Abstract #3401
Robust and fully-automated atrophy measure for multiple sclerosis disease
Ferran Prados 1,2 , Manuel Jorge Cardoso 1 , David M Cash 1,3 , Marc Modat 1,3 , Claudia A. M. Wheeler-Kingshott 2 , and Sebastien Ourselin 1,3
1
Centre for Medical Image Computing,
Department Medical Physics and Bioengineering,
University College of London, London, United Kingdom,
2
NMR
Research Unit, Department of Neuroinflammation, Queen
Square MS Centre, UCL Institute of Neurology, London,
United Kingdom,
3
Dementia
Research Centre, Department of Neurodegenerative
Disease, UCL Institute of Neurology, London, United
Kingdom
Brain atrophy is an accurate predictor of multiple
sclerosis (MS) pathology. In this work, we present a
generalised formulation of the Boundary Shift Integral (GBSI)
using probabilistic segmentations. This method
adaptively estimates a non-binary XOR region-of-interest
from probabilistic brain segmentations of the baseline
and repeat scans, in order to better localise and
capture the brain atrophy. We evaluate the proposed
method by comparing the sample size requirements for an
hypothetical clinical trial of MS disease to that needed
for SIENA. GBSI results reduced sample size, providing
increased sensitivity to disease changes through the use
of the probabilistic XOR region.
This abstract and the presentation materials are available to members only;
a login is required.
Join Here
