A quantitative comparison of functional MRI cluster analysis

Dimitriadou, Evgenia; Barth, Markus; Windischberger, Christian; Hornik, Kurt; Moser, Ewald

doi:10.1016/j.artmed.2004.01.010

Cited by 90 publications

(68 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As for DM techniques applied to MRI data, several work has been done, especially for MRI clustering, as in [16][17][18] to mention some proposals. Most proposed methods are based on the K-Means algorithm [7].…”

Section: Mri Data Analysismentioning

confidence: 99%

“…Most proposed methods are based on the K-Means algorithm [7]. In [16], a quantitative comparison of MRI cluster analysis techniques has been performed and described. With respect to the proposed evaluation, results clearly shown that methods based on the neural gas algorithm [23] and on the K-Means one perform significantly better than all the other methods.…”

Section: Mri Data Analysismentioning

confidence: 99%

See 1 more Smart Citation

Visual MRI: Merging information visualization and non-parametric clustering techniques for MRI dataset analysis

Castellani

Cristani

Combi

et al. 2008

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

SummaryObjective. This paper presents Visual MRI, an innovative tool for the magnetic resonance imaging (MRI) analysis of tumoral tissues. The main goal of the analysis is to separate each magnetic resonance image in meaningful clusters, highlighting zones which are more probably related with the cancer evolution. Such non-invasive analysis serves to address novel cancer treatments, resulting in a less destabilizing and more effective type of therapy than the chemotherapy-based ones. The advancements brought by Visual MRI are two: first, it is an integration of effective infor-

show abstract

Section: Mri Data Analysismentioning

confidence: 99%

Section: Mri Data Analysismentioning

confidence: 99%

Visual MRI: Merging information visualization and non-parametric clustering techniques for MRI dataset analysis

Castellani

Cristani

Combi

et al. 2008

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

show abstract

“…Os métodos não-paramétricos são baseados em geral na classificação voxel a voxel das séries temporais normalizadas utilizando métodos não-supervisionados, tais como os mapas de k-médias, os mapas auto-organizados e os mapas fuzzy cmédias (Chen et al, 2006;Dimitriadou et al, 2004;Windischberger et al, 2003;Somorjai et al, 2002).…”

Section: Métodos De Detecção Não-paramétricos Multiespectraisunclassified

Análise Monoespectral De Imagens Funcionais De Ressonância Magnética Utilizando Mapas Auto-Organizados De Kohonen

Santos¹,

Souza²,

Silva³

et al. 2016

Anais Do 8. Congresso Brasileiro De Redes Neurais

View full text Add to dashboard Cite

Abstract-One of the major challenges at the field of cognitive sciences is mapping the regions of the brain responsible for the motor and behavioral functions. The acquisition of functional magnetic resonance images is an important non-invasive technique to study the neural activity in the human brain. This work presents a new approach for the detection of activated brain regions: the composition and analysis of synthetic multi and monospectral images using statistical methods and proposing non-parametrical methods based on Kohonen self-organized networks.Keywords-Functional magnetic resonance imaging, Detection of neural activity, Pattern recognition, Selforganized Kohonen maps.Resumo-Um dos maiores desafios atuais no campo das ciências cognitivasé mapear as regiões do cérebro responsáveis pelas funções motoras e comportamentais. A aquisição de imagens funcionais de ressonância magnéticá e uma técnica não-invasiva fundamental para o estudo da atividade neural do cérebro humano. Este trabalho apresenta uma nova abordagem para a detecção de regiões cerebrais ativadas: a composição e análise de imagens multiespectrais e monoespectrais sintéticas utilizando métodos estatísticos e propondo métodos não-paramétricos baseados em mapas auto-organizados de Kohonen.Keywords-Ressonância magnética funcional, Detecção de atividade neural, Reconhecimento de padrões, Mapas auto-organizados de Kohonen.

show abstract

“…Functional images were acquired from six normal volunteers using a T 2 * -weighted gradient-echo single-shot EPI sequence (TR ϭ 3 seconds, TE ϭ 50 msec, FOV ϭ 250 ϫ 250 ϫ 100 mm 3 , matrix size ϭ 64 ϫ 64 ϫ 20) on a 1.5-Tesla Siemens Vision MRI scanner. The subjects performed a finger-to-thumb opposition task.…”

Section: Finger Tapping Fmri Datamentioning

confidence: 99%

“…However, the structure of noise is not known and still is an open problem (2). Also, the number of artifacts and their characteristics cannot be predicted or controlled (3). Therefore, validity of model-based statistical methods depends on the extent to which the data satisfy their underlying assumptions.…”

mentioning

confidence: 99%

Functional magnetic resonance imaging activation detection: Fuzzy cluster analysis in wavelet and multiwavelet domains

Jahanian

Soltanian-Zadeh

Hossein-Zadeh

2005

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Purpose: To present novel feature spaces, based on multiscale decompositions obtained by scalar wavelet and multiwavelet transforms, to remedy problems associated with high dimension of functional magnetic resonance imaging (fMRI) time series (when they are used directly in clustering algorithms) and their poor signal-to-noise ratio (SNR) that limits accurate classification of fMRI time series according to their activation contents. Materials and Methods:Using randomization, the proposed method finds wavelet/multiwavelet coefficients that represent the activation content of fMRI time series and combines them to define new feature spaces. Using simulated and experimental fMRI data sets, the proposed feature spaces are compared to the cross-correlation (CC) feature space and their performances are evaluated. In these studies, the false positive detection rate is controlled using randomization. To compare different methods, several points of the receiver operating characteristics (ROC) curves, using simulated data, are estimated and compared. Results:The proposed features suppress the effects of confounding signals and improve activation detection sensitivity. Experimental results show improved sensitivity and robustness of the proposed method compared to the conventional CC analysis. Conclusion:More accurate and sensitive activation detection can be achieved using the proposed feature spaces compared to CC feature space. Multiwavelet features show superior detection sensitivity compared to the scalar wavelet features.

show abstract

A quantitative comparison of functional MRI cluster analysis

Cited by 90 publications

References 38 publications

Visual MRI: Merging information visualization and non-parametric clustering techniques for MRI dataset analysis

Visual MRI: Merging information visualization and non-parametric clustering techniques for MRI dataset analysis

Análise Monoespectral De Imagens Funcionais De Ressonância Magnética Utilizando Mapas Auto-Organizados De Kohonen

Functional magnetic resonance imaging activation detection: Fuzzy cluster analysis in wavelet and multiwavelet domains

Contact Info

Product

Resources

About