Simultaneous use of individual and joint regularization terms in compressive sensing: Joint reconstruction of multi-channel multi-contrast MRI acquisitions

TranSMS: Transformers for Super-Resolution Calibration in Magnetic Particle Imaging

Magnetic particle imaging (MPI) offers exceptional contrast for magnetic nanoparticles (MNP) at high spatio-temporal resolution. A common procedure in MPI starts with a calibration scan to measure the system matrix (SM), which is then used to set up an inverse problem to reconstruct images of the MNP distribution during subsequent scans. This calibration enables the reconstruction to sensitively account for various system imperfections. Yet time-consuming SM measurements have to be repeated under notable changes in system properties. Here, we introduce a novel deep learning approach for accelerated MPI calibration based on Transformers for SM super-resolution (TranSMS). Low-resolution SM measurements are performed using large MNP samples for improved signal-to-noise ratio efficiency, and the high-resolution SM is super-resolved via model-based deep learning. TranSMS leverages a vision transformer module to capture contextual relationships in low-resolution input images, a dense convolutional module for localizing high-resolution image features, and a data-consistency module to ensure measurement fidelity. Demonstrations on simulated and experimental data indicate that TranSMS significantly improves SM recovery and MPI reconstruction for up to 64-fold acceleration in two-dimensional imaging.

A unified model for reconstruction and R2* mapping of accelerated 7T data using the quantitative recurrent inference machine

Quantitative MRI (qMRI) acquired at the ultra-high field of 7 Tesla has been used in visualizing and analyzing subcortical structures. qMRI relies on the acquisition of multiple images with different scan settings, leading to extended scanning times. Data redundancy and prior information from the relaxometry model can be exploited by deep learning to accelerate the imaging process. We propose the quantitative Recurrent Inference Machine (qRIM), with a unified forward model for joint reconstruction and R₂^*-mapping from sparse data, embedded in a Recurrent Inference Machine (RIM), an iterative inverse problem-solving network. To study the dependency of the proposed extension of the unified forward model to network architecture, we implemented and compared a quantitative End-to-End Variational Network (qE2EVN). Experiments were performed with high-resolution multi-echo gradient echo data of the brain at 7T of a cohort study covering the entire adult life span. The error in reconstructed R₂^* from undersampled data relative to reference data significantly decreased for the unified model compared to sequential image reconstruction and parameter fitting using the RIM. With increasing acceleration factor, an increasing reduction in the reconstruction error was observed, pointing to a larger benefit for sparser data. Qualitatively, this was following an observed reduction of image blurriness in R₂^*-maps. In contrast, when using the U-Net as network architecture, a negative bias in R₂^* in selected regions of interest was observed. Compressed Sensing rendered accurate, but less precise estimates of R₂^*. The qE2EVN showed slightly inferior reconstruction quality compared to the qRIM but better quality than the U-Net and Compressed Sensing. Subcortical maturation over age measured by a linearly increasing interquartile range of R₂^* in the striatum was preserved up to an acceleration factor of 9. With the integrated prior of the unified forward model, the proposed qRIM can exploit the redundancy among repeated measurements and shared information between tasks, facilitating relaxometry in accelerated MRI.

Varying undersampling directions for accelerating multiple acquisition magnetic resonance imaging

In this study, we propose a new sampling strategy for efficiently accelerating multiple acquisition MRI. The new sampling strategy is to obtain data along different phase-encoding directions across multiple acquisitions. The proposed sampling strategy was evaluated in multicontrast MR imaging (T1, T2, proton density) and multiple phase-cycled (PC) balanced steady-state free precession (bSSFP) imaging by using convolutional neural networks with central and random sampling patterns. In vivo MRI acquisitions as well as a public database were used to test the concept. Based on both visual inspection and quantitative analysis, the proposed sampling strategy showed better performance than sampling along the same phase-encoding direction in both multicontrast MR imaging and multiple PC-bSSFP imaging, regardless of sampling pattern (central, random) or datasets (public, retrospective and prospective in vivo). For the prospective in vivo applications, acceleration was performed by sampling along different phase-encoding directions at the time of acquisition with a conventional rectangular field of view, which demonstrated the advantage of the proposed sampling strategy in the real environment. Preliminary trials on compressed sensing (CS) also demonstrated improvement of CS with the proposed idea. Sampling along different phase-encoding directions across multiple acquisitions is advantageous for accelerating multiacquisition MRI, irrespective of sampling pattern or datasets, with further improvement through transfer learning.

Utilizing the Wavelet Transform's Structure in Compressed Sensing

Compressed sensing has empowered quality image reconstruction with fewer data samples than previously thought possible. These techniques rely on a sparsifying linear transformation. The Daubechies wavelet transform is commonly used for this purpose. In this work, we take advantage of the structure of this wavelet transform and identify an affine transformation that increases the sparsity of the result. After inclusion of this affine transformation, we modify the resulting optimization problem to comply with the form of the Basis Pursuit Denoising problem. Finally, we show theoretically that this yields a lower bound on the error of the reconstruction and present results where solving this modified problem yields images of higher quality for the same sampling patterns using both magnetic resonance and optical images.

Optimizing multicontrast MRI reconstruction with shareable feature aggregation and selection

This paper proposes a new method for optimizing feature sharing in deep neural network-based, rapid, multicontrast magnetic resonance imaging (MC-MRI). Using the shareable information of MC images for accelerated MC-MRI reconstruction, current algorithms stack the MC images or features without optimizing the sharing protocols, leading to suboptimal reconstruction results. In this paper, we propose a novel feature aggregation and selection scheme in a deep neural network to better leverage the MC features and improve the reconstruction results. First, we propose to extract and use the shareable information by mapping the MC images into multiresolution feature maps with multilevel layers of the neural network. In this way, the extracted features capture complementary image properties, including local patterns from the shallow layers and semantic information from the deep layers. Then, an explicit selection module is designed to compile the extracted features optimally. That is, larger weights are learned to incorporate the constructive, shareable features; and smaller weights are assigned to the unshareable information. We conduct comparative studies on publicly available T2-weighted and T2-weighted fluid attenuated inversion recovery brain images, and the results show that the proposed network consistently outperforms existing algorithms. In addition, the proposed method can recover the images with high fidelity under 16 times acceleration. The ablation studies are conducted to evaluate the effectiveness of the proposed feature aggregation and selection mechanism. The results and the visualization of the weighted features show that the proposed method does effectively improve the usage of the useful features and suppress useless information, leading to overall enhanced reconstruction results. Additionally, the selection module can zero-out repeated and redundant features and improve network efficiency.

Deep unregistered multi-contrast MRI reconstruction

Multiple magnetic resonance images of different contrasts are normally acquired for clinical diagnosis. Recently, research has shown that the previously acquired multi-contrast (MC) images of the same patient can be used as anatomical prior to accelerating magnetic resonance imaging (MRI). However, current MC-MRI networks are based on the assumption that the images are perfectly registered, which is rarely the case in real-world applications. In this paper, we propose an end-to-end deep neural network to reconstruct highly accelerated images by exploiting the shareable information from potentially misaligned reference images of an arbitrary contrast. Specifically, a spatial transformation (ST) module is designed and integrated into the reconstruction network to align the pre-acquired reference images with the images to be reconstructed. The misalignment is further alleviated by maximizing the normalized cross-correlation (NCC) between the MC images. The visualization of feature maps demonstrates that the proposed method effectively reduces the misalignment between the images for shareable information extraction when applied to the publicly available brain datasets. Additionally, the experimental results on these datasets show the proposed network allows the robust exploitation of shareable information across the misaligned MC images, leading to improved reconstruction results.

APIR4EMC: Autocalibrated parallel imaging reconstruction for extended multi-contrast imaging

PURPOSE

To improve image quality of multi-contrast imaging with the proposed Autocalibrated Parallel Imaging Reconstruction for Extended Multi-Contrast Imaging (APIR4EMC).

METHODS

APIR4EMC reconstructs multi-contrast images in an autocalibrated parallel imaging reconstruction framework by adding contrasts as virtual coils. Compensation of signal evolution along the echo train of different contrasts is performed to improve signal prediction for missing samples. As a proof of concept, we performed prospectively accelerated phantom and in-vivo brain acquisitions with T1, T1-fat saturated (Fatsat), T2, PD, and FLAIR contrasts. The k-space sampling patterns of these acquisitions were jointly optimized. Images were jointly reconstructed with the proposed APIR4EMC method as well as individually with GRAPPA. Root mean square error (RMSE) to fully sampled reference images and g-factor maps were computed for both methods in the phantom experiment. Visual evaluation was performed in the in-vivo experiment.

