Moon, Inki

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.

Objective The hypertrophic cardiomyopathy (HCM) risk-sudden cardiac death (SCD) calculator endorsed by the 2014 European Society of Cardiology has not been independently validated in the Asians. We aimed to investigate whether the HCM Risk-SCD calculator effectively predicts SCD in Korean HCM population. Methods An observational, longitudinal cohort study was performed in 730 patients with HCM from 2007 to 2017. The primary endpoint was a composite of SCD and appropriate implantable cardioverter-defibrillator (ICD) therapy. Results During a follow-up period of 4288 person-years, 16 (2.2%) patients reached the primary endpoint. This validation study revealed a calibration slope of 0.892 and C-statistics of 0.718. The primary endpoint occurred in 1.1% (7/615), 4.6% (3/65) and 12.0% (6/50) of low-risk, intermediate-risk and high-risk groups, respectively. Although most patients (85.2%) without the primary endpoint were classified into the low-risk group, 7 of 11 SCD (63.6%) occurred in the low-risk group. In univariable and multivariable analysis, sex (woman) was significantly associated with the primary endpoint and emerged as independent predictor. The addition of sex to the HCM Risk-SCD calculator significantly improved the predictive value of the primary endpoint (net reclassification improvement 0.557, p=0.015). Conclusions In the Korean HCM population, the HCM Risk-SCD calculator had a high negative predictive value and accuracy for predicting SCD or appropriate ICD therapy, but misclassified a few patients experiencing the primary endpoint as low-risk or intermediate-risk groups.