Altmetric

Utility of machine learning algorithms in assessing patients with a systemic right ventricle

File Description SizeFormat 
TGA DL Manuscript R1_changes_accepted_B.docxFile embargoed until 09 January 20201.62 MBMicrosoft Word    Request a copy
Title: Utility of machine learning algorithms in assessing patients with a systemic right ventricle
Authors: Diller, G-P
Babu-Narayan, S
Li, W
Radojevic, J
Kempny, A
Uebing, A
Dimopoulos, K
Baumgartner, H
Gatzoulis, MA
Orwat, S
Item Type: Journal Article
Abstract: Aims: To investigate the utility of novel deep learning (DL) algorithms in recognizing transposition of the great arteries (TGA) after atrial switch procedure or congenitally corrected TGA (ccTGA) based on routine transthoracic echocardiograms. In addition, the ability of DL algorithms for delineation and segmentation of the systemic ventricle was evaluated. Methods and results: In total, 132 patients (92 TGA and atrial switch and 40 with ccTGA; 60% male, age 38.3 ± 12.1 years) and 67 normal controls (57% male, age 48.5 ± 17.9 years) with routine transthoracic examinations were included. Convolutional neural networks were trained to classify patients by underlying diagnosis and a U-Net design was used to automatically segment the systemic ventricle. Convolutional networks were build based on over 100 000 frames of an apical four-chamber or parasternal short-axis view to detect underlying diagnoses. The DL algorithm had an overall accuracy of 98.0% in detecting the correct diagnosis. The U-Net architecture model correctly identified the systemic ventricle in all individuals and achieved a high performance in segmenting the systemic right or left ventricle (Dice metric between 0.79 and 0.88 depending on diagnosis) when compared with human experts. Conclusion: Our study demonstrates the potential of machine learning algorithms, trained on routine echocardiographic datasets to detect underlying diagnosis in complex congenital heart disease. Automated delineation of the ventricular area was also feasible. These methods may in future allow for the longitudinal, objective, and automated assessment of ventricular function.
Issue Date: 8-Aug-2019
Date of Acceptance: 29-Nov-2018
URI: http://hdl.handle.net/10044/1/67689
DOI: https://dx.doi.org/10.1093/ehjci/jey211
ISSN: 2047-2412
Publisher: Oxford University Press (OUP)
Start Page: 925
End Page: 931
Journal / Book Title: EHJ Cardiovascular Imaging / European Heart Journal - Cardiovascular Imaging
Volume: 20
Issue: 8
Copyright Statement: Published on behalf of the European Society of Cardiology. All rights reserved. ©The Author(s) 2019. For permissions, please email: journals.permissions@oup.com
Sponsor/Funder: British Heart Foundation
Funder's Grant Number: FS/11/38/28864
Keywords: adult congenital heart disease
artificial intelligence
machine learning
transthoracic echocardiography
Publication Status: Published
Conference Place: England
Embargo Date: 2020-01-09
Online Publication Date: 2019-01-09
Appears in Collections:National Heart and Lung Institute
Faculty of Medicine



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons