eprintid: 1473502
rev_number: 25
eprint_status: archive
userid: 608
dir: disk0/01/47/35/02
datestamp: 2015-12-23 10:50:52
lastmod: 2021-09-20 22:17:00
status_changed: 2015-12-23 10:50:52
type: article
metadata_visibility: show
creators_name: Simpson, IJ
creators_name: Cardoso, MJ
creators_name: Modat, M
creators_name: Cash, DM
creators_name: Woolrich, MW
creators_name: Andersson, JL
creators_name: Schnabel, JA
creators_name: Ourselin, S
title: Probabilistic non-linear registration with spatially adaptive regularisation
ispublished: pub
divisions: UCL
divisions: B02
divisions: C07
divisions: D07
divisions: F86
divisions: B04
divisions: C05
divisions: F42
keywords: Bayesian inference, Medical image registration, Registration uncertainty, Regularisation
note: © 2015 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/)
abstract: This paper introduces a novel method for inferring spatially varying regularisation 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 components. 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 adaptive 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.
date: 2015-12
date_type: published
official_url: http://dx.doi.org/10.1016/j.media.2015.08.006
oa_status: green
full_text_type: pub
primo: open
primo_central: open_green
article_type_text: Journal Article
verified: verified_manual
elements_id: 1060041
doi: 10.1016/j.media.2015.08.006
pii: S1361-8415(15)00131-0
language_elements: eng
lyricists_name: Cardoso, Manuel
lyricists_name: Cash, David
lyricists_name: Modat, Marc
lyricists_name: Ourselin, Sebastien
lyricists_id: MJMCA47
lyricists_id: DMCAS28
lyricists_id: MMODA28
lyricists_id: SOURS59
actors_name: Poirier, Elizabeth
actors_id: EPPOI23
actors_role: owner
full_text_status: public
publication: Medical Image Analysis
volume: 26
number: 1
pagerange: 203-216
event_location: Netherlands
issn: 1361-8423
citation:        Simpson, IJ;    Cardoso, MJ;    Modat, M;    Cash, DM;    Woolrich, MW;    Andersson, JL;    Schnabel, JA;           Simpson, IJ;  Cardoso, MJ;  Modat, M;  Cash, DM;  Woolrich, MW;  Andersson, JL;  Schnabel, JA;  Ourselin, S;   - view fewer <#>    (2015)    Probabilistic non-linear registration with spatially adaptive regularisation.                   Medical Image Analysis , 26  (1)   pp. 203-216.    10.1016/j.media.2015.08.006 <https://doi.org/10.1016/j.media.2015.08.006>.       Green open access   
 
document_url: https://discovery.ucl.ac.uk/id/eprint/1473502/1/1-s2.0-S1361841515001310-main.pdf