Use this URL to cite or link to this record in EThOS: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.746947
Title: Bayesian generative learning of brain and spinal cord templates from neuroimaging datasets
Author: Blaiotta, Claudia
ISNI:       0000 0004 7227 4916
Awarding Body: UCL (University College London)
Current Institution: University College London (University of London)
Date of Award: 2017
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
Abstract:
In the field of neuroimaging, Bayesian modelling techniques have been largely adopted and recognised as powerful tools for the purpose of extracting quantitative anatomical and functional information from medical scans. Nevertheless the potential of Bayesian inference has not yet been fully exploited, as many available tools rely on point estimation techniques, such as maximum likelihood estimation, rather than on full Bayesian inference. The aim of this thesis is to explore the value of approximate learning schemes, for instance variational Bayes, to perform inference from brain and spinal cord MRI data. The applications that will be explored in this work mainly concern image segmentation and atlas construction, with a particular emphasis on the problem of shape and intensity prior learning, from large training data sets of structural MR scans. The resulting computational tools are intended to enable integrated brain and spinal cord morphometric analyses, as opposed to the approach that is most commonly adopted in neuroimaging, which consists in optimising separate tools for brain and spine morphometrics.
Supervisor: Asuburner, John ; Freund, Patrick ; Cardoso, Manuel Jorge Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.746947  DOI: Not available
Share: