Semi-supervised learning for network-based cardiac MR image segmentation
File(s)
Accepted version
Author(s)
Type
Conference Paper
Abstract
Training a fully convolutional network for pixel-wise (or voxel-wise) image segmentation normally requires a large number of training images with corresponding ground truth label maps. However, it is a challenge to obtain such a large training set in the medical imaging domain, where expert annotations are time-consuming and difficult to obtain. In this paper, we propose a semi-supervised learning approach, in which a segmentation network is trained from both labelled and unlabelled data. The network parameters and the segmentations for the unlabelled data are alternately updated. We evaluate the method for short-axis cardiac MR image segmentation and it has demonstrated a high performance, outperforming a baseline supervised method. The mean Dice overlap metric is 0.92 for the left ventricular cavity, 0.85 for the myocardium and 0.89 for the right ventricular cavity. It also outperforms a state-of-the-art multi-atlas segmentation method by a large margin and the speed is substantially faster.
Date Issued
2017-09-04
Date Acceptance
2017-05-16
Citation
2017, 1034, pp.253-260
ISSN
0302-9743
Publisher
Springer Verlag
Start Page
253
End Page
260
Journal / Book Title
Lecture Notes in Computer Science
Volume
1034
Copyright Statement
© 2017 Springer International Publishing AG 2017. The final authenticated version is available online at https://doi.org/10.1007/978-3-319-66185-8_29
Sponsor
Engineering & Physical Science Research Council (EPSRC)
Commission of the European Communities
Engineering & Physical Science Research Council (EPSRC)
Biogen Idec Ltd
UK DRI Ltd
Medical Research Council (MRC)
Medical Research Council (MRC)
UK DRI Ltd
Grant Number
EP/N014529/1
655033
EP/P001009/1
PO 11024
4050641385
MR/M024903/1
4050641385
N/A
Source
International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)
Subjects
Artificial Intelligence & Image Processing
Publication Status
Published
Start Date
2017-09-11
Finish Date
2017-09-13
Date Publish Online
2017-09-04