Generative Adversarial Networks in Ultrasound Imaging: Extending Field of View Beyond Conventional Limits

TL;DR

This paper presents echoGAN, a conditional GAN model that extends the field of view in ultrasound imaging, specifically transthoracic echocardiography, by generating realistic outpainted cardiac structures, improving diagnostic capabilities.

Contribution

The paper introduces a novel cGAN architecture, echoGAN, for outpainting in ultrasound imaging, enhancing field of view while preserving high resolution, which is a new application in medical imaging.

Findings

echoGAN effectively extends ultrasound FoV with realistic cardiac structures

The model maintains high resolution and detail in generated images

Potential to improve ultrasound navigation and diagnostic accuracy

Abstract

Transthoracic Echocardiography (TTE) is a fundamental, non-invasive diagnostic tool in cardiovascular medicine, enabling detailed visualization of cardiac structures crucial for diagnosing various heart conditions. Despite its widespread use, TTE ultrasound imaging faces inherent limitations, notably the trade-off between field of view (FoV) and resolution. This paper introduces a novel application of conditional Generative Adversarial Networks (cGANs), specifically designed to extend the FoV in TTE ultrasound imaging while maintaining high resolution. Our proposed cGAN architecture, termed echoGAN, demonstrates the capability to generate realistic anatomical structures through outpainting, effectively broadening the viewable area in medical imaging. This advancement has the potential to enhance both automatic and manual ultrasound navigation, offering a more comprehensive view that could significantly reduce the learning curve associated with ultrasound imaging and aid in more accurate diagnoses. The results confirm that echoGAN reliably reproduce detailed cardiac features, thereby promising a significant step forward in the field of non-invasive cardiac naviagation and diagnostics.