Multi-contrast Imaging Research Articles

Recurrent neural network-based simultaneous cardiac T1, T2, and T1ρ mapping.

The purpose of the current study was to explore the feasibility of training a deep neural network to accelerate the process of generating T1, T2, and T1ρ maps for a recently proposed free-breathing cardiac multiparametric mapping technique, where a recurrent neural network (RNN) was utilized to exploit the temporal correlation among the multicontrast images. The RNN-based model was developed for rapid and accurate T1, T2, and T1ρ estimation. Bloch simulation was performed to simulate a dataset of more than 10 million signals and time correspondences with different noise levels for network training. The proposed RNN-based method was compared with a dictionary-matching method and a conventional mapping method to evaluate the model's effectiveness in phantom and in vivo studies at 3 T, respectively. In phantom studies, the RNN-based method and the dictionary-matching method achieved similar accuracy and precision in T1, T2, and T1ρ estimations. In in vivo studies, the estimated T1, T2, and T1ρ values obtained by the two methods achieved similar accuracy and precision for 10 healthy volunteers (T1: 1228.70 ± 53.80 vs. 1228.34 ± 52.91 ms, p > 0.1; T2: 40.70 ± 2.89 vs. 41.19 ± 2.91 ms, p > 0.1; T1ρ: 45.09 ± 4.47 vs. 45.23 ± 4.65 ms, p > 0.1). The RNN-based method can generate cardiac multiparameter quantitative maps simultaneously in just 2 s, achieving 60-fold acceleration compared with the dictionary-matching method. The RNN-accelerated method offers an almost instantaneous approach for reconstructing accurate T1, T2, and T1ρ maps, being much more efficient than the dictionary-matching method for the free-breathing multiparametric cardiac mapping technique, which may pave the way for inline mapping in clinical applications.

Ex-Vivo Hippocampus Segmentation Using Diffusion-Weighted MRI

The hippocampus is a crucial brain structure involved in memory formation, spatial navigation, emotional regulation, and learning. An accurate MRI image segmentation of the human hippocampus plays an important role in multiple neuro-imaging research and clinical practice, such as diagnosing neurological diseases and guiding surgical interventions. While most hippocampus segmentation studies focus on using T1-weighted or T2-weighted MRI scans, we explore the use of diffusion-weighted MRI (dMRI), which offers unique insights into the microstructural properties of the hippocampus. Particularly, we utilize various anisotropy measures derived from diffusion MRI (dMRI), including fractional anisotropy, mean diffusivity, axial diffusivity, and radial diffusivity, for a multi-contrast deep learning approach to hippocampus segmentation. To exploit the unique benefits offered by various contrasts in dMRI images for accurate hippocampus segmentation, we introduce an innovative multimodal deep learning architecture integrating cross-attention mechanisms. Our proposed framework comprises a multi-head encoder designed to transform each contrast of dMRI images into distinct latent spaces, generating separate image feature maps. Subsequently, we employ a gated cross-attention unit following the encoder, which facilitates the creation of attention maps between every pair of image contrasts. These attention maps serve to enrich the feature maps, thereby enhancing their effectiveness for the segmentation task. In the final stage, a decoder is employed to produce segmentation predictions utilizing the attention-enhanced feature maps. The experimental outcomes demonstrate the efficacy of our framework in hippocampus segmentation and highlight the benefits of using multi-contrast images over single-contrast images in diffusion MRI image segmentation.

System characterization of a human-sized 3D real-time magnetic particle imaging scanner for cerebral applications

Since the initial patent in 2001, the Magnetic Particle Imaging community has endeavored to develop a human-applicable Magnetic Particle Imaging scanner, incorporating contributions from various research fields. Here we present an improved head-sized Magnetic Particle Imaging scanner with low power consumption, operated by open-source software and characterize it with an emphasis on human safety. The focus is on the evaluation of the technical components and on phantom experiments for brain perfusion. We achieved 3D single- and multi-contrast imaging at 4 Hz frame rate. The system characterization includes sensitivity, resolution, perfusion and multi-contrast experiments as well as field measurements and sequence analysis. Images were acquired with a clinically approved tracer and within human peripheral nerve stimulation thresholds. This advanced scanner holds potential as a tomographic imager for diagnosing conditions such as ischemic stroke (different stages) or intracranial hemorrhage in environments lacking electromagnetic shielding, such as the intensive care unit.

