Background
Cardiovascular magnetic resonance (CMR) is increasingly utilized to evaluate expanding cardiovascular conditions. The Society for Cardiovascular Magnetic Resonance (SCMR) Registry is a central repository for real-world clinical data to support cardiovascular research, including those relating to outcomes, quality improvement, and machine learning. The SCMR Registry is built on a regulatory-compliant, cloud-based infrastructure that houses searchable content and Digital Imaging and Communications in Medicine images. The goal of this study is to summarize the status of the SCMR Registry at 150,000 exams.

Methods
The processes for data security, data submission, and research access are outlined. We interrogated the Registry and presented a summary of its contents.

Results
Data were compiled from 154,458 CMR scans across 20 United States sites, containing 299,622,066 total images (∼100 terabytes of storage). Across reported values, the human subjects had an average age of 58 years (range 1 month to >90 years old), were 44% (63,070/145,275) female, 72% (69,766/98,008) Caucasian, and had a mortality rate of 8% (9,962/132,979). The most common indication was cardiomyopathy (35,369/131,581, 27%), and most frequently used current procedural terminology code was 75561 (57,195/162,901, 35%). Macrocyclic gadolinium-based contrast agents represented 89% (83,089/93,884) of contrast utilization after 2015. Short-axis cines were performed in 99% (76,859/77,871) of tagged scans, short-axis late gadolinium enhancement (LGE) in 66% (51,591/77,871), and stress perfusion sequences in 30% (23,241/77,871). Mortality data demonstrated increased mortality in patients with left ventricular ejection fraction <35%, the presence of wall motion abnormalities, stress perfusion defects, and infarct LGE, compared to those without these markers. There were 456,678 patient-years of all-cause mortality follow-up, with a median follow-up time of 3.6 years.

Conclusion
The vision of the SCMR Registry is to promote evidence-based utilization of CMR through a collaborative effort by providing a web mechanism for centers to securely upload de-identified data and images for research, education, and quality control. The Registry quantifies changing practice over time and supports large-scale real-world multicenter observational studies of prognostic utility.@en

Background: Voltage mapping to detect ventricular scar is important for guiding catheter ablation, but the field-of-view of unipolar, bipolar, conventional, and microelectrodes as it relates to the extent of viable myocardium (VM) is not well defined. Objectives: The purpose of this study was to evaluate electroanatomic voltage-mapping (EAVM) with different-size electrodes for identifying VM, validated against high-resolution ex-vivo cardiac magnetic resonance (HR-LGE-CMR). Methods: A total of 9 swine with early-reperfusion myocardial infarction were mapped with the QDOT microcatheter. HR-LGE-CMR (0.3-mm slices) were merged with EAVM. At each EAVM point, the underlying VM in multisize transmural cylinders and spheres was quantified from ex vivo CMR and related to unipolar and bipolar voltages recorded from conventional and microelectrodes. Results: In each swine, 220 mapping points (Q1, Q3: 216, 260 mapping points) were collected. Infarcts were heterogeneous and nontransmural. Unipolar and bipolar voltage increased with VM volumes from >175 mm³ up to >525 mm³ (equivalent to a 5-mm radius cylinder with height >6.69 mm). VM volumes in subendocardial cylinders with 1- or 3-mm depth correlated poorly with all voltages. Unipolar voltages recorded with conventional and microelectrodes were similar (difference 0.17 ± 2.66 mV) and correlated best to VM within a sphere of radius 10 and 8 mm, respectively. Distance-weighting did not improve the correlation. Conclusions: Voltage increases with transmural volume of VM but correlates poorly with small amounts of VM, which limits EAVM in defining heterogeneous scar. Microelectrodes cannot distinguish thin from thick areas of subendocardial VM. The field-of-view for unipolar recordings for microelectrodes and conventional electrodes appears to be 8 to 10 mm, respectively, and unexpectedly similar.

@en

Quantitative T1 mapping by MRI is an increasingly important tool for clinical assessment of cardiovascular diseases. The cardiac T1 map is derived by fitting a known signal model to a series of baseline images, while the quality of this map can be deteriorated by involuntary respiratory and cardiac motion. To correct motion, a template image is often needed to register all baseline images, but the choice of template is nontrivial, leading to inconsistent performance sensitive to image contrast. In this work, we propose a novel deep-learning-based groupwise registration framework, which omits the need for a template, and registers all baseline images simultaneously. We design two groupwise losses for this registration framework: the first is a linear principal component analysis (PCA) loss that enforces alignment of baseline images irrespective of the intensity variation, and the second is an auxiliary relaxometry loss that enforces adherence of intensity profile to the signal model. We extensively evaluated our method, termed “PCA-Relax”, and other baseline methods on an in-house cardiac MRI dataset including both pre- and post-contrast T1 sequences. All methods were evaluated under three distinct training-and-evaluation strategies, namely, standard, one-shot, and test-time-adaptation. The proposed PCA-Relax showed further improved performance of registration and mapping over well-established baselines. The proposed groupwise framework is generic and can be adapted to applications involving multiple images.@en

Quantitative cardiac magnetic resonance imaging (MRI) is an increasingly important diagnostic tool for cardiovascular diseases. Yet, co-registration of all baseline images within the quantitative MRI sequence is essential for the accuracy and precision of quantitative maps. However, co-registering all baseline images from a quantitative cardiac MRI sequence remains a nontrivial task because of the simultaneous changes in intensity and contrast, in combination with cardiac and respiratory motion. To address the challenge, we propose a novel motion correction framework based on robust principle component analysis (rPCA) that decomposes quantitative cardiac MRI into low-rank and sparse components, and we integrate the groupwise CNN-based registration backbone within the rPCA framework. The low-rank component of rPCA corresponds to the quantitative mapping (i.e. limited degree of freedom in variation), while the sparse component corresponds to the residual motion, making it easier to formulate and solve the groupwise registration problem. We evaluated our proposed method on cardiac T1 mapping by the modified Look-Locker inversion recovery (MOLLI) sequence, both before and after the Gadolinium contrast agent administration. Our experiments showed that our method effectively improved registration performance over baseline methods without introducing rPCA, and reduced quantitative mapping error in both in-domain (pre-contrast MOLLI) and out-of-domain (post-contrast MOLLI) inference. The proposed rPCA framework is generic and can be integrated with other registration backbones.

@en

Deep learning-based methods have achieved prestigious performance for magnetic resonance imaging (MRI) reconstruction, enabling fast imaging for many clinical applications. Previous methods employ convolutional networks to learn the image prior as the regularization term. In quantitative MRI, the physical model of nuclear magnetic resonance relaxometry is known, providing additional prior knowledge for image reconstruction. However, traditional reconstruction networks are limited to learning the spatial domain prior knowledge, ignoring the relaxometry prior. Therefore, we propose a relaxometry-guided quantitative MRI reconstruction framework to learn the spatial prior from data and the relaxometry prior from MRI physics. Additionally, we also evaluated the performance of two popular reconstruction backbones, namely, recurrent variational networks (RVN) and variational networks (VN) with U-Net. Experiments demonstrate that the proposed method achieves highly promising results in quantitative MRI reconstruction.

@en

Purpose: To develop and evaluate a robust cardiac B+1 mapping sequence at 3 T, using Bloch–Siegert shift (BSS)-based preparations.

Methods: A longitudinal magnetization preparation module was designed to encode |B+1 |. After magnetization tip-down, off-resonant Fermi pulses, placed symmetrically around two refocusing pulses, induced BSS, followed by tipping back of the magnetization. Bloch simulations were used to optimize refocusing pulse parameters and to assess the mapping sensitivity. Relaxation-induced B+1 error was simulated for various T 1 /T 2 times. The effective mapping range was determined in phantom experiments, and |B+1 | maps were compared to the conventional BSS method and subadiabatic hyperbolic-secant 8 (HS8) pulse-sensitized method. Cardiac B+1 maps were acquired in healthy subjects, and evaluated for repeatability and imaging plane intersection consistency. The technique was modified for three-dimensional (3D) acquisition of the whole heart in a single breath-hold, and compared to two-dimensional (2D) acquisition.

