Discriminative MR image feature analysis for automatic schizophrenia and Alzheimer's disease classification

Yanxi Liu, Leonid Teverovskiy, Owen Carmichael, Ron Kikinis, Martha Shenton, Cameron S Carter, V. Andrew Stenger, Simon Davis, Howard Aizenstein, James T. Becker, Oscar L. Lopez, Carolyn C. Meltzer

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

66 Citations (Scopus)

Abstract

We construct a computational framework for automatic central nervous system (CNS) disease discrimination using high resolution Magnetic Resonance Images (MRI) of human brains. More than 3000 MR image features are extracted, forming a high dimensional coarse-to-fine hierarchical image description that quantifies brain asymmetry, texture and statistical properties in corresponding local regions of the brain. Discriminative image feature subspaces are computed, evaluated and selected automatically. Our initial experimental results show 100% and 90% separability between chronicle schizophrenia (SZ) and first episode SZ versus their respective matched controls. Under the same computational framework, we also find higher than 95% separability among Alzheimer's Disease, mild cognitive impairment patients, and their matched controls. An average of 88% classification success rate is achieved using leave-one-out cross validation on five different well-chosen patient-control image sets of sizes from 15 to 27 subjects per disease class.

Original languageEnglish (US)
Title of host publicationLecture Notes in Computer Science
EditorsC. Barillot, D.R. Haynor, P. Hellier
Pages393-401
Number of pages9
Volume3216
EditionPART 1
StatePublished - 2004
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

Brain
Neurology
Magnetic resonance
Textures

ASJC Scopus subject areas

  • Computer Science (miscellaneous)

Cite this

Liu, Y., Teverovskiy, L., Carmichael, O., Kikinis, R., Shenton, M., Carter, C. S., ... Meltzer, C. C. (2004). Discriminative MR image feature analysis for automatic schizophrenia and Alzheimer's disease classification. In C. Barillot, D. R. Haynor, & P. Hellier (Eds.), Lecture Notes in Computer Science (PART 1 ed., Vol. 3216, pp. 393-401)

Discriminative MR image feature analysis for automatic schizophrenia and Alzheimer's disease classification. / Liu, Yanxi; Teverovskiy, Leonid; Carmichael, Owen; Kikinis, Ron; Shenton, Martha; Carter, Cameron S; Stenger, V. Andrew; Davis, Simon; Aizenstein, Howard; Becker, James T.; Lopez, Oscar L.; Meltzer, Carolyn C.

Lecture Notes in Computer Science. ed. / C. Barillot; D.R. Haynor; P. Hellier. Vol. 3216 PART 1. ed. 2004. p. 393-401.