Plug-and-play DPC-based quantitative phase microscope.

Point-of-care testing (POCT) plays an increasingly important role in biomedical research and health care. Quantitative phase microscopes (QPMs) with good contrast, no invasion, no labeling, high speed and automation could be effectively applied for POCT. However, most QPMs are fixed on the optical platform with bulky size, lack of timeliness, which remained challenging in POCT solutions. In this paper, we proposed a plug-and-play QPM with multimode imaging based on the quantitative differential phase contrast (qDPC) method. The system employs a programmable LED array as the light source and uses the GPU to accelerate the calculation, which can realize multi-contrast imaging with six modes. Accurate phase measurement and real-time phase imaging are implemented by the proposed qDPC algorithms for quantitative phase targets and biomedical samples. A 3D electric control platform is designed for mechanical control of field of view and focusing without manual operations. The experimental results verify the robustness and high performance of the setup. Even a rookie could finish the POCT scheme for biomedical applications at the scene using the QPM with a compact size of 140 × 165 × 250 mm3.

A color-based tumor segmentation method for clinical ex vivo breast tissue assessment utilizing a multi-contrast brightfield imaging strategy.

We demonstrate an automated two-step tumor segmentation method leveraging color information from brightfield images of fresh core needle biopsies of breast tissue. Three different color spaces (HSV, CIELAB, YCbCr) were explored for the segmentation task. By leveraging white-light and green-light images, we identified two different types of color transformations that could separate adipose from benign and tumor or cancerous tissue. We leveraged these two distinct color transformation methods in a two-step process where adipose tissue segmentation was followed by benign tissue segmentation thereby isolating the malignant region of the biopsy. Our tumor segmentation algorithm and imaging probe could highlight suspicious regions on unprocessed biopsy tissue to guide selection of areas most similar to malignant tissues for tissue pathology whether it be formalin fixed or frozen sections, expedite tissue selection for molecular testing, detect positive tumor margins, or serve an alternative to tissue pathology, in countries where these services are lacking.

Joint Under-Sampling Pattern and Dual-Domain Reconstruction for Accelerating Multi-Contrast MRI.

Multi-Contrast Magnetic Resonance Imaging (MCMRI) utilizes the short-time reference image to facilitate the reconstruction of the long-time target one, providing a new solution for fast MRI. Although various methods have been proposed, they still have certain limitations. 1) existing methods featuring the preset under-sampling patterns give rise to redundancy between multi-contrast images and limit their model performance; 2) most methods focus on the information in the image domain, prior knowledge in the k-space domain has not been fully explored; and 3) most networks are manually designed and lack certain physical interpretability. To address these issues, we propose a joint optimization of the under-sampling pattern and a deep-unfolding dual-domain network for accelerating MCMRI. Firstly, to reduce the redundant information and sample more contrast-specific information, we propose a new framework to learn the optimal under-sampling pattern for MCMRI. Secondly, a dual-domain model is established to reconstruct the target image in both the image domain and the k-space frequency domain. The model in the image domain introduces a spatial transformation to explicitly model the inconsistent and unaligned structures of MCMRI. The model in the k-space learns prior knowledge from the frequency domain, enabling the model to capture more global information from the input images. Thirdly, we employ the proximal gradient algorithm to optimize the proposed model and then unfold the iterative results into a deep-unfolding network, called MC-DuDoN. We evaluate the proposed MC-DuDoN on MCMRI super-resolution and reconstruction tasks. Experimental results give credence to the superiority of the current model. In particular, since our approach explicitly models the inconsistent structures, it shows robustness on spatially misaligned MCMRI. In the reconstruction task, compared with conventional masks, the learned mask restores more realistic images, even under an ultra-high acceleration ratio ( ×30 ). Code is available at https://github.com/lpcccc-cv/MC-DuDoNet.

