Detecting Outliers in High-Dimensional Neuroimaging Datasets with Robust Covariance Estimators

Virgile Fritsch 1, 2, * Gaël Varoquaux 1, 2, 3 Benjamin Thyreau 2 Jean-Baptiste Poline 1, 2 Bertrand Thirion 1
* Auteur correspondant
1 PARIETAL - Modelling brain structure, function and variability based on high-field MRI data
NEUROSPIN - Service NEUROSPIN, Inria Saclay - Ile de France
2 LNAO - Laboratoire de Neuroimagerie Assistée par Ordinateur
3 UNICOG-U992 - Neuroimagerie cognitive
Abstract : Medical imaging datasets often contain deviant observations, the so-called outliers, due to acquisition or preprocessing artifacts or resulting from large intrinsic inter-subject variability. These can undermine the statistical procedures used in group studies as the latter assume that the cohorts are composed of homogeneous samples with anatomical or functional features clustered around a central mode. The effects of outlying subjects can be mitigated by detecting and removing them with explicit statistical control. With the emergence of large medical imaging databases, exhaustive data screening is no longer possible, and automated outlier detection methods are currently gaining interest. The datasets used in medical imaging are often high-dimensional and strongly correlated. The outlier detection procedure should therefore rely on high-dimensional statistical multivariate models. However, state-of-the-art procedures are not well-suited for such high-dimensional settings. In this work, we introduce regularization in the MCD framework and investigate different regularization schemes. We carry out extensive simulations to provide backing for practical choices in absence of ground truth knowledge. We demonstrate on functional neuroimaging datasets that outlier detection can be performed with small sample sizes and improves group studies.
keyword : outlier detection minimum covariance determinant regularization robust estimation neuroimaging fMRI high-dimension
Type de document :
Article dans une revue
Medical Image Analysis, Elsevier, 2012, 16, pp.1359-1370. 〈10.1016/j.media.2012.05.002〉
Liste complète des métadonnées

Littérature citée [38 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/hal-00701225
Contributeur : Virgile Fritsch <>
Soumis le : jeudi 24 mai 2012 - 19:35:30
Dernière modification le : vendredi 22 juin 2018 - 01:20:18
Document(s) archivé(s) le : samedi 25 août 2012 - 02:45:24

Fichiers

media_outliers.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

CEA | INRIA | CEA-DRF | JOLIOT | NEUROSPIN

Citation

Virgile Fritsch, Gaël Varoquaux, Benjamin Thyreau, Jean-Baptiste Poline, Bertrand Thirion. Detecting Outliers in High-Dimensional Neuroimaging Datasets with Robust Covariance Estimators. Medical Image Analysis, Elsevier, 2012, 16, pp.1359-1370. 〈10.1016/j.media.2012.05.002〉. 〈hal-00701225〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

607

Téléchargements de fichiers

919

Contact


archive-ouverte@inria.fr