Impact of fully automated assessment on interstudy reproducibility of biventricular volumes and function in cardiac magnetic resonance imaging

Abstract Cardiovascular magnetic resonance (CMR) imaging provides reliable assessments of biventricular morphology and function. Since manual post-processing is time-consuming and prone to observer variability, efforts have been directed towards novel artificial intelligence-based fully automated an...

Full description

Bibliographic Details
Main Authors: Sören J. Backhaus, Andreas Schuster, Torben Lange, Christian Stehning, Marcus Billing, Joachim Lotz, Burkert Pieske, Gerd Hasenfuß, Sebastian Kelle, Johannes T. Kowallick
Format: Article
Language:English
Published: Nature Publishing Group 2021-06-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-021-90702-9
id doaj-41f64e5bd021428487980b4594fabd78
record_format Article
spelling doaj-41f64e5bd021428487980b4594fabd782021-06-06T11:38:22ZengNature Publishing GroupScientific Reports2045-23222021-06-0111111010.1038/s41598-021-90702-9Impact of fully automated assessment on interstudy reproducibility of biventricular volumes and function in cardiac magnetic resonance imagingSören J. Backhaus0Andreas Schuster1Torben Lange2Christian Stehning3Marcus Billing4Joachim Lotz5Burkert Pieske6Gerd Hasenfuß7Sebastian Kelle8Johannes T. Kowallick9University Medical Center Göttingen, Department of Cardiology and Pneumology, Georg-August UniversityUniversity Medical Center Göttingen, Department of Cardiology and Pneumology, Georg-August UniversityUniversity Medical Center Göttingen, Department of Cardiology and Pneumology, Georg-August UniversityPhilips HealthcareUniversity Medical Center Göttingen, Department of Cardiology and Pneumology, Georg-August UniversityGerman Center for Cardiovascular Research (DZHK), Partner Site GöttingenGerman Center for Cardiovascular Research (DZHK), Partner Site GöttingenUniversity Medical Center Göttingen, Department of Cardiology and Pneumology, Georg-August UniversityGerman Center for Cardiovascular Research (DZHK), Partner Site GöttingenGerman Center for Cardiovascular Research (DZHK), Partner Site GöttingenAbstract Cardiovascular magnetic resonance (CMR) imaging provides reliable assessments of biventricular morphology and function. Since manual post-processing is time-consuming and prone to observer variability, efforts have been directed towards novel artificial intelligence-based fully automated analyses. Hence, we sought to investigate the impact of artificial intelligence-based fully automated assessments on the inter-study variability of biventricular volumes and function. Eighteen participants (11 with normal, 3 with heart failure and preserved and 4 with reduced ejection fraction (EF)) underwent serial CMR imaging at in median 63 days (range 49–87) interval. Short axis cine stacks were acquired for the evaluation of left ventricular (LV) mass, LV and right ventricular (RV) end-diastolic, end-systolic and stroke volumes as well as EF. Assessments were performed manually (QMass, Medis Medical Imaging Systems, Leiden, Netherlands) by an experienced (3 years) and inexperienced reader (no active reporting, 45 min of training with five cases from the SCMR consensus data) as well as fully automated (suiteHEART, Neosoft, Pewaukee, WI, USA) without any manual corrections. Inter-study reproducibility was overall excellent with respect to LV volumetric indices, best for the experienced observer (intraclass correlation coefficient (ICC) > 0.98, coefficient of variation (CoV, < 9.6%) closely followed by automated analyses (ICC > 0.93, CoV < 12.4%) and lowest for the inexperienced observer (ICC > 0.86, CoV < 18.8%). Inter-study reproducibility of RV volumes was excellent for the experienced observer (ICC > 0.88, CoV < 10.7%) but considerably lower for automated and inexperienced manual analyses (ICC > 0.69 and > 0.46, CoV < 22.8% and < 28.7% respectively). In this cohort, fully automated analyses allowed reliable serial investigations of LV volumes with comparable inter-study reproducibility to manual analyses performed by an experienced CMR observer. In contrast, RV automated quantification with current algorithms still relied on manual post-processing for reliability.https://doi.org/10.1038/s41598-021-90702-9
collection DOAJ
language English
format Article
sources DOAJ
author Sören J. Backhaus
Andreas Schuster
Torben Lange
Christian Stehning
Marcus Billing
Joachim Lotz
Burkert Pieske
Gerd Hasenfuß
Sebastian Kelle
Johannes T. Kowallick
spellingShingle Sören J. Backhaus
Andreas Schuster
Torben Lange
Christian Stehning
Marcus Billing
Joachim Lotz
Burkert Pieske
Gerd Hasenfuß
Sebastian Kelle
Johannes T. Kowallick
Impact of fully automated assessment on interstudy reproducibility of biventricular volumes and function in cardiac magnetic resonance imaging
Scientific Reports
author_facet Sören J. Backhaus
Andreas Schuster
Torben Lange
Christian Stehning
Marcus Billing
Joachim Lotz
Burkert Pieske
Gerd Hasenfuß
Sebastian Kelle
Johannes T. Kowallick
author_sort Sören J. Backhaus
title Impact of fully automated assessment on interstudy reproducibility of biventricular volumes and function in cardiac magnetic resonance imaging
title_short Impact of fully automated assessment on interstudy reproducibility of biventricular volumes and function in cardiac magnetic resonance imaging
title_full Impact of fully automated assessment on interstudy reproducibility of biventricular volumes and function in cardiac magnetic resonance imaging
title_fullStr Impact of fully automated assessment on interstudy reproducibility of biventricular volumes and function in cardiac magnetic resonance imaging
title_full_unstemmed Impact of fully automated assessment on interstudy reproducibility of biventricular volumes and function in cardiac magnetic resonance imaging
title_sort impact of fully automated assessment on interstudy reproducibility of biventricular volumes and function in cardiac magnetic resonance imaging
publisher Nature Publishing Group
series Scientific Reports
issn 2045-2322
publishDate 2021-06-01
description Abstract Cardiovascular magnetic resonance (CMR) imaging provides reliable assessments of biventricular morphology and function. Since manual post-processing is time-consuming and prone to observer variability, efforts have been directed towards novel artificial intelligence-based fully automated analyses. Hence, we sought to investigate the impact of artificial intelligence-based fully automated assessments on the inter-study variability of biventricular volumes and function. Eighteen participants (11 with normal, 3 with heart failure and preserved and 4 with reduced ejection fraction (EF)) underwent serial CMR imaging at in median 63 days (range 49–87) interval. Short axis cine stacks were acquired for the evaluation of left ventricular (LV) mass, LV and right ventricular (RV) end-diastolic, end-systolic and stroke volumes as well as EF. Assessments were performed manually (QMass, Medis Medical Imaging Systems, Leiden, Netherlands) by an experienced (3 years) and inexperienced reader (no active reporting, 45 min of training with five cases from the SCMR consensus data) as well as fully automated (suiteHEART, Neosoft, Pewaukee, WI, USA) without any manual corrections. Inter-study reproducibility was overall excellent with respect to LV volumetric indices, best for the experienced observer (intraclass correlation coefficient (ICC) > 0.98, coefficient of variation (CoV, < 9.6%) closely followed by automated analyses (ICC > 0.93, CoV < 12.4%) and lowest for the inexperienced observer (ICC > 0.86, CoV < 18.8%). Inter-study reproducibility of RV volumes was excellent for the experienced observer (ICC > 0.88, CoV < 10.7%) but considerably lower for automated and inexperienced manual analyses (ICC > 0.69 and > 0.46, CoV < 22.8% and < 28.7% respectively). In this cohort, fully automated analyses allowed reliable serial investigations of LV volumes with comparable inter-study reproducibility to manual analyses performed by an experienced CMR observer. In contrast, RV automated quantification with current algorithms still relied on manual post-processing for reliability.
url https://doi.org/10.1038/s41598-021-90702-9
work_keys_str_mv AT sorenjbackhaus impactoffullyautomatedassessmentoninterstudyreproducibilityofbiventricularvolumesandfunctionincardiacmagneticresonanceimaging
AT andreasschuster impactoffullyautomatedassessmentoninterstudyreproducibilityofbiventricularvolumesandfunctionincardiacmagneticresonanceimaging
AT torbenlange impactoffullyautomatedassessmentoninterstudyreproducibilityofbiventricularvolumesandfunctionincardiacmagneticresonanceimaging
AT christianstehning impactoffullyautomatedassessmentoninterstudyreproducibilityofbiventricularvolumesandfunctionincardiacmagneticresonanceimaging
AT marcusbilling impactoffullyautomatedassessmentoninterstudyreproducibilityofbiventricularvolumesandfunctionincardiacmagneticresonanceimaging
AT joachimlotz impactoffullyautomatedassessmentoninterstudyreproducibilityofbiventricularvolumesandfunctionincardiacmagneticresonanceimaging
AT burkertpieske impactoffullyautomatedassessmentoninterstudyreproducibilityofbiventricularvolumesandfunctionincardiacmagneticresonanceimaging
AT gerdhasenfuß impactoffullyautomatedassessmentoninterstudyreproducibilityofbiventricularvolumesandfunctionincardiacmagneticresonanceimaging
AT sebastiankelle impactoffullyautomatedassessmentoninterstudyreproducibilityofbiventricularvolumesandfunctionincardiacmagneticresonanceimaging
AT johannestkowallick impactoffullyautomatedassessmentoninterstudyreproducibilityofbiventricularvolumesandfunctionincardiacmagneticresonanceimaging
_version_ 1721393705543270400