Semi-supervised learning for network-based cardiac MR image segmentation

File Description SizeFormat 
bai2017miccai.pdfFile embargoed until 01 January 10000443.14 kBAdobe PDF    Request a copy
Title: Semi-supervised learning for network-based cardiac MR image segmentation
Author(s): Bai, W
Oktay, O
Sinclair, M
Suzuki, H
Rajchl, M
Tarroni, G
Glocker, B
King, A
Matthews, P
Rueckert, D
Item 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 chal- lenge 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.
Publication Date: 10-Sep-2017
Date of Acceptance: 16-May-2017
URI: http://hdl.handle.net/10044/1/49165
ISSN: 0302-9743
Publisher: Springer
Journal / Book Title: Lecture Notes in Computer Science
Copyright Statement: This paper is embargoed until publication.
Sponsor/Funder: Commission of the European Communities
Engineering & Physical Science Research Council (EPSRC)
Engineering & Physical Science Research Council (EPSRC)
Funder's Grant Number: 655033
EP/N014529/1
EP/P001009/1
Conference Name: Medical Image Computing and Computer Assisted Intervention
Keywords: Artificial Intelligence & Image Processing
08 Information And Computing Sciences
Publication Status: Accepted
Start Date: 2017-09-10
Finish Date: 2017-09-14
Conference Place: Quebec, Canada
Embargo Date: publication subject to indefinite embargo
Appears in Collections:Faculty of Engineering
Computing
Department of Medicine
Faculty of Medicine



Items in Spiral are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons