Modified GAN Augmentation Algorithms for the MRI-Classification of Myocardial Scar Tissue in Ischemic Cardiomyopathy.
Ontology highlight
ABSTRACT:
SUBMITTER: Sharma UC
PROVIDER: S-EPMC8473636 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Background: Implantable cardioverter-defibrillator (ICD) therapy is associated with several deleterious effects, which can be reduced by antiarrhythmic drugs or catheter ablation. However, it is largely unknown which patients might benefit from these therapies. Therefore, this study aimed to investigate whether myocardial scar characterization improves risk stratification for ventricular arrhythmia (VA) occurrence in patients with ischemic cardiomyopathy and an ICD. Methods: In this study, 82 patients with ischemic cardiomyopathy who received an ICD were enrolled retrospectively. Late gadolinium enhancement cardiac magnetic resonance (LGE-CMR) images were analyzed using an investigational software tool to obtain quantitative data regarding the total scar, core, and border zone (BZ). Data regarding the QRS complex was obtained from electrocardiography (ECG). The primary endpoint was appropriate ICD therapy. Results: During a median follow-up duration of 3.98 years [interquartile range (IQR) 2.89-5.14 years], appropriate therapy occurred in 24 (29.3%) patients. Patients with appropriate ICD therapy had a significantly larger total scar mass [60.0 (IQR 41.2-73.4) vs. 43.3 (IQR 31.2-61.2) g; P = 0.009] and BZ mass [32.9 (IQR 26.9-42.4) vs. 24.5 (IQR 18.8-32.5) g; P = 0.001] than those without appropriate therapy. In multivariable Cox regression analyses, total scar mass [hazard ratio (HR) 1.02 [95% confidence interval (CI) 1.00-1.04]; P = 0.014] and BZ mass (HR 1.04 [95% CI 1.01-1.07]; P = 0.009) independently predicted appropriate ICD therapy. Core mass and the QRS complex, however, were not significantly associated with the primary endpoint. Conclusion: LGE-CMR-based, but not ECG-based myocardial scar characterization improves risk stratification for VA occurrence in patients with ischemic cardiomyopathy who received an ICD.
| S-EPMC8415981 | biostudies-literature
Project description:BackgroundSignificant controversy continues to confound patient selection and referral for revascularization and mitral valve intervention in patients with ischemic cardiomyopathy (ICM). Cardiac magnetic resonance (CMR) enables comprehensive phenotyping with gold-standard tissue characterization and volumetric/functional measures. Therefore, we sought to determine the impact of CMR-enriched phenomapping patients with ICM to identify differential outcomes following surgical revascularization and surgical mitral valve intervention (sMVi).MethodsConsecutive patients with ICM referred for CMR between 2002 and 2017 were evaluated. Latent class analysis was performed to identify phenotypes enriched by comprehensive CMR assessment. The primary end point was death, heart transplant, or left ventricular assist device implantation. A multivariable Cox survival model was developed to determine the association of phenogroups with overall survival. Subgroup analysis was performed to assess the presence of differential response to post-magnetic resonance imaging procedural interventions.ResultsA total of 787 patients were evaluated (63.0±11.2 years, 24.8% women), with 464 primary events. Subsequent surgical revascularization and sMVi occurred in 380 (48.3%) and 157 (19.9%) patients, respectively. Latent class analysis identified 3 distinct clusters of patients, which demonstrated significant differences in overall outcome (P<0.001). Latent class analysis identified differential survival benefit of revascularization in patients as well as patients who underwent revascularization with sMVi, based on phenogroup classification, with phenogroup 3 deriving the most survival benefit from revascularization and revascularization with sMVi (hazard ratio, 0.61 [0.43-0.88]; P=0.0081).ConclusionsCMR-enriched unsupervised phenomapping identified distinct phenogroups, which were associated with significant differential survival benefit following surgical revascularization and sMVi in patients with ICM. Phenomapping provides a novel approach for patient selection, which may enable personalized therapeutic decision-making for patients with ICM.
| S-EPMC11020053 | biostudies-literature
Project description:BackgroundMyocardial scar burden quantified using late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR), has important prognostic value in hypertrophic cardiomyopathy (HCM). However, nearly 50% of HCM patients have no scar but undergo repeated gadolinium-based CMR over their life span. We sought to develop an artificial intelligence (AI)-based screening model using radiomics and deep learning (DL) features extracted from balanced steady state free precession (bSSFP) cine sequences to identify HCM patients without scar.MethodsWe evaluated three AI-based screening models using bSSFP cine image features extracted by radiomics, DL, or combined DL-Radiomics. Images for 759 HCM patients (50 ± 16 years, 66% men) in a multi-center/vendor study were used to develop and test model performance. An external dataset of 100 HCM patients (53 ± 14 years, 70% men) was used to assess model generalizability. Model performance was evaluated using area-under-receiver-operating curve (AUC).ResultsThe DL-Radiomics model demonstrated higher AUC compared to DL and Radiomics in the internal (0.83 vs 0.77, p = 0.006 and 0.78, p = 0.05; n = 159) and external (0.74 vs 0.64, p = 0.006 and 0.71, p = 0.27; n = 100) datasets. The DL-Radiomics model correctly identified 43% and 28% of patients without scar in the internal and external datasets compared to 42% and 16% by Radiomics model and 42% and 23% by DL model, respectively.ConclusionsA DL-Radiomics AI model using bSSFP cine images outperforms DL or Radiomics models alone as a scar screening tool prior to gadolinium administration. Despite its potential, the clinical utility of the model remains limited and further investigation is needed to improve the accuracy and generalizability.
| S-EPMC9235098 | biostudies-literature
Project description:BackgroundDrawing on accumulated patient data from a hospital database, the goal of this retrospective study was to analyze cardiac function associated with global preoperative myocardial scarring assessed by cardiac magnetic resonance with late gadolinium enhancement (CMR-LGE) in patients with ischemic cardiomyopathy (ICM) after coronary artery bypass grafting (CABG).MethodsA total of 57 patients diagnosed with ICM who underwent isolated CABG at Beijing Anzhen Hospital between September 2017 and September 2019 were enrolled in this retrospective study. All these patients underwent a preoperative CMR-LGE examination. Based on postoperative echocardiography results at 6 months, cases were divided into the following 2 groups: improved cardiac function [a difference of left ventricular ejection fraction (LVEF) greater than or equal to 5%] and unimproved cardiac function. The factors contributing to these patients' unimproved cardiac function were investigated.ResultsAt 6 months after surgery, 64.9% (37/57) of cases had improved cardiac function, and 35.1% (20/57) had no improvement. There was no statistical difference between the 2 groups in the Synergy Between Percutaneous Coronary Intervention With Taxus and Cardiac Surgery (SYNTAX) score (41.7±7.6 vs. 42.8±8.3; P=0.603), but compared to the improved group, preoperative myocardial scarring was significantly enlarged in the unimproved group (41.9%±6.4% vs. 27.8%±8.5%; P<0.001). In regression analysis, only preoperative myocardial scarring [odds ratio (OR) =1.44; 95% confidence interval (CI): 1.13-1.83; P=0.003] was associated with no change in cardiac function evaluated by echocardiography after CABG. The median follow-up of 1.6 years (range, 0.6-4.1 years) found that the unimproved group had a higher incidence of major adverse cardiovascular and cerebrovascular events (MACCEs) (8.1% vs. 25.0%; P=0.044), and that the New York Heart Association (NYHA) classification of the unimproved group was higher than that of the improved group (P=0.018).ConclusionsIn ICM patients, a greater amount of preoperative myocardial scarring is associated with unimproved cardiac function after CABG. The measurement of preoperative myocardial scarring may aid clinicians in identifying patients who would benefit from CABG.
| S-EPMC9745517 | biostudies-literature
Project description:BackgroundMyocardial fat deposition (FAT-DEP) has been frequently observed in regions of chronic myocardial infarction in patients with ischemic cardiomyopathy. The role of FAT-DEP within scar-related ventricular tachycardia (VT) circuits has not been investigated.ObjectiveThis pilot study aimed to assess the impact of myocardial FAT-DEP on local electrograms and VT circuits in patients with ischemic cardiomyopathy.MethodsContrast-enhanced computed tomography was performed in 22 patients with ischemic VT. Electroanatomic map points were registered to the corresponding contrast-enhanced computed tomography images. Myocardial FAT-DEP was identified and characterized using a postprocessing image overlay that highlighted areas below 0 Hounsfield units (HU). The mean attenuation of local myocardial regions corresponding to sampled electrograms was measured on short-axis images. The associations of mean attenuation with bipolar and unipolar amplitudes, left ventricular wall thickness, and VT circuit sites were investigated.ResultsOf 1801 electroanatomic map points, 519 (28.8%) were located in regions with FAT-DEP. Significant differences were observed in mean intensity (23.2 ± 35.6 HU vs 81.7 ± 21.9 HU; P < .001), bipolar (0.75 ± 0.83 mV vs 2.9 ± 2.4 mV; P < .001) and unipolar (3.1 ± 1.7 mV vs 7.4 ± 4.3 mV; P < .001) amplitudes, and left ventricular wall thickness (5.2 ± 1.7 mm vs 8.2 ± 2.5 mm; P < .001) between regions with and without FAT-DEP. Lower HU was strongly associated with lower bipolar and unipolar amplitudes (P < .0001, respectively). Importantly, FAT-DEP was associated with critical VT circuit sites with fractionated or isolated potentials.ConclusionFAT-DEP was associated with electrogram characteristics and VT circuit sites. Further work will be needed to determine whether FAT-DEP plays a causal role in the generation of ischemic scar-related VT circuits.
| S-EPMC4485604 | biostudies-literature
Project description:BackgroundThe role of assessment of myocardial viability in identifying patients with ischemic cardiomyopathy who might benefit from surgical revascularization remains controversial. Furthermore, although improvement in left ventricular function is one of the goals of revascularization, its relationship to subsequent outcomes is unclear.MethodsAmong 601 patients who had coronary artery disease that was amenable to coronary-artery bypass grafting (CABG) and who had a left ventricular ejection fraction of 35% or lower, we prospectively assessed myocardial viability using single-photon-emission computed tomography, dobutamine echocardiography, or both. Patients were randomly assigned to undergo CABG and receive medical therapy or to receive medical therapy alone. Left ventricular ejection fraction was measured at baseline and after 4 months of follow-up in 318 patients. The primary end point was death from any cause. The median duration of follow-up was 10.4 years.ResultsCABG plus medical therapy was associated with a lower incidence of death from any cause than medical therapy alone (182 deaths among 298 patients in the CABG group vs. 209 deaths among 303 patients in the medical-therapy group; adjusted hazard ratio, 0.73; 95% confidence interval, 0.60 to 0.90). However, no significant interaction was observed between the presence or absence of myocardial viability and the beneficial effect of CABG plus medical therapy over medical therapy alone (P = 0.34 for interaction). An increase in left ventricular ejection fraction was observed only among patients with myocardial viability, irrespective of treatment assignment. There was no association between changes in left ventricular ejection fraction and subsequent death.ConclusionsThe findings of this study do not support the concept that myocardial viability is associated with a long-term benefit of CABG in patients with ischemic cardiomyopathy. The presence of viable myocardium was associated with improvement in left ventricular systolic function, irrespective of treatment, but such improvement was not related to long-term survival. (Funded by the National Institutes of Health; STICH ClinicalTrials.gov number, NCT00023595.).
