Population shrinkage of covariance (PoSCE) for better individual brain functional-connectivity estimation

Abstract : Estimating covariances from functional Magnetic Resonance Imaging at rest (r-fMRI) can quantify interactions between brain regions. Also known as brain functional connectivity, it reflects inter-subject variations in behavior and cognition, and characterizes neuropathologies. Yet, with noisy and short time-series, as in r-fMRI, covariance estimation is challenging and calls for penalization, as with shrinkage approaches. We introduce population shrinkage of covariance estimator (PoSCE) : a covariance estimator that integrates prior knowledge of covariance distribution over a large population, leading to a non-isotropic shrinkage. The shrinkage is tailored to the Riemannian geometry of symmetric positive definite matrices. It is coupled with a probabilistic modeling of the individual and population covariance distributions. Experiments on two large r-fMRI datasets (HCP n=815, Cam-CAN n=626) show that PoSCE has a better bias-variance trade-off than existing covariance estimates: this estimator relates better functional-connectivity measures to cognition while capturing well intra-subject functional connectivity.
Complete list of metadatas

Cited literature [41 references]  Display  Hide  Download

https://hal.inria.fr/hal-02068389
Contributor : Mehdi Rahim <>
Submitted on : Thursday, March 14, 2019 - 8:17:13 PM
Last modification on : Thursday, March 21, 2019 - 3:23:03 PM
Long-term archiving on : Saturday, June 15, 2019 - 7:21:21 PM

File

MEDIA_PoSCe_2019.pdf
Files produced by the author(s)

Identifiers

Citation

Mehdi Rahim, Bertrand Thirion, Gaël Varoquaux. Population shrinkage of covariance (PoSCE) for better individual brain functional-connectivity estimation. Medical Image Analysis, Elsevier, 2019, ⟨10.1016/j.media.2019.03.001⟩. ⟨hal-02068389⟩

Share

Metrics

Record views

176

Files downloads

330