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.

BACKGROUND: 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.
UNASSIGNED: AI-CS in MRI improves patient care by shortening scan times, reducing patient discomfort and anxiety, and produces high quality images for accurate diagnosis.

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.

OBJECTIVE: 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).
CONCLUSIONS: 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.

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.
CONCLUSIONS: 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.

OBJECTIVE: 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.

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.

UNASSIGNED: 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.
UNASSIGNED: 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).
UNASSIGNED: 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).
UNASSIGNED: CS4 strikes a good balance in 4D flow between flow quantifications and scan time, which could be recommended for routine clinical use.

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.

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.