k-t PCA: temporally constrained k-t BLAST reconstruction using principal component analysis

K-t PCA accelerated in-plane balanced steady-state free precession phase-contrast (PC-SSFP) for all-in-one diastolic function evaluation

PURPOSE

Diastolic function evaluation requires estimates of early and late diastolic mitral filling velocities (E and A) and of mitral annulus tissue velocity (e'). We aimed to develop an MRI method for simultaneous all-in-one diastolic function evaluation in a single scan by generating a 2D phase-contrast (PC) sequence with balanced steady-state free precession (bSSFP) contrast (PC-SSFP). E and A could then be measured with PC, and e' estimated by valve tracking on the magnitude images, using an established deep learning framework.

METHODS

Our PC-SSFP used in-plane flow-encoding, with zeroth and first moment nulling over each TR. For further acceleration, different k-t principal component analysis (PCA) methods were investigated with both retrospective and prospective undersampling. PC-SSFP was compared to separate balanced SSFP cine and PC-gradient echo acquisitions in phantoms and in 10 healthy subjects.

RESULTS

Phantom experiments showed that PC-SSFP measured accurate velocities compared to PC-gradient echo (r = 0.98 for a range of pixel-wise velocities -80 cm/s to 80 cm/s). In subjects, PC-SSFP generated high SNR and myocardium-blood contrast, and excellent agreement for E (limits of agreement [LOA] 0.8 ± 2.4 cm/s, r = 0.98), A (LOA 2.5 ± 4.1 cm/s, r = 0.97), and e' (LOA 0.3 ± 2.6 cm/s, r = 1.00), versus the standard methods. The best k-t PCA approach processed the complex difference data and substituted in raw k-space data. With prospective k-t PCA acceleration, higher frame rates were achieved (50 vs. 25 frames per second without k-t PCA), yielding a 13% higher e'.

CONCLUSION

The proposed PC-SSFP method achieved all-in-one diastolic function evaluation.

The future of CMR: All-in-one vs. real-time CMR (Part 2)

Cardiac Magnetic Resonance (CMR) protocols can be lengthy and complex, which has driven the research community to develop new technologies to make these protocols more efficient and patient-friendly. Two different approaches to improving CMR have been proposed, specifically "all-in-one" CMR, where several contrasts and/or motion states are acquired simultaneously, and "real-time" CMR, in which the examination is accelerated to avoid the need for breathholding and/or cardiac gating. The goal of this two-part manuscript is to describe these two different types of emerging rapid CMR protocols. To this end, the vision of all-in-one and real-time imaging are described, along with techniques which have been devised and tested along the pathway of clinical implementation. The pros and cons of the different methods are presented, and the remaining open needs of each are detailed. Part 1 tackles the "All-in-One" approaches, and Part 2 focuses on the "Real-Time" approaches along with an overall summary of these emerging methods.

A deep unrolled neural network for real-time MRI-guided brain intervention

Accurate navigation and targeting are critical for neurological interventions including biopsy and deep brain stimulation. Real-time image guidance further improves surgical planning and MRI is ideally suited for both pre- and intra-operative imaging. However, balancing spatial and temporal resolution is a major challenge for real-time interventional MRI (i-MRI). Here, we proposed a deep unrolled neural network, dubbed as LSFP-Net, for real-time i-MRI reconstruction. By integrating LSFP-Net and a custom-designed, MR-compatible interventional device into a 3 T MRI scanner, a real-time MRI-guided brain intervention system is proposed. The performance of the system was evaluated using phantom and cadaver studies. 2D/3D real-time i-MRI was achieved with temporal resolutions of 80/732.8 ms, latencies of 0.4/3.66 s including data communication, processing and reconstruction time, and in-plane spatial resolution of 1 × 1 mm2. The results demonstrated that the proposed method enables real-time monitoring of the remote-controlled brain intervention, and showed the potential to be readily integrated into diagnostic scanners for image-guided neurosurgery.

Subspace Model-Assisted Deep Learning for Improved Image Reconstruction

Image reconstruction from limited and/or sparse data is known to be an ill-posed problem and a priori information/constraints have played an important role in solving the problem. Early constrained image reconstruction methods utilize image priors based on general image properties such as sparsity, low-rank structures, spatial support bound, etc. Recent deep learning-based reconstruction methods promise to produce even higher quality reconstructions by utilizing more specific image priors learned from training data. However, learning high-dimensional image priors requires huge amounts of training data that are currently not available in medical imaging applications. As a result, deep learning-based reconstructions often suffer from two known practical issues: a) sensitivity to data perturbations (e.g., changes in data sampling scheme), and b) limited generalization capability (e.g., biased reconstruction of lesions). This paper proposes a new method to address these issues. The proposed method synergistically integrates model-based and data-driven learning in three key components. The first component uses the linear vector space framework to capture global dependence of image features; the second exploits a deep network to learn the mapping from a linear vector space to a nonlinear manifold; the third is an unrolling-based deep network that captures local residual features with the aid of a sparsity model. The proposed method has been evaluated with magnetic resonance imaging data, demonstrating improved reconstruction in the presence of data perturbation and/or novel image features. The method may enhance the practical utility of deep learning-based image reconstruction.

Universal generative modeling in dual domains for dynamic MRI

Dynamic magnetic resonance image reconstruction from incomplete k-space data has generated great research interest due to its ability to reduce scan time. Nevertheless, the reconstruction problem remains a thorny issue due to its ill posed nature. Recently, diffusion models, especially score-based generative models, have demonstrated great potential in terms of algorithmic robustness and flexibility of utilization. Moreover, a unified framework through the variance exploding stochastic differential equation is proposed to enable new sampling methods and further extend the capabilities of score-based generative models. Therefore, by taking advantage of the unified framework, we propose a k-space and image dual-domain collaborative universal generative model (DD-UGM), which combines the score-based prior with a low-rank regularization penalty to reconstruct highly under-sampled measurements. More precisely, we extract prior components from both image and k-space domains via a universal generative model and adaptively handle these prior components for faster processing while maintaining good generation quality. Experimental comparisons demonstrate the noise reduction and detail preservation abilities of the proposed method. Moreover, DD-UGM can reconstruct data of different frames by only training a single frame image, which reflects the flexibility of the proposed model.

Comparison between compressed sensing and segmented cine cardiac magnetic resonance: a meta-analysis

PURPOSE

Highly accelerated compressed sensing cine has allowed for quantification of ventricular function in a single breath hold. However, compared to segmented breath hold techniques, there may be underestimation or overestimation of LV volumes. Furthermore, a heterogeneous sample of techniques have been used in volunteers and patients for pre-clinical and clinical use. This can complicate individual comparisons where small, but statistically significant differences exist in left ventricular morphological and/or functional parameters. This meta-analysis aims to provide a comparison of conventional cine versus compressed sensing based reconstruction techniques in patients and volunteers.

METHODS

Two investigators performed systematic searches for eligible studies using PubMed/MEDLINE and Web of Science to identify studies published 1/1/2010-3/1/2021. Ultimately, 15 studies were included for comparison between compressed sensing cine and conventional imaging.

RESULTS

Compared to conventional cine, there were small, statistically significant overestimation of LV mass, underestimation of stroke volume and LV end diastolic volume (mean difference 2.65 g [CL 0.57-4.73], 2.52 mL [CL 0.73-4.31], and 2.39 mL [CL 0.07-4.70], respectively). Attenuated differences persisted across studies using prospective gating (underestimated stroke volume) and non-prospective gating (underestimation of stroke volume, overestimation of mass). There were no significant differences in LV volumes or LV mass with high or low acceleration subgroups in reference to conventional cine except slight underestimation of ejection fraction among high acceleration studies. Reduction in breath hold acquisition time ranged from 33 to 64%, while reduction in total scan duration ranged from 43 to 97%.

CONCLUSION

LV volume and mass assessment using compressed sensing CMR is accurate compared to conventional parallel imaging cine.

A low-rank deep image prior reconstruction for free-breathing ungated spiral functional CMR at 0.55 T and 1.5 T

OBJECTIVE

This study combines a deep image prior with low-rank subspace modeling to enable real-time (free-breathing and ungated) functional cardiac imaging on a commercial 0.55 T scanner.

MATERIALS AND METHODS

The proposed low-rank deep image prior (LR-DIP) uses two u-nets to generate spatial and temporal basis functions that are combined to yield dynamic images, with no need for additional training data. Simulations and scans in 13 healthy subjects were performed at 0.55 T and 1.5 T using a golden angle spiral bSSFP sequence with images reconstructed using [Formula: see text]-ESPIRiT, low-rank plus sparse (L + S) matrix completion, and LR-DIP. Cartesian breath-held ECG-gated cine images were acquired for reference at 1.5 T. Two cardiothoracic radiologists rated images on a 1-5 scale for various categories, and LV function measurements were compared.

RESULTS

LR-DIP yielded the lowest errors in simulations, especially at high acceleration factors (R [Formula: see text] 8). LR-DIP ejection fraction measurements agreed with 1.5 T reference values (mean bias - 0.3% at 0.55 T and - 0.2% at 1.5 T). Compared to reference images, LR-DIP images received similar ratings at 1.5 T (all categories above 3.9) and slightly lower at 0.55 T (above 3.4).

CONCLUSION

Feasibility of real-time functional cardiac imaging using a low-rank deep image prior reconstruction was demonstrated in healthy subjects on a commercial 0.55 T scanner.

Low-rank motion correction for accelerated free-breathing first-pass myocardial perfusion imaging

PURPOSE

Develop a novel approach for accelerated 2D free-breathing myocardial perfusion via low-rank motion-corrected (LRMC) reconstructions.

METHODS

Myocardial perfusion imaging requires high spatial and temporal resolution, despite scan time constraints. Here, we incorporate LRMC models into the reconstruction-encoding operator, together with high-dimensionality patch-based regularization, to produce high quality, motion-corrected myocardial perfusion series from free-breathing acquisitions. The proposed framework estimates beat-to-beat nonrigid respiratory (and any other incidental) motion and the dynamic contrast subspace from the actual acquired data, which are then incorporated into the proposed LRMC reconstruction. LRMC was compared with iterative SENSitivity Encoding (SENSE) (itSENSE) and low-rank plus sparse (LpS) reconstruction in 10 patients based on image-quality scoring and ranking by two clinical expert readers.

RESULTS

LRMC achieved significantly improved results relative to itSENSE and LpS in terms of image sharpness, temporal coefficient of variation, and expert reader evaluation. Left ventricle image sharpness was approximately 75%, 79%, and 86% for itSENSE, LpS and LRMC, respectively, indicating improved image sharpness for the proposed approach. Corresponding temporal coefficient of variation results were 23%, 11% and 7%, demonstrating improved temporal fidelity of the perfusion signal with the proposed LRMC. Corresponding clinical expert reader scores (1-5, from poor to excellent image quality) were 3.3, 3.9 and 4.9, demonstrating improved image quality with the proposed LRMC, in agreement with the automated metrics.

CONCLUSION

LRMC produces motion-corrected myocardial perfusion in free-breathing acquisitions with substantially improved image quality when compared with iterative SENSE and LpS reconstructions.

Acquisition sequences and reconstruction methods for fast chemical exchange saturation transfer imaging

Chemical exchange saturation transfer (CEST) imaging is an emerging molecular magnetic resonance imaging (MRI) technique that has been developed and employed in numerous diseases. Based on the unique saturation transfer principle, a family of CEST-detectable biomolecules in vivo have been found capable of providing valuable diagnostic information. However, CEST MRI needs a relatively long scan time due to the common long saturation labeling module and typical acquisition of multiple frequency offsets and signal averages, limiting its widespread clinical applications. So far, a plethora of imaging schemes and techniques has been developed to accelerate CEST MRI. In this review, the key acquisition and reconstruction methods for fast CEST imaging are summarized from a practical and systematic point of view. The first acquisition sequence section describes the major development of saturation schemes, readout patterns, ultrafast z-spectroscopy, and saturation-editing techniques for rapid CEST imaging. The second reconstruction method section lists the important advances of parallel imaging, compressed sensing, sparsity in the z-spectrum, and algorithms beyond the Fourier transform for speeding up CEST MRI.

Single-heartbeat cardiac cine imaging via jointly regularized nonrigid motion-corrected reconstruction

The aim of the current study was to develop a novel approach for 2D breath-hold cardiac cine imaging from a single heartbeat, by combining cardiac motion-corrected reconstructions and nonrigidly aligned patch-based regularization. Conventional cardiac cine imaging is obtained via motion-resolved reconstructions of data acquired over multiple heartbeats. Here, we achieve single-heartbeat cine imaging by incorporating nonrigid cardiac motion correction into the reconstruction of each cardiac phase, in conjunction with a motion-aligned patch-based regularization. The proposed Motion-Corrected CINE (MC-CINE) incorporates all acquired data into the reconstruction of each (motion-corrected) cardiac phase, resulting in a better posed problem than motion-resolved approaches. MC-CINE was compared with iterative sensitivity encoding (itSENSE) and Extra-Dimensional Golden Angle Radial Sparse Parallel (XD-GRASP) in 14 healthy subjects in terms of image sharpness, reader scoring (range: 1-5) and reader ranking (range: 1-9) of image quality, and single-slice left ventricular assessment. MC-CINE was significantly superior to both itSENSE and XD-GRASP using 20 heartbeats, two heartbeats, and one heartbeat. Iterative SENSE, XD-GRASP, and MC-CINE achieved a sharpness of 74%, 74%, and 82% using 20 heartbeats, and 53%, 66%, and 82% with one heartbeat, respectively. The corresponding results for reader scoring were 4.0, 4.7, and 4.9 with 20 heartbeats, and 1.1, 3.0, and 3.9 with one heartbeat. The corresponding results for reader ranking were 5.3, 7.3, and 8.6 with 20 heartbeats, and 1.0, 3.2, and 5.4 with one heartbeat. MC-CINE using a single heartbeat presented nonsignificant differences in image quality to itSENSE with 20 heartbeats. MC-CINE and XD-GRASP at one heartbeat both presented a nonsignificant negative bias of less than 2% in ejection fraction relative to the reference itSENSE. It was concluded that the proposed MC-CINE significantly improves image quality relative to itSENSE and XD-GRASP, enabling 2D cine from a single heartbeat.

Deep Learning-Based Reconstruction for Cardiac MRI: A Review

Cardiac magnetic resonance (CMR) is an essential clinical tool for the assessment of cardiovascular disease. Deep learning (DL) has recently revolutionized the field through image reconstruction techniques that allow unprecedented data undersampling rates. These fast acquisitions have the potential to considerably impact the diagnosis and treatment of cardiovascular disease. Herein, we provide a comprehensive review of DL-based reconstruction methods for CMR. We place special emphasis on state-of-the-art unrolled networks, which are heavily based on a conventional image reconstruction framework. We review the main DL-based methods and connect them to the relevant conventional reconstruction theory. Next, we review several methods developed to tackle specific challenges that arise from the characteristics of CMR data. Then, we focus on DL-based methods developed for specific CMR applications, including flow imaging, late gadolinium enhancement, and quantitative tissue characterization. Finally, we discuss the pitfalls and future outlook of DL-based reconstructions in CMR, focusing on the robustness, interpretability, clinical deployment, and potential for new methods.

