echoGAN: Extending the field of view in transthoracic echocardiography through conditional GAN-based outpaintin

Background and Objective:

Transthoracic Echocardiography (TTE) is a fundamental, non-invasive diagnostic tool in cardiovascular medicine, enabling detailed visualization of cardiac structures that is crucial for diagnosing various heart conditions. Despite its widespread use, TTE ultrasound imaging faces inherent limitations, notably a trade-off between field of view (FoV) and resolution.

Methods: This paper introduces a novel conditional Generative Adversarial Network (cGAN), incorporating a domain-aware augmentation technique that simulates the typical cone-shaped FoV in ultrasound. This approach is specifically designed to enable effective outpainting of occluded areas, setting the foundation for our cGAN architecture, termed echoGAN.

Results: The results, obtained on two different datasets, confirm that echoGAN demonstrates the capability to generate realistic anatomical structures through outpainting, effectively broadening the viewable area in medical imaging.

Conclusions: 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.