Flexible Alignment Super-Resolution Network for Multi-Contrast Magnetic Resonance Imaging

Flexible Alignment Super-Resolution Network for Multi-Contrast Magnetic Resonance Imaging

Cardiac MR Fingerprinting: Overview, Technical Developments, and Applications.

Cardiovascular magnetic resonance (CMR) is an established imaging modality with proven utility in assessing cardiovascular diseases. The ability of CMR to characterize myocardial tissue using T1- and T2-weighted imaging, parametric mapping, and late gadolinium enhancement has allowed for the non-invasive identification of specific pathologies not previously possible with modalities like echocardiography. However, CMR examinations are lengthy and technically complex, requiring multiple pulse sequences and different anatomical planes to comprehensively assess myocardial structure, function, and tissue composition. To increase the overall impact of this modality, there is a need to simplify and shorten CMR exams to improve access and efficiency, while also providing reproducible quantitative measurements. Multiparametric MRI techniques that measure multiple tissue properties offer one potential solution to this problem. This review provides an in-depth look at one such multiparametric approach, cardiac magnetic resonance fingerprinting (MRF). The article is structured as follows. First, a brief review of single-parametric and (non-Fingerprinting) multiparametric CMR mapping techniques is presented. Second, a general overview of cardiac MRF is provided covering pulse sequence implementation, dictionary generation, fast k-space sampling methods, and pattern recognition. Third, recent technical advances in cardiac MRF are covered spanning a variety of topics, including simultaneous multislice and 3D sampling, motion correction algorithms, cine MRF, synthetic multicontrast imaging, extensions to measure additional clinically important tissue properties (proton density fat fraction, T2*, and T1ρ), and deep learning methods for image reconstruction and parameter estimation. The last section will discuss potential clinical applications, concluding with a perspective on how multiparametric techniques like MRF may enable streamlined CMR protocols. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 1.

Real-time multi-contrast magnetic particle imaging for the detection of gastrointestinal bleeding

Gastrointestinal bleeding, as a potentially life-threatening condition, is typically diagnosed by radiation-based imaging modalities like computed tomography or more invasively catheter-based angiography. Endoscopy enables examination of the upper gastrointestinal tract and the colon but not of the entire small bowel. Magnetic Particle Imaging (MPI) enables non-invasive, volumetric imaging without ionizing radiation. The aim of this study was to evaluate the feasibility of detecting gastrointestinal bleeding by single- and multi-contrast MPI using human-sized organs. A 3D-printed small bowel phantom and porcine small bowel specimens were prepared with a defect within the bowel wall as the source of a bleeding. For multi-contrast MPI, the bowel lumen was filled with an intestinal tracer representing an orally administered tracer. MPI was performed to evaluate the fluid exchange between the vascular compartment of the bowel wall and the lumen while a blood pool tracer was applied. Leakage of the blood pool tracer was observed to the bowel lumen. Multi-contrast MPI enabled co-registration of both tracers at the same location within the bowel lumen indicating gastrointestinal bleeding. Single- and multi-contrast MPI are feasible to visualize gastrointestinal bleeding. Therefore, MPI might emerge as a useful tool for radiation-free detection of bleeding within the entire gastrointestinal tract.

