Fully automatic estimation of global left ventricular systolic function using deep learning in transoesophageal echocardiography.

IF 0.6 3区 心理学 Q2 PSYCHOLOGY, PSYCHOANALYSIS
Psychoanalytic Dialogues Pub Date : 2023-07-04 eCollection Date: 2023-05-01 DOI:10.1093/ehjimp/qyad007
Erik Andreas Rye Berg, Anders Austlid Taskén, Trym Nordal, Bjørnar Grenne, Torvald Espeland, Idar Kirkeby-Garstad, Håvard Dalen, Espen Holte, Stian Stølen, Svend Aakhus, Gabriel Kiss
{"title":"Fully automatic estimation of global left ventricular systolic function using deep learning in transoesophageal echocardiography.","authors":"Erik Andreas Rye Berg, Anders Austlid Taskén, Trym Nordal, Bjørnar Grenne, Torvald Espeland, Idar Kirkeby-Garstad, Håvard Dalen, Espen Holte, Stian Stølen, Svend Aakhus, Gabriel Kiss","doi":"10.1093/ehjimp/qyad007","DOIUrl":null,"url":null,"abstract":"<p><strong>Aims: </strong>To improve monitoring of cardiac function during major surgery and intensive care, we have developed a method for fully automatic estimation of mitral annular plane systolic excursion (auto-MAPSE) using deep learning in transoesophageal echocardiography (TOE). The aim of this study was a clinical validation of auto-MAPSE in patients with heart disease.</p><p><strong>Methods and results: </strong>TOE recordings were collected from 185 consecutive patients without selection on image quality. Deep-learning-based auto-MAPSE was trained and optimized from 105 patient recordings. We assessed auto-MAPSE feasibility, and agreement and inter-rater reliability with manual reference in 80 patients with and without electrocardiogram (ECG) tracings. Mean processing time for auto-MAPSE was 0.3 s per cardiac cycle/view. Overall feasibility was >90% for manual MAPSE and ECG-enabled auto-MAPSE and 82% for ECG-disabled auto-MAPSE. Feasibility in at least two walls was ≥95% for all methods. Compared with manual reference, bias [95% limits of agreement (LoA)] was -0.5 [-4.0, 3.1] mm for ECG-enabled auto-MAPSE and -0.2 [-4.2, 3.6] mm for ECG-disabled auto-MAPSE. Intra-class correlation coefficient (ICC) for consistency was 0.90 and 0.88, respectively. Manual inter-observer bias [95% LoA] was -0.9 [-4.7, 3.0] mm, and ICC was 0.86.</p><p><strong>Conclusion: </strong>Auto-MAPSE was fast and highly feasible. Inter-rater reliability between auto-MAPSE and manual reference was good. Agreement between auto-MAPSE and manual reference did not differ from manual inter-observer agreement. As the principal advantages of deep-learning-based assessment are speed and reproducibility, auto-MAPSE has the potential to improve real-time monitoring of left ventricular function. This should be investigated in relevant clinical settings.</p>","PeriodicalId":47032,"journal":{"name":"Psychoanalytic Dialogues","volume":"23 1","pages":"qyad007"},"PeriodicalIF":0.6000,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11195714/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Psychoanalytic Dialogues","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1093/ehjimp/qyad007","RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/5/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"PSYCHOLOGY, PSYCHOANALYSIS","Score":null,"Total":0}
引用次数: 0

Abstract

Aims: To improve monitoring of cardiac function during major surgery and intensive care, we have developed a method for fully automatic estimation of mitral annular plane systolic excursion (auto-MAPSE) using deep learning in transoesophageal echocardiography (TOE). The aim of this study was a clinical validation of auto-MAPSE in patients with heart disease.

