Citations

Abstract Objectives: We aimed to compare the segmentation performance of the current prominent deep learning (DL) algorithms with ground-truth segmentations and to validate the reproducibility of the manually created 2D echocardiographic four cardiac chamber ground-truth annotation.Background: Recently emerged DL based fully-automated chamber segmentation and function assessment methods have shown great potential for future application in aiding image acquisition, quantification, and suggestion for diagnosis. However, the performance of current DL algorithms have not previously been compared with each other. In addition, the reproducibility of ground-truth annotations which are the basis of these algorithms have not yet been fully validated.Methods: We retrospectively enrolled 500 consecutive patients who underwent transthoracic echocardiogram (TTE) from December 2019 to December 2020. Simple U-net, Res-U-net, and Dense-U-net algorithms were compared for the segmentation performances and clinical indices such as left atrial volume (LAV), left ventricular end diastolic volume (LVEDV), LV end systolic volume (LVESV), LV mass, and ejection fraction (EF) were evaluated. The inter- and intra- observer variability analysis was performed by two expert sonographers for a randomly selected echocardiographic view in 100 patients (apical 2-chamber, apical 4-chamber, and parasternal short axis views).Results: The overall performance of all DL methods was excellent (average Dice similarity coefficient (DSC) 0.91 to 0.95 and average Intersection over union (IOU) 0.83 to 0.90), with the exception of LV wall area on PSAX view (average DSC of 0.83, IOU 0.72). In addition, there were no significant difference in clinical indices between ground truth and automated DL measurements. For inter- and intra observer variability analysis, the overall intra observer reproducibility was excellent: LAV (ICC = 0.995), LVEDV (ICC = 0.996), LVESV (ICC = 0.997), LV mass (ICC = 0.991) and EF (ICC = 0.984). The inter-observer reproducibility was slightly lower as compared to intraobserver agreement: LAV (ICC = 0.976), LVEDV (ICC = 0.982), LVESV (ICC =0.970), LV mass (ICC = 0.971), and EF (ICC = 0.899).Conclusions: The three current prominent DL-based fully automated methods are able to reliably perform four-chamber segmentation and quantification of clinical indices. Furthermore, we were able to validate the four cardiac chamber ground-truth annotation and demonstrate an overall excellent reproducibility, but still with some degree of inter-observer variability.

Introduction: Ischemic stroke (IS) causes substantial morbidity and mortality in patients undergoing percutaneous coronary intervention (PCI) with a 5 yr incidence ~ 3%. We sought the test the accuracy of Machine learning (ML) algorithms in predicting IS in patients undergoing PCI. Methods: Mayo Clinic CathPCI registry data were retrospectively analyzed from Jan 2003 - June 2018 including 21,872 patients who underwent PCI. The cohort was randomly divided into a training sample (75%, n=16404) and a unique test sample (25%, n=5468) prior to model generation. The risk prediction model was generated utilizing a random forest algorithm (RF model) on 188 unique variables to predict the risk of IS at 6-month, 1, 2, and 5-year post PCI. Conventional risk factors for stroke were used for logistic regression. The receiver operating characteristic (ROC) curve and area under the curve for the RF and logistic regression models were compared for the test cohort. Results: The mean age was 66.9 ± 12.4 years, and 71% were male. Patient demographics and outcomes are shown in Table 1 . The ROC area under the curve for the RF model was superior compared to the logistic regression model in predicting IS at 6 months, 1,2 and 5 yrs for the test cohort ( Figure 1 .) Conclusions: The RF model accurately predicts short and long term risk of IS and outperforms logistic regression analysis in patients undergoing PCI.

Background: Identifying patients at a high risk of mortality post percutaneous coronary intervention (PCI) is of vital clinical importance. We investigated the utility of machine learning algorithms to predict short and intermediate-term risk of all-cause mortality in patients undergoing PCI. Methods: Patient-level demographics, clinical, electrocardiographic ,echocardiographic and angiographic data from January 2006 to December 2017 were extracted from the Mayo Clinic CathPCI registry and clinical records. For patients with multiple PCI events, data collected at the time of the index PCI was used for analysis. Patients who underwent bailout coronary artery bypass graft surgery (CABG) prior to discharge were excluded. 306 variables were incorporated into random forest machine learning model (RF) to predict all-cause mortality at 6 months and 1 year after PCI. Ten-fold cross-validation repeated five times was used to optimize the hyperparameters and estimate its external performance. The National Cardiovascular Data Registry (NCDR) based logistic regression model was used for comparison. The area under receiver operator characteristic curves (AUC) was calculated to assess the ability of the models to predict all-cause mortality. Results: A total of 17356 unique patients were included for the final analysis after excluding 165 patients who underwent CABG surgery during the index hospitalization. The mean age was 66.9 ± 12.5 years;71% were male. Indications for PCI were ST-elevation myocardial infarction (9.4%), non-ST elevation myocardial infarction (12.9%), unstable angina (17.7%), and stable angina (52.8%) in the cohort. In-hospital, 6-month & 1 year mortality rates were 1.9%,4.2% & 5.8% respectively. The RF model was superior to the NCDR model in predicting inhospital, 6-month, 1 year mortality (p<0.0001) ( Figure 1 ). Conclusion: Machine learning is superior to NCDR model in predicting short and intermediate risk of all-cause mortality post PCI.

