Functional Magnetic Resonance Imaging data augmentation through conditional ICA - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Functional Magnetic Resonance Imaging data augmentation through conditional ICA

Résumé

Advances in computational cognitive neuroimaging research are related to the availability of large amounts of labeled brain imaging data, but such data are scarce and expensive to generate. While powerful data generation mechanisms, such as Generative Adversarial Networks (GANs), have been designed in the last decade for computer vision, such improvements have not yet carried over to brain imaging. A likely reason is that GANs training is ill-suited to the noisy, highdimensional and small-sample data available in functional neuroimaging. In this paper, we introduce Conditional Independent Components Analysis (Conditional ICA): a fast functional Magnetic Resonance Imaging (fMRI) data augmentation technique, that leverages abundant restingstate data to create images by sampling from an ICA decomposition. We then propose a mechanism to condition the generator on classes observed with few samples. We first show that the generative mechanism is successful at synthesizing data indistinguishable from observations, and that it yields gains in classification accuracy in brain decoding problems. In particular it outperforms GANs while being much easier to optimize and interpret. Lastly, Conditional ICA enhances classification accuracy in eight datasets without further parameters tuning.
Fichier principal
Vignette du fichier
MICCAI21_TAJINI.pdf (2.71 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03284313 , version 1 (12-07-2021)

Identifiants

  • HAL Id : hal-03284313 , version 1

Citer

Badr Tajini, Hugo Richard, Bertrand Thirion. Functional Magnetic Resonance Imaging data augmentation through conditional ICA. MICCAI 2021 - 24th International Conference on Medical Image Computing and Computer Assisted Intervention, Sep 2021, Strasbourg, France. ⟨hal-03284313⟩
101 Consultations
150 Téléchargements

Partager

Gmail Facebook X LinkedIn More