Automatic cine-based detection of patients at high risk of heart failure with reduced ejection fraction in echocardiograms. Issue 5 (2nd September 2020)

• Record Type: Journal Article
• Authors: Behnami, Delaram; Luong, Christina; Vaseli, Hooman; Girgis, Hany; Abdi, Amir; Hawley, Dale; Gin, Ken; Rohling, Robert; Abolmaesumi, Purang; Tsang, Teresa
• Is Part Of: Computer methods in biomechanics and biomedical engineering. Volume 8:Issue 5(2020)
• Page Start: 502
• Page End: 508
• Publication Date: 2020-09-02
• Subjects: Echocardiography -- recurrent -- convolutional -- ejection fraction; Imaging systems in biology -- Periodicals; Imaging systems in medicine -- Periodicals; Biomechanics -- Data processing -- Periodicals; Biomedical engineering -- Periodicals; 616.0757
• DOI: 10.1080/21681163.2019.1650398
• Languages: English
• ISSNs: 2168-1163

Abstract

ABSTRACT: Heart failure with reduced ejection fraction (HFrEF) is associated with high mortality rates. The identification of patients with HFrEF in urgent and emergent situations can be delayed in the absence of clinicians skilled in acquiring and interpreting echocardiography (echo) images. Although the standard-of-care for measuring ejection fraction (EF) involves segmentation of the left ventricle in echo, experienced interpreters often opt for visual estimation of EF in clinical settings. In this paper, we mimic this process using dual-channel deep neural networks for segmentation-free classification of echo cine loops: low-risk ( 40 % < E F ≤ 75 % ) vs. high-risk (reduced EF, i.e . E F ≤ 40 % ). The proposed architecture utilises densely connected networks for extraction of unsupervised spatial features. Temporal embedding is then achieved by aggregating these frame-level feature vectors and feeding them through recurrent blocks. We use 949 and 237 clinical echo exams to train and validate the proposed method, respectively. We demonstrate that direct cine-based detection of patients at high-risk of HFrEF is feasible using densely connected convolutional and recurrent-based architectures.