Real-Time Automatic Ejection Fraction and Foreshortening Detection Using Deep Learning

Erik Smistad; Andreas Ostvik; Ivar Mjaland SalteDaniela MelichovaThuy Mi NguyenKristina HaugaaHarald BrunvandThor EdvardsenSarah LeclercOlivier BernardBjornar GrenneLasse Lovstakken

首页> 外文期刊>IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control >Real-Time Automatic Ejection Fraction and Foreshortening Detection Using Deep Learning

【24h】

Real-Time Automatic Ejection Fraction and Foreshortening Detection Using Deep Learning

机译：Real-Time Automatic Ejection Fraction and Foreshortening Detection Using Deep Learning

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

Volume and ejection fraction (EF) measurements of the left ventricle (LV) in 2-D echocardiography are associated with a high uncertainty not only due to interobserver variability of the manual measurement, but also due to ultrasound acquisition errors such as apical foreshortening. In this work, a real-time and fully automated EF measurement and foreshortening detection method is proposed. The method uses several deep learning components, such as view classification, cardiac cycle timing, segmentation and landmark extraction, to measure the amount of foreshortening, LV volume, and EF. A data set of 500 patients from an outpatient clinic was used to train the deep neural networks, while a separate data set of 100 patients from another clinic was used for evaluation, where LV volume and EF were measured by an expert using clinical protocols and software. A quantitative analysis using 3-D ultrasound showed that EF is considerably affected by apical foreshortening, and that the proposed method can detect and quantify the amount of apical foreshortening. The bias and standard deviation of the automatic EF measurements were ?3.6 ± 8.1, while the mean absolute difference was measured at 7.2 which are all within the interobserver variability and comparable with related studies. The proposed real-time pipeline allows for a continuous acquisition and measurement workflow without user interaction, and has the potential to significantly reduce the time spent on the analysis and measurement error due to foreshortening, while providing quantitative volume measurements in the everyday echo lab.

著录项

来源
《IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control》 |2020年第12期|2595-2604|共10页
作者
Erik Smistad; Andreas Ostvik; Ivar Mjaland SalteDaniela MelichovaThuy Mi NguyenKristina HaugaaHarald BrunvandThor EdvardsenSarah LeclercOlivier BernardBjornar GrenneLasse Lovstakken;
展开▼
作者单位

Department of Circulation and Medical Imaging, Centre for Innovative Ultrasound Solutions, Norwegian University of Science and Technology, Trondheim, Norway;

Department of Medicine, S?rlandet Hospital at Kristiansand, Kristiansand, Norway;

Department of Cardiology, Oslo University Hospital at Rikshospitalet, Oslo, NorwayFaculty of Medicine, University of Oslo, Oslo, NorwayCREATIS, University of Lyon, Lyon, France;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类无线电设备、电信设备;
关键词
Volume measurement; Ultrasonic variables measurement; Real-time systems; Ultrasonic imaging; Deep learning; Two dimensional displays; Imaging; echocardiography; ejection fraction (EF); foreshortening;

Real-Time Automatic Ejection Fraction and Foreshortening Detection Using Deep Learning

摘要

著录项

相关主题

期刊订阅