Multi-contrast Imaging Research Articles

Single-shot x-ray phase-contrast and dark-field imaging based on coded binary phase mask

We introduce a coded-mask-based multi-contrast imaging method for high-resolution phase-contrast and dark-field imaging. The method uses a binary phase mask designed to provide an ultra-high-contrast pattern and reference-free single-shot measurement and an algorithm based on maximum-likelihood optimization and automatic differentiation to perform simultaneous reconstruction of absorption, phase, and dark-field object images. Further, we demonstrate that the method has great potential for real-time quantitative phase imaging and wavefront sensing when combined with deep learning.

MESMERISED: Super-accelerating T1 relaxometry and diffusion MRI with STEAM at 7 T for quantitative multi-contrast and diffusion imaging

There is an increasing interest in quantitative imaging of T1, T2 and diffusion contrast in the brain due to greater robustness against bias fields and artifacts, as well as better biophysical interpretability in terms of microstructure. However, acquisition time constraints are a challenge, particularly when multiple quantitative contrasts are desired and when extensive sampling of diffusion directions, high b-values or long diffusion times are needed for multi-compartment microstructure modeling. Although ultra-high fields of 7 T and above have desirable properties for many MR modalities, the shortening T2 and the high specific absorption rate (SAR) of inversion and refocusing pulses bring great challenges to quantitative T1, T2 and diffusion imaging. Here, we present the MESMERISED sequence (Multiplexed Echo Shifted Multiband Excited and Recalled Imaging of STEAM Encoded Diffusion). MESMERISED removes the dead time in Stimulated Echo Acquisition Mode (STEAM) imaging by an echo-shifting mechanism. The echo-shift (ES) factor is independent of multiband (MB) acceleration and allows for very high multiplicative (ESxMB) acceleration factors, particularly under moderate and long mixing times. This results in super-acceleration and high time efficiency at 7 T for quantitative T1 and diffusion imaging, while also retaining the capacity to perform quantitative T2 and B1 mapping. We demonstrate the super-acceleration of MESMERISED for whole-brain T1 relaxometry with total acceleration factors up to 36 at 1.8 mm isotropic resolution, and up to 54 at 1.25 mm resolution qT1 imaging, corresponding to a 6x and 9x speedup, respectively, compared to MB-only accelerated acquisitions. We then demonstrate highly efficient diffusion MRI with high b-values and long diffusion times in two separate cases. First, we show that super-accelerated multi-shell diffusion acquisitions with 370 whole-brain diffusion volumes over 8 b-value shells up to b = 7000 s/mm2 can be generated at 2 mm isotropic in under 8 minutes, a data rate of almost a volume per second, or at 1.8 mm isotropic in under 11 minutes, achieving up to 3.4x speedup compared to MB-only. A comparison of b = 7000 s/mm2 MESMERISED against standard MB pulsed gradient spin echo (PGSE) diffusion imaging shows 70% higher SNR efficiency and greater effectiveness in supporting complex diffusion signal modeling. Second, we demonstrate time-efficient sampling of different diffusion times with 1.8 mm isotropic diffusion data acquired at four diffusion times up to 290 ms, which supports both Diffusion Tensor Imaging (DTI) and Diffusion Kurtosis Imaging (DKI) at each diffusion time. Finally, we demonstrate how adding quantitative T2 and B1+ mapping to super-accelerated qT1 and diffusion imaging enables efficient quantitative multi-contrast mapping with the same MESMERISED sequence and the same readout train. MESMERISED extends possibilities to efficiently probe T1, T2 and diffusion contrast for multi-component modeling of tissue microstructure.

High-resolution multicontrast tomography with an X-ray microarray anode–structured target source

Significance Talbot–Lau interferometry (TLI) holds remarkable potential for multicontrast X-ray imaging but suffers from technical challenges associated with microfabrication and limited efficiency. We tackle the frontier challenges in this field by developing a microarray anode–structured target source with a built-in structured illumination scheme. Our development facilitates high-resolution and high-sensitivity TLI imaging without the absorption source grating. We demonstrate the tri-contrast tomography capability with a Drum fish tooth specimen and separate the biological features with different combinations of physical properties. Our approach not only addresses the long-standing challenges in the field of X-ray TLI phase-contrast imaging but also features a compact setup that can potentially be made broadly available to academia research and industrial applications.