Results: Simulations indicate that the proposed preparation can be tailored to achieve high mapping sensitivity across various B+1 ranges, with maximum sensitivity at the upper B+1 range. T 1 /T 2 -induced bias did not exceed 5.2%. Experimentally reproduced B+1 sensitization closely matched simulations for B+1 ≥ 0.3B+1, max (mean difference 0.031±0.022, compared to 0.018±0.025 in the HS8-sensitized method), and showed 20-fold reduction in the standard deviation of repeated scans, compared with conventional BSS B+1 mapping, and an equivalent 2-fold reduction compared with HS8-sensitization. Robust cardiac B+1 map quality was obtained, with an average test-retest variability of 0.027±0.043 relative to normalized B+1 magnitude, and plane intersection bias of 0.052±0.031. 3D acquisitions showed good agreement with2D scans (mean absolute deviation 0.055±0.061).

Conclusion: BSS-based preparations enable robust and tailorable 2D/3D cardiac B+1 mapping at 3 T in a single breath-hold.@en

Purpose: The aim of this study is to develop and optimize an adiabatic (Formula presented.) ((Formula presented.)) mapping method for robust quantification of spin-lock (SL) relaxation in the myocardium at 3T. Methods: Adiabatic SL (aSL) preparations were optimized for resilience against (Formula presented.) and (Formula presented.) inhomogeneities using Bloch simulations. Optimized (Formula presented.) -aSL, Bal-aSL and (Formula presented.) -aSL modules, each compensating for different inhomogeneities, were first validated in phantom and human calf. Myocardial (Formula presented.) mapping was performed using a single breath-hold cardiac-triggered bSSFP-based sequence. Then, optimized (Formula presented.) preparations were compared to each other and to conventional SL-prepared (Formula presented.) maps (RefSL) in phantoms to assess repeatability, and in 13 healthy subjects to investigate image quality, precision, reproducibility and intersubject variability. Finally, aSL and RefSL sequences were tested on six patients with known or suspected cardiovascular disease and compared with LGE, (Formula presented.), and ECV mapping. Results: The highest (Formula presented.) preparation efficiency was obtained in simulations for modules comprising 2 HS pulses of 30 ms each. In vivo (Formula presented.) maps yielded significantly higher quality than RefSL maps. Average myocardial (Formula presented.) values were 183.28 (Formula presented.) 25.53 ms, compared with 38.21 (Formula presented.) 14.37 ms RefSL-prepared (Formula presented.). (Formula presented.) maps showed a significant improvement in precision (avg. 14.47 (Formula presented.) 3.71% aSL, 37.61 (Formula presented.) 19.42% RefSL, p < 0.01) and reproducibility (avg. 4.64 (Formula presented.) 2.18% aSL, 47.39 (Formula presented.) 12.06% RefSL, p < 0.0001), with decreased inter-subject variability (avg. 8.76 (Formula presented.) 3.65% aSL, 51.90 (Formula presented.) 15.27% RefSL, p < 0.0001). Among aSL preparations, (Formula presented.) -aSL achieved the better inter-subject variability. In patients, (Formula presented.) -aSL preparations showed the best artifact resilience among the adiabatic preparations. (Formula presented.) times show focal alteration colocalized with areas of hyper-enhancement in the LGE images. Conclusion: Adiabatic preparations enable robust in vivo quantification of myocardial SL relaxation times at 3T.

