Ling Li1,2, Paul Homer3, Mary Craft3, Shelby Kutty4, Adam Putschoegl3, Amanda Marshall3, David Danford3, Anji Yetman3. 1. Department of Pediatric Cardiology, University of Nebraska College of Medicine and Children's Hospital and Medical Center Omaha, Omaha, NE, USA. ling.li@unmc.edu. 2. Pediatric Cardiology, Child Health Research Institute, Department of Pediatrics, University of Nebraska College of Medicine, 42nd and Emile, Omaha, NE, 68198, USA. ling.li@unmc.edu. 3. Department of Pediatric Cardiology, University of Nebraska College of Medicine and Children's Hospital and Medical Center Omaha, Omaha, NE, USA. 4. Helen B. Taussig Heart Center, Department of Pediatrics, Johns Hopkins Hospital, Baltimore, MD, USA.
Abstract
BACKGROUND: Left ventricular (LV) volumes, ejection fraction (EF), and myocardial strain have been shown to be predictive of clinical and subclinical heart disease. Automation of LV functional assessment overcomes difficult technical challenges and complexities. We sought to assess whether a fully automated assessment of LV function could be reliably used in children and young adults. METHODS: Fifty normal volunteers (22/28, female/male) were prospectively recruited for research echocardiography. LV volumes, EF, and strain were measured both manually and automatically. An experienced sonographer performed all the manual analysis and recorded the analysis timing. The fully automated analyses were accomplished by 5 groups of observers with different knowledge and medical background. AutoLV and AutoSTRAIN (TomTec) were employed for the fully automated LV analysis. The LV volumes, EF, strain, and analysis time were compared between manual and automated methods, and among the 5 groups of observers. RESULTS: Software-determined endocardial border detection was achievable in all subjects. The analysis times of the experienced sonographer were significantly shorter for AutoLV and AutoSTRAIN than manual analyses (both p < 0.001). Strong correlations were seen between conventional EF and AutoLV (r = 0.8373), and between conventional three view global longitudinal strain (GLS) and AutoSTRAIN (r = 0.9766). The volumes from AutoLV and three view GLS from AutoSTRAIN had strong correlations among different observers regardless of level of expertise. EF from AutoLV analysis had moderately strong correlations among different observers. CONCLUSION: Automated pediatric LV analysis is feasible in normal hearts. Machine learning-enabled image analysis saves time and produces results that are comparable to traditional methods.
BACKGROUND: Left ventricular (LV) volumes, ejection fraction (EF), and myocardial strain have been shown to be predictive of clinical and subclinical heart disease. Automation of LV functional assessment overcomes difficult technical challenges and complexities. We sought to assess whether a fully automated assessment of LV function could be reliably used in children and young adults. METHODS: Fifty normal volunteers (22/28, female/male) were prospectively recruited for research echocardiography. LV volumes, EF, and strain were measured both manually and automatically. An experienced sonographer performed all the manual analysis and recorded the analysis timing. The fully automated analyses were accomplished by 5 groups of observers with different knowledge and medical background. AutoLV and AutoSTRAIN (TomTec) were employed for the fully automated LV analysis. The LV volumes, EF, strain, and analysis time were compared between manual and automated methods, and among the 5 groups of observers. RESULTS: Software-determined endocardial border detection was achievable in all subjects. The analysis times of the experienced sonographer were significantly shorter for AutoLV and AutoSTRAIN than manual analyses (both p < 0.001). Strong correlations were seen between conventional EF and AutoLV (r = 0.8373), and between conventional three view global longitudinal strain (GLS) and AutoSTRAIN (r = 0.9766). The volumes from AutoLV and three view GLS from AutoSTRAIN had strong correlations among different observers regardless of level of expertise. EF from AutoLV analysis had moderately strong correlations among different observers. CONCLUSION: Automated pediatric LV analysis is feasible in normal hearts. Machine learning-enabled image analysis saves time and produces results that are comparable to traditional methods.
Authors: Paaladinesh Thavendiranathan; Zoran B Popović; Scott D Flamm; Arun Dahiya; Richard A Grimm; Thomas H Marwick Journal: J Am Soc Echocardiogr Date: 2013-08-28 Impact factor: 5.251
Authors: Rainer Hoffmann; Stephan von Bardeleben; Folkert ten Cate; Adrian C Borges; Jaroslaw Kasprzak; Christian Firschke; Stephane Lafitte; Nidal Al-Saadi; Stefanie Kuntz-Hehner; Marc Engelhardt; Harald Becher; Jean Louis Vanoverschelde Journal: Eur Heart J Date: 2004-12-17 Impact factor: 29.983
Authors: Lissa Sugeng; Victor Mor-Avi; Lynn Weinert; Johannes Niel; Christian Ebner; Regina Steringer-Mascherbauer; Frank Schmidt; Christian Galuschky; Georg Schummers; Roberto M Lang; Hans-Joachim Nesser Journal: Circulation Date: 2006-08-07 Impact factor: 29.690
Authors: Roberto M Lang; Luigi P Badano; Victor Mor-Avi; Jonathan Afilalo; Anderson Armstrong; Laura Ernande; Frank A Flachskampf; Elyse Foster; Steven A Goldstein; Tatiana Kuznetsova; Patrizio Lancellotti; Denisa Muraru; Michael H Picard; Ernst R Rietzschel; Lawrence Rudski; Kirk T Spencer; Wendy Tsang; Jens-Uwe Voigt Journal: J Am Soc Echocardiogr Date: 2015-01 Impact factor: 5.251
Authors: Rainer Hoffmann; Giuseppe Barletta; Stephan von Bardeleben; Jean Louis Vanoverschelde; Jaroslaw Kasprzak; Christian Greis; Harald Becher Journal: J Am Soc Echocardiogr Date: 2014-01-15 Impact factor: 5.251
Authors: Christian Knackstedt; Sebastiaan C A M Bekkers; Georg Schummers; Marcus Schreckenberg; Denisa Muraru; Luigi P Badano; Andreas Franke; Chirag Bavishi; Alaa Mabrouk Salem Omar; Partho P Sengupta Journal: J Am Coll Cardiol Date: 2015-09-29 Impact factor: 24.094
Authors: Anne Marie Valente; Stephen Cook; Pierluigi Festa; H Helen Ko; Rajesh Krishnamurthy; Andrew M Taylor; Carole A Warnes; Jacqueline Kreutzer; Tal Geva Journal: J Am Soc Echocardiogr Date: 2014-02 Impact factor: 5.251