Share Email Print
cover

Proceedings Paper

Gaussian processes with optimal kernel construction for neuro-degenerative clinical onset prediction
Author(s): Liane S. Canas; Benjamin Yvernault; David M. Cash; Erika Molteni; Tom Veale; Tammie Benzinger; Sébastien Ourselin; Simon Mead; Marc Modat
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Gaussian Processes (GP) are a powerful tool to capture the complex time-variations of a dataset. In the context of medical imaging analysis, they allow a robust modelling even in case of highly uncertain or incomplete datasets. Predictions from GP are dependent of the covariance kernel function selected to explain the data variance. To overcome this limitation, we propose a framework to identify the optimal covariance kernel function to model the data.The optimal kernel is defined as a composition of base kernel functions used to identify correlation patterns between data points. Our approach includes a modified version of the Compositional Kernel Learning (CKL) algorithm, in which we score the kernel families using a new energy function that depends both the Bayesian Information Criterion (BIC) and the explained variance score. We applied the proposed framework to model the progression of neurodegenerative diseases over time, in particular the progression of autosomal dominantly-inherited Alzheimer's disease, and use it to predict the time to clinical onset of subjects carrying genetic mutation.

Paper Details

Date Published: 27 February 2018
PDF: 6 pages
Proc. SPIE 10575, Medical Imaging 2018: Computer-Aided Diagnosis, 105750G (27 February 2018); doi: 10.1117/12.2293242
Show Author Affiliations
Liane S. Canas, Univ. College London (United Kingdom)
Benjamin Yvernault, Univ. College London (United Kingdom)
David M. Cash, Univ. College London (United Kingdom)
UCL Institute of Neurology (United Kingdom)
Erika Molteni, Univ. College London (United Kingdom)
Tom Veale, Univ. College London (United Kingdom)
Tammie Benzinger, Washington Univ. School of Medicine in St. Louis (United States)
Sébastien Ourselin, Univ. College London (United Kingdom)
Simon Mead, UCL Institute of Neurology (United Kingdom)
Marc Modat, Univ. College London (United Kingdom)
UCL Institute of Neurology (United Kingdom)


Published in SPIE Proceedings Vol. 10575:
Medical Imaging 2018: Computer-Aided Diagnosis
Nicholas Petrick; Kensaku Mori, Editor(s)

© SPIE. Terms of Use
Back to Top