Dual contrast attention-guided multi-frequency fusion for multi-contrast MRI super-resolution

Objective. Multi-contrast magnetic resonance (MR) imaging super-resolution (SR) reconstruction is an effective solution for acquiring high-resolution MR images. It utilizes anatomical information from auxiliary contrast images to improve the quality of the target contrast images. However, existing studies have simply explored the relationships between auxiliary contrast and target contrast images but did not fully consider different anatomical information contained in multi-contrast images, resulting in texture details and artifacts unrelated to the target contrast images. Approach. To address these issues, we propose a dual contrast attention-guided multi-frequency fusion (DCAMF) network to reconstruct SR MR images from low-resolution MR images, which adaptively captures relevant anatomical information and processes the texture details and low-frequency information from multi-contrast images in parallel. Specifically, after the feature extraction, a feature selection module based on a dual contrast attention mechanism is proposed to focus on the texture details of the auxiliary contrast images and the low-frequency features of the target contrast images. Then, based on the characteristics of the selected features, a high- and low-frequency fusion decoder is constructed to fuse these features. In addition, a texture-enhancing module is embedded in the high-frequency fusion decoder, to highlight and refine the texture details of the auxiliary contrast and target contrast images. Finally, the high- and low-frequency fusion process is constrained by integrating a deeply-supervised mechanism into the DCAMF network. Main results. The experimental results show that the DCAMF outperforms other state-of-the-art methods. The peak signal-to-noise ratio and structural similarity of DCAMF are 39.02 dB and 0.9771 on the IXI dataset and 37.59 dB and 0.9770 on the BraTS2018 dataset, respectively. The image recovery is further validated in segmentation tasks. Significance. Our proposed SR model can enhance the quality of MR images. The results of the SR study provide a reliable basis for clinical diagnosis and subsequent image-guided treatment.

Magnetic resonance coherence pathway unraveling

Efficiently acquiring multi-contrast magnetic resonance imaging data is crucial for patient comfort and clinical throughput. Developing scan acceleration methods tailored for specific applications drastically improves the value of an MRI examination. Here, we propose a novel method to control the aliasing of simultaneously acquired images of multiple spin echo coherence pathways with the goal of producing high quality multi-contrast images from a single acquisition. Modulating the radiofrequency phase of several pulses applied in brief succession also uniquely modulates the phase of spin echo coherence pathways. A method, termed magnetic resonance coherence pathway unraveling (MR-CPU), to control the aliasing of simultaneously acquired coherence pathway images is developed here along with parallel imaging-based reconstruction methods to separate them. MR-CPU was validated in phantom experiments and tested in vivo. High levels of correlation between reference pathway images and MR-CPU-derived coherence pathway images were found from the phantom experiments. Minimal artifacts arising from the separation of the overlapped coherence pathway images were observed in vivo. MR-CPU provides a novel mechanism through which to acquire and separate multiple overlapped coherence pathway images, thus adding to the diagnostic potential of an MRI exam without the penalty of additional scan time.

Carotid artery perivascular adipose tissue on magnetic resonance imaging: a potential indicator for carotid vulnerable atherosclerotic plaque.

Magnetic resonance imaging (MRI) has the potential in assessing the inflammation of perivascular adipose tissue (PVAT) due to its excellent soft tissue contrast. However, evidence is lacking for the association between carotid PVAT measured by MRI and carotid vulnerable atherosclerotic plaques. This study aimed to investigate the association between signal intensity of PVAT and vulnerable plaques in carotid arteries using multi-contrast magnetic resonance (MR) vessel wall imaging. In this cross-sectional study, a total of 104 patients (mean age, 64.9±7.0 years; 86 men) with unilateral moderate-to-severe atherosclerotic stenosis referred to carotid endarterectomy (CEA) were recruited from April 2018 to December 2020 at Department of Neurosurgery of Peking University Third Hospital. All patients underwent multi-contrast MR vessel wall imaging including time-of-flight (ToF) MR angiography, black-blood T1-weighted (T1w) and T2-weighted (T2w) and simultaneous non-contrast angiography and intraplaque hemorrhage (IPH) imaging sequences. Patients with contraindications to endarterectomy or MRI examinations were excluded. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of PVAT were measured on ToF images and vulnerable plaque characteristics including IPH, large lipid-rich necrotic core (LRNC), and fibrous cap rupture (FCR) were identified. The SNR and CNR of PVAT were compared between slices with and without vulnerable plaque features using Mann-Whitney U test and their associations were analyzed using the generalized linear mixed model (GLMM). Carotid artery slices with IPH (30.93±14.56 vs. 27.34±10.02; P<0.001), FCR (30.35±13.82 vs. 27.53±10.37; P=0.006), and vulnerable plaque (29.15±12.52 vs. 27.32±10.05; P=0.016) had significantly higher value of SNR of PVAT compared to those without. After adjusting for clinical confounders, the SNR of PVAT was significantly associated with presence of IPH [odds ratio (OR) =0.627, 95% confidence interval (CI): 0.465-0.847, Puncorr=0.002, PFDR=0.016] and vulnerable plaque (OR =0.762, 95% CI: 0.629-0.924, Puncorr=0.006, PFDR=0.020). However, no significant association was found between the CNR of PVAT and presence of vulnerable plaque features (all P>0.05). The SNR of carotid artery PVAT measured by ToF MR angiography is independently associated with vulnerable atherosclerotic plaque features, suggesting that the signal intensity of PVAT might be an effective indicator for vulnerable plaque.

