Wavelet Imaging Features for Classification of First-Episode Schizophrenia

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14110%2F19%3A00120073" target="_blank" >RIV/00216224:14110/19:00120073 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007%2F978-3-030-23762-2_25" target="_blank" >https://link.springer.com/chapter/10.1007%2F978-3-030-23762-2_25</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-23762-2_25" target="_blank" >10.1007/978-3-030-23762-2_25</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Wavelet Imaging Features for Classification of First-Episode Schizophrenia

Popis výsledku v původním jazyce

Recently, multiple attempts have been made to support computer diagnostics of neuropsychiatric disorders, using neuroimaging data and machine learning methods. This paper deals with the design and implementation of an algorithm for the analysis and classification of magnetic resonance imaging data for the purpose of computer-aided diagnosis of schizophrenia. Features for classification are first extracted using two morphometric methods: voxel-based morphometry (VBM) and deformation-based morphometry (DBM); and then transformed into a wavelet domain by discrete wavelet transform (DWT) with various numbers of decomposition levels. The number of features is reduced by thresholding and subsequent selection by: Fisher’s Discrimination Ratio, Bhattacharyya Distance, and Variances – a metric proposed in the literature recently. Support Vector Machine with a linear kernel is used here as a classifier. The evaluation strategy is based on leave-one-out cross-validation. The highest classification accuracy – 73.08% – was achieved with 1000 features extracted by VBM and DWT at four decomposition levels and selected by Fisher’s Discrimination Ratio and Bhattacharyya distance. In the case of DBM features, the classifier achieved the highest accuracy of 72.12% with 5000 discriminating features, five decomposition levels and the use of Fisher’s Discrimination Ratio.

Název v anglickém jazyce

Wavelet Imaging Features for Classification of First-Episode Schizophrenia

Popis výsledku anglicky

Recently, multiple attempts have been made to support computer diagnostics of neuropsychiatric disorders, using neuroimaging data and machine learning methods. This paper deals with the design and implementation of an algorithm for the analysis and classification of magnetic resonance imaging data for the purpose of computer-aided diagnosis of schizophrenia. Features for classification are first extracted using two morphometric methods: voxel-based morphometry (VBM) and deformation-based morphometry (DBM); and then transformed into a wavelet domain by discrete wavelet transform (DWT) with various numbers of decomposition levels. The number of features is reduced by thresholding and subsequent selection by: Fisher’s Discrimination Ratio, Bhattacharyya Distance, and Variances – a metric proposed in the literature recently. Support Vector Machine with a linear kernel is used here as a classifier. The evaluation strategy is based on leave-one-out cross-validation. The highest classification accuracy – 73.08% – was achieved with 1000 features extracted by VBM and DWT at four decomposition levels and selected by Fisher’s Discrimination Ratio and Bhattacharyya distance. In the case of DBM features, the classifier achieved the highest accuracy of 72.12% with 5000 discriminating features, five decomposition levels and the use of Fisher’s Discrimination Ratio.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/NV17-33136A" target="_blank" >NV17-33136A: Neurominer: odhalování skrytých vzorů v datech ze zobrazování mozku</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Information Technology in Biomedicine, ITIB 2019, Kamień Śląski, Poland, 18-20 June, 2019

ISBN

9783030237615

ISSN

2194-5357

e-ISSN

2194-5365

Počet stran výsledku

12

Strana od-do

280-291

Název nakladatele

Springer

Místo vydání

Kamień Śląski, Poland

Místo konání akce

Kamien Slaski

Datum konání akce

17. 6. 2019

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

000618044200025