Brain Morphometry Methods for Feature Extraction in Random
Subspace Ensemble Neural Network Classification of
First-Episode Schizophrenia

J 2019

Brain Morphometry Methods for Feature Extraction in Random Subspace Ensemble Neural Network Classification of First-Episode Schizophrenia

VYŠKOVSKÝ, Roman, Daniel SCHWARZ and Tomáš KAŠPÁREK

Basic information

Original name

Brain Morphometry Methods for Feature Extraction in Random Subspace Ensemble Neural Network Classification of First-Episode Schizophrenia

Authors

VYŠKOVSKÝ, Roman (203 Czech Republic, guarantor, belonging to the institution), Daniel SCHWARZ (203 Czech Republic, belonging to the institution) and Tomáš KAŠPÁREK (203 Czech Republic, belonging to the institution)

Edition

Neural Computation, CAMBRIDGE, MIT Press, 2019, 0899-7667

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

30103 Neurosciences

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 2.505

RIV identification code

RIV/00216224:14110/19:00108524

Organization unit

Faculty of Medicine

DOI

http://dx.doi.org/10.1162/neco_a_01180

UT WoS

000476941800004

Keywords in English

brain morphometry; schizophrenia; magnetic resonance imaging

Abstract

V originále

Machine learning (ML) is a growing field that provides tools for automatic pattern recognition. The neuroimaging community currently tries to take advantage of ML in order to develop an auxiliary diagnostic tool for schizophrenia diagnostics. In this letter, we present a classification framework based on features extracted from magnetic resonance imaging (MRI) data using two automatic whole-brain morphometry methods: voxel-based (VBM) and deformation-based morphometry (DBM). The framework employs a random subspace ensemble-based artificial neural network classifier-in particular, a multilayer perceptron (MLP). The framework was tested on data from first-episode schizophrenia patients and healthy controls. The experiments differed in terms of feature extraction methods, using VBM, DBM, and a combination of both morphometry methods. Thus, features of different types were available for model adaptation. As we expected, the combination of features increased the MLP classification accuracy up to 73.12%-an improvement of 5% versus MLP-based only on VBM or DBM features. To further verify the findings, other comparisons using support vector machines in place of MLPs were made within the framework. However, it cannot be concluded that any classifier was better than another.

Links

NV17-33136A, research and development project

Name: Neurominer: odhalování skrytých vzorů v datech ze zobrazování mozku

Citovat

VYŠKOVSKÝ, Roman, Daniel SCHWARZ and Tomáš KAŠPÁREK. Brain Morphometry Methods for Feature Extraction in Random Subspace Ensemble Neural Network Classification of First-Episode Schizophrenia. Neural Computation. CAMBRIDGE: MIT Press, 2019, vol. 31, No 5, p. 897-918. ISSN 0899-7667. Available from: https://dx.doi.org/10.1162/neco_a_01180.

@article{1569736,
   author = {Vyškovský, Roman and Schwarz, Daniel and Kašpárek, Tomáš},
   article_location = {CAMBRIDGE},
   article_number = {5},
   doi = {http://dx.doi.org/10.1162/neco_a_01180},
   keywords = {brain morphometry; schizophrenia; magnetic resonance imaging},
   language = {eng},
   issn = {0899-7667},
   journal = {Neural Computation},
   title = {Brain Morphometry Methods for Feature Extraction in Random Subspace Ensemble Neural Network Classification of First-Episode Schizophrenia},
   url = {http://dx.doi.org/10.1162/neco_a_01180},
   volume = {31},
   year = {2019}
}

TY  - JOUR
ID  - 1569736
AU  - Vyškovský, Roman - Schwarz, Daniel - Kašpárek, Tomáš
PY  - 2019
TI  - Brain Morphometry Methods for Feature Extraction in Random Subspace Ensemble Neural Network Classification of First-Episode Schizophrenia
JF  - Neural Computation
VL  - 31
IS  - 5
SP  - 897-918
EP  - 897-918
PB  - MIT Press
SN  - 08997667
KW  - brain morphometry
KW  - schizophrenia
KW  - magnetic resonance imaging
UR  - http://dx.doi.org/10.1162/neco_a_01180
L2  - http://dx.doi.org/10.1162/neco_a_01180
N2  - Machine learning (ML) is a growing field that provides tools for automatic pattern recognition. The neuroimaging community currently tries to take advantage of ML in order to develop an auxiliary diagnostic tool for schizophrenia diagnostics. In this letter, we present a classification framework based on features extracted from magnetic resonance imaging (MRI) data using two automatic whole-brain morphometry methods: voxel-based (VBM) and deformation-based morphometry (DBM). The framework employs a random subspace ensemble-based artificial neural network classifier-in particular, a multilayer perceptron (MLP). The framework was tested on data from first-episode schizophrenia patients and healthy controls. The experiments differed in terms of feature extraction methods, using VBM, DBM, and a combination of both morphometry methods. Thus, features of different types were available for model adaptation. As we expected, the combination of features increased the MLP classification accuracy up to 73.12%-an improvement of 5% versus MLP-based only on VBM or DBM features. To further verify the findings, other comparisons using support vector machines in place of MLPs were made within the framework. However, it cannot be concluded that any classifier was better than another.
ER  -

VYŠKOVSKÝ, Roman, Daniel SCHWARZ and Tomáš KAŠPÁREK. Brain Morphometry Methods for Feature Extraction in Random Subspace Ensemble Neural Network Classification of First-Episode Schizophrenia. \textit{Neural Computation}. CAMBRIDGE: MIT Press, 2019, vol.~31, No~5, p.~897-918. ISSN~0899-7667. Available from: https://dx.doi.org/10.1162/neco\_{}a\_{}01180.

Detailed Information on Publication Record