King's College London

Research portal

Probabilistic Non-Linear Registration with Spatially Adaptive Regularisation

Research output: Contribution to journalArticle

I.J.A. Simpson ; M.J. Cardoso ; M. Modat ; D.M. Cash ; M.W. Woolrich ; J.L.R. Andersson ; Julia Anne Schnabel ; S. Ourselin

Original languageEnglish
Pages (from-to)203-216
JournalMedical image analysis
Volume26
Issue number1
Early online date28 Sep 2015
DOIs
StateE-pub ahead of print - 28 Sep 2015

Documents

King's Authors

Abstract

This paper introduces a novel method for inferring spatially varying regularisa- tion in non-linear registration. This is achieved through full Bayesian inference on a probabilistic registration model, where the prior on the transformation parameters is parameterised as a weighted mixture of spatially localised com- ponents. Such an approach has the advantage of allowing the registration to be more flexibly driven by the data than a traditional globally defined regularisation penalty, such as bending energy. The proposed method adaptively determines the influence of the prior in a local region. The strength of the prior may be reduced in areas where the data better support deformations, or can enforce a stronger constraint in less informative areas. Consequently, the use of such a spatially adaptive prior may reduce unwanted impacts of regularisation on the inferred transformation. This is especially important for applications where the deformation field itself is of interest, such as tensor based morphometry. The proposed approach is demonstrated using synthetic images, and with application to tensor based morphometry analysis of subjects with Alzheimer’s disease and healthy controls. The results indicate that using the proposed spatially adap- tive prior leads to sparser deformations, which provide better localisation of regional volume change. Additionally, the proposed regularisation model leads to more data driven and localised maps of registration uncertainty. This paper also demonstrates for the first time the use of Bayesian model comparison for selecting different types of regularisation.

Download statistics

No data available

View graph of relations

© 2015 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454