Learning an MR acquisition-invariant representation using Siamese neural networks

Conference paper (2019)

Authors

W.M. Kouw University of Copenhagen, Pattern Recognition and Bioinformatics -

M. Loog Pattern Recognition and Bioinformatics - , University of Copenhagen

L.W. Bartels University Medical Center Utrecht

Adriënne M. Mendrik Netherlands eScience Center, University Medical Center Utrecht

Research Group

Pattern Recognition and Bioinformatics () (TU Delft)

MRI Acquisition-variation Representation-learning Siamese-neural-network

More Info

expand_more

To reference this document use:

http://resolver.tudelft.nl/uuid:cbd6ed9e-9df4-4894-bb27-fccfc4f96eb1

Published Date

2019

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Intelligent Systems

Research Group

Pattern Recognition and Bioinformatics

Abstract

Generalization of voxelwise classifiers is hampered by differences between MRI-scanners, e.g. different acquisition protocols and field strengths. To address this limitation, we propose a Siamese neural network (MRAI-net) that extracts acquisition-invariant feature vectors. These can consequently be used by task-specific methods, such as voxelwise classifiers for tissue segmentation. MRAI-net is tested on both simulated and real patient data. Experiments show that MRAI-net outperforms voxelwise classifiers trained on the source or target scanner data when a small number of labeled samples is available.

Files

08759281.pdf

(.pdf | 1.44 Mb)