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.

Feasibility of MR fingerprinting using a high-performance 0.55 T MRI system

BackgroundMR fingerprinting (MRF) is a versatile method for rapid multi-parametric quantification. The application of MRF for lower MRI field could enable multi-contrast imaging and improve exam efficiency on these systems. The purpose of this work is to demonstrate the feasibility of 3D whole-brain T1 and T2 mapping using MR fingerprinting on a contemporary 0.55 T MRI system. Materials and methodsA 3D whole brain stack-of-spirals FISP MRF sequence was implemented for 0.55 T. Quantification was validated using the NIST/ISMRM Quantitative MRI phantom, and T1 and T2 values of white matter, gray matter, and cerebrospinal fluid were measured in 19 healthy subjects. To assess MRF performance in the lower SNR regime of 0.55 T, measurement precision was calculated from 100 simulated pseudo-replicas of in vivo data and within-session measurement repeatability was evaluated. ResultsT1 and T2 values calculated by MRF were strongly correlated to standard measurements in the ISMRM/NIST MRI system phantom (R2 > 0.99), with a small constant bias of approximately 5 ms in T2 values. 3D stack-of-spirals MRF was successfully applied for whole brain quantitative T1 and T2 at 0.55 T, with spatial resolution of 1.2 mm × 1.2 mm × 5 mm, and acquisition time of 8.5 min. Moreover, the T1 and T2 quantifications had precision <5%, despite the lower SNR of 0.55 T. ConclusionA 3D whole-brain stack-of-spirals FISP MRF sequence is feasible for T1 and T2 mapping at 0.55 T.

A prototype spatial-spectral CT system for material decomposition with energy-integrating detectors.

Spectral CT has great potential for a variety of clinical applications due to improved tissue and material discrimination over conventional single-energy CT. Many clinical and preclinical spectral CT systems have two spectral channels enabling dual-energy CT. Strategies include split filtration, dual-layer detectors, photon-counting detectors, and kVp switching. The motivation for this work is the development of an x-ray source spectral modulation device with three or more spectral channels to enable high-sensitivity multi-material decomposition with energy-integrating detectors. We present spatial-spectral filters which are a new x-ray source modulation technology with the potential for additional channel diversity. The filtering device consists of an array of K-edge materials which divide the x-ray beam into spectrally varied beamlets. This design allows for an arbitrary number of spectral channels-trading off spatial and spectral information. We use a one-step model-based material decomposition (MBMD) algorithm to iteratively estimate material density images directly from the spatial-spectral CT data. In this work, we present a prototype spatial-spectral filter integrated with an x-ray CT test bench. The filter is composed of an array of tin, erbium, tantalum, and lead filter tiles which spatially modulate the system spectral sensitivity pattern. In a simulation study, we investigate the particular problem of mis-calibration between the data acquisition and the reconstruction model. With an understanding of the required model accuracy, we present a spectral calibration method to estimate the critical model parameters. To demonstrate feasibility of the spatial-spectral filter with a calibrated beamlet model, we collected a spatial-spectral CT scan of a multicontrast-enhanced phantom containing water, iodine, and gadolinium solutions. With simulations, we show that material decomposition is possible with spatial-spectral-filtered CT data, and we demonstrate the importance of a well-calibrated physical model. We find a 50% increase in error for focal spot model mismatch of 0.27mm and gap width model mismatch of 16mμ. With physical results, we demonstrate that the calibrated system model is in close agreement with the measured data, and that the reconstructed material density images match the ground truth concentrations for the multicontrast phantom. Empirical results indicate gadolinium density estimation had an error of 17-58% mostly due to a systematic constant bias of 0.30-0.60mg/ml. Water density estimates are within 1% and iodine estimates are within 10% of ground truth. These preliminary results demonstrate the potential of spatial-spectral filters to enable multicontrast imaging. Moreover, this device is compatible with energy-integrating detectors and so provides a feasible modification to enable spectral CT imaging with existing single-energy systems.

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.

Traumatic Microbleeds in Mild Traumatic Brain Injury Are Not Associated with Delayed Return to Work or Persisting Post-Concussion Symptoms.

The main objective of this prospective cohort study was to evaluate whether traumatic microbleeds (TMBs) are a significant prognostic factor of return to work (RTW), post-traumatic symptoms, and overall recovery in patients with mild traumatic brain injury (mTBI). One hundred and thirteen patients with mTBI were recruited from the Helsinki University Hospital emergency units. All patients underwent multi-contrast 3T magnetic resonance imaging (MRI) 3-17 days after mTBI. Patients were evaluated in the Traumatic Brain Injury Outpatient Clinic of Helsinki University Hospital 1 month after injury. Post-concussion symptoms were assessed with the Post-Concussion Symptom Questionnaire (RPQ) and overall recovery was assessed with the Glasgow Outcome Scale Extended (GOS-E). Their time to RTW was continuously measured up to 1 year after TBI. Median RTW was 9 days (interquartile range [IQR] 4-30) after mTBI and full RTW rate after 1 year was 98%. Patients with TMBs (n = 22) did not have more post-concussion symptoms (median RPQ 10.0 vs. 7.0, p = 0.217) or worse overall recovery (58% vs. 56% with GOS-E = 8, p = 0.853) than patients without TMBs (n = 91). There was no significant difference in time to RTW (13.5 vs. 7.0 days, p = 0.063). In this study, patients with TMBs did not have delayed RTW or more post-concussion symptoms than other patients with mTBI. TMBs in mTBI do not seem to be a significant prognostic factor of RTW.

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.

Synergistic multi-contrast cardiac magnetic resonance image reconstruction

Cardiac magnetic resonance imaging (CMR) is an important tool for the non-invasive diagnosis of a variety of cardiovascular diseases. Parametric mapping with multi-contrast CMR is able to quantify tissue alterations in myocardial disease and promises to improve patient care. However, magnetic resonance imaging is an inherently slow imaging modality, resulting in long acquisition times for parametric mapping which acquires a series of cardiac images with different contrasts for signal fitting or dictionary matching. Furthermore, extra efforts to deal with respiratory and cardiac motion by triggering and gating further increase the scan time. Several techniques have been developed to speed up CMR acquisitions, which usually acquire less data than that required by the Nyquist-Shannon sampling theorem, followed by regularized reconstruction to mitigate undersampling artefacts. Recent advances in CMR parametric mapping speed up CMR by synergistically exploiting spatial-temporal and contrast redundancies. In this article, we will review the recent developments in multi-contrast CMR image reconstruction for parametric mapping with special focus on low-rank and model-based reconstructions. Deep learning-based multi-contrast reconstruction has recently been proposed in other magnetic resonance applications. These developments will be covered to introduce the general methodology. Current technical limitations and potential future directions are discussed. This article is part of the theme issue 'Synergistic tomographic image reconstruction: part 1'.

A Portable Multicontrast Microscope for Multiscale Imaging of the Microcirculation