@en

Coronavirus disease 2019 (COVID-19) is an ongoing global pandemic that has affected nearly 600 million people to date across the world. While COVID-19 is primarily a respiratory illness, cardiac injury is also known to occur. Cardiovascular magnetic resonance (CMR) imaging is uniquely capable of characterizing myocardial tissue properties in-vivo, enabling insights into the pattern and degree of cardiac injury. The reported prevalence of myocardial involvement identified by CMR in the context of COVID-19 infection among previously hospitalized patients ranges from 26 to 60%. Variations in the reported prevalence of myocardial involvement may result from differing patient populations (e.g. differences in severity of illness) and the varying intervals between acute infection and CMR evaluation. Standardized methodologies in image acquisition, analysis, interpretation, and reporting of CMR abnormalities across would likely improve concordance between studies. This consensus document by the Society for Cardiovascular Magnetic Resonance (SCMR) provides recommendations on CMR imaging and reporting metrics towards the goal of improved standardization and uniform data acquisition and analytic approaches when performing CMR in patients with COVID-19 infection.

@en

In radiological practice, multi-sequence MRI is routinely acquired to characterize anatomy and tissue. However, due to the heterogeneity of imaging protocols and contraindications to contrast agents, some MRI sequences, e.g. contrast-enhanced T1-weighted image (T1ce), may not be acquired. This creates difficulties for large-scale clinical studies for which heterogeneous datasets are aggregated. Modern deep learning techniques have demonstrated the capability of synthesizing missing sequences from existing sequences, through learning from an extensive multi-sequence MRI dataset. In this paper, we propose a novel MR image translation solution based on local implicit neural representations. We split the available MRI sequences into local patches and assign to each patch a local multi-layer perceptron (MLP) that represents a patch in the T1ce. The parameters of these local MLPs are generated by a hypernetwork based on image features. Experimental results and ablation studies on the BraTS challenge dataset showed that the local MLPs are critical for recovering fine image and tumor details, as they allow for local specialization that is highly important for accurate image translation. Compared to a classical pix2pix model, the proposed method demonstrated visual improvement and significantly improved quantitative scores (MSE 0.86 × 10^-3 vs. 1.02 × 10^-3 and SSIM 94.9 vs 94.3).

@en

Background: Electroanatomical voltage mapping (EAVM) has been compared with late gadolinium enhancement cardiovascular magnetic resonance (LGE-CMR), which cannot delineate diffuse fibrosis. T1-mapping CMR overcomes the limitations of LGE-CMR, but it has not been directly compared against EAVM. Objectives: This study aims to assess the relationship between left ventricular (LV) endocardial voltage obtained by EAVM and extracellular volume (ECV) obtained by T1 mapping. Methods: The study investigated patients who underwent endocardial EAVM for ventricular arrhythmias (CARTO 3, Biosense Webster) together with preprocedural contrast-enhanced T1 mapping (Ingenia 3T, Philips Healthcare). After image integration, EAVM datapoints were projected onto LGE-CMR and ECV-encoded images. Average values of unipolar voltage (UV), bipolar voltage (BV), LGE transmurality, and ECV were merged from corresponding cardiac segments (6 per slice) and pooled for analysis. Results: The analysis included data from 628 segments from 18 patients (57 ± 13 years of age, 17% females, LV ejection fraction 48% ± 14%, nonischemic/ischemic cardiomyopathy/controls: 8/6/4 patients). Based on the 95th and 5th percentile values obtained from the controls, ECV >33%, BV <2.9 mV, and UV <6.7 mV were considered abnormal. There was a significant inverse association between voltage and ECV, but only in segments with abnormal ECV. Increased ECV could predict abnormal BV and UV with acceptable accuracy (area under the curve of 0.78 [95% CI: 0.74-0.83] and 0.84 [95% CI: 0.79-0.88]). Conclusions: This study found a significant inverse relationship between LV endocardial voltage and ECV. Real-time integration of T1 mapping may guide catheter mapping and may allow identification of areas of diffuse fibrosis potentially related to ventricular arrhythmias.

