Which fMRI clustering gives good brain parcellations?

By Bertrand Thirion, Gaël Varoquaux, Elvis Dohmatob, Jean-Baptiste Poline. Frontiers in Neuroscience, 2014

347 citations recorded by the source corpus.

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 the cortical surface. While predefined brain atlases do not adapt to the signal in the individual subject 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.

Subfields: Cognitive Neuroscience, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/66b8c20550c5c248cbc127885608876cff501809

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Deep neural network with weight sparsity control and pre-training extracts hierarchical features and enhances classification performance: Evidence from whole-brain resting-state functional connectivity patterns of schizophrenia (2015, neutral): “Alternative options to functionally divide brain regions are available, such as using a variance-minimizing approach based on hierarchical agglomerative clustering or a spatially constrained spectral clustering approach (Craddock et al., 2012; Thirion et al., 2014).”
Classification and Prediction of Brain Disorders Using Functional Connectivity: Promising but Challenging (2018, background): “Considerable research work (Thirion et al., 2014; Glasser et al., 2016) has attempted to delineate a parcellation of brain by employing information of multiple modalities of imaging, however, inconsistencies still exists.”
Human brain mapping: A systematic comparison of parcellation methods for the human cerebral cortex (2017, methodology): “, 2011), and many more as extensively reviewed in (Eickhoff et al., 2015; Thirion et al., 2014; de Reus and van den Heuvel, 2013).”
Deriving reproducible biomarkers from multi‐site resting‐state data: An Autism‐based example (2016, methodology): “We explored two clustering methods: K-Means , a technique to cluster fMRI time series [44, 45], which is a top-down approach minimizing cluster-level variance; and Ward’s clustering , which also minimizes a variance criterion using hierarchical agglomeration.”
Benchmarking functional connectome‐based predictive models for resting‐state fMRI (2019, positive): “We consider four popular datadriven methods to extract brain ROIs from intrinsic brain activity (Yeo et al., 2011; Kahnt et al., 2012; Thirion et al., 2014; Calhoun et al., 2001; Beckmann and Smith, 2004; Abraham et al., 2013).”