Objective To develop a portable microscope capable of interrogating the microcirculation in vivo with multiple contrasts over multiple spatial scales. Methods We used state-of-the-art 3D printing and optics design techniques to fabricate a miniature microscope the size of a US quarter (Fig. 1 a, b)1. It weights 9g and acquires images via three optical contrasts: intrinsic optical signals (IOS)2, laser speckle contrast (LSC)3 and fluorescence (FL). The IOS channel, which relies on light absorption by red blood cell (RBC) bound hemoglobin (HbT), can be used to visualize microvascular morphology, while the LSC channel enables observing blood flow levels by using the orderly flow of RBCs along vessels as a contrast agent. The FL channel can be used for arterio-venous discrimination via the arrival times of an intravenously (iv) injected fluorescent dye (e.g. FITC-Dextran, 70 kDa). The microscope can acquire images at 15 frames per second over a 3x3 mm2 field of view (FoV) at 5 µm resolution. We also designed an adaptor which enhances the resolution tenfold to 0.5 µm. It is operated via USB connections to a laptop, and is portable (Fig. 1c), making it convenient for imaging the microcirculation in a range of preclinical applications. Results We demonstrated the utility of our microscope by using it to interrogate the structure and function of the murine brain and ear microcirculation at different spatial scales. Figs. 1d, e show maps of microvascular morphology and blood flow in a portion of the murine brain under ketamine anesthesia at 5 µm resolution. Fig. 1f shows the map of arrival times of the iv injected fluorescent dye. Dark blue regions corresponding to arrival times less than 0.5 s were used to identify arteries. Figs. 1g, h show plots of changes in HbT (i.e. cerebral blood volume) and cerebral blood flow (CBF) corresponding to an artery and vein (boxes marked “A” and “V” in Fig. 1d) over 3 hours while the animal recovers from anesthesia. Here, the arterial and venous time courses illustrate contrasting flow-volume relationships that indicate the varying systemic effects of anesthesia on components of the microcirculation. Fig 2a shows the microscope with its high-magnification adaptor, while Fig. 2b illustrates the exquisite microvascular details revealed with the adaptor in contrast to images acquired without it. Here, the FL channel was used in conjunction with an iv injected dye to enhance microvascular contrast. One could also “stitch” together these high-resolution images to create a mosaic with wider coverage (Fig. 2c). Since individual RBCs were discernable in these high-resolution images (Fig. 2d), we successfully employed RBC tracking to characterize cellular-scale flow dynamics within the microcirculation (Fig. 2e). Conclusion The multicontrast and multiscale imaging capabilities of our microscope will enable investigators to comprehensively interrogate the structure and function of microcirculation in diverse organ sites and preclinical disease models. Its design and portability enables imaging of unanesthetized animals, convenient usage, and fosters collaborations.

8-inch-diameter field of view for X-ray differential phase-contrast imaging

The X-ray differential phase-contrast imaging (DPCI) based on Talbot–Lau​ interferometers (TLIs) is a promising imaging technique for non-destructive testing. The compact imaging configurations that have a large field-of-view (FoV) require the use of bent phase gratings and large-area analyzer gratings. The cascaded TLIs reduce the aspect ratio requirement of large-area analyzer gratings, which facilitates the fabrication of these gratings. However, the bent silicon-based phase gratings are difficult to obtain directly because of the brittleness of silicon wafers. In this work, we present a method to prepare 5-inch cylindrically bent silicon-based phase gratings and 8-inch analyzer gratings. Moreover, we also present their applications in the cascaded TLIs. The mechanical stress that originates from thermal oxidation enables us to cylindrically bend silicon-based phase gratings. Furthermore, as compared to the use of plane phase gratings, the use of cylindrically bent phase gratings allows Moiré fringes to appear in the entire 8-inch FoV. Finally, Moiré fringes and multi-contrast images of the samples (water, liquid soap filled in heat-shrink tubes) demonstrate the effectiveness of the fabrication of the bent silicon-based phase gratings and imaging in the entire 8-inch FoV. The proposed configuration is applicable for attaining multi-contrast images with 8-inch FoV at a low cost.

Data-Driven multi-Contrast spectral microstructure imaging with InSpect: INtegrated SPECTral component estimation and mapping.

We introduce and demonstrate an unsupervised machine learning technique for spectroscopic analysis of quantitative MRI experiments. Our algorithm supports estimation of one-dimensional spectra from single-contrast data, and multidimensional correlation spectra from simultaneous multi-contrast data. These spectrum-based approaches allow model-free investigation of tissue properties, but require regularised inversion of a Laplace transform or Fredholm integral, which is an ill-posed calculation. Here we present a method that addresses this limitation in a data-driven way. The algorithm simultaneously estimates a canonical basis of spectral components and voxelwise maps of their weightings, thereby pooling information across whole images to regularise the ill-posed problem. We show in simulations that our algorithm substantially outperforms current voxelwise spectral approaches. We demonstrate the method on multi-contrast diffusion-relaxometry placental MRI scans, revealing anatomically-relevant sub-structures, and identifying dysfunctional placentas. Our algorithm vastly reduces the data required to reliably estimate spectra, opening up the possibility of quantitative MRI spectroscopy in a wide range of new applications. Our InSpect code is available at github.com/paddyslator/inspect.

Deep Learning-Based ECG-Free Cardiac Navigation for Multi-Dimensional and Motion-Resolved Continuous Magnetic Resonance Imaging.

