Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Pitfalls in the clustering of neuroimage data and improvements by global optimization strategies
Autore:
Moller, U; Ligges, M; Grunling, C; Georgiewa, P; Kaiser, WA; Witte, H; Blanz, B;
Indirizzi:
Univ Jena, Clin Child & Adolescents Psychiat, D-6900 Jena, Germany Univ Jena Jena Germany D-6900 Adolescents Psychiat, D-6900 Jena, Germany Univ Jena, Inst Diagnost & Intervent Radiol, D-6900 Jena, Germany Univ Jena Jena Germany D-6900 t & Intervent Radiol, D-6900 Jena, Germany Univ Jena, Inst Med Stat Comp Sci & Documentat, D-6900 Jena, Germany Univ Jena Jena Germany D-6900 omp Sci & Documentat, D-6900 Jena, Germany
Titolo Testata:
NEUROIMAGE
fascicolo: 1, volume: 14, anno: 2001,
parte:, 1
pagine: 206 - 218
SICI:
1053-8119(200107)14:1<206:PITCON>2.0.ZU;2-U
Fonte:
ISI
Lingua:
ENG
Soggetto:
MR-IMAGES; TIME-SERIES; ACTIVATION; FMRI; CLASSIFICATION; SEGMENTATION; SEARCH;
Keywords:
clustering; vector quantization; global optimization; functional MRI; neuroimaging;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Life Sciences
Citazioni:
33
Recensione:
Indirizzi per estratti:
Indirizzo: Moller, U Univ Jena, Clin Child & Adolescents Psychiat, D-6900 Jena, Germany Univ Jena Jena Germany D-6900 s Psychiat, D-6900 Jena, Germany
Citazione:
U. Moller et al., "Pitfalls in the clustering of neuroimage data and improvements by global optimization strategies", NEUROIMAGE, 14(1), 2001, pp. 206-218

Abstract

In this paper, we examined three vector quantization (VQ) methods used forthe unsupervised classification (clustering) of functional magnetic resonance imaging (fMRI) data. Classification means that each brain volume element (voxel), according to a given scanning raster, was assigned to one group of voxels based on similarity of the fMRI signal patterns. It was investigated how the VQ methods can isolate a cluster that describes the region involved in a particular brain function. As an example, word processing was stimulated by a word comparison task. VQ analysis methodology was verified using simulated fMRI response patterns. It was demonstrated in detail that VQ based on global rather than local optimization of the objective function yielded a higher performance. Performance was measured in statistically relevant series of VQ attempts using several indices for goodness, reliability and efficiency of VQ solutions. Furthermore, it was shown that a poor local optimization caused either an underestimation or an overestimation of the stimulus-induced brain activation. However, this was not observed if the cluster analysis was based upon a global optimization strategy. (C) 2001 Academic Press.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 27/01/20 alle ore 01:47:47