Quantification of Epicardial Adipose Tissue Volume and Attenuation for Cardiac CT Scans Using Deep Learning in a Single Multi-Task Framework.

Background: Recent studies have shown that epicardial adipose tissue (EAT) is an independent atrial fibrillation (AF) prognostic marker and has influence on the myocardial function. In computed tomography (CT), EAT volume (EATv) and density (EATd) are parameters that are often used to quantify EAT. While increased EATv has been found to correlate with the prevalence and the recurrence of AF after ablation therapy, higher EATd correlates with inflammation due to arrest of lipid maturation and with high risk of plaque presence and plaque progression. Automation of the quantification task diminishes the variability in readings introduced by different observers in manual quantification and results in high reproducibility of studies and less time-consuming analysis. Our objective is to develop a fully automated quantification of EATv and EATd using a deep learning (DL) framework. Methods: We proposed a framework that consists of image classification and segmentation DL models and performs the task of selecting images with EAT from all the CT images acquired for a patient, and the task of segmenting the EAT from the output images of the preceding task. EATv and EATd are estimated using the segmentation masks to define the region of interest. For our experiments, a 300-patient dataset was divided into two subsets, each consisting of 150 patients: Dataset 1 (41,979 CT slices) for training the DL models, and Dataset 2 (36,428 CT slices) for evaluating the quantification of EATv and EATd. Results: The classification model achieved accuracies of 98% for precision, recall and F 1 scores, and the segmentation model achieved accuracies in terms of mean ( ± std.) and median dice similarity coefficient scores of 0.844 ( ± 0.19) and 0.84, respectively. Using the evaluation set (Dataset 2), our approach resulted in a Pearson correlation coefficient of 0.971 ( R 2 = 0.943) between the label and predicted EATv, and the correlation coefficient of 0.972 ( R 2 = 0.945) between the label and predicted EATd. Conclusions: We proposed a framework that provides a fast and robust strategy for accurate EAT segmentation, and volume (EATv) and attenuation (EATd) quantification tasks. The framework will be useful to clinicians and other practitioners for carrying out reproducible EAT quantification at patient level or for large cohorts and high-throughput projects.

Repeat catheter ablation for atrial fibrillation.

Catheter ablation of atrial fibrillation (AF) is an established therapy that reduces AF burden, improves quality of life, and reduces the risks of cardiovascular outcomes. Although there are clear guidelines for the application of de novo catheter ablation, there is less evidence to guide recommendations for repeat catheter ablation in patients who experience recurrent AF. In this review, we examine the rationale for repeat ablation, mechanisms of recurrence, patient selection, optimal timing, and procedural strategies. We discuss additional important considerations, including treatment of comorbidities and risk factors, risk of complications, and effectiveness. Mechanisms of recurrent AF are often due to non-pulmonary vein (non-PV) triggers; however, there is insufficient evidence supporting the routine use of empiric lesion sets during repeat ablation. The emergence of pulsed field ablation may alter the safety and effectiveness of de novo and repeat ablation. Extrapolation of data from randomized trials of de novo ablation does not optimally inform efficacy in cases of redo ablation. Additional large, randomized controlled trials are needed to address important clinical questions regarding procedural strategies and timing of repeat ablation.

Machine Learning of Cardiac Anatomy and the Risk of New-Onset Atrial Fibrillation After TAVR.

BACKGROUND: New-onset atrial fibrillation (NOAF) occurs in 5% to 15% of patients who undergo transfemoral transcatheter aortic valve replacement (TAVR). Cardiac imaging has been underutilized to predict NOAF following TAVR. OBJECTIVES: The objective of this analysis was to compare and assess standard, manual echocardiographic and cardiac computed tomography (cCT) measurements as well as machine learning-derived cCT measurements of left atrial volume index and epicardial adipose tissue as risk factors for NOAF following TAVR. METHODS: The study included 1,385 patients undergoing elective, transfemoral TAVR for severe, symptomatic aortic stenosis. Each patient had standard and machine learning-derived measurements of left atrial volume and epicardial adipose tissue from cardiac computed tomography. The outcome of interest was NOAF within 30 days following TAVR. We used a 2-step statistical model including random forest for variable importance ranking, followed by multivariable logistic regression for predictors of highest importance. Model discrimination was assessed by using the C-statistic to compare the performance of the models with and without imaging. RESULTS: Forty-seven (5.0%) of 935 patients without pre-existing atrial fibrillation (AF) experienced NOAF. Patients with pre-existing AF had the largest left atrial volume index at 76.3 ± 28.6 cm3/m2 followed by NOAF at 68.1 ± 26.6 cm3/m2 and then no AF at 57.0 ± 21.7 cm3/m2 (P < 0.001). Multivariable regression identified the following risk factors in association with NOAF: left atrial volume index ≥76 cm2 (OR: 2.538 [95% CI: 1.165-5.531]; P = 0.0191), body mass index <22 kg/m2 (OR: 4.064 [95% CI: 1.500-11.008]; P = 0.0058), EATv (OR: 1.007 [95% CI: 1.000-1.014]; P = 0.043), aortic annulus area ≥659 mm2 (OR: 6.621 [95% CI: 1.849-23.708]; P = 0.004), and sinotubular junction diameter ≥35 mm (OR: 3.891 [95% CI: 1.040-14.552]; P = 0.0435). The C-statistic of the model was 0.737, compared with 0.646 in a model that excluded imaging variables. CONCLUSIONS: Underlying cardiac structural differences derived from cardiac imaging may be useful in predicting NOAF following transfemoral TAVR, independent of other clinical risk factors.

Using machine learning to enhance prediction of atrial fibrillation recurrence after catheter ablation.

Background: Traditional risk scores for recurrent atrial fibrillation (AF) following catheter ablation utilize readily available clinical and echocardiographic variables and yet have limited discriminatory capacity. Use of data from cardiac imaging and deep learning may help improve accuracy and prediction of recurrent AF after ablation. Methods: We evaluated patients with symptomatic, drug-refractory AF undergoing catheter ablation. All patients underwent pre-ablation cardiac computed tomography (cCT). LAVi was computed using a deep-learning algorithm. In a two-step analysis, random survival forest (RSF) was used to generate prognostic models with variables of highest importance, followed by Cox proportional hazard regression analysis of the selected variables. Events of interest included early and late recurrence. Results: Among 653 patients undergoing AF ablation, the most important factors associated with late recurrence by RSF analysis at 24 (+/-18) months follow-up included LAVi and early recurrence. In total, 5 covariates were identified as independent predictors of late recurrence: LAVi (HR per mL/m2 1.01 [1.01-1.02]; p < .001), early recurrence (HR 2.42 [1.90-3.09]; p < .001), statin use (HR 1.38 [1.09-1.75]; p = .007), beta-blocker use (HR 1.29 [1.01-1.65]; p = .043), and adjunctive cavotricuspid isthmus ablation [HR 0.74 (0.57-0.96); p = .02]. Survival analysis demonstrated that patients with both LAVi >66.7 mL/m2 and early recurrence had the highest risk of late recurrence risk compared with those with LAVi <66.7 mL/m2 and no early recurrence (HR 4.52 [3.36-6.08], p < .001). Conclusions: Machine learning-derived, full volumetric LAVi from cCT is the most important pre-procedural risk factor for late AF recurrence following catheter ablation. The combination of increased LAVi and early recurrence confers more than a four-fold increased risk of late recurrence.

Generalizable Framework for Atrial Volume Estimation for Cardiac CT Images Using Deep Learning With Quality Control Assessment.

