Determining the Number of States in Dynamic Functional Connectivity Using Cluster Validity Indexes

Overview

Journal J Neurosci Methods

Specialty Neurology

Date 2020 Feb 29

PMID 32109439

Citations 22

Authors

Victor M Vergara

Mustafa Salman

Anees Abrol

Flor A Espinoza

Vince D Calhoun

Affiliations

Soon will be listed here.

Abstract

Background: Clustering analysis is employed in brain dynamic functional connectivity (dFC) to cluster the data into a set of dynamic states. These states correspond to different patterns of functional connectivity that iterate through time. Although several cluster validity index (CVI) methods to determine the best clustering partition exists, the appropriateness of methods to apply in the case of dynamic connectivity analysis has not been determined.

New Method: Currently employed indexes do not provide a crisp answer on what is the best number of clusters. In addition, there is a lack of CVI testing in the context of dFC data. This work tests a comprehensive set of twenty four cluster validity indexes applied to addiction data and suggest the best ones for clustering dynamic functional connectivity.

Results: Out of the twenty four considered CVIs, Davies-Bouldin and Ray-Turi were the most suitable methods to find the number of clusters in both simulation and real data. The solution for these two CVIs is to find a local minimum critical point, which can be automated using computational algorithms.

Comparison With Existing Methods: Elbow-Criterion, Silhouette and GAP-Statistic methods have been widely used in dFC studies. These methods are included among the tested CVIs where the performances of all twenty four CVIs are compared.

Conclusions: Davies-Bouldin and Ray-Turi CVIs showed better performance among a group of twenty four CVIs in determining the number of clusters to use in dFC analysis.

Citing Articles

Cluster validity indices for automatic clustering: A comprehensive review.

Ikotun A, Habyarimana F, Ezugwu A Heliyon. 2025; 11(2):e41953.

PMID: 39897868 PMC: 11787482. DOI: 10.1016/j.heliyon.2025.e41953.

Human brain state dynamics are highly reproducible and associated with neural and behavioral features.

Lee K, Ji J, Fonteneau C, Berkovitch L, Rahmati M, Pan L PLoS Biol. 2024; 22(9):e3002808.

PMID: 39316635 PMC: 11421804. DOI: 10.1371/journal.pbio.3002808.

Aberrant brain dynamics in major depressive disorder during working memory task.

Sun F, Liu Z, Yang J, Fan Z, Wang F, Yang J Eur Arch Psychiatry Clin Neurosci. 2024; .

PMID: 38976050 DOI: 10.1007/s00406-024-01854-4.

More reliable biomarkers and more accurate prediction for mental disorders using a label-noise filtering-based dimensional prediction method.

Xing Y, van Erp T, Pearlson G, Kochunov P, Calhoun V, Du Y iScience. 2024; 27(3):109319.

PMID: 38482500 PMC: 10933544. DOI: 10.1016/j.isci.2024.109319.

Revisiting delusion subtypes in schizophrenia based on their underlying structures.

van der Vaart A, Ma Y, Chiappelli J, Bruce H, Kvarta M, Warner A J Psychiatr Res. 2024; 171:75-83.

PMID: 38246028 PMC: 10923062. DOI: 10.1016/j.jpsychires.2023.12.025.

References

Davies D, Bouldin D . A cluster separation measure. IEEE Trans Pattern Anal Mach Intell. 2011; 1(2):224-7. View

Calhoun V, Miller R, Pearlson G, Adali T . The chronnectome: time-varying connectivity networks as the next frontier in fMRI data discovery. Neuron. 2014; 84(2):262-74. PMC: 4372723. DOI: 10.1016/j.neuron.2014.10.015. View

MARRIOTT F . Practical problems in a method of cluster analysis. Biometrics. 1971; 27(3):501-14. View

Lindquist M, Xu Y, Nebel M, Caffo B . Evaluating dynamic bivariate correlations in resting-state fMRI: a comparison study and a new approach. Neuroimage. 2014; 101:531-46. PMC: 4165690. DOI: 10.1016/j.neuroimage.2014.06.052. View

Zalesky A, Breakspear M . Towards a statistical test for functional connectivity dynamics. Neuroimage. 2015; 114:466-70. DOI: 10.1016/j.neuroimage.2015.03.047. View

