Cine Cardiac Magnetic Resonance Research Articles

A comprehensive stroke risk assessment by combining atrial computational fluid dynamics simulations and functional patient data

Stroke, a major global health concern often rooted in cardiac dynamics, demands precise risk evaluation for targeted intervention. Current risk models, like the CHA2DS2-VASc\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ ext {CHA}_2\ ext {DS}_2\ ext {-VASc}$$\\end{document} score, often lack the granularity required for personalized predictions. In this study, we present a nuanced and thorough stroke risk assessment by integrating functional insights from cardiac magnetic resonance (CMR) with patient-specific computational fluid dynamics (CFD) simulations. Our cohort, evenly split between control and stroke groups, comprises eight patients. Utilizing CINE CMR, we compute kinematic features, revealing smaller left atrial volumes for stroke patients. The incorporation of patient-specific atrial displacement into our hemodynamic simulations unveils the influence of atrial compliance on the flow fields, emphasizing the importance of LA motion in CFD simulations and challenging the conventional rigid wall assumption in hemodynamics models. Standardizing hemodynamic features with functional metrics enhances the differentiation between stroke and control cases. While standalone assessments provide limited clarity, the synergistic fusion of CMR-derived functional data and patient-informed CFD simulations offers a personalized and mechanistic understanding, distinctly segregating stroke from control cases. Specifically, our investigation reveals a crucial clinical insight: normalizing hemodynamic features based on ejection fraction fails to differentiate between stroke and control patients. Differently, when normalized with stroke volume, a clear and clinically significant distinction emerges and this holds true for both the left atrium and its appendage, providing valuable implications for precise stroke risk assessment in clinical settings. This work introduces a novel framework for seamlessly integrating hemodynamic and functional metrics, laying the groundwork for improved predictive models, and highlighting the significance of motion-informed, personalized risk assessments.

Focal ischemic myocardial fibrosis assessed by late gadolinium enhancement cardiovascular magnetic resonance in patients with hypertrophic cardiomyopathy

BackgroundIn patients with hypertrophic cardiomyopathy (HCM), ischemic myocardial fibrosis assessed by late gadolinium enhancement (I-LGE) using cardiovascular magnetic resonance (CMR) have been reported. However, the clinical significance of I-LGE has not been completely understood. We aim to evaluate the I-LGE differ phenotypically from HCM without LGE or nonischemic myocardial fibrosis assessed by late gadolinium enhancement (NI-LGE) in the left ventricle (LV).MethodsThe patients with HCM whom was underwent CMR were enrolled, using cine cardiac magnetic resonance to evaluate LV function and LGE to detect the myocardial fibrosis. Three groups were assorted: 1) HCM without LGE; 2) HCM with LGE involved the subendocardial layer was defined as I-LGE; 3) HCM with LGE not involved the subendocardial layer was defined as NI-LGE.ResultsWe enrolled 122 patients with HCM in the present study. LGE was detected in 58 of 122 (48%) patients with HCM, and 22 (18%) of patients reported I-LGE. HCM with I-LGE had increased higher left ventricular mass index (LVMI) (P < 0.0001) than HCM with NI-LGE or without LGE. In addition, HCM with I-LGE had a larger LV end- systolic volume (P = 0.045), lower LV ejection fraction (LVEF) (P = 0.026), higher LV myocardial mass (P < 0.001) and thicker LV wall (P < 0.001) more than HCM without LGE alone. The I-LGE were significantly associated with LVEF (OR: 0.961; P = 0.016), LV mass (OR: 1.028; P < 0.001), and maximal end-diastolic LVWT (OR: 1.567; P < 0.001). On multivariate analysis, LVEF (OR: 0.948; P = 0.013) and maximal end-diastolic LVWT (OR: 1.548; P = 0.001) were associated with higher risk for I-LGE compared to HCM without LGE. Noticeably, the maximal end-diastolic LVWT (OR: 1.316; P = 0.011) was the only associated with NI-LGE compared to HCM without LGE.ConclusionsI-LGE is not uncommon in patients with HCM. HCM with I-LGE was associated with significant LV hypertrophy, extensive LGE and poor LV ejection fraction. We should consider focal ischemic myocardial fibrosis when applying LGE to risk stratification for HCM.

DeepMesh: Mesh-Based Cardiac Motion Tracking Using Deep Learning.

3D motion estimation from cine cardiac magnetic resonance (CMR) images is important for the assessment of cardiac function and the diagnosis of cardiovascular diseases. Current state-of-the art methods focus on estimating dense pixel-/voxel-wise motion fields in image space, which ignores the fact that motion estimation is only relevant and useful within the anatomical objects of interest, e.g., the heart. In this work, we model the heart as a 3D mesh consisting of epi- and endocardial surfaces. We propose a novel learning framework, DeepMesh, which propagates a template heart mesh to a subject space and estimates the 3D motion of the heart mesh from CMR images for individual subjects. In DeepMesh, the heart mesh of the end-diastolic frame of an individual subject is first reconstructed from the template mesh. Mesh-based 3D motion fields with respect to the end-diastolic frame are then estimated from 2D short- and long-axis CMR images. By developing a differentiable mesh-to-image rasterizer, DeepMesh is able to leverage 2D shape information from multiple anatomical views for 3D mesh reconstruction and mesh motion estimation. The proposed method estimates vertex-wise displacement and thus maintains vertex correspondences between time frames, which is important for the quantitative assessment of cardiac function across different subjects and populations. We evaluate DeepMesh on CMR images acquired from the UK Biobank. We focus on 3D motion estimation of the left ventricle in this work. Experimental results show that the proposed method quantitatively and qualitatively outperforms other image-based and mesh-based cardiac motion tracking methods.

STADNet: Spatial-Temporal Attention-Guided Dual-Path Network for cardiac cine MRI super-resolution

Cardiac cine magnetic resonance imaging (MRI) is a commonly used clinical tool for evaluating cardiac function and morphology. However, its diagnostic accuracy may be compromised by the low spatial resolution. Current methods for cine MRI super-resolution reconstruction still have limitations. They typically rely on 3D convolutional neural networks or recurrent neural networks, which may not effectively capture long-range or non-local features due to their limited receptive fields. Optical flow estimators are also commonly used to align neighboring frames, which may cause information loss and inaccurate motion estimation. Additionally, pre-warping strategies may involve interpolation, leading to potential loss of texture details and complicated anatomical structures. To overcome these challenges, we propose a novel Spatial-Temporal Attention-Guided Dual-Path Network (STADNet) for cardiac cine MRI super-resolution. We utilize transformers to model long-range dependencies in cardiac cine MR images and design a cross-frame attention module in the location-aware spatial path, which enhances the spatial details of the current frame by using complementary information from neighboring frames. We also introduce a recurrent flow-enhanced attention module in the motion-aware temporal path that exploits the correlation between cine MRI frames and extracts the motion information of the heart. Experimental results demonstrate that STADNet outperforms SOTA approaches and has significant potential for clinical practice.

Cine-cardiac magnetic resonance to distinguish between ischemic and non-ischemic cardiomyopathies: a machine learning approach.

This work aimed to derive a machine learning (ML) model for the differentiation between ischemic cardiomyopathy (ICM) and non-ischemic cardiomyopathy (NICM) on non-contrast cardiovascular magnetic resonance (CMR). This retrospective study evaluated CMR scans of 107 consecutive patients (49 ICM, 58 NICM), including atrial and ventricular strain parameters. We used these data to compare an explainable tree-based gradient boosting additive model with four traditional ML models for the differentiation of ICM and NICM. The models were trained and internally validated with repeated cross-validation according to discrimination and calibration. Furthermore, we examined important variables for distinguishing between ICM and NICM. A total of 107 patients and 38 variables were available for the analysis. Of those, 49 were ICM (34 males, mean age 60 ± 9years) and 58 patients were NICM (38 males, mean age 56 ± 19years). After 10 repetitions of the tenfold cross-validation, the proposed model achieved the highest area under curve (0.82, 95% CI [0.47-1.00]) and lowest Brier score (0.19, 95% CI [0.13-0.27]), showing competitive diagnostic accuracy and calibration. At the Youden's index, sensitivity was 0.72 (95% CI [0.68-0.76]), the highest of all. Analysis of predictions revealed that both atrial and ventricular strain CMR parameters were important for the identification of ICM patients. The current study demonstrated that using a ML model, multi chamber myocardial strain, and function on non-contrast CMR parameters enables the discrimination between ICM and NICM with competitive diagnostic accuracy. A machine learning model based on non-contrast cardiovascular magnetic resonance parameters may discriminate between ischemic and non-ischemic cardiomyopathy enabling wider access to cardiovascular magnetic resonance examinations with lower costs and faster imaging acquisition. • The exponential growth in cardiovascular magnetic resonance examinations may require faster and more cost-effective protocols. • Artificial intelligence models can be utilized to distinguish between ischemic and non-ischemic etiologies. • Machine learning using non-contrast CMR parameters can effectively distinguish between ischemic and non-ischemic cardiomyopathies.

A Deep Learning-Based Integrated Framework for Quality-Aware Undersampled Cine Cardiac MRI Reconstruction and Analysis.

Cine cardiac magnetic resonance (CMR) imaging is considered the gold standard for cardiac function evaluation. However, cine CMR acquisition is inherently slow and in recent decades considerable effort has been put into accelerating scan times without compromising image quality or the accuracy of derived results. In this article, we present a fully-automated, quality-controlled integrated framework for reconstruction, segmentation and downstream analysis of undersampled cine CMR data. The framework produces high quality reconstructions and segmentations, leading to undersampling factors that are optimised on a scan-by-scan basis. This results in reduced scan times and automated analysis, enabling robust and accurate estimation of functional biomarkers. To demonstrate the feasibility of the proposed approach, we perform simulations of radial k-space acquisitions using in-vivo cine CMR data from 270 subjects from the UK Biobank (with synthetic phase) and in-vivo cine CMR data from 16 healthy subjects (with real phase). The results demonstrate that the optimal undersampling factor varies for different subjects by approximately 1 to 2 seconds per slice. We show that our method can produce quality-controlled images in a mean scan time reduced from 12 to 4 seconds per slice, and that image quality is sufficient to allow clinically relevant parameters to be automatically estimated to lie within 5% mean absolute difference.

Comparing Strain Assessment in Compressed Sensing and Conventional Cine MRI.

The aim of this study is to assess the feasibility of compressed sensing (CS) acceleration methods compared to conventional segmented cine (Seg) cardiac magnetic resonance (CMR) for evaluating left ventricular (LV) function and strain by feature tracking (FT). In this prospective study, 45 healthy volunteers underwent CMR imaging used Seg, threefold (CS3), fourfold (CS4), and eightfold (CS8) CS acceleration. Cine images were scored for quality (1-5 scale). LV volumetric and functional parameters and global longitudinal (GLS), circumferential (GCS), and radial strains (GRS) were quantified. LV volumetric and functional parameters exhibited no differences between Seg and all CS cines (all P > 0.05). The strains were similar for Seg, CS3, and CS4 (all P > 0.05). Similarly, no significant differences were observed in GRS and GCS between Seg and CS8 (all P > 0.05), but the global longitudinal strain was significantly lower for CS8 versus Seg (P < 0.001). Image quality declined with CS acceleration, especially in long-axis views with CS8. CS cine MRI at acceleration factor 4 maintained good image quality and accurate measurements of LV function and strain, although there was a slight reduction in the quality of long-axis images and GLS with CS8. CS acceleration up to a factor of 4 enabled fast CMR evaluations, making it suitable for clinical use.

The effects of flip angle and gadolinium contrast agent on single breath-hold compressed sensing cardiac magnetic resonance cine for biventricular global strain assessment.

Due to its potential to significantly reduce scanning time while delivering accurate results for cardiac volume function, compressed sensing (CS) has gained traction in cardiovascular magnetic resonance (CMR) cine. However, further investigation is necessary to explore its feasibility and impact on myocardial strain results. A total of 102 participants [75 men, 46.5 ± 17.1 (SD) years] were included in this study. Each patient underwent four consecutive cine sequences with the same slice localization, including the reference multi-breath-hold balanced steady-state free precession (bSSFPref) cine, the CS cine with the same flip angle as bSSFPref before (CS45) and after (eCS45) contrast enhancement, and the CS cine (eCS70) with a 70-degree flip angle after contrast enhancement. Biventricular strain parameters were derived from cine images. Two-tailed paired t-tests were used for data analysis. Global radial strain (GRS), global circumferential strain (GCS), and global longitudinal strain (GLS) were observed to be significantly lower in comparison to those obtained from bSSFPref sequences for both the right and left ventricles (all p < 0.001). No significant difference was observed on biventricular GRS-LAX (long-axis) and GLS values derived from enhanced and unenhanced CS cine sequences with the same flip angle, but remarkable reductions were noted in GRS-SAX (short-axis) and GCS values (p < 0.001). After contrast injection, a larger flip angle caused a significant elevation in left ventricular strain results (p < 0.001) but did not affect the right ventricle. The increase in flip angle appeared to compensate for contrast agent affection on left ventricular GRS-SAX, GCS values, and right ventricular GRS-LAX, GLS values. Despite incorporating gadolinium contrast agents and applying larger flip angles, single breath-hold CS cine sequences consistently yielded diminished strain values for both ventricles when compared with conventional cine sequences. Prior to employing this single breath-hold CS cine sequence to refine the clinical CMR examination procedure, it is crucial to consider its impact on myocardial strain results.

Cardiovascular magnetic resonance imaging-derived intraventricular pressure gradients in ST-segment elevation myocardial infarction: a long-term follow-up study

Abstract Aims Recently, novel post-processing tools have become available that measure intraventricular pressure gradients (IVPGs) on routinely obtained long-axis cine cardiac magnetic resonance (CMR) images. IVPGs provide a comprehensive overview of both systolic and diastolic left ventricular (LV) functions. Whether IVPGs are associated with clinical outcome after ST-elevation myocardial infarction (STEMI) is currently unknown. Here, we investigated the association between CMR-derived LV-IVPGs and major adverse cardiovascular events (MACE) in a large reperfused STEMI cohort with long-term outcome. Methods and results In this prospectively enrolled multi-centre cohort study, 307 patients underwent CMR within 14 days after the first STEMI. LV-IVPGs (from apex-to-base) were estimated on the long-axis cine images. During a median follow-up of 9.7 (5.9–12.5) years, MACE (i.e. composite of cardiovascular death and de novo heart failure hospitalisation) occurred in 49 patients (16.0%). These patients had larger infarcts, more often microvascular injury, and impaired LV-IVPGs. In univariable Cox regression, overall LV-IVPG was significantly associated with MACE and remained significantly associated after adjustment for common clinical risk factors (hazard ratio (HR) 0.873, 95% confidence interval (CI) 0.794–0.961, P = 0.005) and myocardial injury parameters (HR 0.906, 95% CI 0.825–0.995, P = 0.038). However, adjusted for LV ejection fraction and LV global longitudinal strain (GLS), overall LV-IVPG does not provide additional prognostic information (HR 0.959, 95% CI 0.866–1.063, P = 0.426). Conclusion Early after STEMI, CMR-derived LV-IVPGs are univariably associated with MACE and this association remains significant after adjustment for common clinical risk factors and measures of infarct severity. However, LV-IVPGs do not add prognostic value to LV ejection fraction and LV GLS.

Kiosk 6R-FA-05 - Cardiac Magnetic Resonance Cine Images Derived-radiomics for the Prediction of Event FBee Survival in Patients with St-segment Elevation Myocardial Infarction

Kiosk 6R-FA-05 - Cardiac Magnetic Resonance Cine Images Derived-radiomics for the Prediction of Event FBee Survival in Patients with St-segment Elevation Myocardial Infarction

Kiosk 8R-FB-08 - Automated Cloud-deployable Pipeline for 3D Cardiac Shape Phenomics FBom 2D Cine Cardiac Magnetic Resonance Imaging

Kiosk 8R-FB-08 - Automated Cloud-deployable Pipeline for 3D Cardiac Shape Phenomics FBom 2D Cine Cardiac Magnetic Resonance Imaging

Optical Flow-Guided Cine MRI Segmentation With Learned Corrections.

In cardiac cine magnetic resonance imaging (MRI), the heart is repeatedly imaged at numerous time points during the cardiac cycle. Frequently, the temporal evolution of a certain region of interest such as the ventricles or the atria is highly relevant for clinical diagnosis. In this paper, we devise a novel approach that allows for an automatized propagation of an arbitrary region of interest (ROI) along the cardiac cycle from respective annotated ROIs provided by medical experts at two different points in time, most frequently at the end-systolic (ES) and the end-diastolic (ED) cardiac phases. At its core, a 3D TV- L1 -based optical flow algorithm computes the apparent motion of consecutive MRI images in forward and backward directions. Subsequently, the given terminal annotated masks are propagated by this bidirectional optical flow in 3D, which results, however, in improper initial estimates of the segmentation masks due to numerical inaccuracies. These initially propagated segmentation masks are then refined by a 3D U-Net-based convolutional neural network (CNN), which was trained to enforce consistency with the forward and backward warped masks using a novel loss function. Moreover, a penalization term in the loss function controls large deviations from the initial segmentation masks. This method is benchmarked both on a new dataset with annotated single ventricles containing patients with severe heart diseases and on a publicly available dataset with different annotated ROIs. We emphasize that our novel loss function enables fine-tuning the CNN on a single patient, thereby yielding state-of-the-art results along the complete cardiac cycle.

AI approach to biventricular function assessment in cine-MRI: an ultra-small training dataset and multivendor study

Objective. It was a great challenge to train an excellent and generalized model on an ultra-small data set composed of multi-orientation cardiac cine magnetic resonance imaging (MRI) images. We try to develop a 3D deep learning method based on an ultra-small training data set from muti-orientation cine MRI images and assess its performance of automated biventricular structure segmentation and function assessment in multivendor. Approach. We completed the training and testing of our deep learning networks using only heart datasets of 150 cases (90 cases for training and 60 cases for testing). This datasets were obtained from three different MRI vendors and each subject included two phases of the cardiac cycle and three cine sequences. A 3D deep learning algorithm combining Transformers and U-Net was trained. The performance of the segmentation was evaluated using the Dice metric and Hausdorff distance (HD). Based on this, the manual and automatic results of cardiac function parameters were compared with Pearson correlation, intraclass correlation coefficient (ICC) and Bland–Altman analysis in multivendor. Main results. The results show that the average Dice of 0.92, 0.92, 0.94 and HD95 of 2.50, 1.36, 1.37 for three sequences. The automatic and manual results of seven parameters were excellently correlated with the lowest r2 value of 0.824 and the highest of 0.983. The ICC (0.908–0.989, P < 0.001) showed that the results were highly consistent. Bland–Altman with a 95% limit of agreement showed there was no significant difference except for the difference in RVESV (P = 0.005) and LVM (P < 0.001). Significance. The model had high accuracy in segmentation and excellent correlation and consistency in function assessment. It provides a fast and effective method for studying cardiac MRI and heart disease.

Association of Lipoprotein(a) Levels With Myocardial Fibrosis in the Multi-Ethnic Study of Atherosclerosis.

Lipoprotein(a) (Lp[a]) has been identified as an emerging risk factor for adverse cardiovascular (CV) outcomes, including heart failure. However, the connections among Lp(a), myocardial fibrosis (interstitial and replacement), and cardiac remodeling as pathways to CV diseases remains unclear. This study investigated the relationship between Lp(a) levels and myocardial fibrosis by cardiac magnetic resonance (CMR) T1 mapping and late gadolinium enhancement, as well as cardiac remodeling by cine CMR, in the MESA (Multi-Ethnic Study of Atherosclerosis) cohort. The study included 2,040 participants with baseline Lp(a) measurements and T1 mapping for interstitial myocardial fibrosis (IMF) evaluation in 2010. Lp(a) was analyzed as a continuous variable (per log unit) and using clinical cutoff values of 30 and 50mg/dL. Multivariate linear and logistic regression were used to assess the associations of Lp(a) with CMR measures of extracellular volume (ECV fraction [ECV%]), native T1 time, and myocardial scar, as well as parameters of cardiac remodeling, in 2,826 participants. Higher Lp(a) levels were associated with increased ECV% (per log-unit Lp[a]; β=0.2%; P=0.007) and native T1 time (per log-unit Lp[a]; β=4%; P< 0.001). Similar relationships were observed between elevated Lp(a) levels and a higher risk of clinically significant IMF defined by prognostic thresholds per log-unit Lp(a) of ECV% (OR: 1.20; 95%CI: 1.04-1.43) and native T1 (OR: 1.2; 95%CI: 1.1-1.4) equal to 30% and 955ms, respectively. Clinically used Lp(a) cutoffs (30 and 50mg/dL) were associated with greater prevalence of myocardial scar (OR: 1.85; 95%CI: 1.1-3.2 and OR: 1.9; 95%CI: 1.1-3.4, respectively). Finally, higher Lp(a) levels were associated with left atrial enlargement and dysfunction. Elevated Lp(a) levels are linked to greater subclinical IMF, increased myocardial scar prevalence, and left atrial remodeling.

Cardiac Magnetic Resonance Identifies Responders to Cardiac Resynchronization Therapy with an Assessment of Septal Scar and Left Ventricular Dyssynchrony.

Background: The response to cardiac resynchronization therapy (CRT) depends on septal viability and correction of abnormal septal motion. This study investigates if cardiac magnetic resonance (CMR) as a single modality can identify CRT responders with combined imaging of pathological septal motion (septal flash) and septal scar. Methods: In a prospective, multicenter, observational study of 136 CRT recipients, septal scar was assessed using late gadolinium enhancement (LGE) (n = 127) and septal flash visually from cine CMR sequences. The primary endpoint was CRT response, defined as ≥15% reduction in LV end-systolic volume with echocardiography after 6 months. The secondary endpoint was heart transplantation or death of any cause assessed after 39 ± 13 months. Results: Septal scar and septal flash were independent predictors of CRT response in multivariable analysis (both p < 0.001), while QRS duration and morphology were not. The combined approach of septal scar and septal flash predicted CRT response with an area under the curve of 0.86 (95% confidence interval (CI): 0.78-0.94) and was a strong predictor of long-term survival without heart transplantation (hazard ratio 0.27, 95% CI: 0.10-0.79). The accuracy of the approach was similar in the subgroup with intermediate (130-150 ms) QRS duration. The combined approach was superior to septal scar and septal flash alone (p < 0.01). Conclusions: The combined assessment of septal scar and septal flash using CMR as a single-image modality identifies CRT responders with high accuracy and predicts long-term survival.

Developing and evaluating a chronic ischemic cardiomyopathy in swine model by rest and stress CMR.

A large animal model of chronic coronary artery disease (CAD) is crucial for the understanding the underlying pathophysiological processes of chronic CAD and consequences for cardiac structure and function. The goal of this study was to develop a chronic model of CAD in a swine model and to evaluate the changes of myocardial structure, myocardial motility, and myocardial viability during coronary stenosis. A total of 30 swine (including 24 experimental animals and 6 controls) were enrolled. The chronic ischemia model was constructed by using Ameroid constrictor in experimental group. The 24 experimental animals were further divided into 4 groups (6 animals in each group) and were sacrificed at 1, 2, 3 and 4 weeks after operation for pathological examination, respectively. Cardiac magnetic resonance (CMR) was performed preoperatively and weekly postoperatively until sacrificed both in experimental and control group. CMR cine images, rest/adenosine triphosphate (ATP) stress myocardial contrast perfusion and LGE were performed and analyzed. The rest wall thickening (WT) score was calculated from rest cine images. The MPRI (myocardial perfusion reserve index) and MPR (myocardial perfusion reserve) were calculated based on rest and stress perfusion images. Pathology staining including triphenyltetrazolium chloride, HE and picrosirus red staining were performed after swine were sacrificed and collagen volume fraction (CVF) was calculated. The time to formation of ischemic, hibernating, and infarcted myocardium was recorded. In experimental group, from 1w to 4w after surgery, the rest WT score decreased gradually from 35.2 ± 2.0%, 32.0 ± 2.9% to 30.5 ± 3.0% and finally 29.06 ± 1.78%, p < 0.001. Left ventricular ejection fraction was gradually impaired after modeling (58.9 ± 12.6%, 56.3 ± 10.1%, 55.3 ± 9.0%, 53.8 ± 9.9%, respectively). And the MPR and MPRI also decreased stepwise with extent of surgery time (MPRI dropped from 2.1 ± 0.4, 2.0 ± 0.2 to 1.8 ± 0.3 and finally 1.7 ± 0.1, p = 0.004; MPR dropped from 2.3 ± 0.4, 2.1 ± 0.2 to 1.9 ± 0.4 and finally 1.8 ± 0.1, p < 0.001). Stronger associations between MPR, MPRI and CVF were paralleled lower wall thickening scores in fibrosis-affected areas. The ischemic myocardium was first appeared in the first week after surgery (involving ten segments), hibernated myocardium was first appeared in the second week after surgery (involving seventeen segments). LGE was first appeared in eight swine in the third weeks after surgery (16 segments). At 4w after surgery, average 9.6g scar tissue was found among 6 swine. At the same time, histological analysis established the presence of fibrosis and ongoing apoptosis in the infarcted area. In conclusion, our study provided valuable insights into the pathophysiological processes of chronic CAD and its consequences for cardiac structure and function in a large animal model through combining myocardial motion and stress perfusion.

Abstract 14417: Regional 4D Cardiac Magnetic Resonance Strain Associates With Late Gadolinium Enhancement in Duchenne Muscular Dystrophy Associated Cardiomyopathy

Introduction: Cardiomyopathy (CM) is the leading cause of death in Duchenne muscular dystrophy (DMD). Onset and clinical progression are varied. Cardiac magnetic resonance (CMR) late gadolinium enhancement (LGE) can detect fibrofatty replacement prior to decreased left ventricular ejection fraction (LVEF) but requires administration of gadolinium contrast agents. Non-contrast methods to characterize CM onset and progression could decrease scan time and exposure to gadolinium. Using a novel 4D (3D+time) regional strain analysis method, we hypothesized that the regional magnitude of surface area strain (E a ) would be significantly decreased in DMD patients with LGE and that E a would correlate with decreased LVEF . Methods: Short-axis cine CMR images for 43 pediatric DMD patients (13.6 ± 4.2 years) were compiled into 4D sequences for regional strain analysis (Fig. 1A). For all 4D sequences, epi- and endocardial borders were segmented across one cardiac cycle for kinematic analysis using a custom-built MATLAB graphical user interface (MathWorks, Natick, MA). Regional E a was measured by determining the relative change in the localized 4D endocardial surface mesh compared to end-diastole. Unpaired t-test and Spearman’s rho were used to determine statistical significance and correlation. Results: DMD patients had a range of CM severity: 13 with reduced LVEF of &lt;55% (30% of total) and 28 with LGE (65% of total). Peak E a was significantly different between patients with and without LGE in the basal inferior ( p =0.022), basal inferolateral ( p &lt;0.001), basal anterolateral ( p =0.002), mid inferolateral ( p =0.004), mid anterolateral ( p =0.018), and apical anterior ( p &lt;0.032), regions (Fig.1B). Basal E a also correlated significantly with LVEF ( rho =-0.45, p&lt; 0.001; Fig. 1C). Conclusion: Regional E a from 4D CMR in DMD was reduced in patients with LGE compared to those without LGE particularly in the basolateral regions. Peak basal E a correlated with a reduction in LVEF. LVEF.

Automatic classification of heart failure based on Cine-CMR images.

Heart failure (HF) is a serious and complex syndrome with a high mortality rate. In clinical diagnosis, the correct classification of HF is helpful. In our previous work, we proposed a self-supervised learning framework of HF classification (SSLHF) on cine cardiac magnetic resonance images (Cine-CMR). However, this method lacks the integration of three dimensions of spatial information and temporal information. Thus, this study aims at proposing an automatic 4D HF classification algorithm. To construct a 4D classification model, we proposed an extensional framework called 4D-SSLHF. It mainly consists of self-supervised image restoration and HF classification. The image restoration proxy task utilizes three image transformation methods to enhance the exploration of spatial and temporal information in the Cine-CMR. In the classification task, we proposed a Siamese Conv-LSTM network by combining the Siamese network and bi-directional Conv-LSTM to integrate the features of the four dimensions simultaneously. Experimental results on 184 patients from Shanghai Chest Hospital achieved an AUC of 0.8794 and an ACC of 0.8402 in the five-fold cross-validation. Compared with our previous work, the improvements in AUC and ACC were 2.89 % and 1.94 %, respectively. In this study, we proposed a novel self-supervised learning framework named 4D-SSLHF for HF classification based on Cine-CMR. The proposed 4D-SSLHF can mine 3D spatial information and temporal information in Cine-CMR images well and accurately classify different categories of HF. The good classification results show our method's potential to assist physicians in choosing personalized treatment.

