Unsupervised domain adaptation in brain lesion segmentation with adversarial networks
File(s)
Accepted version
Author(s)
Type
Conference Paper
Abstract
Significant advances have been made towards building accu- rate automatic segmentation systems for a variety of biomedical applica- tions using machine learning. However, the performance of these systems often degrades when they are applied on new data that differ from the training data, for example, due to variations in imaging protocols. Man- ually annotating new data for each test domain is not a feasible solution. In this work we investigate unsupervised domain adaptation using ad- versarial neural networks to train a segmentation method which is more invariant to differences in the input data, and which does not require any annotations on the test domain. Specifically, we learn domain-invariant features by learning to counter an adversarial network, which attempts to classify the domain of the input data by observing the activations of the segmentation network. Furthermore, we propose a multi-connected domain discriminator for improved adversarial training. Our system is evaluated using two MR databases of subjects with traumatic brain in- juries, acquired using different scanners and imaging protocols. Using our unsupervised approach, we obtain segmentation accuracies which are close to the upper bound of supervised domain adaptation.
Date Issued
2017-06-25
Date Acceptance
2017-02-09
Publisher
Springer
Journal / Book Title
Lecture Notes Computer Science
Is Replaced By
10044/1/77450
Copyright Statement
© Springer International Publishing AG 2017. The final publication is available at Springer via https://link.springer.com/chapter/10.1007%2F978-3-319-59050-9_47
Sponsor
Commission of the European Communities
NVIDIA Corporation
Engineering & Physical Science Research Council (EPSRC)
Grant Number
HEALTH-F2-2013-602150
EP/N023668/1
Source
Information Processing in Medical Imaging
Publication Status
Accepted
Start Date
2017-06-25
Finish Date
2017-06-30
Coverage Spatial
Boone, USA