Latest Advances in Image Acceleration: All Dimensions are Fair Game

Magnetic resonance imaging (MRI) is a versatile modality that can generate high-resolution images with a variety of tissue contrasts. However, MRI is a slow technique and requires long acquisition times, which increase with higher temporal and spatial resolution and/or when multiple contrasts and large volumetric coverage is required. In order to speedup MR data acquisition, several approaches have been introduced in the literature. Most of these techniques acquire less data than required and exploit intrinsic redundancies in the MR images to recover the information that was not sampled. This article presents a review of MR acquisition and reconstruction methods that have exploited redundancies in the temporal, spatial, and contrast/parametric dimensions to accelerate image data acquisition, focusing on cardiac and abdominal MR imaging applications. The review describes how each of these dimensions has been separately exploited for speeding up MR acquisition to then discuss more advanced techniques where multiple dimensions are exploited together for further reducing scan times. Finally, future directions for multidimensional image acceleration and remaining technical challenges are discussed. EVIDENCE LEVEL: 5 TECHNICAL EFFICACY: 1.

Signal intensity informed multi-coil encoding operator for physics-guided deep learning reconstruction of highly accelerated myocardial perfusion CMR

PURPOSE

To develop a physics-guided deep learning (PG-DL) reconstruction strategy based on a signal intensity informed multi-coil (SIIM) encoding operator for highly-accelerated simultaneous multislice (SMS) myocardial perfusion cardiac MRI (CMR).

METHODS

First-pass perfusion CMR acquires highly-accelerated images with dynamically varying signal intensity/SNR following the administration of a gadolinium-based contrast agent. Thus, using PG-DL reconstruction with a conventional multi-coil encoding operator leads to analogous signal intensity variations across different time-frames at the network output, creating difficulties in generalization for varying SNR levels. We propose to use a SIIM encoding operator to capture the signal intensity/SNR variations across time-frames in a reformulated encoding operator. This leads to a more uniform/flat contrast at the output of the PG-DL network, facilitating generalizability across time-frames. PG-DL reconstruction with the proposed SIIM encoding operator is compared to PG-DL with conventional encoding operator, split slice-GRAPPA, locally low-rank (LLR) regularized reconstruction, low-rank plus sparse (L + S) reconstruction, and regularized ROCK-SPIRiT.

RESULTS

Results on highly accelerated free-breathing first pass myocardial perfusion CMR at three-fold SMS and four-fold in-plane acceleration show that the proposed method improves upon the reconstruction methods use for comparison. Substantial noise reduction is achieved compared to split slice-GRAPPA, and aliasing artifacts reduction compared to LLR regularized reconstruction, L + S reconstruction and PG-DL with conventional encoding. Furthermore, a qualitative reader study indicated that proposed method outperformed all methods.

CONCLUSION

PG-DL reconstruction with the proposed SIIM encoding operator improves generalization across different time-frames /SNRs in highly accelerated perfusion CMR.

Manifold Learning via Linear Tangent Space Alignment (LTSA) for Accelerated Dynamic MRI With Sparse Sampling

The spatial resolution and temporal frame-rate of dynamic magnetic resonance imaging (MRI) can be improved by reconstructing images from sparsely sampled k -space data with mathematical modeling of the underlying spatiotemporal signals. These models include sparsity models, linear subspace models, and non-linear manifold models. This work presents a novel linear tangent space alignment (LTSA) model-based framework that exploits the intrinsic low-dimensional manifold structure of dynamic images for accelerated dynamic MRI. The performance of the proposed method was evaluated and compared to state-of-the-art methods using numerical simulation studies as well as 2D and 3D in vivo cardiac imaging experiments. The proposed method achieved the best performance in image reconstruction among all the compared methods. The proposed method could prove useful for accelerating many MRI applications, including dynamic MRI, multi-parametric MRI, and MR spectroscopic imaging.

Advances in machine learning applications for cardiovascular 4D flow MRI

Four-dimensional flow magnetic resonance imaging (MRI) has evolved as a non-invasive imaging technique to visualize and quantify blood flow in the heart and vessels. Hemodynamic parameters derived from 4D flow MRI, such as net flow and peak velocities, but also kinetic energy, turbulent kinetic energy, viscous energy loss, and wall shear stress have shown to be of diagnostic relevance for cardiovascular diseases. 4D flow MRI, however, has several limitations. Its long acquisition times and its limited spatio-temporal resolutions lead to inaccuracies in velocity measurements in small and low-flow vessels and near the vessel wall. Additionally, 4D flow MRI requires long post-processing times, since inaccuracies due to the measurement process need to be corrected for and parameter quantification requires 2D and 3D contour drawing. Several machine learning (ML) techniques have been proposed to overcome these limitations. Existing scan acceleration methods have been extended using ML for image reconstruction and ML based super-resolution methods have been used to assimilate high-resolution computational fluid dynamic simulations and 4D flow MRI, which leads to more realistic velocity results. ML efforts have also focused on the automation of other post-processing steps, by learning phase corrections and anti-aliasing. To automate contour drawing and 3D segmentation, networks such as the U-Net have been widely applied. This review summarizes the latest ML advances in 4D flow MRI with a focus on technical aspects and applications. It is divided into the current status of fast and accurate 4D flow MRI data generation, ML based post-processing tools for phase correction and vessel delineation and the statistical evaluation of blood flow.

Simultaneous multi-parametric acquisition and reconstruction techniques in cardiac magnetic resonance imaging: Basic concepts and status of clinical development

Simultaneous multi-parametric acquisition and reconstruction techniques (SMART) are gaining attention for their potential to overcome some of cardiovascular magnetic resonance imaging's (CMR) clinical limitations. The major advantages of SMART lie within their ability to simultaneously capture multiple "features" such as cardiac motion, respiratory motion, T1/T2 relaxation. This review aims to summarize the overarching theory of SMART, describing key concepts that many of these techniques share to produce co-registered, high quality CMR images in less time and with less requirements for specialized personnel. Further, this review provides an overview of the recent developments in the field of SMART by describing how they work, the parameters they can acquire, their status of clinical testing and validation, and by providing examples for how their use can improve the current state of clinical CMR workflows. Many of the SMART are in early phases of development and testing, thus larger scale, controlled trials are needed to evaluate their use in clinical setting and with different cardiac pathologies.

Altered Aortic Hemodynamics and Relative Pressure in Patients with Dilated Cardiomyopathy

Ventricular-vascular interaction is central in the adaptation to cardiovascular disease. However, cardiomyopathy patients are predominantly monitored using cardiac biomarkers. The aim of this study is therefore to explore aortic function in dilated cardiomyopathy (DCM). Fourteen idiopathic DCM patients and 16 controls underwent cardiac magnetic resonance imaging, with aortic relative pressure derived using physics-based image processing and a virtual cohort utilized to assess the impact of cardiovascular properties on aortic behaviour. Subjects with reduced left ventricular systolic function had significantly reduced aortic relative pressure, increased aortic stiffness, and significantly delayed time-to-pressure peak duration. From the virtual cohort, aortic stiffness and aortic volumetric size were identified as key determinants of aortic relative pressure. As such, this study shows how advanced flow imaging and aortic hemodynamic evaluation could provide novel insights into the manifestation of DCM, with signs of both altered aortic structure and function derived in DCM using our proposed imaging protocol.