Figueroa C, Cabral J, Mocking R, Rapuano K, van Hartevelt T, Deco G . Altered ability to access a clinically relevant control network in patients remitted from major depressive disorder. Hum Brain Mapp. 2019; 40(9):2771-2786. PMC: 6865599. DOI: 10.1002/hbm.24559. View

Agosta F, Galantucci S, Filippi M . Advanced magnetic resonance imaging of neurodegenerative diseases. Neurol Sci. 2016; 38(1):41-51. DOI: 10.1007/s10072-016-2764-x. View

Leonardi N, Van De Ville D . On spurious and real fluctuations of dynamic functional connectivity during rest. Neuroimage. 2014; 104:430-6. DOI: 10.1016/j.neuroimage.2014.09.007. View

Zalesky A, Fornito A, Cocchi L, Gollo L, Breakspear M . Time-resolved resting-state brain networks. Proc Natl Acad Sci U S A. 2014; 111(28):10341-6. PMC: 4104861. DOI: 10.1073/pnas.1400181111. View

10.

Ma S, Correa N, Li X, Eichele T, Calhoun V, Adali T . Automatic identification of functional clusters in FMRI data using spatial dependence. IEEE Trans Biomed Eng. 2011; 58(12):3406-17. PMC: 3222740. DOI: 10.1109/TBME.2011.2167149. View

11.

Espinoza F, Liu J, Ciarochi J, Turner J, Vergara V, Caprihan A . Dynamic functional network connectivity in Huntington's disease and its associations with motor and cognitive measures. Hum Brain Mapp. 2019; 40(6):1955-1968. PMC: 6865767. DOI: 10.1002/hbm.24504. View

12.

Allen E, Damaraju E, Plis S, Erhardt E, Eichele T, Calhoun V . Tracking whole-brain connectivity dynamics in the resting state. Cereb Cortex. 2012; 24(3):663-76. PMC: 3920766. DOI: 10.1093/cercor/bhs352. View

13.

Yeo B, Krienen F, Sepulcre J, Sabuncu M, Lashkari D, Hollinshead M . The organization of the human cerebral cortex estimated by intrinsic functional connectivity. J Neurophysiol. 2011; 106(3):1125-65. PMC: 3174820. DOI: 10.1152/jn.00338.2011. View

14.

Vergara V, Weiland B, Hutchison K, Calhoun V . The Impact of Combinations of Alcohol, Nicotine, and Cannabis on Dynamic Brain Connectivity. Neuropsychopharmacology. 2017; 43(4):877-890. PMC: 5809800. DOI: 10.1038/npp.2017.280. View

15.

Schulz D, Huston J . The sliding window correlation procedure for detecting hidden correlations: existence of behavioral subgroups illustrated with aged rats. J Neurosci Methods. 2002; 121(2):129-37. DOI: 10.1016/s0165-0270(02)00224-8. View

16.

Himberg J, Hyvarinen A, Esposito F . Validating the independent components of neuroimaging time series via clustering and visualization. Neuroimage. 2004; 22(3):1214-22. DOI: 10.1016/j.neuroimage.2004.03.027. View

17.

Edwards A, Cavalli-Sforza L . A METHOD FOR CLUSTER ANALYSIS. Biometrics. 1965; 21:362-75. View

18.

Vergara V, Mayer A, Kiehl K, Calhoun V . Dynamic functional network connectivity discriminates mild traumatic brain injury through machine learning. Neuroimage Clin. 2018; 19:30-37. PMC: 6051314. DOI: 10.1016/j.nicl.2018.03.017. View

19.

Cordes D, Haughton V, Arfanakis K, Carew J, Turski P, Moritz C . Frequencies contributing to functional connectivity in the cerebral cortex in "resting-state" data. AJNR Am J Neuroradiol. 2001; 22(7):1326-33. PMC: 7975218. View

20.

Damaraju E, Allen E, Belger A, Ford J, McEwen S, Mathalon D . Dynamic functional connectivity analysis reveals transient states of dysconnectivity in schizophrenia. Neuroimage Clin. 2014; 5:298-308. PMC: 4141977. DOI: 10.1016/j.nicl.2014.07.003. View