction.

BACKGROUND AND OBJECTIVE: As a widely used technique for Magnetic Resonance Image (MRI) acceleration, compressed sensing MRI involves two main issues: designing an effective sampling strategy and reconstructing the image from significantly under-sampled K-space data. In this paper, an innovative approach is proposed to address these two challenges simultaneously. METHODS: A novel MRI reconstruction method, termed as LUCMT, is implemented by integrating a learnable under-sampling strategy with a reconstruction network based on the Cross Multi-head Attention Transformer. In contrast to conventional static sampling methods, the proposed adaptive sampling scheme is processed optimally by learning the optimal sampling technique, which involves binarizing the sampling pattern by a sigmoid function and computing gradients by backpropagation. And the reconstruction network is designed by using CS-MRI depth unfolding network that incorporates a Cross Multi-head Attention (CMA) module with inertial and gradient descent terms. RESULTS: T1 brain MR images from the FastMRI dataset are used to validate the performance of the proposed method. A series of experiments are conducted to validate the superior performance of our proposed network in terms of quantitative metrics and visual quality. Compared with other state-of-the-art reconstruction methods, LUCMT achieves better reconstruction performances with more accurate details. Specifically, LUCMT achieves PSNR and SSIM results of 41.87/0.9749, 46.64/0.9868, 50.41/0.9924, and 53.51/0.9955 at sampling rates of 10 %, 20 %, 30 %, and 40 %, respectively. CONCLUSIONS: The proposed LUCMT method can provide a promising way for generating optimal under-sampling mask and accelerating MRI reconstruction accurately.

Discrete Illumination-Based Compressed Ultrafast Photography for High-Fidelity Dynamic Imaging.

Compressed ultrafast photography (CUP) can capture irreversible or difficult-to-repeat dynamic scenes at the imaging speed of more than one billion frames per second, which is obtained by compressive sensing-based image reconstruction from a compressed 2D image through the discretization of detector pixels. However, an excessively high data compression ratio in CUP severely degrades the image reconstruction quality, thereby restricting its ability to observe ultrafast dynamic scenes with complex spatial structures. To address this issue, a discrete illumination-based CUP (DI-CUP) with high fidelity is reported. In DI-CUP, the dynamic scenes are loaded into an ultrashort laser pulse train with controllable sub-pulse number and time interval, thus the data compression ratio, as well as the overlap between adjacent frames, is greatly decreased and flexibly controlled through the discretization of dynamic scenes based on laser pulse train illumination, and high-fidelity image reconstruction can be realized within the same observation time window. Furthermore, the superior performance of DI-CUP is verified by observing femtosecond laser-induced ablation dynamics and plasma channel evolution, which are hardly resolved in the spatial structures using conventional CUP. It is anticipated that DI-CUP will be widely and dependably used in the real-time observations of various ultrafast dynamics.

Computer simulation and modeling of glow discharge optical emission coded aperture elemental mapping.

BACKGROUND: Elemental mapping (EM) yields necessary insights into mechanisms of interest in solid samples across multiple disciplines. There are several EM techniques available but long acquisition time is a common limitation. Glow discharge optical emission spectroscopy (GDOES) allows direct quantitative multi-EM at very high throughput (∼10 s s) when coupled to traditional hyperspectral imaging (HSI) techniques. However, GDOES consumes the sample via sputtering, such that traditional HSI sequential scanning requirements lead to loss of information/resolution, which is compounded for multi-EM and limits nanomaterials analysis. Thus, there is a need for faster HSI to enable GDOES multi-EM of nanoscale materials. RESULTS: Here, a new technique is described, Glow discharge Optical emission Coded Aperture elemental Mapping (GOCAM), that takes advantage of compressive coded aperture spectral imaging to enable multi-EM in a single camera exposure. In this first phase of development, computer model simulations were implemented to study the effects of coded aperture parameters on data fidelity, which showed the best fidelity is achieved at smaller mask element sizes and transmittance of 60 %. In addition, SeSCIGPU demonstrated the best fidelity performance compared to several compressed sensing reconstruction algorithms, including TwIST, GAP-TV, SeSCICPU, and ADMM-TV, as evaluated by studying the effects of varying the corresponding hyperparameters. SIGNIFICANCE: This study shows GOCAM's feasibility and provides a starting point for the second phase hardware development currently underway. GOCAM's potential to allow multi-EM from solid surfaces in a fraction of a second will be particularly enabling for nanostructured materials characterization.

Compressed SENSitivity Encoding (SENSE): Qualitative and Quantitative Analysis.

BACKGROUND: This study aimed to qualitatively and quantitatively evaluate T1-TSE, T2-TSE and 3D FLAIR sequences obtained with and without Compressed-SENSE technique by assessing the contrast (C), the contrast-to-noise ratio (CNR) and the signal-to-noise ratio (SNR). METHODS: A total of 142 MRI images were acquired: 69 with Compressed-SENSE and 73 without Compressed-SENSE. All the MRI images were contoured, spatially aligned and co-registered using 3D Slicer Software. Two radiologists manually drew 12 regions of interests on three different structures of CNS: white matter (WM), grey matter (GM) and cerebrospinal fluid (CSF). RESULTS: C values were significantly higher in Compressed-SENSE T1-TSE compared to No Compressed-SENSE T1-TSE for three different structures of the CNS. C values were also significantly lower for Compressed-SENSE 3D FLAIR and Compressed-SENSE T2-TSE compared to the corresponding No Compressed-SENSE scans. While CNR values did not significantly differ in GM-WM between Compressed-SENSE and No Compressed-SENSE for the 3D FLAIR and T1-TSE sequences, the differences in GM-CSF and WM-CSF were always statistically significant. CONCLUSION: Compressed-SENSE for 3D T2 FLAIR, T1w and T2w sequences enables faster MRI acquisition, reducing scan time and maintaining equivalent image quality. Compressed-SENSE is very useful in specific medical conditions where lower SAR levels are required without sacrificing the acquisition of helpful diagnostic sequences.

Observation of intracranial artery and venous sinus hemodynamics using compressed sensing-accelerated 4D flow MRI: performance at different acceleration factors.

Objective: To investigate the feasibility and performance of 4D flow MRI accelerated by compressed sensing (CS) for the hemodynamic quantification of intracranial artery and venous sinus. Materials and methods: Forty healthy volunteers were prospectively recruited, and 20 volunteers underwent 4D flow MRI of cerebral artery, and the remaining volunteers underwent 4D flow MRI of venous sinus. A series of 4D flow MRI was acquired with different acceleration factors (AFs), including sensitivity encoding (SENSE, AF = 4) and CS (AF = CS4, CS6, CS8, and CS10) at a 3.0 T MRI scanner. The hemodynamic parameters, including flow rate, mean velocity, peak velocity, max axial wall shear stress (WSS), average axial WSS, max circumferential WSS, average circumferential WSS, and 3D WSS, were calculated at the internal carotid artery (ICA), transverse sinus (TS), straight sinus (SS), and superior sagittal sinus (SSS). Results: Compared to the SENSE4 scan, for the left ICA C2, mean velocity measured by CS8 and CS10 groups, and 3D WSS measured by CS6, CS8, and CS10 groups were underestimated; for the right ICA C2, mean velocity measured by CS10 group, and 3D WSS measured by CS8 and CS10 groups were underestimated; for the right ICA C4, mean velocity measured by CS10 group, and 3D WSS measured by CS8 and CS10 groups were underestimated; and for the right ICA C7, mean velocity and 3D WSS measured by CS8 and CS10 groups, and average axial WSS measured by CS8 group were also underestimated (all p < 0.05). For the left TS, max axial WSS and 3D WSS measured by CS10 group were significantly underestimated (p = 0.032 and 0.003). Similarly, for SS, mean velocity, peak velocity, average axial WSS measured by the CS8 and CS10 groups, max axial WSS measured by CS6, CS8, and CS10 groups, and 3D WSS measured by CS10 group were significantly underestimated compared to the SENSE4 scan (p = 0.000-0.021). The hemodynamic parameters measured by CS4 group had only minimal bias and great limits of agreement compared to conventional 4D flow (SENSE4) in the ICA and every venous sinus (the max/min upper limit to low limit of the 95% limits of agreement = 11.4/0.03 to 0.004/-5.7, 14.4/0.05 to -0.03/-9.0, 12.6/0.04 to -0.03/-9.4, 16.8/0.04 to 0.6/-14.1; the max/min bias = 5.0/-1.2, 3.5/-1.4, 4.5/-1.1, 6.6/-4.0 for CS4, CS6, CS8, and CS10, respectively). Conclusion: CS4 strikes a good balance in 4D flow between flow quantifications and scan time, which could be recommended for routine clinical use.

Evaluation of 3D T1-weighted spoiled gradient echo MR image quality using artificial intelligence image reconstruction techniques in the pediatric brain.