Methods and results: TOE recordings were collected from 185 consecutive patients without selection on image quality. Deep-learning-based auto-MAPSE was trained and optimized from 105 patient recordings. We assessed auto-MAPSE feasibility, and agreement and inter-rater reliability with manual reference in 80 patients with and without electrocardiogram (ECG) tracings. Mean processing time for auto-MAPSE was 0.3 s per cardiac cycle/view. Overall feasibility was >90% for manual MAPSE and ECG-enabled auto-MAPSE and 82% for ECG-disabled auto-MAPSE. Feasibility in at least two walls was ≥95% for all methods. Compared with manual reference, bias [95% limits of agreement (LoA)] was -0.5 [-4.0, 3.1] mm for ECG-enabled auto-MAPSE and -0.2 [-4.2, 3.6] mm for ECG-disabled auto-MAPSE. Intra-class correlation coefficient (ICC) for consistency was 0.90 and 0.88, respectively. Manual inter-observer bias [95% LoA] was -0.9 [-4.7, 3.0] mm, and ICC was 0.86.

Conclusion: Auto-MAPSE was fast and highly feasible. Inter-rater reliability between auto-MAPSE and manual reference was good. Agreement between auto-MAPSE and manual reference did not differ from manual inter-observer agreement. As the principal advantages of deep-learning-based assessment are speed and reproducibility, auto-MAPSE has the potential to improve real-time monitoring of left ventricular function. This should be investigated in relevant clinical settings.

在经食道超声心动图中使用深度学习全自动估测左心室整体收缩功能
目的:为了改善大手术和重症监护期间的心脏功能监测,我们开发了一种在经食道超声心动图(TOE)中使用深度学习全自动估算二尖瓣环平面收缩期偏移(auto-MAPSE)的方法。本研究的目的是在心脏病患者中对自动 MAPSE 进行临床验证:收集了 185 名连续患者的 TOE 记录,未对图像质量进行选择。基于深度学习的自动 MAPSE 从 105 份患者记录中进行了训练和优化。我们评估了自动 MAPSE 的可行性,以及与 80 名有和没有心电图(ECG)记录的患者的人工参考的一致性和评分者之间的可靠性。自动 MAPSE 的平均处理时间为每个心动周期/视图 0.3 秒。手动 MAPSE 和支持心电图的自动 MAPSE 的总体可行性大于 90%,支持心电图的自动 MAPSE 的总体可行性大于 82%。所有方法在至少两壁的可行性均≥95%。与人工参考相比,启用心电图的自动 MAPSE 的偏差[95% 一致性限值 (LoA)] 为 -0.5 [-4.0, 3.1] 毫米,启用心电图的自动 MAPSE 为 -0.2 [-4.2, 3.6] 毫米。一致性的类内相关系数 (ICC) 分别为 0.90 和 0.88。人工观察者间偏差[95% LoA]为-0.9 [-4.7, 3.0]毫米,ICC 为 0.86:结论:Auto-MAPSE 快速且非常可行。自动 MAPSE 与人工参考之间的评分者间可靠性良好。自动 MAPSE 与人工参考之间的一致性与人工观察者之间的一致性没有差异。由于基于深度学习的评估的主要优势在于速度和可重复性,因此自动 MAPSE 有可能改善左心室功能的实时监测。这一点应在相关临床环境中加以研究。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Psychoanalytic Dialogues
Psychoanalytic Dialogues PSYCHOLOGY, PSYCHOANALYSIS-
CiteScore
1.50
自引率
33.30%
发文量
56
期刊介绍: Launched in 1991, Psychoanalytic Dialogues was founded on the premise that within the diverse world of psychoanalysis there had developed a set of overlapping perspectives that regarded relational configurations of self and others, real and fantasied, as the primary units of human motivation and psychodynamic explanation. These perspectives emerged within interpersonal psychoanalysis; British objct relations theories; self psychology; the empirical traditions of infancy research and child development; and certain currents of contemporary Freudian thought. This common relational model has come to provide a vitalizing framework within which clinical contributions can be situated and developed.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信