2-Dimensional Echocardiographic Global Longitudinal Strain With Artificial Intelligence Using Open Data From a UK-Wide Collaborative.
artificial intelligence
echocardiography
global longitudinal strain
Journal
JACC. Cardiovascular imaging
ISSN: 1876-7591
Titre abrégé: JACC Cardiovasc Imaging
Pays: United States
ID NLM: 101467978
Informations de publication
Date de publication:
28 Jun 2024
28 Jun 2024
Historique:
received:
28
08
2023
revised:
19
04
2024
accepted:
25
04
2024
medline:
14
7
2024
pubmed:
14
7
2024
entrez:
13
7
2024
Statut:
aheadofprint
Résumé
Global longitudinal strain (GLS) is reported to be more reproducible and prognostic than ejection fraction. Automated, transparent methods may increase trust and uptake. The authors developed open machine-learning-based GLS methodology and validate it using multiexpert consensus from the Unity UK Echocardiography AI Collaborative. We trained a multi-image neural network (Unity-GLS) to identify annulus, apex, and endocardial curve on 6,819 apical 4-, 2-, and 3-chamber images. The external validation dataset comprised those 3 views from 100 echocardiograms. End-systolic and -diastolic frames were each labelled by 11 experts to form consensus tracings and points. They also ordered the echocardiograms by visual grading of longitudinal function. One expert calculated global strain using 2 proprietary packages. The median GLS, averaged across the 11 individual experts, was -16.1 (IQR: -19.3 to -12.5). Using each case's expert consensus measurement as the reference standard, individual expert measurements had a median absolute error of 2.00 GLS units. In comparison, the errors of the machine methods were: Unity-GLS 1.3, proprietary A 2.5, proprietary B 2.2. The correlations with the expert consensus values were for individual experts 0.85, Unity-GLS 0.91, proprietary A 0.73, proprietary B 0.79. Using the multiexpert visual ranking as the reference, individual expert strain measurements found a median rank correlation of 0.72, Unity-GLS 0.77, proprietary A 0.70, and proprietary B 0.74. Our open-source approach to calculating GLS agrees with experts' consensus as strongly as the individual expert measurements and proprietary machine solutions. The training data, code, and trained networks are freely available online.
Sections du résumé
BACKGROUND
BACKGROUND
Global longitudinal strain (GLS) is reported to be more reproducible and prognostic than ejection fraction. Automated, transparent methods may increase trust and uptake.
OBJECTIVES
OBJECTIVE
The authors developed open machine-learning-based GLS methodology and validate it using multiexpert consensus from the Unity UK Echocardiography AI Collaborative.
METHODS
METHODS
We trained a multi-image neural network (Unity-GLS) to identify annulus, apex, and endocardial curve on 6,819 apical 4-, 2-, and 3-chamber images. The external validation dataset comprised those 3 views from 100 echocardiograms. End-systolic and -diastolic frames were each labelled by 11 experts to form consensus tracings and points. They also ordered the echocardiograms by visual grading of longitudinal function. One expert calculated global strain using 2 proprietary packages.
RESULTS
RESULTS
The median GLS, averaged across the 11 individual experts, was -16.1 (IQR: -19.3 to -12.5). Using each case's expert consensus measurement as the reference standard, individual expert measurements had a median absolute error of 2.00 GLS units. In comparison, the errors of the machine methods were: Unity-GLS 1.3, proprietary A 2.5, proprietary B 2.2. The correlations with the expert consensus values were for individual experts 0.85, Unity-GLS 0.91, proprietary A 0.73, proprietary B 0.79. Using the multiexpert visual ranking as the reference, individual expert strain measurements found a median rank correlation of 0.72, Unity-GLS 0.77, proprietary A 0.70, and proprietary B 0.74.
CONCLUSIONS
CONCLUSIONS
Our open-source approach to calculating GLS agrees with experts' consensus as strongly as the individual expert measurements and proprietary machine solutions. The training data, code, and trained networks are freely available online.
Identifiants
pubmed: 39001730
pii: S1936-878X(24)00188-8
doi: 10.1016/j.jcmg.2024.04.017
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved.
Déclaration de conflit d'intérêts
Funding Support and Author Disclosures Dr Rajani has received speaker fees from Siemens Healthcare and GE Medical; and has provided consultancy to Medtronic and Edwards Lifesciences. Dr Rana has provided consultancy to Philips and Occlutech. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose.