Electromagnetic neural source imaging under sparsity constraints with SURE-based hyperparameter tuning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Electromagnetic neural source imaging under sparsity constraints with SURE-based hyperparameter tuning

Abstract

Estimators based on non-convex sparsity-promoting penalties were shown to yield state-of-the-art solutions to the magneto-/electroencephalography (M/EEG) brain source localization problem. In this paper we tackle the model selection problem of these estimators: we propose to use a proxy of the Stein's Unbiased Risk Estimator (SURE) to automatically select their regularization parameters. The effectiveness of the method is demonstrated on realistic simulations and 30 subjects from the Cam-CAN dataset. To our knowledge, this is the first time that sparsity promoting estimators are automatically calibrated at such a scale. Results show that the proposed SURE approach outperforms cross-validation strategies and state-of-the-art Bayesian statistics methods both computationally and statistically.
Fichier principal
Vignette du fichier
submission_camera_ready.pdf (881.09 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03418092 , version 1 (06-11-2021)

Identifiers

  • HAL Id : hal-03418092 , version 1

Cite

Pierre-Antoine Bannier, Quentin Bertrand, Joseph Salmon, Alexandre Gramfort. Electromagnetic neural source imaging under sparsity constraints with SURE-based hyperparameter tuning. Medical imaging meets NeurIPS 2021, Dec 2021, Sydney, Australia. ⟨hal-03418092⟩
130 View
125 Download

Share

Gmail Mastodon Facebook X LinkedIn More