| S-EPMC6814246 | biostudies-literature
Project description:ObjectiveThe purpose of this study was to develop an algorithm incorporating MRI metrics to classify patients with mild traumatic brain injury (mTBI) and controls.MethodsThis was an institutional review board-approved, Health Insurance Portability and Accountability Act-compliant prospective study. We recruited patients with mTBI and healthy controls through the emergency department and general population. We acquired data on a 3.0T Siemens Trio magnet including conventional brain imaging, resting-state fMRI, diffusion-weighted imaging, and magnetic field correlation (MFC), and performed multifeature analysis using the following MRI metrics: mean kurtosis (MK) of thalamus, MFC of thalamus and frontal white matter, thalamocortical resting-state networks, and 5 regional gray matter and white matter volumes including the anterior cingulum and left frontal and temporal poles. Feature selection was performed using minimal-redundancy maximal-relevance. We used classifiers including support vector machine, naive Bayesian, Bayesian network, radial basis network, and multilayer perceptron to test maximal accuracy.ResultsWe studied 24 patients with mTBI and 26 controls. Best single-feature classification uses thalamic MK yielding 74% accuracy. Multifeature analysis yields 80% accuracy using the full feature set, and up to 86% accuracy using minimal-redundancy maximal-relevance feature selection (MK thalamus, right anterior cingulate volume, thalamic thickness, thalamocortical resting-state network, thalamic microscopic MFC, and sex).ConclusionMultifeature analysis using diffusion-weighted imaging, MFC, fMRI, and volumetrics may aid in the classification of patients with mTBI compared with controls based on optimal feature selection and classification methods.Classification of evidenceThis study provides Class III evidence that classification algorithms using multiple MRI features accurately identifies patients with mTBI as defined by American Congress of Rehabilitation Medicine criteria compared with healthy controls.
| S-EPMC4180485 | biostudies-literature
Project description:Estimation of hemorrhagic transformation (HT) risk is crucial for treatment decision-making after acute ischemic stroke. We aimed to determine the accuracy of multiparametric MRI-based predictive algorithms in calculating probability of HT after stroke. Spontaneously, hypertensive rats were subjected to embolic stroke and, after 3?h treated with tissue plasminogen activator (Group I: n?=?6) or vehicle (Group II: n?=?7). Brain MRI measurements of T2, T2*, diffusion, perfusion, and blood-brain barrier permeability were obtained at 2, 24, and 168?h post-stroke. Generalized linear model and random forest (RF) predictive algorithms were developed to calculate the probability of HT and infarction from acute MRI data. Validation against seven-day outcome on MRI and histology revealed that highest accuracy of hemorrhage prediction was achieved with a RF-based model that included spatial brain features (Group I: area under the receiver-operating characteristic curve (AUC)?=?0.85?±?0.14; Group II: AUC?=?0.89?±?0.09), with significant improvement over perfusion- or permeability-based thresholding methods. However, overlap between predicted and actual tissue outcome was significantly lower for hemorrhage prediction models (maximum Dice's Similarity Index (DSI)?=?0.20?±?0.06) than for infarct prediction models (maximum DSI?=?0.81?±?0.06). Multiparametric MRI-based predictive algorithms enable early identification of post-ischemic tissue at risk of HT and may contribute to improved treatment decision-making after acute ischemic stroke.
| S-EPMC5536810 | biostudies-other
Project description:BACKGROUND:While left ventricular ejection fraction (LVEF) has been shown to have prognostic value in ischemic cardiomyopathy (ICMX) patients, right ventricular ejection fraction (RVEF) has not been systematically evaluated in either ICMX or non-ischemic cardiomyopathy (NICMX) patients. Moreover, an accurate estimation of RVEF is problematic due to the geometry of the right ventricle (RV). Over the years, there have been improvements in the resolution, image acquisition and post-processing software for cardiac magnetic resonance imaging (CMR), such that CMR has become the "gold standard" for measuring RV volumetrics and RVEF. We hypothesize that CMR defines RVEF more so than LVEF and might have prognostic capabilities in ischemic and non-ischemic cardiomyopathy patients (ICMX and NICMX). METHODS:Patients that underwent CMR at our institution between January 2005 and October 2012 were retrospectively selected if three-dimensional (3D) LVEF < 35%. Patients were further divided into ICMX and NICMX groups. The electronic medical record (EMR) database inquiry determined all-cause mortality and major adverse cardiovascular events (MACE). Additionally, a Social Security Death Index (SSI) database inquiry was performed to determine all-cause mortality in patients who were lost to follow-up. Patients were further sub-grouped on the basis of 3D RVEF ≥ 20%. Separately, patients were sub-grouped by LVEF ≥ 20% in both ICMX and NICMX cases. A cut-off of ≥20% was chosen for the RVEF based on the results of prior studies showing significance based on Kaplan⁻Meier (KM) survival curves. Cumulative event rates were estimated for each subgroup using the KM analysis and were compared using the log-rank test. The 3D RV/LVEFs were compared to all-cause mortality and MACE. ICMX patients were defined using the World Health Organization (WHO) criteria. RESULTS:From a 7000-patient CMR database, 753 heart failure patients were selected. Eighty-seven patients met WHO definition of ICMX and NICMX (43 ICMX and 44 NICMX). The study patients were followed for a median of 3 years (Interquartile range or IQR 1.5⁻6.5 years). The mean age of patients was 58 ± 13 years; 79% were male. In ICMX, mean 3D LVEF was 21% ± 6% and mean 3D RVEF was 38% ± 14%, while for NICMX, mean 3D LVEF was 16% ± 6% and mean 3D RVEF was 30% ± 14% (p < 0.005 for intra- and inter-group comparison). It should be noted that LVEF < RVEF in both groups and the ejection fraction (EF) in NICMX was less than the corresponding EF in ICMX. Overall mortality was higher in ICMX than NICMX (12/40, 30% vs. 7/43, 16%; p < 0.05). Patients were stratified based on both RVEF and LVEF with a threshold of EF ≥ 20% separately. RVEF but not LVEF was a significant predictor of death for NICMX (χ² = 8; p < 0.005), while LVEF did not predict death in ICMX (χ² = 2, p = not significant). Similarly, time to MACE was predicted by RVEF for NICMX (χ² = 9; p < 0.005) but not by LVEF in ICMX (χ² = 1; p = NS). Importantly, RVEF, while predictive of NICMX MACE, did not emerge as a predictor of survival or MACE in ICMX. CONCLUSIONS:Via 3D CMR in non-ischemic CMX patients, RVEF has important value in predicting death and time to first MACE while 3D LVEF is far less predictive.
| S-EPMC6468852 | biostudies-other
Project description:Preclinical investigations support the concept that donor cells more oriented towards a cardiovascular phenotype favor repair. In light of this philosophy, we previously identified HDAC1 as a mediator of cardiac mesenchymal cell (CMC) cardiomyogenic lineage commitment and paracrine signaling potency in vitro-suggesting HDAC1 as a potential therapeutically exploitable target to enhance CMC cardiac reparative capacity. In the current study, we examined the effects of pharmacologic HDAC1 inhibition, using the benzamide class 1 isoform-selective HDAC inhibitor entinostat (MS-275), on CMC cardiomyogenic lineage commitment and CMC-mediated myocardial repair in vivo. Human CMCs pre-treated with entinostat or DMSO diluent control were delivered intramyocardially in an athymic nude rat model of chronic ischemic cardiomyopathy 30 days after a reperfused myocardial infarction. Indices of cardiac function were assessed by echocardiography and left ventricular (LV) Millar conductance catheterization 35 days after treatment. Compared with naïve CMCs, entinostat-treated CMCs exhibited heightened capacity for myocyte-like differentiation in vitro and superior ability to attenuate LV remodeling and systolic dysfunction in vivo. The improvement in CMC therapeutic efficacy observed with entinostat pre-treatment was not associated with enhanced donor cell engraftment, cardiomyogenesis, or vasculogenesis, but instead with more efficient inhibition of myocardial fibrosis and greater increase in myocyte size. These results suggest that HDAC inhibition enhances the reparative capacity of CMCs, likely via a paracrine mechanism that improves ventricular compliance and contraction and augments myocyte growth and function.
| S-EPMC6335654 | biostudies-literature