JANOUŠOVÁ, Eva, Daniel SCHWARZ a Tomáš KAŠPÁREK. Combining various types of classifiers and features extracted from magnetic resonance imaging data in schizophrenia recognition. Psychiatry Research: Neuroimaging. CLARE: ELSEVIER IRELAND LTD, 2015, roč. 232, č. 3, s. 237-249. ISSN 0925-4927. doi:10.1016/j.pscychresns.2015.03.004.
Další formáty:   BibTeX LaTeX RIS
Základní údaje
Originální název Combining various types of classifiers and features extracted from magnetic resonance imaging data in schizophrenia recognition
Autoři JANOUŠOVÁ, Eva (203 Česká republika, garant, domácí), Daniel SCHWARZ (203 Česká republika, domácí) a Tomáš KAŠPÁREK (203 Česká republika, domácí).
Vydání Psychiatry Research: Neuroimaging, CLARE, ELSEVIER IRELAND LTD, 2015, 0925-4927.
Další údaje
Originální jazyk angličtina
Typ výsledku Článek v odborném periodiku
Obor 30000 3. Medical and Health Sciences
Stát vydavatele Irsko
Utajení není předmětem státního či obchodního tajemství
Impakt faktor Impact factor: 2.477
Kód RIV RIV/00216224:14110/15:00087443
Organizační jednotka Lékařská fakulta
Doi http://dx.doi.org/10.1016/j.pscychresns.2015.03.004
UT WoS 000354552900006
Klíčová slova anglicky Computational neuroanatomy; Classification; Intersubject principal component analysis (isPCA); Modified maximum uncertainty linear; discriminant analysis (mMLDA); Centroid method; Average linkage
Štítky EL OK
Příznaky Mezinárodní význam, Recenzováno
Změnil Změnila: Soňa Böhmová, učo 232884. Změněno: 9. 7. 2015 14:50.
Anotace
We investigated a combination of three classification algorithms, namely the modified maximum uncertainty linear discriminant analysis (mMLDA), the centroid method, and the average linkage, with three types of features extracted from three-dimensional T1-weighted magnetic resonance (MR) brain images, specifically MR intensities, grey matter densities, and local deformations for distinguishing 49 first episode schizophrenia male patients from 49 healthy male subjects. The feature sets were reduced using intersubject principal component analysis before classification. By combining the classifiers, we were able to obtain slightly improved results when compared with single classifiers. The best classification performance (81.6% accuracy, 75.5% sensitivity, and 87.8% specificity) was significantly better than classification by chance. We also showed that classifiers based on features calculated using more computation-intensive image preprocessing perform better; mMLDA with classification boundary calculated as weighted mean discriminative scores of the groups had improved sensitivity but similar accuracy compared to the original MLDA; reducing a number of eigenvectors during data reduction did not always lead to higher classification accuracy, since noise as well as the signal important for classification were removed. Our findings provide important information for schizophrenia research and may improve accuracy of computer aided diagnostics of neuropsychiatric diseases.
Návaznosti
NT13359, projekt VaVNázev: Pokročilé metody rozpoznávání MR obrazů mozku pro podporu diagnostiky neuropsychiatrických poruch
Investor: Ministerstvo zdravotnictví ČR, Zapojení prvku umělé inteligence do plánování efektivního operačního programu
VytisknoutZobrazeno: 4. 10. 2022 16:44