DLUHOŠ, Petr, Daniel SCHWARZ, Wiepke CAHN, Neeltje van HAREN, René KAHN, Filip ŠPANIEL, Jiří HORÁČEK, Tomáš KAŠPÁREK a Hugo SCHNACK. Multi-center machine learning in imaging psychiatry: A meta-model approach. NeuroImage, San Diego: Academic Press Inc Elsevier Science, 2017, roč. 155, 15 July 2017, s. 10-24. ISSN 1053-8119. doi:10.1016/j.neuroimage.2017.03.027.
Další formáty:   BibTeX LaTeX RIS
Základní údaje
Originální název Multi-center machine learning in imaging psychiatry: A meta-model approach
Autoři DLUHOŠ, Petr (203 Česká republika, garant, domácí), Daniel SCHWARZ (203 Česká republika, domácí), Wiepke CAHN (528 Nizozemsko), Neeltje van HAREN (528 Nizozemsko), René KAHN (528 Nizozemsko), Filip ŠPANIEL (203 Česká republika), Jiří HORÁČEK (203 Česká republika), Tomáš KAŠPÁREK (203 Česká republika, domácí) a Hugo SCHNACK (528 Nizozemsko).
Vydání NeuroImage, San Diego, Academic Press Inc Elsevier Science, 2017, 1053-8119.
Další údaje
Originální jazyk angličtina
Typ výsledku Článek v odborném periodiku
Obor 30103 Neurosciences
Stát vydavatele Spojené státy americké
Utajení není předmětem státního či obchodního tajemství
Impakt faktor Impact factor: 5.426
Kód RIV RIV/00216224:14110/17:00097266
Organizační jednotka Lékařská fakulta
Doi http://dx.doi.org/10.1016/j.neuroimage.2017.03.027
UT WoS 000405460900002
Klíčová slova anglicky classification; combining models; first-episode schizophrenia; Machine learning; multi-center; prediction; support vector machines (SVM)
Štítky EL OK, podil
Příznaky Mezinárodní význam, Recenzováno
Změnil Změnila: Soňa Böhmová, učo 232884. Změněno: 20. 3. 2018 17:37.
Anotace
One of the biggest problems in automated diagnosis of psychiatric disorders from medical images is the lack of sufficiently large samples for training. Sample size is especially important in the case of highly heterogeneous disorders such as schizophrenia, where machine learning models built on relatively low numbers of subjects may suffer from poor generalizability. Via multicenter studies and consortium initiatives researchers have tried to solve this problem by combining data sets from multiple sites. The necessary sharing of (raw) data is, however, often hindered by legal and ethical issues. Moreover, in the case of very large samples, the computational complexity might become too large. The solution to this problem could be distributed learning. In this paper we investigated the possibility to create a meta-model by combining support vector machines (SVM) classifiers trained on the local datasets, without the need for sharing medical images or any other personal data. Validation was done in a 4-center setup comprising of 480 first-episode schizophrenia patients and healthy controls in total. We built SVM models to separate patients from controls based on three different kinds of imaging features derived from structural MRI scans, and compared models built on the joint multicenter data to the meta-models. The results showed that the combined meta-model had high similarity to the model built on all data pooled together and comparable classification performance on all three imaging features. Both similarity and performance was superior to that of the local models. We conclude that combining models is thus a viable alternative that facilitates data sharing and creating bigger and more informative models.
Návaznosti
LQ1601, projekt VaVNázev: CEITEC 2020 (Akronym: CEITEC2020)
Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, Národní program udržitelnosti II (LQ)
VytisknoutZobrazeno: 4. 4. 2020 09:12