Reducing annotation burden in MR: A novel MR-contrast guided contrastive learning approach for image segmentation.

Contrastive learning, a successful form of representational learning, has shown promising results in pretraining deep learning (DL) models for downstream tasks. When working with limited annotation data, as in medical image segmentation tasks, learning domain-specific local representations can further improve the performance of DL models. In this work, we extend the contrastive learning framework to utilize domain-specific contrast information from unlabeled Magnetic Resonance (MR) images to improve the performance of downstream MR image segmentation tasks in the presence of limited labeled data. The contrast in MR images is controlled by underlying tissue properties (e.g., T1 or T2) and image acquisition parameters. We hypothesize that learning to discriminate local representations based on underlying tissue properties should improve subsequent segmentation tasks on MR images. We propose a novel constrained contrastive learning (CCL) strategy that uses tissue-specific information via a constraint map to define positive and negative local neighborhoods for contrastive learning, embedding this information in the representational space during pretraining. For a given MR contrast image, the proposed strategy uses local signal characteristics (constraint map) across a set of related multi-contrast MR images as a surrogate for underlying tissue information. We demonstrate the utility of the approach for downstream: (1) multi-organ segmentation tasks in T2-weighted images where a DL model learns T2 information with constraint maps from a set of 2D multi-echo T2-weighted images (n=101) and (2) tumor segmentation tasks in multi-parametric images from the public brain tumor segmentation (BraTS) (n=80) dataset where DL models learn T1 and T2 information from multi-parametric BraTS images. Performance is evaluated on downstream multi-label segmentation tasks with limited data in (1) T2-weighted images of the abdomen from an in-house Radial-T2 (Train/Test=30/20), (2) public Cartesian-T2 (Train/Test=6/12) dataset, and (3) multi-parametric MR images from the public brain tumor segmentation dataset (BraTS) (Train/Test=40/50). The performance of the proposed CCL strategy is compared to state-of-the-art self-supervised contrastive learning techniques. In each task, a model is also trained using all available labeled data for supervised baseline performance. The proposed CCL strategy consistently yielded improved Dice scores, Precision, and Recall metrics, and reduced HD95 values across all segmentation tasks. We also observed performance comparable to the baseline with reduced annotation effort. The t-SNE visualization of features for T2-weighted images demonstrates its ability to embed T2 information in the representational space. On the BraTS dataset, we also observed that using an appropriate multi-contrast space to learn T1+T2, T1, or T2 information during pretraining further improved the performance of tumor segmentation tasks. Learning to embed tissue-specific information that controls MR image contrast with the proposed constrained contrastive learning improved the performance of DL models on subsequent segmentation tasks compared to conventional self-supervised contrastive learning techniques. The use of such domain-specific local representations could help understand, improve performance, and mitigate the scarcity of labeled data in MR image segmentation tasks.

