Computer-aided Diagnostics of Schizophrenia: Comparison of
Different Feature Extraction Methods

J 2017

Computer-aided Diagnostics of Schizophrenia: Comparison of Different Feature Extraction Methods

KŮS, Radomír a Daniel SCHWARZ

Základní údaje

Originální název

Computer-aided Diagnostics of Schizophrenia: Comparison of Different Feature Extraction Methods

Autoři

KŮS, Radomír a Daniel SCHWARZ

Vydání

Acta Polytechnica Hungarica, BUDAPEST, Budapest TECH, 2017, 1785-8860

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Maďarsko

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 0.909

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14110/17:00113794

Organizační jednotka

Lékařská fakulta

Klíčová slova anglicky

feature extraction; computer-aided diagnosis; schizophrenia; brain morphometry; voxel-based morphometry; deformation-based morphometry; magnetic resonance imaging; classification; machine learning

Štítky

rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 27. 4. 2020 09:27, Mgr. Tereza Miškechová

Anotace

V originále

Receiving an early diagnosis of schizophrenia is a crucial step towards its treatment. However, in current thinking, the diagnosis is based on time-consuming criteria, burdened with subjectivity. Hence, objective and more reliable therapeutic tests are desirable for the clinical practice of Psychiatry. Since schizophrenia is characterized by progressive brain volume changes during the course of the disease, many studies have recently turned attention to machine learning and brain morphometric techniques serving as tools for computer-aided diagnosis of schizophrenia based on neuroimaging data. In our study, the methodology is applied to distinguish between 52 first-episode schizophrenia patients and 52 healthy volunteers on the basis of T1-weighted magnetic resonance images of their brains preprocessed by the means of voxel-based and deformation-based morphometry. The proposed classification schemes vary in the feature extraction and selection steps. Namely, Mann-Whitney testing is implemented as a simple univariate approach playing the role of a comparator to multivariate methods such as inter-subject PCA, the K-SVD algorithm, and pattern-based morphometry. The highest classification accuracy, 70%, is reached with the pattern-based morphometry technique. The study points out the difference between univariate and multivariate approaches towards neuroimaging data. Additionally, the contrast between feature extraction capabilities of voxel-based and deformation-based morphometry is demonstrated.

Citovat

KŮS, Radomír a Daniel SCHWARZ. Computer-aided Diagnostics of Schizophrenia: Comparison of Different Feature Extraction Methods. Acta Polytechnica Hungarica. BUDAPEST: Budapest TECH, 2017, roč. 14, č. 5, s. 181-196. ISSN 1785-8860. Dostupné z: https://doi.org/10.12700/APH.14.5.2017.5.12.

@article{1649758,
   author = {Kůs, Radomír and Schwarz, Daniel},
   article_location = {BUDAPEST},
   article_number = {5},
   doi = {https://doi.org/10.12700/APH.14.5.2017.5.12},
   keywords = {feature extraction; computer-aided diagnosis; schizophrenia; brain morphometry; voxel-based morphometry; deformation-based morphometry; magnetic resonance imaging; classification; machine learning},
   language = {eng},
   issn = {1785-8860},
   journal = {Acta Polytechnica Hungarica},
   title = {Computer-aided Diagnostics of Schizophrenia: Comparison of Different Feature Extraction Methods},
   url = {http://acta.uni-obuda.hu/Radomir_Daniel_76.pdf},
   volume = {14},
   year = {2017}
}

TY  - JOUR
ID  - 1649758
AU  - Kůs, Radomír - Schwarz, Daniel
PY  - 2017
TI  - Computer-aided Diagnostics of Schizophrenia: Comparison of Different Feature Extraction Methods
JF  - Acta Polytechnica Hungarica
VL  - 14
IS  - 5
SP  - 181-196
EP  - 181-196
PB  - Budapest TECH
SN  - 17858860
KW  - feature extraction
KW  - computer-aided diagnosis
KW  - schizophrenia
KW  - brain morphometry
KW  - voxel-based morphometry
KW  - deformation-based morphometry
KW  - magnetic resonance imaging
KW  - classification
KW  - machine learning
UR  - http://acta.uni-obuda.hu/Radomir_Daniel_76.pdf
L2  - http://acta.uni-obuda.hu/Radomir_Daniel_76.pdf
N2  - Receiving an early diagnosis of schizophrenia is a crucial step towards its treatment. However, in current thinking, the diagnosis is based on time-consuming criteria, burdened with subjectivity. Hence, objective and more reliable therapeutic tests are desirable for the clinical practice of Psychiatry. Since schizophrenia is characterized by progressive brain volume changes during the course of the disease, many studies have recently turned attention to machine learning and brain morphometric techniques serving as tools for computer-aided diagnosis of schizophrenia based on neuroimaging data. In our study, the methodology is applied to distinguish between 52 first-episode schizophrenia patients and 52 healthy volunteers on the basis of T1-weighted magnetic resonance images of their brains preprocessed by the means of voxel-based and deformation-based morphometry. The proposed classification schemes vary in the feature extraction and selection steps. Namely, Mann-Whitney testing is implemented as a simple univariate approach playing the role of a comparator to multivariate methods such as inter-subject PCA, the K-SVD algorithm, and pattern-based morphometry. The highest classification accuracy, 70%, is reached with the pattern-based morphometry technique. The study points out the difference between univariate and multivariate approaches towards neuroimaging data. Additionally, the contrast between feature extraction capabilities of voxel-based and deformation-based morphometry is demonstrated.
ER  -

KŮS, Radomír a Daniel SCHWARZ. Computer-aided Diagnostics of Schizophrenia: Comparison of Different Feature Extraction Methods. \textit{Acta Polytechnica Hungarica}. BUDAPEST: Budapest TECH, 2017, roč.~14, č.~5, s.~181-196. ISSN~1785-8860. Dostupné z: https://doi.org/10.12700/APH.14.5.2017.5.12.

Přehled o publikaci