Automatic deep learning-based myocardial infarction segmentation from delayed enhancement MRI.
Adaptive framework
CNN
DE-MRI
Myocardial infarction
Semantic segmentation
Journal
Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
ISSN: 1879-0771
Titre abrégé: Comput Med Imaging Graph
Pays: United States
ID NLM: 8806104
Informations de publication
Date de publication:
01 2022
01 2022
Historique:
received:
26
01
2021
revised:
04
10
2021
accepted:
04
11
2021
pubmed:
6
12
2021
medline:
3
5
2022
entrez:
5
12
2021
Statut:
ppublish
Résumé
Delayed Enhancement cardiac MRI (DE-MRI) has become indispensable for the diagnosis of myocardial diseases. However, to quantify the disease severity, doctors need time to manually annotate the scar and myocardium. To address this issue, in this paper we propose an automatic myocardial infarction segmentation approach on the left ventricle from short-axis DE-MRI based on Convolutional Neural Networks (CNN). The objective is to segment myocardial infarction on short-axis DE-MRI images of the left ventricle acquired 10 min after the injection of a gadolinium-based contrast agent. The segmentation of the infarction area is realized in two stages: a first CNN model finds the contour of myocardium and a second CNN model segments the infarction. Compared to the manual intra-observer and inter-observer variations for the segmentation of myocardial infarction, and to the automatic segmentation with Gaussian Mixture Model, our proposal achieves satisfying segmentation results on our dataset of 904 DE-MRI slices.
Identifiants
pubmed: 34864579
pii: S0895-6111(21)00163-4
doi: 10.1016/j.compmedimag.2021.102014
pii:
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
102014Informations de copyright
Copyright © 2021 Elsevier Ltd. All rights reserved.