Representation learning for cross-modality classification

TY - GEN

T1 - Representation learning for cross-modality classification

AU - Tulder, Gijs van

AU - de Bruijne, Marleen

PY - 2017

Y1 - 2017

N2 - Differences in scanning parameters or modalities can complicate image analysis based on supervised classification. This paper presents two representation learning approaches, based on autoencoders, that address this problem by learning representations that are similar across domains. Both approaches use, next to the data representation objective, a similarity objective to minimise the difference between representations of corresponding patches from each domain. We evaluated the methods in transfer learning experiments on multi-modal brain MRI data and on synthetic data. After transforming training and test data from different modalities to the common representations learned by our methods, we trained classifiers for each of pair of modalities. We found that adding the similarity term to the standard objective can produce representations that are more similar and can give a higher accuracy in these cross-modality classification experiments.

AB - Differences in scanning parameters or modalities can complicate image analysis based on supervised classification. This paper presents two representation learning approaches, based on autoencoders, that address this problem by learning representations that are similar across domains. Both approaches use, next to the data representation objective, a similarity objective to minimise the difference between representations of corresponding patches from each domain. We evaluated the methods in transfer learning experiments on multi-modal brain MRI data and on synthetic data. After transforming training and test data from different modalities to the common representations learned by our methods, we trained classifiers for each of pair of modalities. We found that adding the similarity term to the standard objective can produce representations that are more similar and can give a higher accuracy in these cross-modality classification experiments.

U2 - 10.1007/978-3-319-61188-4_12

DO - 10.1007/978-3-319-61188-4_12

M3 - Article in proceedings

SN - 978-3-319-61187-7

T3 - Lecture notes in computer science

SP - 126

EP - 136

BT - Medical Computer Vision and Bayesian and Graphical Models for Biomedical Imaging

A2 - Müller, Henning

A2 - Kelm, B. Michael

A2 - Arbel, Tal

A2 - Cai, Weidong

A2 - Cardoso, M. Jorge

A2 - Langs, Georg

A2 - Menze, Bjoern

A2 - Metaxas, Dimitris

A2 - Montillo, Albert

A2 - Wells, William M.

A2 - Zhang, Shaoting

A2 - Chung, Albert C. S.

A2 - Jenkinson, Mark

A2 - Ribbens, Annemie

PB - Springer

T2 - MICCAI International Workshop on Medical Computer Vision 2016

Y2 - 21 October 2016 through 21 October 2016

ER -