BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:A functional data approach to identifying Alzheimer's disease from
  multimodal cortical surface data
DTSTART:20231208T151500
DTEND:20231208T170000
DTSTAMP:20260408T092613Z
UID:1c5be4b0b08ccc60132f97c51a83ccb68b7253ddee9a4d9244d65567
CATEGORIES:Conferences - Seminars
DESCRIPTION:Eardi Lila\, University of Washington\nIn this talk\, we intro
 duce a novel statistical framework for the classification of multimodal co
 rtical surface data. The motivating application is the identification of s
 ubjects with Alzheimer's disease from their cortical surface geometry and 
 associated cortical thickness map. The model proposed is based upon a refo
 rmulation of the image classification problem as a regularized multivariat
 e functional linear regression model. This allows us to adopt a direct app
 roach to the estimation of the most discriminant direction while controlli
 ng for its complexity with an appropriate geometric regularizer.\nWe apply
  the proposed method to a pooled dataset from the Alzheimer's Disease Neur
 oimaging Initiative and the Parkinson's Progression Markers Initiative\, a
 nd are able to estimate discriminant directions that capture both cortical
  geometric and thickness predictive features of Alzheimer's disease\, whic
 h are consistent with the existing neuroscience literature.\n 
LOCATION:MA A3 30 https://plan.epfl.ch/?room==MA%20A3%2030
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR