BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Statistical learning for structural neuroimaging data - Remi Cuing
 net\, ICM Paris
DTSTART:20110811T090000Z
DTEND:20110811T100000Z
UID:TALK32278@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:Brain image analyses have widely relied on univariate voxel-wi
 se methods. In such analyses\, brain images are first spatially registered
  to a common stereotaxic space\, and then mass univariate statistical test
 s are performed in each voxel to detect significant group differences. How
 ever\, the sensitivity of theses approaches is limited when the difference
 s involve a combination of different brain structures. Recently\, there ha
 s been a growing interest in support vector machines methods to overcome t
 he limits of these analyses. \n\nThis talk will focus on machine learning 
 methods for population analysis and patient classification in neuroimaging
 . First\, we evaluated the performances of different classification strate
 gies for the identification of patients with Alzheimer’s disease based o
 n T1-weighted MRI. However\, in these approaches\, the specificity of neur
 oimaging data was not taken into account in the classification method per 
 se. Brain images are indeed a prototypical case of structured data\, whose
  structure is governed by the underlying anatomical and functional organiz
 ation. Therefore we introduced a framework to introduce spatial and anatom
 ical priors in SVM for brain image analysis based on regularization operat
 ors. The proposed framework was applied to the classification of brain mag
 netic resonance (MR) images (based on gray matter concentration maps and c
 ortical thickness measures) from 137 patients with Alzheimer’s disease a
 nd 162 elderly controls. The results demonstrated that the proposed classi
 fier generates less-noisy and consequently more interpretable feature maps
  with high classification performances.
LOCATION:Small lecture theatre\, Microsoft Research Ltd\, 7 J J Thomson Av
 enue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR