Automatic Detection of the Aortic Annular Plane and Coronary Ostia from Multidetector Computed Tomography.
Journal
Journal of interventional cardiology
ISSN: 1540-8183
Titre abrégé: J Interv Cardiol
Pays: United States
ID NLM: 8907826
Informations de publication
Date de publication:
2020
2020
Historique:
received:
09
12
2019
revised:
20
04
2020
accepted:
28
04
2020
entrez:
19
6
2020
pubmed:
19
6
2020
medline:
24
11
2020
Statut:
epublish
Résumé
Anatomic landmark detection is crucial during preoperative planning of transcatheter aortic valve implantation (TAVI) to select the proper device size and assess the risk of complications. The detection is currently a time-consuming manual process influenced by the image quality and subject to operator variability. In this work, we propose a novel automatic method to detect the relevant aortic landmarks from MDCT images using deep learning techniques. We trained three convolutional neural networks (CNNs) with 344 multidetector computed tomography (MDCT) acquisitions to detect five anatomical landmarks relevant for TAVI planning: the three basal attachment points of the aortic valve leaflets and the left and right coronary ostia. The detection strategy used these three CNN models to analyse a single MDCT image and yield three segmentation volumes as output. These segmentation volumes were averaged into one final segmentation volume, and the final predicted landmarks were obtained during a postprocessing step. Finally, we constructed the aortic annular plane, defined by the three predicted hinge points, and measured the distances from this plane to the predicted coronary ostia (i.e., coronary height). The methodology was validated on 100 patients. The automatic landmark detection was able to detect all the landmarks and showed high accuracy as the median distance between the ground truth and predictions is lower than the interobserver variations (1.5 mm [1.1-2.1], 2.0 mm [1.3-2.8] with a paired difference -0.5 ± 1.3 mm and
Identifiants
pubmed: 32549802
doi: 10.1155/2020/9843275
pmc: PMC7275208
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
9843275Informations de copyright
Copyright © 2020 Patricio Astudillo et al.
Déclaration de conflit d'intérêts
The following disclosures have been reported by the authors: Peter de Jaegere is a consultant for Medtronic. Johan Bosmans is a consultant for Medtronic. Ole De Backer has been a consultant for Abbott. Matthieu De Beule and Peter Mortier are shareholders of FEops. Francesco Iannaccone is an employee of FEops. Joni Dambre and Patricio Astudillo have no conflicts of interest to declare.
Références
Eur J Cardiothorac Surg. 2014 Aug;46(2):207-12; discussion 212
pubmed: 24431165
N Engl J Med. 2019 May 2;380(18):1695-1705
pubmed: 30883058
J Am Coll Cardiol. 2006 Aug 1;48(3):e1-148
pubmed: 16875962
PLoS One. 2018 Jul 25;13(7):e0200317
pubmed: 30044802
J Cardiovasc Comput Tomogr. 2019 Jan - Feb;13(1):1-20
pubmed: 30630686
JACC Cardiovasc Interv. 2009 Sep;2(9):811-20
pubmed: 19778768
JACC Cardiovasc Interv. 2013 Sep;6(9):955-64
pubmed: 23954060
N Engl J Med. 2019 May 2;380(18):1706-1715
pubmed: 30883053
IEEE Trans Med Imaging. 2018 Aug;37(8):1822-1834
pubmed: 29994628
Circ Cardiovasc Imaging. 2014 Jul;7(4):747-54
pubmed: 25027456
IEEE Trans Med Imaging. 2012 Dec;31(12):2307-21
pubmed: 22955891
Int J Cardiovasc Imaging. 2016 Mar;32(3):501-11
pubmed: 26498339
Ann Cardiothorac Surg. 2012 Jul;1(2):245-56
pubmed: 23977503
Comput Methods Programs Biomed. 2018 May;158:113-122
pubmed: 29544777
Eur Radiol. 2014 Oct;24(10):2353-9
pubmed: 24895033
IEEE Trans Image Process. 2017 Oct;26(10):4753-4764
pubmed: 28678706
Eur Radiol. 2015 Jul;25(7):1975-83
pubmed: 25708961
Minim Invasive Ther Allied Technol. 2019 Jun;28(3):157-164
pubmed: 30039720
JACC Cardiovasc Imaging. 2013 Feb;6(2):249-62
pubmed: 23489539
N Engl J Med. 2011 Jun 9;364(23):2187-98
pubmed: 21639811
Ann Thorac Surg. 2011 Mar;91(3):716-23
pubmed: 21352985