MGDUN: An interpretable network for multi-contrast MRI image super-resolution reconstruction

Magnetic resonance imaging (MRI) Super-Resolution (SR) aims to obtain high resolution (HR) images with more detailed information for precise diagnosis and quantitative image analysis. Deep unfolding networks outperform general MRI SR reconstruction methods by providing better performance and improved interpretability, which enhance the trustworthiness required in clinical practice. Additionally, current SR reconstruction techniques often rely on a single contrast or a simple multi-contrast fusion mechanism, ignoring the complex relationships between different contrasts. To address these issues, in this paper, we propose a Model-Guided multi-contrast interpretable Deep Unfolding Network (MGDUN) for medical image SR reconstruction, which explicitly incorporates the well-studied multi-contrast MRI observation model into an unfolding iterative network. Specifically, we manually design an objective function for MGDUN that can be iteratively computed by the half-quadratic splitting algorithm. The iterative MGDUN algorithm is unfolded into a special model-guided deep unfolding network that explicitly takes into account both the multi-contrast relationship matrix and the MRI observation matrix during the end-to-end optimization process. Extensive experimental results on the multi-contrast IXI dataset and the BraTs 2019 dataset demonstrate the superiority of our proposed model, with PSNR reaching 37.3366 and 35.9690 respectively. Our proposed MGDUN provides a promising solution for multi-contrast MR image super-resolution reconstruction. Code is available at https://github.com/yggame/MGDUN.

Multi-Scale Label-Free Human Brain Imaging with Integrated Serial Sectioning Polarization Sensitive Optical Coherence Tomography and Two-Photon Microscopy.

The study of aging and neurodegenerative processes in the human brain requires a comprehensive understanding of cytoarchitectonic, myeloarchitectonic, and vascular structures. Recent computational advances have enabled volumetric reconstruction of the human brain using thousands of stained slices, however, tissue distortions and loss resulting from standard histological processing have hindered deformation-free reconstruction. Here, the authorsdescribe an integrated serial sectioning polarization-sensitive optical coherence tomography (PSOCT) and two photon microscopy (2PM) system to provide label-free multi-contrast imaging of intact brain structures, including scattering, birefringence, and autofluorescence of human brain tissue. The authors demonstrate high-throughput reconstruction of 4 × 4 × 2cm3 sample blocks and simple registration between PSOCT and 2PM images that enablecomprehensive analysis of myelin content, vascular structure, and cellular information. The high-resolution 2PM images provide microscopic validation and enrichment of the cellular information provided by the PSOCT optical properties on the same sample, revealing the densely packed fibers, capillaries, and lipofuscin-filled cell bodies in the cortex and white matter. It is shown that theimaging system enables quantitative characterization of various pathological features in aging process, including myelin degradation, lipofuscin accumulation, and microvascular changes, which opens up numerous opportunities in the study of neurodegenerative diseases in the future.

HACA3: A unified approach for multi-site MR image harmonization.

The lack of standardization and consistency of acquisition is a prominent issue in magnetic resonance (MR) imaging. This often causes undesired contrast variations in the acquired images due to differences in hardware and acquisition parameters. In recent years, image synthesis-based MR harmonization with disentanglement has been proposed to compensate for the undesired contrast variations. The general idea is to disentangle anatomy and contrast information from MR images to achieve cross-site harmonization. Despite the success of existing methods, we argue that major improvements can be made from three aspects. First, most existing methods are built upon the assumption that multi-contrast MR images of the same subject share the same anatomy. This assumption is questionable, since different MR contrasts are specialized to highlight different anatomical features. Second, these methods often require a fixed set of MR contrasts for training (e.g., both T1-weighted and T2-weighted images), limiting their applicability. Lastly, existing methods are generally sensitive to imaging artifacts. In this paper, we present Harmonization with Attention-based Contrast, Anatomy, and Artifact Awareness (HACA3), a novel approach to address these three issues. HACA3 incorporates an anatomy fusion module that accounts for the inherent anatomical differences between MR contrasts. Furthermore, HACA3 can be trained and applied to any combination of MR contrasts and is robust to imaging artifacts. HACA3 is developed and evaluated on diverse MR datasets acquired from 21 sites with varying field strengths, scanner platforms, and acquisition protocols. Experiments show that HACA3 achieves state-of-the-art harmonization performance under multiple image quality metrics. We also demonstrate the versatility and potential clinical impact of HACA3 on downstream tasks including white matter lesion segmentation for people with multiple sclerosis and longitudinal volumetric analyses for normal aging subjects. Code is available at https://github.com/lianruizuo/haca3.

