GAN-enhanced Conditional Echocardiogram Generation

TL;DR

This paper introduces a GAN-based method for generating realistic echocardiogram images conditioned on specific cardiac structure segmentations, aiding semi-supervised cardiac image analysis.

Contribution

It presents a novel GAN architecture with a conditional patch-based discriminator for high-quality echo generation based on segmentation masks.

Findings

Generated echoes match given segmentation masks.

Method produces high-quality, realistic echocardiogram frames.

Facilitates semi-supervised training of cardiac analysis models.

Abstract

Echocardiography (echo) is a common means of evaluating cardiac conditions. Due to the label scarcity, semi-supervised paradigms in automated echo analysis are getting traction. One of the most sought-after problems in echo is the segmentation of cardiac structures (e.g. chambers). Accordingly, we propose an echocardiogram generation approach using generative adversarial networks with a conditional patch-based discriminator. In this work, we validate the feasibility of GAN-enhanced echo generation with different conditions (segmentation masks), namely, the left ventricle, ventricular myocardium, and atrium. Results show that the proposed adversarial algorithm can generate high-quality echo frames whose cardiac structures match the given segmentation masks. This method is expected to facilitate the training of other machine learning models in a semi-supervised fashion as suggested in similar researches.