Clustering of fMRI data: the elusive optimal number of clusters
Model-free methods are widely used for the processing of brain fMRI data collected under natural stimulations, sleep, or rest. Among them is the popular fuzzy c-mean algorithm, commonly combined with cluster validity (CV) indices to identify the ‘true’ number of clusters (components), in an unsuperv...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2018-10-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/5416.pdf |
| _version_ | 1797418873104891904 |
|---|---|
| author | Mohamed L. Seghier |
| author_facet | Mohamed L. Seghier |
| author_sort | Mohamed L. Seghier |
| collection | DOAJ |
| description | Model-free methods are widely used for the processing of brain fMRI data collected under natural stimulations, sleep, or rest. Among them is the popular fuzzy c-mean algorithm, commonly combined with cluster validity (CV) indices to identify the ‘true’ number of clusters (components), in an unsupervised way. CV indices may however reveal different optimal c-partitions for the same fMRI data, and their effectiveness can be hindered by the high data dimensionality, the limited signal-to-noise ratio, the small proportion of relevant voxels, and the presence of artefacts or outliers. Here, the author investigated the behaviour of seven robust CV indices. A new CV index that incorporates both compactness and separation measures is also introduced. Using both artificial and real fMRI data, the findings highlight the importance of looking at the behavior of different compactness and separation measures, defined here as building blocks of CV indices, to depict a full description of the data structure, in particular when no agreement is found between CV indices. Overall, for fMRI, it makes sense to relax the assumption that only one unique c-partition exists, and appreciate that different c-partitions (with different optimal numbers of clusters) can be useful explanations of the data, given the hierarchical organization of many brain networks. |
| first_indexed | 2024-03-09T06:39:18Z |
| format | Article |
| id | doaj.art-70bf2349f3f54ff7b878f7c17a0d7d7e |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-09T06:39:18Z |
| publishDate | 2018-10-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-70bf2349f3f54ff7b878f7c17a0d7d7e2023-12-03T10:53:04ZengPeerJ Inc.PeerJ2167-83592018-10-016e541610.7717/peerj.5416Clustering of fMRI data: the elusive optimal number of clustersMohamed L. Seghier0Cognitive Neuroimaging Unit, Emirates College for Advanced Education, Abu Dhabi, United Arab EmiratesModel-free methods are widely used for the processing of brain fMRI data collected under natural stimulations, sleep, or rest. Among them is the popular fuzzy c-mean algorithm, commonly combined with cluster validity (CV) indices to identify the ‘true’ number of clusters (components), in an unsupervised way. CV indices may however reveal different optimal c-partitions for the same fMRI data, and their effectiveness can be hindered by the high data dimensionality, the limited signal-to-noise ratio, the small proportion of relevant voxels, and the presence of artefacts or outliers. Here, the author investigated the behaviour of seven robust CV indices. A new CV index that incorporates both compactness and separation measures is also introduced. Using both artificial and real fMRI data, the findings highlight the importance of looking at the behavior of different compactness and separation measures, defined here as building blocks of CV indices, to depict a full description of the data structure, in particular when no agreement is found between CV indices. Overall, for fMRI, it makes sense to relax the assumption that only one unique c-partition exists, and appreciate that different c-partitions (with different optimal numbers of clusters) can be useful explanations of the data, given the hierarchical organization of many brain networks.https://peerj.com/articles/5416.pdfFunctional MRIData-driven analysisUnsupervised fuzzy clusteringBrain networksCluster validityFuzzy compactness and separation |
| spellingShingle | Mohamed L. Seghier Clustering of fMRI data: the elusive optimal number of clusters PeerJ Functional MRI Data-driven analysis Unsupervised fuzzy clustering Brain networks Cluster validity Fuzzy compactness and separation |
| title | Clustering of fMRI data: the elusive optimal number of clusters |
| title_full | Clustering of fMRI data: the elusive optimal number of clusters |
| title_fullStr | Clustering of fMRI data: the elusive optimal number of clusters |
| title_full_unstemmed | Clustering of fMRI data: the elusive optimal number of clusters |
| title_short | Clustering of fMRI data: the elusive optimal number of clusters |
| title_sort | clustering of fmri data the elusive optimal number of clusters |
| topic | Functional MRI Data-driven analysis Unsupervised fuzzy clustering Brain networks Cluster validity Fuzzy compactness and separation |
| url | https://peerj.com/articles/5416.pdf |
| work_keys_str_mv | AT mohamedlseghier clusteringoffmridatatheelusiveoptimalnumberofclusters |