Automated quantification of myocardial tissue characteristics from native T
Automation
Bayes Theorem
Cardiomyopathies
/ diagnostic imaging
Case-Control Studies
Humans
Image Interpretation, Computer-Assisted
Magnetic Resonance Imaging
Myocardium
/ pathology
Neural Networks, Computer
Predictive Value of Tests
Quality Control
Reproducibility of Results
Stroke Volume
Uncertainty
Ventricular Function, Left
Automatic analysis
Cardiac MR Segmentation
Convolutional neural networks
Native T1 mapping
Quality control
UK Biobank
Journal
Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance
ISSN: 1532-429X
Titre abrégé: J Cardiovasc Magn Reson
Pays: England
ID NLM: 9815616
Informations de publication
Date de publication:
20 08 2020
20 08 2020
Historique:
entrez:
21
8
2020
pubmed:
21
8
2020
medline:
7
10
2020
Statut:
epublish
Résumé
Tissue characterisation with cardiovascular magnetic resonance (CMR) parametric mapping has the potential to detect and quantify both focal and diffuse alterations in myocardial structure not assessable by late gadolinium enhancement. Native T Convolutional neural networks (CNNs) with Bayesian inference are a category of artificial neural networks which model the uncertainty of the network output. This study presents an automated framework for tissue characterisation from native shortened modified Look-Locker inversion recovery ShMOLLI T T The proposed pipeline allows for automatic analysis of myocardial native T
Sections du résumé
BACKGROUND
Tissue characterisation with cardiovascular magnetic resonance (CMR) parametric mapping has the potential to detect and quantify both focal and diffuse alterations in myocardial structure not assessable by late gadolinium enhancement. Native T
METHODS
Convolutional neural networks (CNNs) with Bayesian inference are a category of artificial neural networks which model the uncertainty of the network output. This study presents an automated framework for tissue characterisation from native shortened modified Look-Locker inversion recovery ShMOLLI T
RESULTS
T
CONCLUSIONS
The proposed pipeline allows for automatic analysis of myocardial native T
Identifiants
pubmed: 32814579
doi: 10.1186/s12968-020-00650-y
pii: 10.1186/s12968-020-00650-y
pmc: PMC7439533
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Validation Study
Langues
eng
Sous-ensembles de citation
IM
Pagination
60Subventions
Organisme : Wellcome Trust
ID : WT 203148/Z/16/Z
Pays : United Kingdom
Organisme : Department of Health
Pays : United Kingdom
Références
Eur J Radiol. 2018 Dec;109:223-234
pubmed: 30539758
Circ Cardiovasc Imaging. 2013 May 1;6(3):392-8
pubmed: 23564562
J Cardiovasc Magn Reson. 2013 Oct 14;15:92
pubmed: 24124732
J Cardiovasc Magn Reson. 2017 Sep 28;19(1):74
pubmed: 28954631
Echo Res Pract. 2017 Jun;4(2):G1-G13
pubmed: 28592613
J Cardiovasc Magn Reson. 2019 Mar 14;21(1):18
pubmed: 30866968
JACC Cardiovasc Imaging. 2020 Mar;13(3):684-695
pubmed: 31326477
Circ Res. 2016 Jul 8;119(2):277-99
pubmed: 27390332
Radiology. 2014 May;271(2):365-72
pubmed: 24475837
J Cardiovasc Magn Reson. 2016 Feb 01;18:8
pubmed: 26830817
Int J Cardiovasc Imaging. 2018 Oct;34(10):1637-1645
pubmed: 29790036
J Cardiovasc Magn Reson. 2012 Feb 20;14:17
pubmed: 22348519
J Cardiovasc Magn Reson. 2013 Jan 20;15:13
pubmed: 23331520
Neuroimage. 2006 Jul 1;31(3):1116-28
pubmed: 16545965
J Cardiovasc Magn Reson. 2017 Oct 9;19(1):75
pubmed: 28992817
Circulation. 1998 May 12;97(18):1837-47
pubmed: 9603539
J Cardiovasc Magn Reson. 2017 Apr 5;19(1):41
pubmed: 28376820
Sci Rep. 2018 Feb 20;8(1):3361
pubmed: 29463828
JACC Cardiovasc Imaging. 2017 Oct;10(10 Pt A):1180-1193
pubmed: 28982571
N Engl J Med. 2000 Nov 16;343(20):1445-53
pubmed: 11078769
J Thorac Imaging. 2014 May;29(3):147-54
pubmed: 24576837
J Magn Reson Imaging. 2014 Jul;40(1):221-8
pubmed: 24115597
J Cardiovasc Magn Reson. 2019 Jan 14;21(1):7
pubmed: 30636630
J Cardiovasc Magn Reson. 2018 Sep 14;20(1):65
pubmed: 30217194