Wavelet Features for Recognition of First Episode of
Schizophrenia from MRI Brain Images

J 2014

Wavelet Features for Recognition of First Episode of Schizophrenia from MRI Brain Images

DLUHOŠ, Petr, Daniel SCHWARZ a Tomáš KAŠPÁREK

Základní údaje

Originální název

Wavelet Features for Recognition of First Episode of Schizophrenia from MRI Brain Images

Autoři

DLUHOŠ, Petr (203 Česká republika, domácí), Daniel SCHWARZ (203 Česká republika, garant, domácí) a Tomáš KAŠPÁREK (203 Česká republika, domácí)

Vydání

Radioengineering, SPOLECNOST PRO RADIOELEKTRONICKE INZENYRSTVI, 2014, 1210-2512

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

30000 3. Medical and Health Sciences

Stát vydavatele

Česká republika

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 0.653

Kód RIV

RIV/00216224:14110/14:00075409

Organizační jednotka

Lékařská fakulta

UT WoS

000334729400033

Klíčová slova anglicky

schizophrenia; machine learning; neuroimaging; classification; wavelet transform; MRI

Štítky

EL OK, podil

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 24. 9. 2014 11:01, Ing. Mgr. Věra Pospíšilíková

Anotace

V originále

Machine learning methods are increasingly used in various fields of medicine, contributing to early diagnosis and better quality of care. These outputs are particularly desirable in case of neuropsychiatric disorders, such as schizophrenia, due to the inherent potential for creating a new gold standard in the diagnosis and differentiation of particular disorders. This paper presents a scheme for automated classification from magnetic resonance images based on multiresolution representation in the wavelet domain. Implementation of the proposed algorithm, utilizing support vector machines classifier, is introduced and tested on a dataset containing 104 patients with first episode schizophrenia and healthy volunteers. Optimal parameters of different phases of the algorithm are sought and the quality of classification is estimated by robust cross validation techniques. Values of accuracy, sensitivity and specificity over 71% are achieved.

Návaznosti

ED3.2.00/08.0144, projekt VaV

Název: CERIT Scientific Cloud

NT13359, projekt VaV

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

Investor: Ministerstvo zdravotnictví ČR, Zapojení prvku umělé inteligence do plánování efektivního operačního programu

Přiložené soubory

EL_Schwarz_Wavelet_2.pdf

Požádat o autorskou verzi souboru

Citovat

DLUHOŠ, Petr, Daniel SCHWARZ a Tomáš KAŠPÁREK. Wavelet Features for Recognition of First Episode of Schizophrenia from MRI Brain Images. Radioengineering. SPOLECNOST PRO RADIOELEKTRONICKE INZENYRSTVI, 2014, roč. 23, č. 1, s. 274-281. ISSN 1210-2512.

@article{1181736,
   author = {Dluhoš, Petr and Schwarz, Daniel and Kašpárek, Tomáš},
   article_number = {1},
   keywords = {schizophrenia; machine learning; neuroimaging; classification; wavelet transform; MRI},
   language = {eng},
   issn = {1210-2512},
   journal = {Radioengineering},
   title = {Wavelet Features for Recognition of First Episode of Schizophrenia from MRI Brain Images},
   url = {http://www.radioeng.cz/fulltexts/2014/14_01_0274_0281.pdf},
   volume = {23},
   year = {2014}
}

TY  - JOUR
ID  - 1181736
AU  - Dluhoš, Petr - Schwarz, Daniel - Kašpárek, Tomáš
PY  - 2014
TI  - Wavelet Features for Recognition of First Episode of Schizophrenia from MRI Brain Images
JF  - Radioengineering
VL  - 23
IS  - 1
SP  - 274-281
EP  - 274-281
PB  - SPOLECNOST PRO RADIOELEKTRONICKE INZENYRSTVI
SN  - 12102512
KW  - schizophrenia
KW  - machine learning
KW  - neuroimaging
KW  - classification
KW  - wavelet transform
KW  - MRI
UR  - http://www.radioeng.cz/fulltexts/2014/14_01_0274_0281.pdf
N2  - Machine learning methods are increasingly used in various fields of medicine, contributing to early diagnosis and better quality of care. These outputs are particularly desirable in case of neuropsychiatric disorders, such as schizophrenia, due to the inherent potential for creating a new gold standard in the diagnosis and differentiation of particular disorders. This paper presents a scheme for automated classification from magnetic resonance images based on multiresolution representation in the wavelet domain. Implementation of the proposed algorithm, utilizing support vector machines classifier, is introduced and tested on a dataset containing 104 patients with first episode schizophrenia and healthy volunteers. Optimal parameters of different phases of the algorithm are sought and the quality of classification is estimated by robust cross validation techniques. Values of accuracy, sensitivity and specificity over 71% are achieved.
ER  -

DLUHOŠ, Petr, Daniel SCHWARZ a Tomáš KAŠPÁREK. Wavelet Features for Recognition of First Episode of Schizophrenia from MRI Brain Images. \textit{Radioengineering}. SPOLECNOST PRO RADIOELEKTRONICKE INZENYRSTVI, 2014, roč.~23, č.~1, s.~274-281. ISSN~1210-2512.

Podrobný výpis o publikaci