Spatiotemporal clustering of fMRI time series in the spectral domain

Meyer, François G.; Chinrungrueng, Jatuporn

doi:10.1016/j.media.2004.07.002

Cited by 27 publications

(22 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…11(d)-(f) are 0.8402, 0.8279, and 0.7451 with2,3,and4samplepointsdelay,respectively.Thesethreeclusters are all specified as meaningful clusters. These facts mean that the BOLD dynamic responses of various local brain regions are different in both response pattern and delay, and this information may be very helpful in further detail study of the brain information process, such as the spatio-temporal connectivity of the fMRI data [17]. Apparently, such a further detailed segregation ability of HC is a distinct priority over the SPM.…”

Section: Detailed Results Of the Actual Visual Fmri Experiments Datamentioning

confidence: 99%

“…Comparing various clustering methods, we found that the definition of distance between two time series is the determinant factor of a clustering analysis [9]- [12], [17], [18]. There are two main shortcomings of clustering methods, one is the stability when the noise level is high; the second is a resource problem because a fMRI slice of 128 128 voxels with 80 temporal points will produce a clustering matrix of 16 384 16 384.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Integrated Neighborhood Correlation and Hierarchical Clustering Approach of Functional MRI

Chen

Yuan

Yao

et al. 2006

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Abstract-Clustering analysis is a promising data-driven method for the analysis of functional magnetic resonance imaging (fMRI) time series, however, the huge computation load makes it difficult for practical use. In this paper, neighborhood correlation (NC) and hierarchical clustering (HC) methods are integrated as a new approach where fMRI data are processed first by NC to get a preliminary image of brain activations, and then by HC to remove some noises. In HC, to better use spatial and temporal information in fMRI data, a new spatio-temporal measure is introduced. A simulation study and an application to visual fMRI data show that the brain activations can be effectively detected and that different response patterns can be discriminated. These results suggest that the proposed new integrated approach could be useful in detecting weak fMRI signals.

show abstract

Section: Detailed Results Of the Actual Visual Fmri Experiments Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Integrated Neighborhood Correlation and Hierarchical Clustering Approach of Functional MRI

Chen

Yuan

Yao

et al. 2006

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

“…This section describes a form of artificial data used by Francois et al [11]. In general, fMRI signal is a stochastic process.…”

Section: A Artificial Datamentioning

confidence: 99%

“…It has been used as an exploratory data analysis technique in fMRI time series. In this case, several approaches based on c-means have emerged [10] such as spatiotemporal clustering analysis of fMRI data [11] and Fuzzy clustering analysis (FCA) [12]. Therefore, hierarchical clustering analysis (HCA) [13] has been gained its place with its ability to produce connectivity map in fMRI data.…”

Section: Introductionmentioning

confidence: 99%

fMRI Data Analysis Using Dempster-Shafer Method with Estimating Voxel Selectivity by Belief Measure

Abdelouahab¹,

Moussaoui²,

Abdelmalik³

2016

ijacsa

View full text Add to dashboard Cite

Abstract-In the functional Magnetic Resonance Imaging (fMRI) data analysis, detecting the activated voxels is a challenging research problem where the existing methods have shown some limits. We propose a new method wherein brain mapping is done based on Dempster-Shafer theory of evidence (DS) that is a useful method in uncertain representation analysis. Dempster-Shafer allows finding the activated regions by checking the activated voxels in fMRI data. The activated brain areas related to a given stimulus are detected by using a belief measure as a metric for evaluating activated voxels. To test the performance of the proposed method, artificial and real auditory data have been employed. The comparison of the introduced method with the t-test and GLM method has clearly shown that the proposed method can provide a higher correct detection of activated voxels.

show abstract

“…Data clustering is a well-known technique in various areas of computer science and related domains. Although data mining can be considered as the main origin of clustering, but it is vastly used in other fields of study such as bio informatics, energy studies, machine learning, networking, pattern recognition and therefore a lot of research works has been done in this area [10]- [13]. From the very beginning researchers were dealing with clustering algorithms in order to handle their complexity and computational cost and consequently increase scalability and speed.…”

Section: Introductionmentioning

confidence: 99%

Big Data Clustering: A Review

Shirkhorshidi

Aghabozorgi

Wah

et al. 2014

Lecture Notes in Computer Science

171

View full text Add to dashboard Cite

Abstract.Clustering is an essential data mining and tool for analyzing big data. There are difficulties for applying clustering techniques to big data duo to new challenges that are raised with big data. As Big Data is referring to terabytes and petabytes of data and clustering algorithms are come with high computational costs, the question is how to cope with this problem and how to deploy clustering techniques to big data and get the results in a reasonable time. This study is aimed to review the trend and progress of clustering algorithms to cope with big data challenges from very first proposed algorithms until today's novel solutions. The algorithms and the targeted challenges for producing improved clustering algorithms are introduced and analyzed, and afterward the possible future path for more advanced algorithms is illuminated based on today's available technologies and frameworks.

show abstract

Spatiotemporal clustering of fMRI time series in the spectral domain

Cited by 27 publications

References 34 publications

An Integrated Neighborhood Correlation and Hierarchical Clustering Approach of Functional MRI

An Integrated Neighborhood Correlation and Hierarchical Clustering Approach of Functional MRI

fMRI Data Analysis Using Dempster-Shafer Method with Estimating Voxel Selectivity by Belief Measure

Big Data Clustering: A Review

Contact Info

Product

Resources

About