Integrin α4 Positive Subpopulation in Adipose Derived Stem Cells Effectively Reduces Infarct Size through Enhanced Engraftment into Myocardial Infarction.

The efficacy of adipose-derived stem cells (ASCs) on myocardial infarction is limited due to poor survival and engraftment. Integrin-mediated cell adhesion is a prerequisite for its survival and homing. ASCs expressed insufficient integrin α4, limiting their homing capacity. This study aims to characterize integrin α4＋ ASC subpopulation and investigate their therapeutic efficacy in myocardial infarction. We used fluorescence-activated cell sorting to harvest integrin α4＋ ASCs subpopulation, which were characterized in vitro and transplanted into myocardial infarction model. Positron emission tomography imaging were performed to measure infarction size. Cardiac cine magnetic resonance imaging was used to evaluate heart contractile function. Compared with the unfractionated ASCs, integrin α4＋ ASCs subpopulation secreted a higher level of angiogenic growth factors, migrated more rapidly, and exhibited a stronger anti-apoptotic capacity. Vascular cell adhesion molecule-1 was obviously up-regulated at 3 days after myocardial infarction, which interacted with integrin α4 receptor on the surface of ASCs to enhance the survival and adhesion. Thus, we implanted unfractionated ASCs or integrin α4＋ ASCs subpopulation into the 3-day infarcted myocardium. Integrin α4＋ ASCs subpopulation exhibited more robust engraftment into the infarcted myocardium. Integrin α4＋ ASCs subpopulation more effectively decreased infarct size and strengthen cardiac function recovery than did the unfractionated ASCs. Integrin α4＋ ASCs subpopulation is superior to unfractionated ASCs in ameliorating ischemic myocardial damage in animal model. Mechanistically, their more robust engraftment into the infarct area, higher migratory capacity and their increased release of paracrine factors contribute to enhanced tissue repair.

Prognostic prediction of left ventricular myocardial noncompaction using machine learning and cardiac magnetic resonance radiomics.

Although there are many studies on the prognostic factors of left ventricular myocardial noncompaction (LVNC), the determinants are varied and not entirely consistent. This study aimed to build predictive models using radiomics features and machine learning to predict major adverse cardiovascular events (MACEs) in patients with LVNC. In total, 96 patients with LVNC were included and randomly divided into training and test cohorts. A total of 105 cine cardiac magnetic resonance (CMR)-derived radiomics features and 35 clinical characteristics were extracted. Five different oversampling algorithms were compared for selection of the optimal imbalanced processing. Feature importance was assessed with extreme gradient boosting (XGBoost). We compared the performance of 5 machine learning classification methods with different sample:feature ratios to determine the optimal hybrid classification strategy. Subsequently, radiomics, clinical, and combined radiomics-clinical models were developed and compared. The machine learning pipeline included an adaptive synthetic (ADASYN) algorithm for imbalanced processing, XGBoost feature selection with a sample:feature ratio of 10, and support vector machine (SVM) modeling. The areas under the receiver operating characteristic curves (AUCs) of the radiomics model, clinical model, and combined model in the validation cohort were 0.87 (sensitivity 83.33%, specificity 64.29%), 0.65 (sensitivity 16.67%, specificity 78.57%), and 0.92 (specificity 33.33%, sensitivity 100.00%), respectively. The radiomics model performed similarly to the clinical and combined models (P=0.124 and P=0.621, respectively). The performance of the combined model was significantly better than that of the clinical model (P=0.003). The machine learning-based cine CMR radiomics model performed well at predicting MACEs in patients with LVNC. Adding radiomics features offered incremental prognostic value over clinical factors alone.