Synthetic multi-contrast late gadolinium enhancement imaging using post-contrast magnetic resonance fingerprinting.

Late gadolinium enhancement (LGE) MRI is the non-invasive reference standard for identifying myocardial scar and fibrosis but has limitations, including difficulty delineating subendocardial scar and operator dependence on image quality. The purpose of this work is to assess the feasibility of generating multi-contrast synthetic LGE images from post-contrast T1 and T2 maps acquired using magnetic resonance fingerprinting (MRF). Fifteen consecutive patients with a history of prior ischemic cardiomyopathy (12 men; mean age 63 13 years) were prospectively scanned at 1.5 T between Oct 2020 and May 2021 using conventional LGE and MRF after injection of gadolinium contrast. Three classes of synthetic LGE images were derived from MRF post-contrast T1 and T2 maps: bright-blood phase-sensitive inversion recovery (PSIR), black- and gray-blood T2 -prepared PSIR (T2 -PSIR), and a novel "tissue-optimized" image to enhance differentiation among scar, viable myocardium, and blood. Image quality was assessed on a 1-5 Likert scale by two cardiologists, and contrast was quantified as the mean absolute difference (MAD) in pixel intensities between two tissues, with different methods compared using Kruskal-Wallis with Bonferroni post hoc tests. Per-patient and per-segment scar detection rates were evaluated using conventional LGE images as reference. Image quality scores were highest for synthetic PSIR (4.0) and reference images (3.8), followed by synthetic tissue-optimized (3.3), gray-blood T2 -PSIR (3.0), and black-blood T2 -PSIR (2.6). Among synthetic images, PSIR yielded the highest myocardium/scar contrast (MAD = 0.42) but the lowest blood/scar contrast (MAD = 0.05), and vice versa for T2 -PSIR, while tissue-optimized images achieved a balance among all tissues (myocardium/scar MAD = 0.16, blood/scar MAD = 0.26, myocardium/blood MAD = 0.10). Based on reference mid-ventricular LGE scans, 13/15 patients had myocardial scar. The per-patient sensitivity/accuracy for synthetic images were the following: PSIR, 85/87%; black-blood T2 -PSIR, 62/53%; gray-blood T2 -PSIR, 100/93%; tissue optimized, 100/93%. Synthetic multi-contrast LGE images can be generated from post-contrast MRF data without additional scan time, with initial feasibility shown in ischemic cardiomyopathy patients.

McLARO: Multi-contrast learned acquisition and reconstruction optimization for simultaneous quantitative multi-parametric mapping.

