Extraction of discriminative functional MRI activation patterns and an application to Alzheimer's disease

Despina Kontos, Vasileios Megalooikonomou, Dragoljub Pokrajac, Alexandar Lazarevic, Zoran Obradovic, Orest Boyko, James Ford, Filia Makedon, Andrew Saykin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

16 Citations (Scopus)

Abstract

We propose a novel Dynamic Recursive Partitioning approach for discovering discriminative patterns of functional MRI activation. The goal is to efficiently identify spatial regions that are associated with non-spatial variables through adaptive recursive partitioning of the 3D space into a number of hyper-rectangles utilizing statistical tests. As a case study, we analyze fMRI datasets obtained from a study that explores neuroanatomical correlates of semantic processing in Alzheimer's disease. We seek to discover brain activation areas that discriminate controls from patients. We evaluate the results by presenting classification experiments that utilize information extracted from these regions. The discovered areas elucidated large hemispheric and lobar differences being consistent with prior findings. The overall classification accuracy based on activation patterns in these areas exceeded 90%. The proposed approach being general enough has great potential for elucidating structure-function relationships and can be valuable to human brain mapping.

Original languageEnglish (US)
Title of host publicationLecture Notes in Computer Science
EditorsC. Barillot, D.R. Haynor, P. Hellier
Pages727-735
Number of pages9
Volume3217
Edition1 PART 2
StatePublished - 2004
Externally publishedYes
EventMedical Image Computing and Computer-Assisted Intervention, MICCAI 2004 - 7th International Conference, Proceedings - Saint-Malo, France
Duration: Sep 26 2004Sep 29 2004

Other

OtherMedical Image Computing and Computer-Assisted Intervention, MICCAI 2004 - 7th International Conference, Proceedings
CountryFrance
CitySaint-Malo
Period9/26/049/29/04

Fingerprint

Chemical activation
Brain mapping
Statistical tests
Brain
Semantics
Processing
Magnetic Resonance Imaging
Experiments

ASJC Scopus subject areas

  • Computer Science (miscellaneous)

Cite this

Kontos, D., Megalooikonomou, V., Pokrajac, D., Lazarevic, A., Obradovic, Z., Boyko, O., ... Saykin, A. (2004). Extraction of discriminative functional MRI activation patterns and an application to Alzheimer's disease. In C. Barillot, D. R. Haynor, & P. Hellier (Eds.), Lecture Notes in Computer Science (1 PART 2 ed., Vol. 3217, pp. 727-735)

Extraction of discriminative functional MRI activation patterns and an application to Alzheimer's disease. / Kontos, Despina; Megalooikonomou, Vasileios; Pokrajac, Dragoljub; Lazarevic, Alexandar; Obradovic, Zoran; Boyko, Orest; Ford, James; Makedon, Filia; Saykin, Andrew.