Single projection driven real-time multi-contrast (SPIDERM) MR imaging using pre-learned spatial subspace and linear transformation

Objective. To develop and test the feasibility of a novel Single ProjectIon DrivEn Real-time Multi-contrast (SPIDERM) MR imaging technique that can generate real-time 3D images on-the-fly with flexible contrast weightings and a low latency. Approach. In SPIDERM, a ‘prep’ scan is first performed, with sparse k-space sampling periodically interleaved with the central k-space line (navigator data), to learn a subject-specific model, incorporating a spatial subspace and a linear transformation between navigator data and subspace coordinates. A ‘live’ scan is then performed by repeatedly acquiring the central k-space line only to dynamically determine subspace coordinates. With the ‘prep’-learned subspace and ‘live’ coordinates, real-time 3D images are generated on-the-fly with computationally efficient matrix multiplication. When implemented based on a multi-contrast pulse sequence, SPIDERM further allows for data-driven image contrast regeneration to convert real-time contrast-varying images into contrast-frozen images at user’s discretion while maintaining motion states. Both digital phantom and in-vivo experiments were performed to evaluate the technical feasibility of SPIDERM. Main results. The elapsed time from the input of the central k-space line to the generation of real-time contrast-frozen 3D images was approximately 45 ms, permitting a latency of 55 ms or less. Motion displacement measured from SPIDERM and reference images showed excellent correlation ( R 2 ≥ 0.983 ). Geometric variation from the ground truth in the digital phantom was acceptable as demonstrated by pancreas contour analysis (Dice ≥ 0.84, mean surface distance ≤ 0.95 mm). Quantitative image quality metrics showed good consistency between reference images and contrast-varying SPIDREM images in in-vivo studies (mean NMRSE = 0.141 , PSNR = 3 0.12 , SSIM = 0.88 ). Significance. SPIDERM is capable of generating real-time multi-contrast 3D images with a low latency. An imaging framework based on SPIDERM has the potential to serve as a standalone package for MR-guided radiation therapy by offering adaptive simulation through a ‘prep’ scan and real-time image guidance through a ‘live’ scan.

Dynamic imaging using motion-compensated smoothness regularization on manifolds (MoCo-SToRM)

Objective. We introduce an unsupervised motion-compensated reconstruction scheme for high-resolution free-breathing pulmonary magnetic resonance imaging.Approach. We model the image frames in the time series as the deformed version of the 3D template image volume. We assume the deformation maps to be points on a smooth manifold in high-dimensional space. Specifically, we model the deformation map at each time instant as the output of a CNN-based generator that has the same weight for all time-frames, driven by a low-dimensional latent vector. The time series of latent vectors account for the dynamics in the dataset, including respiratory motion and bulk motion. The template image volume, the parameters of the generator, and the latent vectors are learned directly from the k-t space data in an unsupervised fashion.Main results. Our experimental results show improved reconstructions compared to state-of-the-art methods, especially in the context of bulk motion during the scans.Significance. The proposed unsupervised motion-compensated scheme jointly estimates the latent vectors that capture the motion dynamics, the corresponding deformation maps, and the reconstructed motion-compensated images from the raw k-t space data of each subject. Unlike current motion-resolved strategies, the proposed scheme is more robust to bulk motion events during the scan.

Free-breathing motion-informed locally low-rank quantitative 3D myocardial perfusion imaging

Purpose

To propose respiratory motion‐informed locally low‐rank reconstruction (MI‐LLR) for robust free‐breathing single‐bolus quantitative 3D myocardial perfusion CMR imaging. Simulation and in‐vivo results are compared to locally low‐rank (LLR) and compressed sensing reconstructions (CS) for reference.

Methods

Data were acquired using a 3D Cartesian pseudo‐spiral in‐out k‐t undersampling scheme (R = 10) and reconstructed using MI‐LLR, which encompasses two stages. In the first stage, approximate displacement fields are derived from an initial LLR reconstruction to feed a motion‐compensated reference system to a second reconstruction stage, which reduces the rank of the inverse problem. For comparison, data were also reconstructed with LLR and frame‐by‐frame CS using wavelets as sparsifying transform (ℓ1‐wavelet).

Reconstruction accuracy relative to ground truth was assessed using synthetic data for realistic ranges of breathing motion, heart rates, and SNRs. In‐vivo experiments were conducted in healthy subjects at rest and during adenosine stress. Myocardial blood flow (MBF) maps were derived using a Fermi model.

Results

Improved uniformity of MBF maps with reduced local variations was achieved with MI‐LLR. For rest and stress, intra‐volunteer variation of absolute and relative MBF was lower in MI‐LLR (±0.17 mL/g/min [26%] and ±1.07 mL/g/min [33%]) versus LLR (±0.19 mL/g/min [28%] and ±1.22 mL/g/min [36%]) and versus ℓ1‐wavelet (±1.17 mL/g/min [113%] and ±6.87 mL/g/min [115%]). At rest, intra‐subject MBF variation was reduced significantly with MI‐LLR.

Conclusion

The combination of pseudo‐spiral Cartesian undersampling and dual‐stage MI‐LLR reconstruction improves free‐breathing quantitative 3D myocardial perfusion CMR imaging under rest and stress condition.

Click here for author‐reader discussions

Quantitative myocardial first-pass perfusion imaging of CO2 -induced vasodilation in rats

Inducible hypercapnia is an alternative for increasing the coronary blood flow necessary to facilitate the quantification of myocardial blood flow during hyperemia. The current study aimed to quantify the pharmacokinetic effect of a CO₂ gas challenge on myocardial perfusion in rats using high-resolution, first-pass perfusion CMR and compared it with pharmacologically induced hyperemia using regadenoson. A dual-contrast, saturation-recovery, gradient-echo sequence with a Cartesian readout was used on a small-animal 9.4-T scanner; additional cine images during hyperemia/rest were recorded with an ultrashort echo time sequence. The mean myocardial blood flow value at rest was 6.1 ± 1.4 versus 13.9 ± 3.7 and 14.3 ± 4 mL/g/min during vasodilation with hypercapnia and regadenoson, respectively. Accordingly, the myocardial flow reserve value was 2.6 ± 1.1 for the gas challenge and 2.5 ± 1.4 for regadenoson. During hyperemia with both protocols, a significantly increased cardiac output was found. It was concluded that hypercapnia leads to significantly increased coronary flow and yields similar myocardial flow reserves in healthy rats as compared with pharmacological stimulation. Accordingly, inducible hypercapnia can be selected as an alternative stressor in CMR studies of myocardial blood flow in small animals.

Time domain principal component analysis for rapid, real-time 2D MRI reconstruction from undersampled data

PURPOSE

A rapid real-time 2D accelerated method was developed for magnetic resonance imaging (MRI) using principal component analysis (PCA) in the temporal domain. This method employs a moving window of previous dynamic frames to reconstruct the current, real-time frame within this window. This technique could be particularly useful in real-time tracking applications such as in MR-guided radiotherapy, where low latency real-time reconstructions are essential.

METHODS

The method was tested retrospectively on 15 fully-sampled data sets of lung patient data acquired on a 3T Philips Achieva system. High frequency data are incoherently undersampled, while the central low-frequency data are always acquired to characterize the temporal fluctuations through PCA. The undersampling pattern is derived in such a way that all of k-space is acquired within a pre-determined number of frames. The missing data in the current frame are then filled in by fitting the temporal characterizations to the acquired undersampled data, using a pre-determined number of PCs. A subset of six patients was used to test the contour ability of the images. Various accelerations between 3x and 8x were tested along with the optimal number of PCs for fitting. A comparison was also performed with previous work from our group proposed by Dietz et al. as well as with a standard low resolution acquisition. In order to determine how the method would perform at lower signal to noise ratio (SNR), noise levels of 2×, 4×, and 6× were added to the 3T data. Metrics such as normalised mean square error and Dice coefficient were used to measure the reconstruction image quality and contour ability.

RESULTS

The proposed method demonstrated good temporal robustness as consistent metrics were detected for the duration of the imaging session. It was found that the optimal number of PCs for temporal fitting was dependent on the acceleration rate. For the data tested, five PCs were found to be optimal at the acceleration rates of 3× and 4×. This number decreases to three at accelerations of 5× and 6× and further decreases to two at an acceleration rate of 8×, likely due to greater instability with fewer acquired data points. The use of too many PCs for fitting increased the chances of noisy reconstruction which affected contourability.

CONCLUSIONS

The proposed 2D real-time MR acceleration method demonstrated greater robustness in the metrics over time when compared with previous real-time PCA methods using metrics such as normalised mean squared error, peak SNR and structural similarity up to an acceleration of 8x. Improved temporal robustness of image structure contourability and accurate definition was also demonstrated using several metrics including the Dice coefficient. Reconstruction of raw acquired data can be performed at approximately 50 ms per frame using an Intel core i5 CPU. The method has the advantage of being very flexible in terms of hardware requirements as it can operate successfully on a single coil channel and does not require specialized computing power to implement in real-time.

Recommendation for Cardiac Magnetic Resonance Imaging-Based Phenotypic Study: Imaging Part

Cardiac magnetic resonance (CMR) imaging provides important biomarkers for the early diagnosis of many cardiovascular diseases and has been reported to reveal phenome-wide associations of cardiac/aortic structure and functionality in population studies. Nevertheless, due to the complexity of operation and variations among manufactural vendors, magnetic field strengths, coils, sequences, scan parameters, and image analysis approaches, CMR is rarely used in large cohort studies. Existing guidelines mainly focused on the diagnosis of cardiovascular diseases, which did not aim to basic research. The purpose of this study was to propose a recommendation for CMR based phenotype measurements for cohort study. We classify the imaging sequences of CMR into three categories according to the importance and universality of corresponding measurable phenotypes. The acquisition time and repeatability of the phenotypic measurement were also taken into consideration during the categorization. Unlike other guidelines, this recommendation focused on quantitative measurement of large amount of phenotypes from CMR.

Subspace-constrained approaches to low-rank fMRI acceleration

Acceleration methods in fMRI aim to reconstruct high fidelity images from under-sampled k-space, allowing fMRI datasets to achieve higher temporal resolution, reduced physiological noise aliasing, and increased statistical degrees of freedom. While low levels of acceleration are typically part of standard fMRI protocols through parallel imaging, there exists the potential for approaches that allow much greater acceleration. One such existing approach is k-t FASTER, which exploits the inherent low-rank nature of fMRI. In this paper, we present a reformulated version of k-t FASTER which includes additional L2 constraints within a low-rank framework.

We evaluated the effect of three different constraints against existing low-rank approaches to fMRI reconstruction: Tikhonov constraints, low-resolution priors, and temporal subspace smoothness. The different approaches are separately tested for robustness to under-sampling and thermal noise levels, in both retrospectively and prospectively-undersampled finger-tapping task fMRI data. Reconstruction quality is evaluated by accurate reconstruction of low-rank subspaces and activation maps.

The use of L2 constraints was found to achieve consistently improved results, producing high fidelity reconstructions of statistical parameter maps at higher acceleration factors and lower SNR values than existing methods, but at a cost of longer computation time. In particular, the Tikhonov constraint proved very robust across all tested datasets, and the temporal subspace smoothness constraint provided the best reconstruction scores in the prospectively-undersampled dataset. These results demonstrate that regularized low-rank reconstruction of fMRI data can recover functional information at high acceleration factors without the use of any model-based spatial constraints.

On the use of low-dimensional temporal subspace constraints to reduce reconstruction time and improve image quality of accelerated 4D-MRI

BACKGROUND AND PURPOSE

The purpose of this work is to investigate the use of low-dimensional temporal subspace constraints for 4D-MRI reconstruction from accelerated data in the context of MR-guided online adaptive radiation therapy (MRgOART).

MATERIALS AND METHODS

Subspace basis functions are derived directly from the accelerated golden angle radial stack-of-stars 4D-MRI data. The reconstruction times, image quality, and motion estimates are investigated as a function of the number of subspace coefficients and compared with a conventional frame-by-frame reconstruction. These experiments were performed in five patients with four 4D-MRI scans per patient on a 1.5T MR-Linac.

RESULTS

If two or three subspace coefficients are used, the iterative reconstruction time is reduced by 32% and 18%, respectively, compared to conventional parallel imaging with compressed sensing reconstructions. No significant difference was found between motion estimates made with the subspace-constrained reconstructions (p > 0.08). Qualitative improvements in image quality included reduction in apparent noise and reductions in streaking artifacts from the radial k-space coverage.

CONCLUSION

Incorporating subspace constraints for accelerated 4D-MRI reconstruction reduces noise and residual undersampling artifacts in the images while reducing computation time, making it a strong candidate for use in clinical MRgOART workflows.

Compressed sensing plus motion (CS + M): A new perspective for improving undersampled MR image reconstruction

We address the problem of reconstructing high quality images from undersampled MRI data. This is a challenging task due to the highly ill-posed nature of the problem. In particular, in dynamic MRI scans, the interaction between the target structure and the physical motion affects the acquired measurements leading to blurring artefacts and loss of fine details. In this work, we propose a framework for dynamic MRI reconstruction framed under a new multi-task optimisation model called Compressed Sensing Plus Motion (CS + M). Firstly, we propose a single optimisation problem that simultaneously computes the MRI reconstruction and the physical motion. Secondly, we show our model can be efficiently solved by breaking it up into two computationally tractable problems. The potentials and generalisation capabilities of our approach are demonstrated in different clinical applications including cardiac cine, cardiac perfusion and brain perfusion imaging. We show, through numerical experiments, that the proposed scheme reduces blurring artefacts, and preserves the target shape and fine details in the reconstruction. We also report the highest quality reconstruction under high undersampling rates in comparison to several state of the art techniques.

A fast navigator (fastNAV) for prospective respiratory motion correction in first-pass myocardial perfusion imaging

PURPOSE

To develop and evaluate a fast respiratory navigator (fastNAV) for cardiac MR perfusion imaging with subject-specific prospective slice tracking.

METHODS

A fastNAV was developed for dynamic contrast-enhanced cardiac MR perfusion imaging by combining spatially nonselective saturation with slice-selective tip-up and slice-selective excitation pulses. The excitation slice was angulated from the tip-up slice in the transverse plane to overlap only in the right hemidiaphragm for suppression of signal outside the right hemidiaphragm. A calibration scan was developed to enable the estimation of subject-specific tracking factors. Perfusion imaging using subject-specific fastNAV-based slice tracking was then compared to a conventional sequence (ie, without slice tracking) in 10 patients under free-breathing conditions. Respiratory motion in perfusion images was quantitatively assessed by measuring the average overlap of the left ventricle across images (avDice, 0:no overlap/1:perfect overlap) and the average displacement of the center of mass of the left ventricle (avCoM). Image quality was subjectively assessed using a 4-point scoring system (1: poor, 4: excellent).

RESULTS

The fastNAV calibration was successfully performed in all subjects (average tracking factor of 0.46 ± 0.13, R = 0.94 ± 0.03). Prospective motion correction using fastNAV led to higher avDice (0.94 ± 0.02 vs. 0.90 ± 0.03, P < .001) and reduced avCoM (4.03 ± 0.84 vs. 5.22 ± 1.22, P < .001). There were no statistically significant differences between the 2 sequences in terms of image quality (both sequences: median = 3 and interquartile range = 3-4, P = 1).

CONCLUSION

fastNAV enables fast and robust right hemidiaphragm motion tracking in a perfusion sequence. In combination with subject-specific slice tracking, fastNAV reduces the effect of respiratory motion during free-breathing cardiac MR perfusion imaging.

Combined simultaneous multislice bSSFP and compressed sensing for first-pass myocardial perfusion at 1.5 T with high spatial resolution and coverage

PURPOSE

To implement and evaluate a pseudorandom undersampling scheme for combined simultaneous multislice (SMS) balanced SSFP (bSSFP) and compressed-sensing (CS) reconstruction to enable myocardial perfusion imaging with high spatial resolution and coverage at 1.5 T.

METHODS

A prospective pseudorandom undersampling scheme that is compatible with SMS-bSSFP phase-cycling requirements and CS was developed. The SMS-bSSFP CS with pseudorandom and linear undersampling schemes were compared in a phantom. A high-resolution (1.4 × 1.4 mm2 ) six-slice SMS-bSSFP CS perfusion sequence was compared with a conventional (1.9 × 1.9 mm2 ) three-slice sequence in 10 patients. Qualitative assessment of image quality, perceived SNR, and number of diagnostic segments and quantitative measurements of sharpness, upslope index, and contrast ratio were performed.

RESULTS

In phantom experiments, pseudorandom undersampling resulted in residual artifact (RMS error) reduction by a factor of 7 compared with linear undersampling. In vivo, the proposed sequence demonstrated higher perceived SNR (2.9 ± 0.3 vs. 2.2 ± 0.6, P = .04), improved sharpness (0.35 ± 0.03 vs. 0.32 ± 0.05, P = .01), and a higher number of diagnostic segments (100% vs. 94%, P = .03) compared with the conventional sequence. There were no significant differences between the sequences in terms of image quality (2.5 ± 0.4 vs. 2.8 ± 0.2, P = .08), upslope index (0.11 ± 0.02 vs. 0.10 ± 0.01, P = .3), or contrast ratio (3.28 ± 0.35 vs. 3.36 ± 0.43, P = .7).

CONCLUSION

A pseudorandom k-space undersampling compatible with SMS-bSSFP and CS reconstruction has been developed and enables cardiac MR perfusion imaging with increased spatial resolution and myocardial coverage, increased number of diagnostic segments and perceived SNR, and no difference in image quality, upslope index, and contrast ratio.

From 2D to 4D Phase-Contrast MRI in the Neurovascular System: Will It Be a Quantum Jump or a Fancy Decoration?

Considering the crosstalk between the flow and vessel wall, hemodynamic assessment of the neurovascular system may offer a well-integrated solution for both diagnosis and management by adding prognostic significance to the standard CT/MR angiography. 4D flow MRI or time-resolved 3D velocity-encoded phase-contrast MRI has long been promising for the hemodynamic evaluation of the great vessels, but challenged in clinical studies for assessing intracranial vessels with small diameter due to long scan times and low spatiotemporal resolution. Current accelerated MRI techniques, including parallel imaging with compressed sensing and radial k-space undersampling acquisitions, have decreased scan times dramatically while preserving spatial resolution. 4D flow MRI visualized and measured 3D complex flow of neurovascular diseases such as aneurysm, arteriovenous shunts, and atherosclerotic stenosis using parameters including flow volume, velocity vector, pressure gradients, and wall shear stress. In addition to the noninvasiveness of the phase contrast technique and retrospective flow measurement through the wanted windows of the analysis plane, 4D flow MRI has shown several advantages over Doppler ultrasound or computational fluid dynamics. The evaluation of the flow status and vessel wall can be performed simultaneously in the same imaging modality. This article is an overview of the recent advances in neurovascular 4D flow MRI techniques and their potential clinical applications in neurovascular disease. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY STAGE: 3.

Real-time exercise stress cardiac MRI with Fourier-series reconstruction from golden-angle radial data

Magnetic resonance imaging (MRI) can measure cardiac response to exercise stress for evaluating and managing heart patients in the practice of clinical cardiology. However, exercise stress cardiac MRI have been clinically limited by the ability of available MRI techniques to quantitatively measure fast and unstable cardiac dynamics during exercise. The presented work is to develop a new real-time MRI technique for improved quantitative performance of exercise stress cardiac MRI. This technique seeks to represent real-time cardiac images as a sparse Fourier-series along the time. With golden-angle radial acquisition, parallel imaging and compressed sensing can be integrated into a linear system of equations for resolving Fourier coefficients that are in turn used to generate real-time cardiac images from the Fourier-series representation. Fourier-series reconstruction from golden-angle radial data can effectively address data insufficiency due to MRI speed limitation, providing a real-time approach to exercise stress cardiac MRI. To demonstrate the feasibility, an exercise stress cardiac MRI experiment was run to investigate biventricular response to in-scanner biking exercise in a cohort of sixteen healthy volunteers. It was found that Fourier-series reconstruction from golden-angle radial data effectively detected exercise-induced increase in stroke volume and ejection fraction in a healthy heart. The presented work will improve the applications of exercise stress cardiac MRI in the practice of clinical cardiology.

Accelerating CEST MRI in the mouse brain at 9.4 T by exploiting sparsity in the Z-spectrum domain

PURPOSE

Chemical exchange saturation transfer (CEST) is an MR contrast modality offering an enhanced sensitivity for the detection of dilute metabolites with exchangeable protons. Quantitative analysis requires the acquisition of a number of images (usually between 20 and 50 RF offsets) per Z-spectrum, leading to long acquisition times of the order of 5-40 min in practice. In this work, we explore the possibility of employing sparsity in the Z-spectrum domain (irradiation offset dimension) to provide an accelerated acquisition scheme without compromising the quality of reconstructed CEST spectra.

METHOD AND THEORY

Ex vivo and in vivo data were acquired on an experimental, small animal 9.4 T system. Three different reconstruction methods were tested: k-Z SPARSE, k-Z SLR and k-Z principal component analysis (PCA) using retrospective undersampling with net acceleration factors R = 2, 3, 5. The quality of the reconstructed data was compared with respect to CEST spectra and full magnetization transfer ratio (MTR) asymmetry maps.

RESULTS

In both phantom and in vivo data, CEST spectra and the resulting MTR asymmetry maps were reconstructed without significant deterioration in data quality. For a low acceleration factor (R = 2, 3) all applied methods resulted in similar data quality, while for high acceleration factor (R = 5) only k-Z PCA and k-Z SLR could be used. Loss in spatial resolution was observed in reconstruction with k-Z PCA for all acceleration factors. An example of prospective undersampling with acceleration factor R = 3 and k-Z PCA reconstruction demonstrates improved CEST maps when compared with fully sampled data acquisition with either three times longer scan duration or threefold prolonged acquisition window per frequency offset.

CONCLUSION

The acquisition time of CEST spectra can be significantly accelerated by exploiting the sparsity of the Z-domain. For prospective and retrospective analysis using k-Z PCA, an acceleration factor of up to R = 3 can be used without significant loss in data quality.

Virtual clinical trials in medical imaging: a review

The accelerating complexity and variety of medical imaging devices and methods have outpaced the ability to evaluate and optimize their design and clinical use. This is a significant and increasing challenge for both scientific investigations and clinical applications. Evaluations would ideally be done using clinical imaging trials. These experiments, however, are often not practical due to ethical limitations, expense, time requirements, or lack of ground truth. Virtual clinical trials (VCTs) (also known as in silico imaging trials or virtual imaging trials) offer an alternative means to efficiently evaluate medical imaging technologies virtually. They do so by simulating the patients, imaging systems, and interpreters. The field of VCTs has been constantly advanced over the past decades in multiple areas. We summarize the major developments and current status of the field of VCTs in medical imaging. We review the core components of a VCT: computational phantoms, simulators of different imaging modalities, and interpretation models. We also highlight some of the applications of VCTs across various imaging modalities.

Extreme MRI: Large-scale volumetric dynamic imaging from continuous non-gated acquisitions

PURPOSE

To develop a framework to reconstruct large-scale volumetric dynamic MRI from rapid continuous and non-gated acquisitions, with applications to pulmonary and dynamic contrast-enhanced (DCE) imaging.

THEORY AND METHODS

The problem considered here requires recovering 100 gigabytes of dynamic volumetric image data from a few gigabytes of k-space data, acquired continuously over several minutes. This reconstruction is vastly under-determined, heavily stressing computing resources as well as memory management and storage. To overcome these challenges, we leverage intrinsic three-dimensional (3D) trajectories, such as 3D radial and 3D cones, with ordering that incoherently cover time and k-space over the entire acquisition. We then propose two innovations: (a) A compressed representation using multiscale low-rank matrix factorization that constrains the reconstruction problem, and reduces its memory footprint. (b) Stochastic optimization to reduce computation, improve memory locality, and minimize communications between threads and processors. We demonstrate the feasibility of the proposed method on DCE imaging acquired with a golden-angle ordered 3D cones trajectory and pulmonary imaging acquired with a bit-reversed ordered 3D radial trajectory. We compare it with "soft-gated" dynamic reconstruction for DCE and respiratory-resolved reconstruction for pulmonary imaging.

RESULTS

The proposed technique shows transient dynamics that are not seen in gating-based methods. When applied to datasets with irregular, or non-repetitive motions, the proposed method displays sharper image features.

CONCLUSIONS

We demonstrated a method that can reconstruct massive 3D dynamic image series in the extreme undersampling and extreme computation setting.

Acquisition strategies for spatially resolved magnetic resonance detection of hyperpolarized nuclei

Hyperpolarization is an emerging method in magnetic resonance imaging that allows nuclear spin polarization of gases or liquids to be temporarily enhanced by up to five or six orders of magnitude at clinically relevant field strengths and administered at high concentration to a subject at the time of measurement. This transient gain in signal has enabled the non-invasive detection and imaging of gas ventilation and diffusion in the lungs, perfusion in blood vessels and tissues, and metabolic conversion in cells, animals, and patients. The rapid development of this method is based on advances in polarizer technology, the availability of suitable probe isotopes and molecules, improved MRI hardware and pulse sequence development. Acquisition strategies for hyperpolarized nuclei are not yet standardized and are set up individually at most sites depending on the specific requirements of the probe, the object of interest, and the MRI hardware. This review provides a detailed introduction to spatially resolved detection of hyperpolarized nuclei and summarizes novel and previously established acquisition strategies for different key areas of application.

Pseudo-spiral sampling and compressed sensing reconstruction provides flexibility of temporal resolution in accelerated aortic 4D flow MRI: A comparison with k-t principal component analysis

INTRODUCTION

Time-resolved three-dimensional phase contrast MRI (4D flow) of aortic blood flow requires acceleration to reduce scan time. Two established techniques for highly accelerated 4D flow MRI are k-t principal component analysis (k-t PCA) and compressed sensing (CS), which employ either regular or random k-space undersampling. The goal of this study was to gain insights into the quantitative differences between k-t PCA- and CS-derived aortic blood flow, especially for high temporal resolution CS 4D flow MRI.

METHODS

The scan protocol consisted of both k-t PCA and CS accelerated 4D flow MRI, as well as a 2D flow reference scan through the ascending aorta acquired in 15 subjects. 4D flow scans were accelerated with factor R = 8. For CS accelerated scans, we used a pseudo-spiral Cartesian sampling scheme, which could additionally be reconstructed at higher temporal resolution, resulting in R = 13. 4D flow data were compared with the 2D flow scan in terms of flow, peak flow and stroke volume. A 3D peak systolic voxel-wise velocity and wall shear stress (WSS) comparison between k-t PCA and CS 4D flow was also performed.

RESULTS

The mean difference in flow/peak flow/stroke volume between the 2D flow scan and the 4D flow CS with R = 8 and R = 13 was 4.2%/9.1%/3.0% and 5.3%/7.1%/1.9%, respectively, whereas for k-t PCA with R = 8 the difference was 9.7%/25.8%/10.4%. In the voxel-by-voxel 4D flow comparison we found 13.6% and 3.5% lower velocity and WSS values of k-t PCA compared with CS with R = 8, and 15.9% and 5.5% lower velocity and WSS values of k-t PCA compared with CS with R = 13.

CONCLUSION

Pseudo-spiral accelerated 4D flow acquisitions in combination with CS reconstruction provides a flexible choice of temporal resolution. We showed that our proposed strategy achieves better agreement in flow values with 2D reference scans compared with using k-t PCA accelerated acquisitions.

Spatio-Temporal Deep Learning-Based Undersampling Artefact Reduction for 2D Radial Cine MRI With Limited Training Data

In this work we reduce undersampling artefacts in two-dimensional (2D) golden-angle radial cine cardiac MRI by applying a modified version of the U-net. The network is trained on 2D spatio-temporal slices which are previously extracted from the image sequences. We compare our approach to two 2D and a 3D deep learning-based post processing methods, three iterative reconstruction methods and two recently proposed methods for dynamic cardiac MRI based on 2D and 3D cascaded networks. Our method outperforms the 2D spatially trained U-net and the 2D spatio-temporal U-net. Compared to the 3D spatio-temporal U-net, our method delivers comparable results, but requiring shorter training times and less training data. Compared to the compressed sensing-based methods kt-FOCUSS and a total variation regularized reconstruction approach, our method improves image quality with respect to all reported metrics. Further, it achieves competitive results when compared to the iterative reconstruction method based on adaptive regularization with dictionary learning and total variation and when compared to the methods based on cascaded networks, while only requiring a small fraction of the computational and training time. A persistent homology analysis demonstrates that the data manifold of the spatio-temporal domain has a lower complexity than the one of the spatial domain and therefore, the learning of a projection-like mapping is facilitated. Even when trained on only one single subject without data-augmentation, our approach yields results which are similar to the ones obtained on a large training dataset. This makes the method particularly suitable for training a network on limited training data. Finally, in contrast to the spatial 2D U-net, our proposed method is shown to be naturally robust with respect to image rotation in image space and almost achieves rotation-equivariance where neither data-augmentation nor a particular network design are required.

From Compressed-Sensing to Artificial Intelligence-Based Cardiac MRI Reconstruction

Cardiac magnetic resonance (CMR) imaging is an important tool for the non-invasive assessment of cardiovascular disease. However, CMR suffers from long acquisition times due to the need of obtaining images with high temporal and spatial resolution, different contrasts, and/or whole-heart coverage. In addition, both cardiac and respiratory-induced motion of the heart during the acquisition need to be accounted for, further increasing the scan time. Several undersampling reconstruction techniques have been proposed during the last decades to speed up CMR acquisition. These techniques rely on acquiring less data than needed and estimating the non-acquired data exploiting some sort of prior information. Parallel imaging and compressed sensing undersampling reconstruction techniques have revolutionized the field, enabling 2- to 3-fold scan time accelerations to become standard in clinical practice. Recent scientific advances in CMR reconstruction hinge on the thriving field of artificial intelligence. Machine learning reconstruction approaches have been recently proposed to learn the non-linear optimization process employed in CMR reconstruction. Unlike analytical methods for which the reconstruction problem is explicitly defined into the optimization process, machine learning techniques make use of large data sets to learn the key reconstruction parameters and priors. In particular, deep learning techniques promise to use deep neural networks (DNN) to learn the reconstruction process from existing datasets in advance, providing a fast and efficient reconstruction that can be applied to all newly acquired data. However, before machine learning and DNN can realize their full potentials and enter widespread clinical routine for CMR image reconstruction, there are several technical hurdles that need to be addressed. In this article, we provide an overview of the recent developments in the area of artificial intelligence for CMR image reconstruction. The underlying assumptions of established techniques such as compressed sensing and low-rank reconstruction are briefly summarized, while a greater focus is given to recent advances in dictionary learning and deep learning based CMR reconstruction. In particular, approaches that exploit neural networks as implicit or explicit priors are discussed for 2D dynamic cardiac imaging and 3D whole-heart CMR imaging. Current limitations, challenges, and potential future directions of these techniques are also discussed.

Time-domain principal component reconstruction (tPCR): A more efficient and stable iterative reconstruction framework for non-Cartesian functional MRI

PURPOSE

To improve the reconstruction efficiency (i.e., computational load) and stability of iterative reconstruction for non-Cartesian fMRI when using high undersampling rates and/or in the presence of strong off-resonance effects.

THEORY AND METHODS

The magnetic resonance encephalography (MREG) sequence with 3D non-Cartesian trajectory and 0.1s repetition time (TR) was applied to acquire fMRI datasets. Different from a conventional time-point-by-time-point sequential reconstruction (SR), the proposed time-domain principal component reconstruction (tPCR) performs three steps: (1) decomposing the k-t-space fMRI datasets into time-domain principal component space using singular value decomposition, (2) reconstructing each principal component with redistributed computation power according to their weights, and (3) combining the reconstructed principal components back to image-t-space. The comparison of reconstruction accuracy was performed by simulation experiments and then verified in real fMRI data.

RESULTS

The simulation experiments showed that the proposed tPCR was able to significantly reduce reconstruction errors, and subsequent functional activation errors, relative to SR at identical computational cost. Alternatively, at fixed reconstruction accuracy, computation time was greatly reduced. The improved performance was particularly obvious for L1-norm nonlinear reconstructions relative to L2-norm linear reconstructions and robust to different regularization strength, undersampling rates, and off-resonance effects intensity. By examining activation maps, tPCR was also found to give similar improvements in real fMRI experiments.

CONCLUSION

The proposed proof-of-concept tPCR framework could improve (1) the reconstruction efficiency of iterative reconstruction, and (2) the reconstruction stability especially for nonlinear reconstructions. As a practical consideration, the improved reconstruction speed promotes the application of highly undersampled non-Cartesian fast fMRI.

State-of-the-Art Quantitative Assessment of Myocardial Ischemia by Stress Perfusion Cardiac Magnetic Resonance

Ischemic heart disease remains the foremost determinant of death and disability across the world. Quantification of the ischemia burden is currently the preferred approach to predict event risk and to trigger adequate treatment. Cardiac magnetic resonance (CMR) can be a prime protagonist in this scenario due to its synergistic features. It allows assessment of wall motility, myocardial perfusion, and tissue scar by means of late gadolinium enhancement imaging. We discuss the clinical and preclinical aspects of gadolinium-based, perfusion CMR imaging, including the relevance of high spatial resolution and 3-dimensional whole-heart coverage, among important features of this auspicious method.

Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learning

The field of medical image reconstruction has seen roughly four types of methods. The first type tended to be analytical methods, such as filtered back-projection (FBP) for X-ray computed tomography (CT) and the inverse Fourier transform for magnetic resonance imaging (MRI), based on simple mathematical models for the imaging systems. These methods are typically fast, but have suboptimal properties such as poor resolution-noise trade-off for CT. A second type is iterative reconstruction methods based on more complete models for the imaging system physics and, where appropriate, models for the sensor statistics. These iterative methods improved image quality by reducing noise and artifacts. The FDA-approved methods among these have been based on relatively simple regularization models. A third type of methods has been designed to accommodate modified data acquisition methods, such as reduced sampling in MRI and CT to reduce scan time or radiation dose. These methods typically involve mathematical image models involving assumptions such as sparsity or low-rank. A fourth type of methods replaces mathematically designed models of signals and systems with data-driven or adaptive models inspired by the field of machine learning. This paper focuses on the two most recent trends in medical image reconstruction: methods based on sparsity or low-rank models, and data-driven methods based on machine learning techniques.

Online Adaptive Image Reconstruction (OnAIR) Using Dictionary Models

Sparsity and low-rank models have been popular for reconstructing images and videos from limited or corrupted measurements. Dictionary or transform learning methods are useful in applications such as denoising, inpainting, and medical image reconstruction. This paper proposes a framework for online (or time-sequential) adaptive reconstruction of dynamic image sequences from linear (typically undersampled) measurements. We model the spatiotemporal patches of the underlying dynamic image sequence as sparse in a dictionary, and we simultaneously estimate the dictionary and the images sequentially from streaming measurements. Multiple constraints on the adapted dictionary are also considered such as a unitary matrix, or low-rank dictionary atoms that provide additional efficiency or robustness. The proposed online algorithms are memory efficient and involve simple updates of the dictionary atoms, sparse coefficients, and images. Numerical experiments demonstrate the usefulness of the proposed methods in inverse problems such as video reconstruction or inpainting from noisy, subsampled pixels, and dynamic magnetic resonance image reconstruction from very limited measurements.

An isolated beating pig heart platform for a comprehensive evaluation of intracardiac blood flow with 4D flow MRI: a feasibility study

Background

Cardiac magnetic resonance imaging (MRI) in large animals is cumbersome for various reasons, including ethical considerations, costs of housing and maintenance, and need for anaesthesia. Our primary purpose was to show the feasibility of an isolated beating pig heart model for four-dimensional (4D) flow MRI for investigating intracardiac blood flow patterns and flow parameters using slaughterhouse side products. In addition, the feasibility of evaluating transcatheter aortic valve replacement (TAVR) in the model was investigated.

Methods

Seven slaughterhouse pig hearts were installed in the MRI-compatible isolated beating pig heart platform. First, Langendorff perfusion mode was established; then, the system switched to working mode, in which blood was actively pumped by the left ventricle. A pacemaker ensured a stable HR during 3-T MRI scanning. All hearts were submitted to human physiological conditions of cardiac output and stayed vital for several hours. Aortic flow was measured from which stroke volume, cardiac output, and regurgitation fraction were calculated.

Results

4D flow MRI acquisitions were successfully conducted in all hearts. Stroke volume was 31 ± 6 mL (mean ± standard deviation), cardiac output 3.3 ± 0.9 L/min, and regurgitation fraction 16% ± 9%. With 4D flow, intracardiac and coronary flow patterns could be visualised in all hearts. In addition, we could study valve function and regurgitation in two hearts after TAVR.

Conclusions

The feasibility of 4D flow MRI in an isolated beating pig heart loaded to physiological conditions was demonstrated. The platform is promising for preclinical assessment of cardiac blood flow and function.

Electronic supplementary material

The online version of this article (10.1186/s41747-019-0114-5) contains supplementary material, which is available to authorized users.

Reconstruction techniques for cardiac cine MRI

The present survey describes the state-of-the-art techniques for dynamic cardiac magnetic resonance image reconstruction. Additionally, clinical relevance, main challenges, and future trends of this image modality are outlined. Thus, this paper aims to provide a general vision about cine MRI as the standard procedure in functional evaluation of the heart, focusing on technical methodologies.

GRASP-Pro: imProving GRASP DCE-MRI through self-calibrating subspace-modeling and contrast phase automation

PURPOSE

To propose a highly accelerated, high-resolution dynamic contrast-enhanced MRI (DCE-MRI) technique called GRASP-Pro (golden-angle radial sparse parallel imaging with imProved performance) through a joint sparsity and self-calibrating subspace constraint with automated selection of contrast phases.

METHODS

GRASP-Pro reconstruction enforces a combination of an explicit low-rank subspace-constraint and a temporal sparsity constraint. The temporal basis used to construct the subspace is learned from an intermediate reconstruction step using the low-resolution portion of radial k-space, which eliminates the need for generating the basis using auxiliary data or a physical signal model. A convolutional neural network was trained to generate the contrast enhancement curve in the artery, from which clinically relevant contrast phases are automatically selected for evaluation. The performance of GRASP-Pro was demonstrated for high spatiotemporal resolution DCE-MRI of the prostate and was compared against standard GRASP in terms of overall image quality, image sharpness, and residual streaks and/or noise level.

RESULTS

Compared to GRASP, GRASP-Pro reconstructed dynamic images with enhanced sharpness, less residual streaks and/or noise, and finer delineation of the prostate without prolonging reconstruction time. The image quality improvement reached statistical significance (P < 0.05) in all the assessment categories. The neural network successfully generated contrast enhancement curves in the artery, and corresponding peak enhancement indexes correlated well with that from the manual selection.

CONCLUSION

GRASP-Pro is a promising method for rapid and continuous DCE-MRI. It enables superior reconstruction performance over standard GRASP and allows reliable generation of artery enhancement curve to guide the selection of desired contrast phases for improving the efficiency of GRASP MRI workflow.