Regional quality estimation for echocardiography using deep learning

TL;DR

This paper introduces three deep learning-based methods for regional quality estimation in echocardiography, demonstrating that end-to-end models and coherence-based metrics outperform classical image quality metrics in correlating with expert annotations.

Contribution

The study develops and compares three novel methods for regional echocardiogram quality assessment, highlighting the effectiveness of deep learning approaches over traditional metrics.

Findings

End-to-end deep learning model achieves correlation rho=0.69 with expert annotations.

Coherence-based method outperforms classical metrics with rho=0.58.

Classical gCNR metric shows poor correlation, rho=0.24.

Abstract

Automatic estimation of cardiac ultrasound image quality can be beneficial for guiding operators and ensuring the accuracy of clinical measurements. Previous work often fails to distinguish the view correctness of the echocardiogram from the image quality. Additionally, previous studies only provide a global image quality value, which limits their practical utility. In this work, we developed and compared three methods to estimate image quality: 1) classic pixel-based metrics like the generalized contrast-to-noise ratio (gCNR) on myocardial segments as region of interest and left ventricle lumen as background, obtained using a U-Net segmentation 2) local image coherence derived from a U-Net model that predicts coherence from B-Mode images 3) a deep convolutional network that predicts the quality of each region directly in an end-to-end fashion. We evaluate each method against manual regional image quality annotations by three experienced cardiologists. The results indicate poor performance of the gCNR metric, with Spearman correlation to the annotations of rho = 0.24. The end-to-end learning model obtains the best result, rho = 0.69, comparable to the inter-observer correlation, rho = 0.63. Finally, the coherence-based method, with rho = 0.58, outperformed the classical metrics and is more generic than the end-to-end approach. The image quality prediction tool is available as an open source Python library at https://github.com/GillesVanDeVyver/arqee.