For the clinical assessment of cardiac vitality, time-continuous tomographic imaging of the heart is used. To further detect e.g., pathological tissue, multiple imaging contrasts enable a thorough diagnosis using magnetic resonance imaging (MRI). For this purpose, time-continous and multi-contrast imaging protocols were proposed. The acquired signals are binned using navigation approaches for a motion-resolved reconstruction. Mostly, external sensors such as electrocardiograms (ECG) are used for navigation, leading to additional workflow efforts. Recent sensor-free approaches are based on pipelines requiring prior knowledge, e.g., typical heart rates. We present a sensor-free, deep learning-based navigation that diminishes the need for manual feature engineering or the necessity of prior knowledge compared to previous works. A classifier is trained to estimate the R-wave timepoints in the scan directly from the imaging data. Our approach is evaluated on 3-D protocols for continuous cardiac MRI, acquired in-vivo and free-breathing with single or multiple imaging contrasts. We achieve an accuracy of > 98% on previously unseen subjects, and a well comparable image quality with the state-of-the-art ECG-based reconstruction. Our method enables an ECG-free workflow for continuous cardiac scans with simultaneous anatomic and functional imaging with multiple contrasts. It can be potentially integrated without adapting the sampling scheme to other continuous sequences by using the imaging data for navigation and reconstruction.

Accelerated multicontrast reconstruction for synthetic MRI using joint parallel imaging and variable splitting networks

Synthetic magnetic resonance imaging (MRI) requires the acquisition of multicontrast images to estimate quantitative parameter maps, such as T1 , T2 , and proton density (PD). The study aims to develop a multicontrast reconstruction method based on joint parallel imaging (JPI) and joint deep learning (JDL) to enable further acceleration of synthetic MRI. The JPI and JDL methods are extended and combined to improve reconstruction for better-quality, synthesized images. JPI is performed as a first step to estimate the missing k-space lines, and JDL is then performed to correct and refine the previous estimate with a trained neural network. For the JDL architecture, the original variable splitting network (VS-Net) is modified and extended to form a joint variable splitting network (JVS-Net) to apply to multicontrast reconstructions. The proposed method is designed and tested for multidynamic multiecho (MDME) images with Cartesian uniform under-sampling using acceleration factors between 4 and 8. It is demonstrated that the normalized root-mean-square error (nRMSE) is lower and the structural similarity index measure (SSIM) values are higher with the proposed method compared to both the JPI and JDL methods individually. The method also demonstrates the potential to produce a set of synthesized contrast-weighted images that closely resemble those from the fully sampled acquisition without erroneous artifacts. Combining JPI and JDL enables the reconstruction of highly accelerated synthetic MRIs.

Synthesis of brain tumor multicontrast MR images for improved data augmentation.

Medical image analysis using deep neural networks has been actively studied. For accurate training of deep neural networks, the learning data should be sufficient and have good quality and generalized characteristics. However, in medical images, it is difficult to acquire sufficient patient data because of the difficulty of patient recruitment, the burden of annotation of lesions by experts, and the invasion of patients' privacy. In comparison, the medical images of healthy volunteers can be easily acquired. To resolve this data bias problem, the proposed method synthesizes brain tumor images from normal brain images. Our method can synthesize a huge number of brain tumor multicontrast MR images from numerous healthy brain multicontrast MR images and various concentric circles. Because tumors have complex characteristics, the proposed method simplifies them into concentric circles that are easily controllable. Then, it converts the concentric circles into various realistic tumor masks through deep neural networks. The tumor masks are used to synthesize realistic brain tumor images from normal brain images. We performed a qualitative and quantitative analysis to assess the usefulness of augmented data from the proposed method. Data augmentation by the proposed method provided significant improvements to tumor segmentation compared with other GAN-based methods. Intuitive experimental results are available online at https://github.com/KSH0660/BrainTumor. The proposed method can control the grade tumor masks by the concentric circles, and synthesize realistic brain tumor multicontrast MR images. In terms of data augmentation, the proposed method can successfully synthesize brain tumor images that can be used to train tumor segmentation networks or other deep neural networks.

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

PurposeTo improve image quality of multi-contrast imaging with the proposed Autocalibrated Parallel Imaging Reconstruction for Extended Multi-Contrast Imaging (APIR4EMC). MethodsAPIR4EMC 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. ResultsCompared 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. ConclusionCompared to single contrast reconstruction with GRAPPA, APIR4EMC reduces artifacts and noise amplification in accelerated multi-contrast imaging.

A Coarse-to-Fine Deformable Transformation Framework for Unsupervised Multi-Contrast MR Image Registration with Dual Consistency Constraint.

Multi-contrast magnetic resonance (MR) image registration is useful in the clinic to achieve fast and accurate imaging-based disease diagnosis and treatment planning. Nevertheless, the efficiency and performance of the existing registration algorithms can still be improved. In this paper, we propose a novel unsupervised learning-based framework to achieve accurate and efficient multi-contrast MR image registration. Specifically, an end-to-end coarse-to-fine network architecture consisting of affine and deformable transformations is designed to improve the robustness and achieve end-to-end registration. Furthermore, a dual consistency constraint and a new prior knowledge-based loss function are developed to enhance the registration performances. The proposed method has been evaluated on a clinical dataset containing 555 cases, and encouraging performances have been achieved. Compared to the commonly utilized registration methods, including VoxelMorph, SyN, and LT-Net, the proposed method achieves better registration performance with a Dice score of 0.8397± 0.0756 in identifying stroke lesions. With regards to the registration speed, our method is about 10 times faster than the most competitive method of SyN (Affine) when testing on a CPU. Moreover, we prove that our method can still perform well on more challenging tasks with lacking scanning information data, showing the high robustness for the clinical application.

Cascaded residual U-net for fully automatic segmentation of 3D carotid artery in high-resolution multi-contrast MR images

Accurate and automatic carotid artery segmentation for magnetic resonance (MR) images is eagerly expected, which can greatly assist a comprehensive study of atherosclerosis and accelerate the translation. Although many efforts have been made, identification of the inner lumen and outer wall in diseased vessels is still a challenging task due to complex vascular deformation, blurred wall boundary, and confusing componential expression. In this paper, we introduce a novel fully automatic 3D framework for simultaneously segmenting the carotid artery from high-resolution multi-contrast MR sequences based on deep learning. First, an optimal channel fitting structure is designed for identity mapping, and a novel 3D residual U-net is used as a basic network. Second, high-resolution MR images are trained using both patch-level and global-level strategies, and the two pre-segmentation results are optimized based on structural characteristics. Third, the optimized pre-segmentation results are cascaded with the patch-cropped MR volume data and trained to segment the carotid lumen and wall. Extensive experiments demonstrate the proposed method outperforms the state-of-the-art 3D Unet-based segmentation models.

Improving subspace constrained radial fast spin echo MRI using block matching driven non-local low rank regularization

Subspace-constrained reconstruction methods restrict the relaxation signals (of size M) in the scene to a pre-determined subspace (of size K≪M) and allow multi-contrast imaging and parameter mapping from accelerated acquisitions. However, these constraints yield poor image quality at some imaging contrasts, which can impact the parameter mapping performance. Additional regularization such as the use of joint-sparse (JS) or locally-low-rank (LLR) constraints can help improve the recovery of these images but are not sufficient when operating at high acceleration rates. We propose a method, non-local rank 3D (NLR3D), that is built on block matching and transform domain low rank constraints to allow high quality recovery of subspace-coefficient images (SCI) and subsequent multi-contrast imaging and parameter mapping. The performance of NLR3D was evaluated using Monte-Carlo (MC) simulations and compared against the JS and LLR methods. In vivo T 2 mapping results are presented on brain and knee datasets. MC results demonstrate improved bias, variance, and MSE behavior in both the multi-contrast images and parameter maps when compared to the JS and LLR methods. In vivo brain and knee results at moderate and high acceleration rates demonstrate improved recovery of high SNR early TE images as well as parameter maps. No significant difference was found in the T2 values measured in ROIs between the NLR3D reconstructions and the reference images (Wilcoxon signed rank test). The proposed method, NLR3D, enables recovery of high-quality SCI and, consequently, the associated multi-contrast images and parameter maps.