Real-Time Automatic Ejection Fraction and Foreshortening Detection Using Deep Learning

Abstract

Volume and ejection fraction (EF) measurements of the left ventricle (LV) in 2-D echocardiography are associated with a high uncertainty not only due to interobserver variability of the manual measurement, but also due to ultrasound acquisition errors such as apical foreshortening. In this work, a real-time and fully automated EF measurement and foreshortening detection method is proposed. The method uses several deep learning components, such as view classification, cardiac cycle timing, segmentation and landmark extraction, to measure the amount of foreshortening, LV volume, and EF. A data set of 500 patients from an outpatient clinic was used to train the deep neural networks, while a separate data set of 100 patients from another clinic was used for evaluation, where LV volume and EF were measured by an expert using clinical protocols and software. A quantitative analysis using 3-D ultrasound showed that EF is considerably affected by apical foreshortening, and that the proposed method can detect and quantify the amount of apical foreshortening. The bias

Myocardial Function Imaging in Echocardiography Using Deep Learning

“…The average runtime of the networks and pipelines are reasonable compared to previously reported findings [12], [19]. The CNN is fast compared to the Farnebäck implementation used, but more work must be conducted to achieve real-time performance in echocardiography.…”

“…The network was first described by Smistad et al [27] and later used in the CAMUS study of Leclerc et al [25]. Recently, it has been used with success in an automatic measurement pipeline for ejection fraction and foreshortening detection [19]. In this study, we use the segmentation of the myocardium m .…”

“…Utilizing DL models in a cascade for fully automating clinical measurements have also become a popular research topic, for instance for measurements such as EF and strain [18]. We recently demonstrated an accuracy within interobserver variability on calculations of EF, with possibility for real-time analysis and quality assurance on-site [19]. In this study we aim to extend our work by incorporating ME in an automatic pipeline, in order to do fully automatic deformation measurements.…”

Technology trends and applications of deep learning in ultrasonography: image quality enhancement, diagnostic support, and improving workflow efficiency

“…Measurements of the volume of the LV and ejection fraction (EF) in two-dimensional echocardiography have a high uncertainty due to inter-observer variability of manual measurements and acquisition errors such as apical foreshortening. Smistad et al [ 88 ] proposed a real-time and fully automated EF measurement and foreshortening detection method. This method measured the amount of foreshortening, LV volume, and EF by employing deep learning features including view classification, cardiac cycle timing, segmentation, and landmark extraction.…”

LU-Net: A Multistage Attention Network to Improve the Robustness of Segmentation of Left Ventricular Structures in 2-D Echocardiography

“…By definition, these techniques are optimal to the data they are trained on. Such approaches have been applied in the context of left ventricular structures analysis [10], [11], in particular for segmentation. In 2012, Carneiro et al exploited deep belief networks and the decoupling of rigid and nonrigid classifiers to improve robustness in terms of image conditions and shape variability [12].…”