To develop a method for rapid sub-millimeter T1 , T2 , , and QSM mapping in a single scan using multi-contrast learned acquisition and reconstruction optimization (mcLARO). A pulse sequence was developed by interleaving inversion recovery and T2 magnetization preparations and single-echo and multi-echo gradient echo acquisitions, which sensitized k-space data to T1 , T2 , , and magnetic susceptibility. The proposed mcLARO optimized both the multi-contrast k-space under-sampling pattern and image reconstruction based on image feature fusion using a deep learning framework. The proposed mcLARO method with under-sampling was validated in a retrospective ablation study and compared with other deep learning reconstruction methods, including MoDL and Wave-MoDL, using fully sampled data as reference. Various under-sampling ratios in mcLARO were investigated. mcLARO was also evaluated in a prospective study using separately acquired conventionally sampled quantitative maps as reference standard. The retrospective ablation study showed improved image sharpness of mcLARO compared to the baseline network without the multi-contrast sampling pattern optimization or image feature fusion module. The under-sampling ratio experiment showed that higher under-sampling ratios resulted in blurrier images and lower precision of quantitative values. The prospective study showed that small or negligible bias and narrow 95% limits of agreement on regional T1 , T2 , , and QSM values by mcLARO (5:39 mins) compared to reference scans (40:03 mins in total). mcLARO outperformed MoDL and Wave-MoDL in terms of image sharpness, noise suppression, and artifact removal. mcLARO enabled fast sub-millimeter T1 , T2 , , and QSM mapping in a single scan.

One Model to Synthesize Them All: Multi-Contrast Multi-Scale Transformer for Missing Data Imputation.

Multi-contrast magnetic resonance imaging (MRI) is widely used in clinical practice as each contrast provides complementary information. However, the availability of each imaging contrast may vary amongst patients, which poses challenges to radiologists and automated image analysis algorithms. A general approach for tackling this problem is missing data imputation, which aims to synthesize the missing contrasts from existing ones. While several convolutional neural networks (CNN) based algorithms have been proposed, they suffer from the fundamental limitations of CNN models, such as the requirement for fixed numbers of input and output channels, the inability to capture long-range dependencies, and the lack of interpretability. In this work, we formulate missing data imputation as a sequence-to-sequence learning problem and propose a multi-contrast multi-scale Transformer (MMT), which can take any subset of input contrasts and synthesize those that are missing. MMT consists of a multi-scale Transformer encoder that builds hierarchical representations of inputs combined with a multi-scale Transformer decoder that generates the outputs in a coarse-to-fine fashion. The proposed multi-contrast Swin Transformer blocks can efficiently capture intra- and inter-contrast dependencies for accurate image synthesis. Moreover, MMT is inherently interpretable as it allows us to understand the importance of each input contrast in different regions by analyzing the in-built attention maps of Transformer blocks in the decoder. Extensive experiments on two large-scale multi-contrast MRI datasets demonstrate that MMT outperforms the state-of-the-art methods quantitatively and qualitatively.

Physical model-based cascaded generative adversarial networks for accelerating quantitative multi-parametric magnetic resonance imaging

To explore the feasibility and interpretation of physical model- based cascaded generative adversarial networks for accelerating quantitative multi-echo multi-parametric magnetic resonance imaging using raw multi-echo multicoil k-space data. A physical model-based cascaded generative adversarial network is proposed to enhance image feature information to obtain high-quality reconstructed images using joint training of multi-domain information and learning of key parameters required for image reconstruction through a system matrix and adaptively optimizing the k-space generator and image generator structures. Raw multi-echo multi-coil k-space data are used to accelerate multi-contrast multi-parametric magnetic resonance imaging. A physically driven deep learning reconstruction method is used to increase the generalization capability and improve the model performance by building a system matrix function instead of direct end-to-end training of the model. In terms of overall image quality, the proposed model achieved significant improvements compared to other methods. On an 80- case test set, the average PSNR value of the reconstructed images was 34.13, SSIM was 0.965, and NRMSE was 0.114. In terms of multi-contrast multi-parametric image reconstruction, the model achieved PSNR values of 38.87 for PDW, 35.62 for T1W, and 34.38 for T2* Map, which were significantly better than those of other methods for quantitative evaluation. The model also produced clearer features of the brain gray matter, white matter, and cerebrospinal fluid. Furthermore, compared with the existing methods with a reconstruction time difference of less than 10%, the proposed method achieved the highest improvement of up to 20% in the metrics of PSNR, SSIM, and NRMSE. Compared with other existing methods, the physical model-based cascaded generative adversarial networks can reconstruct more image details and features, thus improving the quality and accuracy of the reconstructed images.