Generalizable fully automated multi-label segmentation of four-chamber view echocardiograms based on deep convolutional adversarial networks.

A major issue in translation of the artificial intelligence platforms for automatic segmentation of echocardiograms to clinics is their generalizability. The present study introduces and verifies a novel generalizable and efficient fully automatic multi-label segmentation method for four-chamber view echocardiograms based on deep fully convolutional networks (FCNs) and adversarial training. For the first time, we used generative adversarial networks for pixel classification training, a novel method in machine learning not currently used for cardiac imaging, to overcome the generalization problem.

Assessment of transmitral vortex formation in patients with diastolic dysfunction.

Background: Previous experimental models have related transmitral vortex formation to the longitudinal recoil of left ventricle. However, little is known about the relationships among left ventricular (LV) longitudinal relaxation, transmitral filling patterns, and LV vortex formation in clinical settings. The aim of this study was to compare the vortex formation time index among a heterogeneous group of patients with diastolic dysfunction to understand the relationship between transmitral vortex formation and abnormal diastolic filling patterns.

Is there a role for antiarrhythmic drugs in patients with implantable defibrillators?

With remarkable advancement in technology and clinical research, implantable cardioverter defibrillators (ICDs) have replaced antiarrhythmic drugs as the preferred modality for both primary and secondary prevention of arrhythmic deaths. However, concomitant use of antiarrhythmics in patients with ICDs remains common, often for prevention or reduction of appropriate and inappropriate shocks caused by ventricular and supraventricular arrhythmias, respectively. The role of empiric antiarrhythmic therapy in this patient population remains less clearly defined, with conflicting information from various small randomized trials.