PURPOSE: To assess image quality and diagnostic confidence of 3D T1-weighted spoiled gradient echo (SPGR) MRI using artificial intelligence (AI) reconstruction. MATERIALS AND METHODS: This prospective, IRB-approved study enrolled 50 pediatric patients (mean age = 11.8 ± 3.1 years) undergoing clinical brain MRI. In addition to standard of care (SOC) compressed SENSE (CS = 2.5), 3D T1-weighted SPGR images were obtained with higher CS acceleration factors (5 and 8) to evaluate the ability of AI reconstruction to improve image quality and reduce scan time. Images were reviewed independently on dedicated research PACS workstations by two neuroradiologists. Quantitative analysis of signal intensities to calculate apparent grey and white matter signal to noise (aSNR) and grey-white matter apparent contrast to noise ratios (aCNR) was performed. RESULTS: AI improved overall image quality compared to standard CS reconstruction in 35% (35/100) of evaluations in CS = 2.5 (average scan time = 221 ± 6.9 s), 100% (46/46) of CS = 5 (average scan time = 113.3 ± 4.6 s) and 94% (47/50) of CS = 8 (average scan time = 74.1 ± 0.01 s). Quantitative analysis revealed significantly higher grey matter aSNR, white matter aSNR and grey-white matter aCNR with AI reconstruction compared to standard reconstruction for CS 5 and 8 (all p-values < 0.001), however not for CS 2.5. CONCLUSIONS: AI reconstruction improved overall image quality and gray-white matter qualitative and quantitative aSNR and aCNR in highly accelerated (CS = 5 and 8) 3D T1W SPGR images in the majority of pediatric patients.

Accelerating multipool CEST MRI of Parkinson's disease using deep learning-based Z-spectral compressed sensing.

PURPOSE: To develop a deep learning-based approach to reduce the scan time of multipool CEST MRI for Parkinson's disease (PD) while maintaining sufficient prediction accuracy. METHOD: A deep learning approach based on a modified one-dimensional U-Net, termed Z-spectral compressed sensing (CS), was proposed to recover dense Z-spectra from sparse ones. The neural network was trained using simulated Z-spectra generated by the Bloch equation with various parameter settings. Its feasibility and effectiveness were validated through numerical simulations and in vivo rat brain experiments, compared with commonly used linear, pchip, and Lorentzian interpolation methods. The proposed method was applied to detect metabolism-related changes in the 6-hydroxydopamine PD model with multipool CEST MRI, including APT, CEST@2 ppm, nuclear Overhauser enhancement, direct saturation, and magnetization transfer, and the prediction performance was evaluated by area under the curve. RESULTS: The numerical simulations and in vivo rat-brain experiments demonstrated that the proposed method could yield superior fidelity in retrieving dense Z-spectra compared with existing methods. Significant differences were observed in APT, CEST@2 ppm, nuclear Overhauser enhancement, and direct saturation between the striatum regions of wild-type and PD models, whereas magnetization transfer exhibited no significant difference. Receiver operating characteristic analysis demonstrated that multipool CEST achieved better predictive performance compared with individual pools. Combined with Z-spectral CS, the scan time of multipool CEST MRI can be reduced to 33% without distinctly compromising prediction accuracy. CONCLUSION: The integration of Z-spectral CS with multipool CEST MRI can enhance the prediction accuracy of PD and maintain the scan time within a reasonable range.

High Resolution TOF-MRA Using Compressed Sensing-based Deep Learning Image Reconstruction for the Visualization of Lenticulostriate Arteries: A Preliminary Study.

PURPOSE: To investigate the visibility of the lenticulostriate arteries (LSAs) in time-of-flight (TOF)-MR angiography (MRA) using compressed sensing (CS)-based deep learning (DL) image reconstruction by comparing its image quality with that obtained by the conventional CS algorithm. METHODS: Five healthy volunteers were included. High-resolution TOF-MRA images with the reduction (R)-factor of 1 were acquired as full-sampling data. Images with R-factors of 2, 4, and 6 were then reconstructed using CS-DL and conventional CS (the combination of CS and sensitivity conceding; CS-SENSE) reconstruction, respectively. In the quantitative assessment, the number of visible LSAs (identified by two radiologists), length of each depicted LSA (evaluated by one radiological technologist), and normalized mean squared error (NMSE) value were assessed. In the qualitative assessment, the overall image quality and the visibility of the peripheral LSA were visually evaluated by two radiologists. RESULTS: In the quantitative assessment of the DL-CS images, the number of visible LSAs was significantly higher than those obtained with CS-SENSE in the R-factors of 4 and 6 (Reader 1) and in the R-factor of 6 (Reader 2). The length of the depicted LSAs in the DL-CS images was significantly longer in the R-factor 6 compared to the CS-SENSE result. The NMSE value in CS-DL was significantly lower than in CS-SENSE for R-factors of 4 and 6. In the qualitative assessment of DL-CS images, the overall image quality was significantly higher than that obtained with CS-SENSE in the R-factors 4 and 6 (Reader 1) and in the R-factor 4 (Reader 2). The visibility of the peripheral LSA was significantly higher than that shown by CS-SENSE in all R-factors (Reader 1) and in the R-factors 2 and 4 (Reader 2). CONCLUSION: CS-DL reconstruction demonstrated preserved image quality for the depiction of LSAs compared to the conventional CS-SENSE when the R-factor is elevated.