UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Partial least squares modelling for imaging-genetics in Alzheimer's disease: Plausibility and generalization

Lorenzi, M; Gutman, B; Hibar, DP; Altmann, A; Jahanshad, N; Thompson, PM; Ourselin, S; (2016) Partial least squares modelling for imaging-genetics in Alzheimer's disease: Plausibility and generalization. In: Proceedings of the 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI). (pp. pp. 838-841). IEEE: Prague, Czech Republic. Green open access

[thumbnail of Altmann_ISBI2015_final.pdf]
Preview
Text
Altmann_ISBI2015_final.pdf

Download (379kB) | Preview

Abstract

In this work we evaluate the ability of PLS in generalizing to unseen clinical cohorts when applied to the analysis of the joint variation between genotype and phenotype in Alzheimer's disease (AD). The model is trained on single-nucleotide polymorphisms (SNPs) and brain volumes obtained from the ADNI database for a large cohort of healthy individuals and AD patients, and validated on the ADNI MCI and ENIGMA cohorts. The experimental results confirm the ability of PLS in providing a meaningful description of the joint dynamics between brain atrophy and genotype data in AD, while providing important generalization results when tested on clinically heterogeneous cohorts.

Type: Proceedings paper
Title: Partial least squares modelling for imaging-genetics in Alzheimer's disease: Plausibility and generalization
Event: 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI)
ISBN-13: 9781479923502
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/ISBI.2016.7493396
Publisher version: http://dx.doi.org/10.1109/ISBI.2016.7493396
Additional information: Copyright © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Keywords: machine learning, GWA, imaging-genetics, genotype, phenotype, Alzheimer's disease
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng
URI: https://discovery.ucl.ac.uk/id/eprint/1509187
Downloads since deposit
1,021Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item