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

Liu, Y, Teverovskiy, L, Carmichael, O, Kikinis, R, Shenton, M, Carter, CS, Stenger, VA, Davis, S, Aizenstein, H, Becker, JT, Lopez, OL & Meltzer, CC 2004, Discriminative MR image feature analysis for automatic schizophrenia and Alzheimer's disease classification. in C Barillot, DR Haynor & P Hellier (eds), Lecture Notes in Computer Science. PART 1 edn, vol. 3216, pp. 393-401, Medical Image Computing and Computer-Assisted Intervention, MICCAI 2004 - 7th International Conference, Proceedings, Saint-Malo, France, 9/26/04.
Liu Y, Teverovskiy L, Carmichael O, Kikinis R, Shenton M, Carter CS et al. Discriminative MR image feature analysis for automatic schizophrenia and Alzheimer's disease classification. In Barillot C, Haynor DR, Hellier P, editors, Lecture Notes in Computer Science. PART 1 ed. Vol. 3216. 2004. p. 393-401
Liu, Yanxi ; Teverovskiy, Leonid ; Carmichael, Owen ; Kikinis, Ron ; Shenton, Martha ; Carter, Cameron S ; Stenger, V. Andrew ; Davis, Simon ; Aizenstein, Howard ; Becker, James T. ; Lopez, Oscar L. ; Meltzer, Carolyn C. / Discriminative MR image feature analysis for automatic schizophrenia and Alzheimer's disease classification. Lecture Notes in Computer Science. editor / C. Barillot ; D.R. Haynor ; P. Hellier. Vol. 3216 PART 1. ed. 2004. pp. 393-401
@inproceedings{65ce5e101f74442b8ba68e6b0e011c70,
title = "Discriminative MR image feature analysis for automatic schizophrenia and Alzheimer's disease classification",
abstract = "We construct a computational framework for automatic central nervous system (CNS) disease discrimination using high resolution Magnetic Resonance Images (MRI) of human brains. More than 3000 MR image features are extracted, forming a high dimensional coarse-to-fine hierarchical image description that quantifies brain asymmetry, texture and statistical properties in corresponding local regions of the brain. Discriminative image feature subspaces are computed, evaluated and selected automatically. Our initial experimental results show 100{\%} and 90{\%} separability between chronicle schizophrenia (SZ) and first episode SZ versus their respective matched controls. Under the same computational framework, we also find higher than 95{\%} separability among Alzheimer's Disease, mild cognitive impairment patients, and their matched controls. An average of 88{\%} classification success rate is achieved using leave-one-out cross validation on five different well-chosen patient-control image sets of sizes from 15 to 27 subjects per disease class.",
author = "Yanxi Liu and Leonid Teverovskiy and Owen Carmichael and Ron Kikinis and Martha Shenton and Carter, {Cameron S} and Stenger, {V. Andrew} and Simon Davis and Howard Aizenstein and Becker, {James T.} and Lopez, {Oscar L.} and Meltzer, {Carolyn C.}",
year = "2004",
language = "English (US)",
volume = "3216",
pages = "393--401",
editor = "C. Barillot and D.R. Haynor and P. Hellier",
booktitle = "Lecture Notes in Computer Science",
edition = "PART 1",

}

TY - GEN

T1 - Discriminative MR image feature analysis for automatic schizophrenia and Alzheimer's disease classification

AU - Liu, Yanxi

AU - Teverovskiy, Leonid

AU - Carmichael, Owen

AU - Kikinis, Ron

AU - Shenton, Martha

AU - Carter, Cameron S

AU - Stenger, V. Andrew

AU - Davis, Simon

AU - Aizenstein, Howard

AU - Becker, James T.

AU - Lopez, Oscar L.

AU - Meltzer, Carolyn C.

PY - 2004

Y1 - 2004

N2 - We construct a computational framework for automatic central nervous system (CNS) disease discrimination using high resolution Magnetic Resonance Images (MRI) of human brains. More than 3000 MR image features are extracted, forming a high dimensional coarse-to-fine hierarchical image description that quantifies brain asymmetry, texture and statistical properties in corresponding local regions of the brain. Discriminative image feature subspaces are computed, evaluated and selected automatically. Our initial experimental results show 100% and 90% separability between chronicle schizophrenia (SZ) and first episode SZ versus their respective matched controls. Under the same computational framework, we also find higher than 95% separability among Alzheimer's Disease, mild cognitive impairment patients, and their matched controls. An average of 88% classification success rate is achieved using leave-one-out cross validation on five different well-chosen patient-control image sets of sizes from 15 to 27 subjects per disease class.

AB - We construct a computational framework for automatic central nervous system (CNS) disease discrimination using high resolution Magnetic Resonance Images (MRI) of human brains. More than 3000 MR image features are extracted, forming a high dimensional coarse-to-fine hierarchical image description that quantifies brain asymmetry, texture and statistical properties in corresponding local regions of the brain. Discriminative image feature subspaces are computed, evaluated and selected automatically. Our initial experimental results show 100% and 90% separability between chronicle schizophrenia (SZ) and first episode SZ versus their respective matched controls. Under the same computational framework, we also find higher than 95% separability among Alzheimer's Disease, mild cognitive impairment patients, and their matched controls. An average of 88% classification success rate is achieved using leave-one-out cross validation on five different well-chosen patient-control image sets of sizes from 15 to 27 subjects per disease class.

UR - http://www.scopus.com/inward/record.url?scp=20344383494&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=20344383494&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:20344383494

VL - 3216

SP - 393

EP - 401

BT - Lecture Notes in Computer Science

A2 - Barillot, C.

A2 - Haynor, D.R.

A2 - Hellier, P.

ER -