3D high-resolution cardiac segmentation reconstruction from 2D views using conditional variational autoencoders
File(s)
Accepted version
Author(s)
Type
Conference Paper
Abstract
Accurate segmentation of heart structures imaged by cardiac MR is key for the quantitative analysis of pathology. High-resolution 3D MR sequences enable whole-heart structural imaging but are time-consuming, expensive to acquire and they often require long breath holds that are not suitable for patients. Consequently, multiplanar breath-hold 2D cines sequences are standard practice but are disadvantaged by lack of whole-heart coverage and low through-plane resolution. To address this, we propose a conditional variational autoencoder architecture able to learn a generative model of 3D high-resolution left ventricular (LV) segmentations which is conditioned on three 2D LV segmentations of one short-axis and two long-axis images. By only employing these three 2D segmentations, our model can efficiently reconstruct the 3D high-resolution LV segmentation of a subject. When evaluated on 400 unseen healthy volunteers, our model yielded an average Dice score of 87.92 ± 0.15 and outperformed competing architectures (TL-net, Dice score = 82.60 ± 0.23, p = 2.2 · 10 -16 ).
Date Issued
2019-07-11
Date Acceptance
2019-04-01
Citation
2019 IEEE 16TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2019), 2019, pp.1643-1646
ISSN
1945-7928
Publisher
IEEE
Start Page
1643
End Page
1646
Journal / Book Title
2019 IEEE 16TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2019)
Copyright Statement
©2019 IEEE.
Sponsor
Imperial College Healthcare NHS Trust- BRC Funding
British Heart Foundation
Imperial College Healthcare NHS Trust- BRC Funding
Identifier
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000485040000350&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
Grant Number
RDC04
NH/17/1/32725
RDB02
Source
16th IEEE International Symposium on Biomedical Imaging (ISBI)
Subjects
Cardiac MR
Variational Autoencoder
3D Segmentation Reconstruction
Deep Learning
MASS
Publication Status
Published
Start Date
2019-04-08
Finish Date
2019-04-11
Coverage Spatial
Venice, ITALY
Date Publish Online
2019-07-11