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
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.

Auteurs

Catherine C Stowell (CC)

National Heart & Lung Institute, Imperial College, London, United Kingdom.

James P Howard (JP)

National Heart & Lung Institute, Imperial College, London, United Kingdom.

Tiffany Ng (T)

National Heart & Lung Institute, Imperial College, London, United Kingdom.

Graham D Cole (GD)

Department of Cardiology, Charing Cross Hospital, London, United Kingdom.

Sanjeev Bhattacharyya (S)

Department of Cardiology, St Bartholomew's Hospital, London, United Kingdom.

Jobanpreet Sehmi (J)

Department of Cardiology, West Hertfordshire Hospitals NHS Trust, Watford, United Kingdom.

Maysaa Alzetani (M)

Department of Cardiology, Luton & Dunstable University Hospital, Bedfordshire, United Kingdom.

Camelia D Demetrescu (CD)

Department of Cardiology, Guy's and St Thomas' NHS Foundation Trust, London, United Kingdom.

Adam Hartley (A)

National Heart & Lung Institute, Imperial College, London, United Kingdom.

Amar Singh (A)

Department of Cardiology, Lewisham & Greenwich NHS Trust, London, United Kingdom.

Arjun Ghosh (A)

Barts Heart Centre and Hatter Cardiovascular Institute, University College London Hospital, London, United Kingdom.

Kavitha Vimalesvaran (K)

National Heart & Lung Institute, Imperial College, London, United Kingdom.

Kenneth Mangion (K)

School of Cardiovascular and Metabolic Health, University of Glasgow, Glasgow, United Kingdom.

Ronak Rajani (R)

Cardiovascular Directorate, St. Thomas' Hospital, King's College, London, United Kingdom.

Bushra S Rana (BS)

Department of Cardiology, Hammersmith Hospital, London, United Kingdom.

Massoud Zolgharni (M)

School of Computing and Engineering, University of West London, London, United Kingdom.

Darrel P Francis (DP)

National Heart & Lung Institute, Imperial College, London, United Kingdom. Electronic address: d.francis@imperial.ac.uk.

Matthew J Shun-Shin (MJ)

National Heart & Lung Institute, Imperial College, London, United Kingdom.

Classifications MeSH