@en

Purpose: To investigate and mitigate the influence of physiological and acquisition-related parameters on myocardial blood flow (MBF) measurements obtained with myocardial Arterial Spin Labeling (myoASL). Methods: A Flow-sensitive Alternating Inversion Recovery (FAIR) myoASL sequence with bSSFP and spoiled GRE (spGRE) readout is investigated for MBF quantification. Bloch-equation simulations and phantom experiments were performed to evaluate how variations in acquisition flip angle (FA), acquisition matrix size (AMS), heart rate (HR) and blood (Formula presented.) relaxation time ((Formula presented.)) affect quantification of myoASL-MBF. In vivo myoASL-images were acquired in nine healthy subjects. A corrected MBF quantification approach was proposed based on subject-specific (Formula presented.) values and, for spGRE imaging, subtracting an additional saturation-prepared baseline from the original baseline signal. Results: Simulated and phantom experiments showed a strong dependence on AMS and FA ((Formula presented.) >0.73), which was eliminated in simulations and alleviated in phantom experiments using the proposed saturation-baseline correction in spGRE. Only a very mild HR dependence ((Formula presented.) >0.59) was observed which was reduced when calculating MBF with individual (Formula presented.). For corrected spGRE, in vivo mean global spGRE-MBF ranged from 0.54 to 2.59 mL/g/min and was in agreement with previously reported values. Compared to uncorrected spGRE, the intra-subject variability within a measurement (0.60 mL/g/min), between measurements (0.45 mL/g/min), as well as the inter-subject variability (1.29 mL/g/min) were improved by up to 40% and were comparable with conventional bSSFP. Conclusion: Our results show that physiological and acquisition-related factors can lead to spurious changes in myoASL-MBF if not accounted for. Using individual (Formula presented.) and a saturation-baseline can reduce these variations in spGRE and improve reproducibility of FAIR-myoASL against acquisition parameters.

@en

Ischemic heart disease (IHD) is one of the leading causes of death worldwide. Myocardial infarction (MI) represents a third of all IHD cases, and cardiac magnetic resonance imaging (MRI) is often used to assess its damage to myocardial viability. Late gadolinium enhancement (LGE) is the current gold standard, but the use of gadolinium-based agents limits the clinical applicability in some patients. Spin-lock (SL) dispersion has recently been proposed as a promising non-contrast biomarker for the assessment of MI. However, at 3T, the required range of SL preparations acquired at different amplitudes suffers from specific absorption rate (SAR) limitations and off-resonance artifacts. Relaxation Along a Fictitious Field (RAFF) is an alternative to SL preparations with lower SAR requirements, while still sampling relaxation in the rotating frame. In this study, a single breath-hold simultaneous TRAFF2 and T2 mapping sequence is proposed for SL dispersion mapping at 3T. Excellent reproducibility (coefficient of variations lower than 10%) was achieved in phantom experiments, indicating good intrascan repeatability. The average myocardial TRAFF2, T2, and SL dispersion obtained with the proposed sequence (68.0±10.7 ms, 44.0±4.0 ms, and 0.4±0.2 ×10-4 s2, respectively) were comparable to the reference methods (62.7±11.7 ms, 41.2±2.4 ms, and 0.3±0.2x 10-4s2, respectively). High visual map quality, free of B0 and B1+ related artifacts, for T2, TRAFF2, and SL dispersion maps were obtained in phantoms and in vivo, suggesting promise in clinical use at 3T. Clinical relevance - and imaging promises non-contrast assessment of scar and focal fibrosis in a single breath-hold using approximate spin-lock dispersion mapping.

@en

Quantitative MRI (qMRI) of the heart has become an important clinical tool for examining myocardial tissue properties. Because heart is a moving object, it is usually imaged with electrocardiogram and respiratory gating during acquisition, to “freeze” its motion. In reality, gating is more-often-than-not imperfect given the heart rate variability and nonideal breath-hold. qMRI of the heart, consequently, is characteristic of varying image contrast as well as residual motion, the latter compromising the quality of quantitative mapping. Motion correction is an important step prior to parametric mapping, however, a long-standing difficulty for registering the dynamic sequence is that the contrast across frames varies wildly: depending on the acquisition scheme some frames can have extremely poor contrast, which fails both traditional optimization-based and modern learning-based registration methods. In this work, we propose a novel framework named DisQ, which Disentangles Quantitative mapping sequences into the latent space of contrast and anatomy, fully unsupervised. The disentangled latent spaces serve for the purpose of generating a series of images with identical contrast, which enables easy and accurate registration of all frames. We applied our DisQ method to the modified Look-Locker inversion recovery (MOLLI) sequence, and demonstrated improved performance of T₁ mapping. In addition, we showed the possibility of generating a dynamic series of baseline images with exactly the same shape, strictly registered and perfectly “frozen". Our proposed DisQ methodology readily extends to other types of cardiac qMRI such as T₂ mapping and perfusion.

@en

The self-configuring nnU-Net has achieved leading performance in a large range of medical image segmentation challenges. It is widely considered as the model of choice and a strong baseline for medical image segmentation. However, despite its extraordinary performance, nnU-Net does not supply a measure of uncertainty to indicate its possible failure. This can be problematic for large-scale image segmentation applications, where data are heterogeneous and nnU-Net may fail without notice. In this work, we introduce a novel method to estimate nnU-Net uncertainty for medical image segmentation. We propose a highly effective scheme for posterior sampling of weight space for Bayesian uncertainty estimation. Different from previous baseline methods such as Monte Carlo Dropout and mean-field Bayesian Neural Networks, our proposed method does not require a variational architecture and keeps the original nnU-Net architecture intact, thereby preserving its excellent performance and ease of use. Additionally, we boost the segmentation performance over the original nnU-Net via marginalizing multi-modal posterior models. We applied our method on the public ACDC and M &M datasets of cardiac MRI and demonstrated improved uncertainty estimation over a range of baseline methods. The proposed method further strengthens nnU-Net for medical image segmentation in terms of both segmentation accuracy and quality control.

@en

COVID-19 is associated with myocardial injury caused by ischemia, inflammation, or myocarditis. Cardiovascular magnetic resonance (CMR) is the noninvasive reference standard for cardiac function, structure, and tissue composition. CMR is a potentially valuable diagnostic tool in patients with COVID-19 presenting with myocardial injury and evidence of cardiac dysfunction. Although COVID-19–related myocarditis is likely infrequent, COVID-19–related cardiovascular histopathology findings have been reported in up to 48% of patients, raising the concern for long-term myocardial injury. Studies to date report CMR abnormalities in 26% to 60% of hospitalized patients who have recovered from COVID-19, including functional impairment, myocardial tissue abnormalities, late gadolinium enhancement, or pericardial abnormalities. In athletes post–COVID-19, CMR has detected myocarditis-like abnormalities. In children, multisystem inflammatory syndrome may occur 2 to 6 weeks after infection; associated myocarditis and coronary artery aneurysms are evaluable by CMR. At this time, our understanding of COVID-19–related cardiovascular involvement is incomplete, and multiple studies are planned to evaluate patients with COVID-19 using CMR. In this review, we summarize existing studies of CMR for patients with COVID-19 and present ongoing research. We also provide recommendations for clinical use of CMR for patients with acute symptoms or who are recovering from COVID-19.

@en

Purpose: To develop automated vestibular schwannoma measurements on contrast-enhanced T1-and T2-weighted MRI scans. Materials and Methods: MRI data from 214 patients in 37 different centers were retrospectively analyzed between 2020 and 2021. Patients with hearing loss (134 positive for vestibular schwannoma [mean age 6 SD, 54 years 6 12; 64 men] and 80 negative for vestibular schwannoma) were randomly assigned to a training and validation set and to an independent test set. A convolutional neural network (CNN) was trained using fivefold cross-validation for two models (T1 and T2). Quantitative analysis, including Dice index, Hausdorff distance, surface-to-surface distance (S2S), and relative volume error, was used to compare the computer and the human delineations. An observer study was performed in which two experienced physicians evaluated both delineations. Results: The T1-weighted model showed state-of-the-art performance, with a mean S2S distance of less than 0.6 mm for the whole tumor and the intrameatal and extrameatal tumor parts. The whole tumor Dice index and Hausdorff distance were 0.92 and 2.1 mm in the independent test set, respectively. T2-weighted images had a mean S2S distance less than 0.6 mm for the whole tumor and the intrameatal and extrameatal tumor parts. The whole tumor Dice index and Hausdorff distance were 0.87 and 1.5 mm in the independent test set. The observer study indicated that the tool was similar to human delineations in 85%–92% of cases. Conclusion: The CNN model detected and delineated vestibular schwannomas accurately on contrast-enhanced T1-and T2-weighted MRI scans and distinguished the clinically relevant difference between intrameatal and extrameatal tumor parts.

@en

Left ventricular thrombus (LVT) after acute ST-segment elevation myocardial infarction (STEMI) are generally associated with poorer outcomes for patients at long-term follow-up. We hypothesis that tissue characteristics and strain parameters by cardiac magnetic resonance (CMR) imaging may indicate the interactions of LVT with ventricular myocardium remodeling at both acute stage and chronic stages in STEMI patients. This retrospective study included 111 consecutive STEMI patients (38 with LVT and 73 without LVT). All patients underwent CMR during acute stage (within 7 days) and chronic stage (after at least 2 months) periods after percutaneous coronary intervention (PCI). Left ventricular native T1, extracellular volume (ECV), radial, circumferential, and longitudinal strain were analyzed in both phases. Major adverse cardiac events (MACE, including cardiovascular death, myocardial reinfarction, and hospitalization for heart failure), thromboembolic and bleeding events, were the clinical endpoints of the study. During the acute stage, left ventricular ejection fraction (LVEF) (OR 0.77, P value = 0.01) and longitudinal strain (OR 1.90, P value < 0.001) were correlated with LVT formation. Strain parameters were reduced, while the native T1 and ECV values of both the infarcted area and remote myocardium were elevated in LVT patients. During the chronic stage, LVT resolved in 29 of 38 patients (76%). LVT remaining patients had lower LVEF, a larger LV, and higher ECV in the acute stage than those of the LVT-resolved patients. In the long-term follow up of 678 days, LVT (HR 2.45, P value = 0.02), aneurysm (HR 1.81, P value = 0.04), and native T1 (HR 2.44, P value = 0.01) were identified as three independent predictors of MACE, the incidence of thromboembolic events and bleeding events by a multivariable stepwise Cox proportional hazards regression. STEMI patients developing LVT had worse LV function, myocardial infarction extent, strain, and higher T1 and ECV values than STEMI patients without LVT. The LVT-remaining patients in the chronic stage had poorer functional and mapping parameters beginning in the first week. During the acute stage, LVEF and global longitudinal strain were independent correlated with LVT formation. During the long-term follow up, LVT, aneurysm and elevated myocardial T1 were associated with adverse outcomes in acute STEMI patients.@en

Embedding high-dimensional data onto a low-dimensional manifold is of both theoretical and practical value. In this article, we propose to combine deep neural networks (DNN) with mathematics-guided embedding rules for high-dimensional data embedding. We introduce a generic deep embedding network (DEN) framework, which is able to learn a parametric mapping from high-dimensional space to low-dimensional space, guided by well-established objectives such as Kullback-Leibler (KL) divergence minimization. We further propose a recursive strategy, called deep recursive embedding (DRE), to make use of the latent data representations for boosted embedding performance. We exemplify the flexibility of DRE by different architectures and loss functions, and benchmarked our method against the two most popular embedding methods, namely, t-distributed stochastic neighbor embedding (t-SNE) and uniform manifold approximation and projection (UMAP). The proposed DRE method can map out-of-sample data and scale to extremely large datasets. Experiments on a range of public datasets demonstrated improved embedding performance in terms of local and global structure preservation, compared with other state-of-The-Art embedding methods. Code is available at https://github.com/tao-Aimi/DeepRecursiveEmbedding.

@en