OBJECTIVES: Cardiac computed tomography (CCT) is a common pre-operative imaging modality to evaluate pulmonary vein anatomy and left atrial appendage thrombus in patients undergoing catheter ablation (CA) for atrial fibrillation (AF). These images also allow for full volumetric left atrium (LA) measurement for recurrence risk stratification, as larger LA volume (LAV) is associated with higher recurrence rates. Our objective is to apply deep learning (DL) techniques to fully automate the computation of LAV and assess the quality of the computed LAV values. METHODS: Using a dataset of 85,477 CCT images from 337 patients, we proposed a framework that consists of several processes that perform a combination of tasks including the selection of images with LA from all other images using a ResNet50 classification model, the segmentation of images with LA using a UNet image segmentation model, the assessment of the quality of the image segmentation task, the estimation of LAV, and quality control (QC) assessment. RESULTS: Overall, the proposed LAV estimation framework achieved accuracies of 98% (precision, recall, and F1 score metrics) in the image classification task, 88.5% (mean dice score) in the image segmentation task, 82% (mean dice score) in the segmentation quality prediction task, and R 2 (the coefficient of determination) value of 0.968 in the volume estimation task. It correctly identified 9 out of 10 poor LAV estimations from a total of 337 patients as poor-quality estimates. CONCLUSIONS: We proposed a generalizable framework that consists of DL models and computational methods for LAV estimation. The framework provides an efficient and robust strategy for QC assessment of the accuracy for DL-based image segmentation and volume estimation tasks, allowing high-throughput extraction of reproducible LAV measurements to be possible.

Genetic regulation of OAS1 nonsense-mediated decay underlies association with COVID-19 hospitalization in patients of European and African ancestries.

The chr12q24.13 locus encoding OAS1-OAS3 antiviral proteins has been associated with coronavirus disease 2019 (COVID-19) susceptibility. Here, we report genetic, functional and clinical insights into this locus in relation to COVID-19 severity. In our analysis of patients of European (n = 2,249) and African (n = 835) ancestries with hospitalized versus nonhospitalized COVID-19, the risk of hospitalized disease was associated with a common OAS1 haplotype, which was also associated with reduced severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) clearance in a clinical trial with pegIFN-λ1. Bioinformatic analyses and in vitro studies reveal the functional contribution of two associated OAS1 exonic variants comprising the risk haplotype. Derived human-specific alleles rs10774671-A and rs1131454 -A decrease OAS1 protein abundance through allele-specific regulation of splicing and nonsense-mediated decay (NMD). We conclude that decreased OAS1 expression due to a common haplotype contributes to COVID-19 severity. Our results provide insight into molecular mechanisms through which early treatment with interferons could accelerate SARS-CoV-2 clearance and mitigate against severe COVID-19.

Screening and Analysis of Janelia FlyLight Project Enhancer-Gal4 Strains Identifies Multiple Gene Enhancers Active During Hematopoiesis in Normal and Wasp-Challenged Drosophila Larvae.

A GFP expression screen has been conducted on >1000 Janelia FlyLight Project enhancer-Gal4 lines to identify transcriptional enhancers active in the larval hematopoietic system. A total of 190 enhancers associated with 87 distinct genes showed activity in cells of the third instar larval lymph gland and hemolymph. That is, gene enhancers were active in cells of the lymph gland posterior signaling center (PSC), medullary zone (MZ), and/or cortical zone (CZ), while certain of the transcriptional control regions were active in circulating hemocytes. Phenotypic analyses were undertaken on 81 of these hematopoietic-expressed genes, with nine genes characterized in detail as to gain- and loss-of-function phenotypes in larval hematopoietic tissues and blood cells. These studies demonstrated the functional requirement of the cut gene for proper PSC niche formation, the hairy, Btk29A, and E2F1 genes for blood cell progenitor production in the MZ domain, and the longitudinals lacking, dFOXO, kayak, cap-n-collar, and delilah genes for lamellocyte induction and/or differentiation in response to parasitic wasp challenge and infestation of larvae. Together, these findings contribute substantial information to our knowledge of genes expressed during the larval stage of Drosophila hematopoiesis and newly identify multiple genes required for this developmental process.