Meeting Banner
Abstract #1416

Shape and Spatial Pattern Analysis through Covariance-based Estimations of MS lesions: the SSPACE-MS study

Carmen Tur1,2, Francesco Grussu1,3, Ferran Prados1,4,5, Baris Kanber4, Thalis Charalambous1,6, Declan T. Chard1,7, Olga Ciccarelli1,7, and Claudia A.M. Gandini Wheeler-Kingshott1,8,9
1UCL Queen Square Institute of Neurology, University College London, London, United Kingdom, 2Neurology, Luton and Dunstable University Hospital, Luton, United Kingdom, 3Centre for Medical Image Computing, Department of Computer Science, University College London, London, United Kingdom, 4Centre for Medical Image Computing, Medical Physics and Biomedical Engineering department, University College London, London, United Kingdom, 5e-Health center, Universitat Oberta de Catalunya, Barcelona, Spain, 6Department of Medicine, St. George’s University of London, London, United Kingdom, 7University College London Hospitals Biomedical Research Centre, National Institute for Health Research, London, United Kingdom, 8Department of Brain and Behavioural Sciences, University of Pavia, Pavia, Italy, 9Brain MRI 3T Research Centre, IRCCS Mondino Foundation, Pavia, Italy

Lesion load is the main predictor of future disability in multiple sclerosis (MS) but its predictive power is limited possibly because key aspects of lesions, such as their spatial distribution, morphology or pathological substrate are not being considered. Here we demonstrate the relevance of shape and spatial features of white matter lesions in the development of disability in MS through a novel approach. This new methodological framework (SSPACE-MS) is based on the analysis of the covariance matrix defined by the spatial position of lesional voxels. It can be applied longitudinally and is easily implementable in clinical practice.

This abstract and the presentation materials are available to 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here