Skip to Main content Skip to Navigation
New interface
Journal articles

Which fMRI clustering gives good brain parcellations?

Abstract : Analysis and interpretation of neuroimaging data often require one to divide the brain into a number of regions, or parcels, with homogeneous characteristics, be these regions defined in the brain volume or on on the cortical surface. While predefined brain atlases do not adapt to the signal in the individual subjects images, parcellation approaches use brain activity (e.g. found in some functional contrasts of interest) and clustering techniques to define regions with some degree of signal homogeneity. In this work, we address the question of which clustering technique is appropriate and how to optimize the corresponding model. We use two principled criteria: goodness of fit (accuracy), and reproducibility of the parcellation across bootstrap samples. We study these criteria on both simulated and two task-based functional Magnetic Resonance Imaging datasets for the Ward, spectral and K-means clustering algorithms. We show that in general Ward's clustering performs better than alternative methods with regard to reproducibility and accuracy and that the two criteria diverge regarding the preferred models (reproducibility leading to more conservative solutions), thus deferring the practical decision to a higher level alternative, namely the choice of a trade-off between accuracy and stability.
Complete list of metadata

Cited literature [1 references]  Display  Hide  Download
Contributor : Bertrand Thirion Connect in order to contact the contributor
Submitted on : Wednesday, June 25, 2014 - 11:16:58 PM
Last modification on : Monday, July 25, 2022 - 3:44:44 AM
Long-term archiving on: : Thursday, September 25, 2014 - 11:49:18 AM


Files produced by the author(s)



Bertrand Thirion, Gaël Varoquaux, Elvis Dohmatob, Jean-Baptiste Poline. Which fMRI clustering gives good brain parcellations?. Frontiers in Neuroscience, 2014, 8 (167), pp.13. ⟨10.3389/fnins.2014.00167⟩. ⟨hal-01015172⟩



Record views


Files downloads