Brain Image Classification Based on Automated Morphometry and
Penalised Linear Discriminant Analysis with Resampling

D 2015

Brain Image Classification Based on Automated Morphometry and Penalised Linear Discriminant Analysis with Resampling

JANOUŠOVÁ, Eva; Daniel SCHWARZ; Giovanni MONTANA and Tomáš KAŠPÁREK

Basic information

Original name

Brain Image Classification Based on Automated Morphometry and Penalised Linear Discriminant Analysis with Resampling

Authors

JANOUŠOVÁ, Eva (203 Czech Republic, guarantor, belonging to the institution); Daniel SCHWARZ (203 Czech Republic, belonging to the institution); Giovanni MONTANA (826 United Kingdom of Great Britain and Northern Ireland) and Tomáš KAŠPÁREK (203 Czech Republic, belonging to the institution)

Edition

Warsaw, Los Alamitos, Proceedings of the 2015 Federated Conference on Computer Science and Information Systems, p. 263-268, 6 pp. 2015

Publisher

Polskie Towarzystwo Informatyczne, IEEE

Other information

Language

English

Type of outcome

Proceedings paper

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Poland

Confidentiality degree

is not subject to a state or trade secret

Publication form

electronic version available online

References:

URL

RIV identification code

RIV/00216224:14110/15:00088877

Organization unit

Faculty of Medicine

ISBN

978-83-60810-66-8

ISSN

DOI

https://doi.org/10.15439/2015F147

UT WoS

000376494300031

EID Scopus

2-s2.0-84958051750

Keywords in English

pattern recognition; computational neuroanatomy; classification; penalized linear discriminant analysis with resampling; deformation-based morphometry; magnetic resonance imaging; schizophrenia

Abstract

In the original language

This paper presents a new data-driven classification pipeline for discriminating two groups of individuals based on the medical images of their brain. The algorithm combines deformation-based morphometry and penalised linear discriminant analysis with resampling. The method is based on sparse representation of the original brain images using deformation logarithms reflecting the differences in the brain in comparison to the normal template anatomy. The sparse data enables efficient data reduction and classification via the penalised linear discriminant analysis with resampling. The classification accuracy obtained in an experiment with magnetic resonance brain images of first episode schizophrenia patients and healthy controls is comparable to the related state-of-the-art studies.

Links

NT13359, research and development project

Name: Pokročilé metody rozpoznávání MR obrazů mozku pro podporu diagnostiky neuropsychiatrických poruch

Investor: Ministry of Health of the CR

Cite

JANOUŠOVÁ, Eva; Daniel SCHWARZ; Giovanni MONTANA and Tomáš KAŠPÁREK. Brain Image Classification Based on Automated Morphometry and Penalised Linear Discriminant Analysis with Resampling. Online. In Maria Ganzha, Leszek Maciaszek, Marcin Paprzycki. Proceedings of the 2015 Federated Conference on Computer Science and Information Systems. Warsaw, Los Alamitos: Polskie Towarzystwo Informatyczne, IEEE, 2015, p. 263-268. ISBN 978-83-60810-66-8. Available from: https://doi.org/10.15439/2015F147.

@inproceedings{1352750,
   author = {Janoušová, Eva and Schwarz, Daniel and Montana, Giovanni and Kašpárek, Tomáš},
   address = {Warsaw, Los Alamitos},
   booktitle = {Proceedings of the 2015 Federated Conference on Computer Science and Information Systems},
   doi = {https://doi.org/10.15439/2015F147},
   editor = {Maria Ganzha, Leszek Maciaszek, Marcin Paprzycki},
   keywords = {pattern recognition; computational neuroanatomy; classification; penalized linear discriminant analysis with resampling; deformation-based morphometry; magnetic resonance imaging; schizophrenia},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Warsaw, Los Alamitos},
   isbn = {978-83-60810-66-8},
   pages = {263-268},
   publisher = {Polskie Towarzystwo Informatyczne, IEEE},
   title = {Brain Image Classification Based on Automated Morphometry and Penalised Linear Discriminant Analysis with Resampling},
   url = {https://fedcsis.org/proceedings/2015/pliks/147.pdf},
   year = {2015}
}

TY  - CONF
ID  - 1352750
AU  - Janoušová, Eva - Schwarz, Daniel - Montana, Giovanni - Kašpárek, Tomáš
PY  - 2015
TI  - Brain Image Classification Based on Automated Morphometry and Penalised Linear Discriminant Analysis with Resampling
PB  - Polskie Towarzystwo Informatyczne, IEEE
CY  - Warsaw, Los Alamitos
SN  - 9788360810668
KW  - pattern recognition
KW  - computational neuroanatomy
KW  - classification
KW  - penalized linear discriminant analysis with resampling
KW  - deformation-based morphometry
KW  - magnetic resonance imaging
KW  - schizophrenia
UR  - https://fedcsis.org/proceedings/2015/pliks/147.pdf
N2  - This paper presents a new data-driven classification pipeline for discriminating two groups of individuals based on the medical images of their brain. The algorithm combines deformation-based morphometry and penalised linear discriminant analysis with resampling. The method is based on sparse representation of the original brain images using deformation logarithms reflecting the differences in the brain in comparison to the normal template anatomy. The sparse data enables efficient data reduction and classification via the penalised linear discriminant analysis with resampling. The classification accuracy obtained in an experiment with magnetic resonance brain images of first episode schizophrenia patients and healthy controls is comparable to the related state-of-the-art studies.
ER  -

JANOUŠOVÁ, Eva; Daniel SCHWARZ; Giovanni MONTANA and Tomáš KAŠPÁREK. Brain Image Classification Based on Automated Morphometry and Penalised Linear Discriminant Analysis with Resampling. Online. In Maria Ganzha, Leszek Maciaszek, Marcin Paprzycki. \textit{Proceedings of the 2015 Federated Conference on Computer Science and Information Systems}. Warsaw, Los Alamitos: Polskie Towarzystwo Informatyczne, IEEE, 2015, p.~263-268. ISBN~978-83-60810-66-8. Available from: https://doi.org/10.15439/2015F147.

Přehled o publikaci