Background: Left atrial appendage occlusion (LAAO) devices have successfully provided an alternative therapeutic option in patients with atrial fibrillation and high bleeding risk. However, patients with thrombocytopenia (TP) were underrepresented in the milestone trials, and the optimal strategy of postprocedural antithrombotic therapy in this group of patients remains unclear. Methods: Patients were identified from the National Cardiac Database Registry - LAAO database at all three Mayo Clinic sites in the period from 1/2016-10/2019. Patients were further divided into TP (platelet &lt; 150 x 10^9/L) and control (platelet &gt; 150 x 10^9 /L) groups for clinical outcome analysis. Outcome endpoints include composite of bleeding (GI bleeding, hemorrhagic stroke, and other non-intracranial hemorrhage) and composite thrombotic events (device thrombus, ischemic stroke, TIA and undetermined stroke). Results: A total of 249 consecutive patients were included in the final analysis. The mean age was 76.7 ± 7.2 years, and 169 (67.9%) were male; 242 (97.2%) were white. The mean CHA2DS2-VASc score was 5.3 ±1.5, and the HAS-BLED score was 3.0 ± 1.1. TP at baseline was present in 74 (29.7%) patients. The median follow-up time was 6.8 months. The use of post-procedural antithrombotic regimens was similar between the two groups (Table 1). When comparing the TP group to control, there was no significant difference in composite bleeding events (10.8% vs. 8.0%, P = 0.069) and thrombotic events (2.7% vs. 2.3%, P= 0.170). Conclusions: The presence of baseline TP does not significantly increase post-procedural bleeding risk in atrial fibrillation/atrial flutter patients who underwent an LAAO occlusion procedure with the Watchman device (Boston Scientific). This group of patients can be treated with the same antithrombotic regimen as patients with normal platelet levels. Future studies are still warranted to determine the optimal antithrombotic regimen.

AbstractIntroductionThe right ventricle (RV) strain measured by speckle tracking (RVS) is an echocardiographic parameter used to assess RV function. We compared RVS to RV fractional area change (FAC%), tricuspid annular plane systolic excursion (TAPSE) and Doppler tissue imaging‐derived peak systolic velocity (Sʹ) in the assessment of right ventricular (RV) systolic function measured using cardiac magnetic resonance imaging (MRI).MethodsWe enrolled consecutive patients who underwent cardiac MRI between Jan 2012 and Dec 2017 and a transthoracic echocardiogram (TTE) within 1 month of the MRI with no interval event. Baseline clinical characteristics and MRI parameters were extracted from chart review. Echocardiographic parameters were measured prospectively. TTE parameters including RVS, TAPSE, Sʹ, and FAC% were tested for accuracy to identify impaired RV EF (EF < 45% & <30%) using receiver operator curves.ResultsThe study cohort included 500 patients with mean age 55 years ± 18 and peak tricuspid regurgitation velocity 2.7 ± 1.4 m/s. The area under ROC for RVS was 0.69 (95% CI 0.63–0.75) and 0.78 (95% CI 0.70–0.88) to predict RVEF < 45% & RVEF < 30%, respectively. The RV FAC% had second highest accuracy of predicting RVEF among all the TTE parameters tested in study.ConclusionRight ventricular strain is the most accurate echocardiographic method to detect impaired right ventricular systolic function when using MRI as the gold standard.

Pulmonary vein (PV) stenosis is a rare and serious complication of radiofrequency catheter ablation (RFCA) for atrial fibrillation. However, it can be asymptomatic or mildly symptomatic depending on the severity of the stenosis and the development of compensatory mechanisms. This study provides a detailed description and visualization of a unique type of venous collaterals that bypass the PV stenosis and drain directly in the left atrium alleviating PV stenosis sequelae. This study reports a case of a 61-year-old male who presented with mild dyspnea and fatigue 3 years post atrial fibrillation RFCA. After a thorough evaluation of the case, a redo-ablation was planned. As a part of the preablation workup, a transesophageal echocardiography (TEE), a ventilation-perfusion (V/Q) scan of the lungs, and a chest computed tomography angiogram (CTA) were performed. The TEE revealed total obstruction of the left superior PV, with no color Doppler flow detected. It also showed evidence of multiple collateral flows at the os of the left superior PV. The V/Q scan showed a large perfusion defect involving the entire left upper lobe consistent with a compromised left upper PV flow. The CTA with 3D volume rendering revealed the total occlusion of the left superior PV at its ostium. Moreover, the scan confirmed the pulmonary venous drainage via small collateral channels that was suggested by the TEE.

AbstractA previously healthy 49‐year‐old male patient presented with COVID‐19 infection and required mechanical ventilation and extracorporeal membrane oxygenation due to severe hypoxemia. Echocardiography showed cardiac dysfunction with an apical sparing strain pattern, which rapidly normalized within a week. Apical sparing myocardial strain in patients with COVID‐19 infection may suggest reverse‐type stress cardiomyopathy.