Lecture Notes in Computer Science. ed. / C. Barillot; D.R. Haynor; P. Hellier. Vol. 3217 1 PART 2. ed. 2004. p. 727-735.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kontos, D, Megalooikonomou, V, Pokrajac, D, Lazarevic, A, Obradovic, Z, Boyko, O, Ford, J, Makedon, F & Saykin, A 2004, Extraction of discriminative functional MRI activation patterns and an application to Alzheimer's disease. in C Barillot, DR Haynor & P Hellier (eds), Lecture Notes in Computer Science. 1 PART 2 edn, vol. 3217, pp. 727-735, Medical Image Computing and Computer-Assisted Intervention, MICCAI 2004 - 7th International Conference, Proceedings, Saint-Malo, France, 9/26/04.
Kontos D, Megalooikonomou V, Pokrajac D, Lazarevic A, Obradovic Z, Boyko O et al. Extraction of discriminative functional MRI activation patterns and an application to Alzheimer's disease. In Barillot C, Haynor DR, Hellier P, editors, Lecture Notes in Computer Science. 1 PART 2 ed. Vol. 3217. 2004. p. 727-735
Kontos, Despina ; Megalooikonomou, Vasileios ; Pokrajac, Dragoljub ; Lazarevic, Alexandar ; Obradovic, Zoran ; Boyko, Orest ; Ford, James ; Makedon, Filia ; Saykin, Andrew. / Extraction of discriminative functional MRI activation patterns and an application to Alzheimer's disease. Lecture Notes in Computer Science. editor / C. Barillot ; D.R. Haynor ; P. Hellier. Vol. 3217 1 PART 2. ed. 2004. pp. 727-735
@inproceedings{75cb66c1341e473d8a12811741fd19db,
title = "Extraction of discriminative functional MRI activation patterns and an application to Alzheimer's disease",
abstract = "We propose a novel Dynamic Recursive Partitioning approach for discovering discriminative patterns of functional MRI activation. The goal is to efficiently identify spatial regions that are associated with non-spatial variables through adaptive recursive partitioning of the 3D space into a number of hyper-rectangles utilizing statistical tests. As a case study, we analyze fMRI datasets obtained from a study that explores neuroanatomical correlates of semantic processing in Alzheimer's disease. We seek to discover brain activation areas that discriminate controls from patients. We evaluate the results by presenting classification experiments that utilize information extracted from these regions. The discovered areas elucidated large hemispheric and lobar differences being consistent with prior findings. The overall classification accuracy based on activation patterns in these areas exceeded 90{\%}. The proposed approach being general enough has great potential for elucidating structure-function relationships and can be valuable to human brain mapping.",
author = "Despina Kontos and Vasileios Megalooikonomou and Dragoljub Pokrajac and Alexandar Lazarevic and Zoran Obradovic and Orest Boyko and James Ford and Filia Makedon and Andrew Saykin",
year = "2004",
language = "English (US)",
volume = "3217",
pages = "727--735",
editor = "C. Barillot and D.R. Haynor and P. Hellier",
booktitle = "Lecture Notes in Computer Science",
edition = "1 PART 2",

}

TY - GEN

T1 - Extraction of discriminative functional MRI activation patterns and an application to Alzheimer's disease

AU - Kontos, Despina

AU - Megalooikonomou, Vasileios

AU - Pokrajac, Dragoljub

AU - Lazarevic, Alexandar

AU - Obradovic, Zoran

AU - Boyko, Orest

AU - Ford, James

AU - Makedon, Filia

AU - Saykin, Andrew

PY - 2004

Y1 - 2004

N2 - We propose a novel Dynamic Recursive Partitioning approach for discovering discriminative patterns of functional MRI activation. The goal is to efficiently identify spatial regions that are associated with non-spatial variables through adaptive recursive partitioning of the 3D space into a number of hyper-rectangles utilizing statistical tests. As a case study, we analyze fMRI datasets obtained from a study that explores neuroanatomical correlates of semantic processing in Alzheimer's disease. We seek to discover brain activation areas that discriminate controls from patients. We evaluate the results by presenting classification experiments that utilize information extracted from these regions. The discovered areas elucidated large hemispheric and lobar differences being consistent with prior findings. The overall classification accuracy based on activation patterns in these areas exceeded 90%. The proposed approach being general enough has great potential for elucidating structure-function relationships and can be valuable to human brain mapping.

AB - We propose a novel Dynamic Recursive Partitioning approach for discovering discriminative patterns of functional MRI activation. The goal is to efficiently identify spatial regions that are associated with non-spatial variables through adaptive recursive partitioning of the 3D space into a number of hyper-rectangles utilizing statistical tests. As a case study, we analyze fMRI datasets obtained from a study that explores neuroanatomical correlates of semantic processing in Alzheimer's disease. We seek to discover brain activation areas that discriminate controls from patients. We evaluate the results by presenting classification experiments that utilize information extracted from these regions. The discovered areas elucidated large hemispheric and lobar differences being consistent with prior findings. The overall classification accuracy based on activation patterns in these areas exceeded 90%. The proposed approach being general enough has great potential for elucidating structure-function relationships and can be valuable to human brain mapping.

UR - http://www.scopus.com/inward/record.url?scp=20344381295&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=20344381295&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:20344381295

VL - 3217

SP - 727

EP - 735

BT - Lecture Notes in Computer Science

A2 - Barillot, C.

A2 - Haynor, D.R.

A2 - Hellier, P.

ER -