BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250705T121321EDT-6634vRaNiE@132.216.98.100
DTSTAMP:20250705T161321Z
DESCRIPTION:Farouk Nathoo\, PhD\n\nProfessor\, Mathematics and Statistics\n
 	University of Victoria\, BC\n\nWHEN: Wednesday\, February 21\, 2024\, from
  3:30 to 4:30 p.m.\n\nWHERE: hybrid | 2001 9IÖÆ×÷³§Ãâ·Ñ College Avenue\, room 12
 01\; Zoom\n\nNOTE: Dr. Nathoo will be presenting from Victoria\, BC\n\nAbs
 tract\n\nDealing with the high dimension of both neuroimaging data and gen
 etic data is a difficult problem in the association of genetic data to neu
 roimaging. In this article\, we tackle the latter problem with an eye towa
 rd developing solutions that are relevant for disease prediction. Supporte
 d by a vast literature on the predictive power of neural networks\, our pr
 oposed solution uses neural networks to extract from neuroimaging data fea
 tures that are relevant for predicting Alzheimer’s Disease (AD) for subseq
 uent relation to genetics. The neuroimaging-genetic pipeline we propose is
  comprised of image processing\, neuroimaging feature extraction and genet
 ic association steps. We present a neural network classifier for extractin
 g neuroimaging features that are related with the disease. The proposed me
 thod is data-driven and requires no expert advice or a priori selection of
  regions of interest. We further propose a multivariate regression with pr
 iors specified in the Bayesian framework that allows for group sparsity at
  multiple levels including SNPs and genes.\n\nSpeaker bio\n\nLink to websi
 te: https://www.math.uvic.ca/~nathoo/ \n
DTSTART:20240221T203000Z
DTEND:20240221T213000Z
SUMMARY:Neural Network Feature Extraction and Bayesian Group Sparse Multita
 sk Regression for Imaging Genetics
URL:/epi-biostat-occh/channels/event/neural-network-fe
 ature-extraction-and-bayesian-group-sparse-multitask-regression-imaging-ge
 netics-353632
END:VEVENT
END:VCALENDAR