RESULTS

Compared to GRAPPA, APIR4EMC reduced artifacts and improved SNR of the reconstructed images in the phantom acquisitions. Quantitatively, APIR4EMC substantially reduced noise amplification (g-factor) as well as RMSE compared to GRAPPA. Signal evolution compensation reduced artifacts. In the in-vivo experiments, 1 mm³ isotropic 3D images with contrasts of T1, T1-Fatsat, T2, PD, and FLAIR were acquired in as little as 7.5 min with the acceleration factor of 9. Reconstruction quality was consistent with the phantom results.

CONCLUSION

Compared to single contrast reconstruction with GRAPPA, APIR4EMC reduces artifacts and noise amplification in accelerated multi-contrast imaging.

Joint calibrationless reconstruction of highly undersampled multicontrast MR datasets using a low-rank Hankel tensor completion framework

PURPOSE

To jointly reconstruct highly undersampled multicontrast two-dimensional (2D) datasets through a low-rank Hankel tensor completion framework.

METHODS

A multicontrast Hankel tensor completion (MC-HTC) framework is proposed to exploit the shareable information in multicontrast datasets with respect to their highly correlated image structure, common spatial support, and shared coil sensitivity for joint reconstruction. This is achieved by first organizing multicontrast k-space datasets into a single block-wise Hankel tensor. Subsequent low-rank tensor approximation via higher-order singular value decomposition (HOSVD) uses the image structural correlation by considering different contrasts as virtual channels. Meanwhile, the HOSVD imposes common spatial support and shared coil sensitivity by treating data from different contrasts as from additional k-space kernels. The missing k-space data are then recovered by iteratively performing such low-rank approximation and enforcing data consistency. This joint reconstruction framework was evaluated using multicontrast multichannel 2D human brain datasets (T₁ -weighted, T₂ -weighted, fluid-attenuated inversion recovery, and T₁ -weighted-inversion recovery) of identical image geometry with random and uniform undersampling schemes.

RESULTS

The proposed method offered high acceleration, exhibiting significantly less residual errors when compared with both single-contrast SAKE (simultaneous autocalibrating and k-space estimation) and multicontrast J-LORAKS (joint parallel-imaging-low-rank matrix modeling of local k-space neighborhoods) low-rank reconstruction. Furthermore, the MC-HTC framework was applied uniquely to Cartesian uniform undersampling by incorporating a novel complementary k-space sampling strategy where the phase-encoding direction among different contrasts is orthogonally alternated.

CONCLUSION

The proposed MC-HTC approach presents an effective tensor completion framework to jointly reconstruct highly undersampled multicontrast 2D datasets without coil-sensitivity calibration.

On the regularization of feature fusion and mapping for fast MR multi-contrast imaging via iterative networks

Multi-contrast (MC) Magnetic Resonance Imaging (MRI) of the same patient usually requires long scanning times, despite the images sharing redundant information. In this work, we propose a new iterative network that utilizes the sharable information among MC images for MRI acceleration. The proposed network has reinforced data fidelity control and anatomy guidance through an iterative optimization procedure of Gradient Descent, leading to reduced uncertainties and improved reconstruction results. Through a convolutional network, the new method incorporates a learnable regularization unit that is capable of extracting, fusing, and mapping shareable information among different contrasts. Specifically, a dilated inception block is proposed to promote multi-scale feature extractions and increase the receptive field diversity for contextual information incorporation. Lastly, an optimal MC information feeding protocol is built through the design of a complementary feature extractor block. Comprehensive experiments demonstrated the superiority of the proposed network, both qualitatively and quantitatively.

Accelerated high-resolution free-breathing 3D whole-heart T2-prepared black-blood and bright-blood cardiovascular magnetic resonance

BACKGROUND

The free-breathing 3D whole-heart T2-prepared Bright-blood and black-blOOd phase SensiTive inversion recovery (BOOST) cardiovascular magnetic resonance (CMR) sequence was recently proposed for simultaneous bright-blood coronary CMR angiography and black-blood late gadolinium enhancement (LGE) imaging. This sequence enables simultaneous visualization of cardiac anatomy, coronary arteries and fibrosis. However, high-resolution (< 1.4 × 1.4 × 1.4 mm3) fully-sampled BOOST requires long acquisition times of ~ 20 min.

METHODS

In this work, we propose to extend a highly efficient respiratory-resolved motion-corrected reconstruction framework (XD-ORCCA) to T2-prepared BOOST to enable high-resolution 3D whole-heart coronary CMR angiography and black-blood LGE in a clinically feasible scan time. Twelve healthy subjects were imaged without contrast injection (pre-contrast BOOST) and 10 patients with suspected cardiovascular disease were imaged after contrast injection (post-contrast BOOST). A quantitative analysis software was used to compare accelerated pre-contrast BOOST against the fully-sampled counterpart (vessel sharpness and length of the left and right coronary arteries). Moreover, three cardiologists performed diagnostic image quality scoring for clinical 2D LGE and both bright- and black-blood 3D BOOST imaging using a 4-point scale (1-4, non-diagnostic-fully diagnostic). A two one-sided test of equivalence (TOST) was performed to compare the pre-contrast BOOST images. Nonparametric TOST was performed to compare post-contrast BOOST image quality scores.

RESULTS

The proposed method produces images from 3.8 × accelerated non-contrast-enhanced BOOST acquisitions with comparable vessel length and sharpness to those obtained from fully- sampled scans in healthy subjects. Moreover, in terms of visual grading, the 3D BOOST LGE datasets (median 4) and the clinical 2D counterpart (median 3.5) were found to be statistically equivalent (p < 0.05). In addition, bright-blood BOOST images allowed for visualization of the proximal and middle left anterior descending and right coronary sections with high diagnostic quality (mean score > 3.5).

CONCLUSIONS

The proposed framework provides high-resolution 3D whole-heart BOOST images from a single free-breathing acquisition in ~ 7 min.

Tomographic Field Free Line Magnetic Particle Imaging With an Open-Sided Scanner Configuration

Superparamagnetic iron oxide nanoparticles (SPIONs) have a high potential for use in clinical diagnostic and therapeutic applications. In vivo distribution of SPIONs can be imaged with the Magnetic Particle Imaging (MPI) method, which uses an inhomogeneous magnetic field with a field free region (FFR). The spatial distribution of the SPIONs are obtained by scanning the FFR inside the field of view (FOV) and sensing SPION related magnetic field disturbance. MPI magnets can be configured to generate a field free point (FFP), or a field free line (FFL) to scan the FOV. FFL scanners provide more sensitivity, and are also more suitable for scanning large regions compared to FFP scanners. Interventional procedures will benefit greatly from FFL based open magnet configurations. Here, we present the first open-sided MPI system that can electronically scan the FOV with an FFL to generate tomographic MPI images. Magnetic field measurements show that FFL can be rotated electronically in the horizontal plane and translated in three dimensions to generate 3D MPI images. Using the developed scanner, we obtained 2D images of dot and cylinder phantoms with varying iron concentrations between 11 [Formula: see text]/ml and 770 [Formula: see text]/ml. We used a measurement based system matrix image reconstruction method that minimizes l₁ -norm and total variation in the images. Furthermore, we present 2D imaging results of two 4 mm-diameter vessel phantoms with 0% and 75% stenosis. The experiments show high quality imaging results with a resolution down to 2.5 mm for a relatively low gradient field of 0.6 T/m.

Trends in Compressive Sensing for EEG Signal Processing Applications

The tremendous progress of big data acquisition and processing in the field of neural engineering has enabled a better understanding of the patient's brain disorders with their neural rehabilitation, restoration, detection, and diagnosis. An integration of compressive sensing (CS) and neural engineering emerges as a new research area, aiming to deal with a large volume of neurological data for fast speed, long-term, and energy-saving purposes. Furthermore, electroencephalography (EEG) signals for brain-computer interfaces (BCIs) have shown to be very promising, with diverse neuroscience applications. In this review, we focused on EEG-based approaches which have benefited from CS in achieving fast and energy-saving solutions. In particular, we examine the current practices, scientific opportunities, and challenges of CS in the growing field of BCIs. We emphasized on summarizing major CS reconstruction algorithms, the sparse basis, and the measurement matrix used in CS to process the EEG signal. This literature review suggests that the selection of a suitable reconstruction algorithm, sparse basis, and measurement matrix can help to improve the performance of current CS-based EEG studies. In this paper, we also aim at providing an overview of the reconstruction free CS approach and the related literature in the field. Finally, we discuss the opportunities and challenges that arise from pushing the integration of the CS framework for BCI applications.