Multilevel Modeling with Structured Penalties for Classification from Imaging Genetics data

Pascal Lu 1 Olivier Colliot 1
1 ARAMIS - Algorithms, models and methods for images and signals of the human brain
UPMC - Université Pierre et Marie Curie - Paris 6, ICM - Institut du Cerveau et de la Moëlle Epinière = Brain and Spine Institute, Inria de Paris
Abstract : In this paper, we propose a framework for automatic classification of patients from multimodal genetic and brain imaging data by optimally combining them. Additive models with unadapted penalties (such as the classical group lasso penalty or L_1-multiple kernel learning) treat all modalities in the same manner and can result in undesirable elimination of specific modalities when their contributions are unbalanced. To overcome this limitation, we introduce a multilevel model that combines imaging and genetics and that considers joint effects between these two modalities for diagnosis prediction. Furthermore, we propose a framework allowing to combine several penalties taking into account the structure of the different types of data, such as a group lasso penalty over the genetic modality and a L_2-penalty on imaging modalities. Finally , we propose a fast optimization algorithm, based on a proximal gradient method. The model has been evaluated on genetic (single nucleotide polymorphisms-SNP) and imaging (anatomical MRI measures) data from the ADNI database, and compared to additive models. It exhibits good performances in AD diagnosis; and at the same time, reveals relationships between genes, brain regions and the disease status.
Type de document :
Communication dans un congrès
3rd MICCAI Workshop on Imaging Genetics (MICGen 2017), Sep 2017, Québec City, Canada. Springer, Lecture Notes in Computer Science, 1 (21), pp.230-240, 2017, Graphs in Biomedical Image Analysis, Computational Anatomy and Imaging Genetics. 〈http://www.springer.com/us/book/9783319676746〉
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01578441
Contributeur : Pascal Lu <>
Soumis le : mardi 29 août 2017 - 11:19:08
Dernière modification le : jeudi 11 janvier 2018 - 06:28:02

Fichier

10.1007:978-3-319-67675-3 21.p...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01578441, version 1

Collections

Citation

Pascal Lu, Olivier Colliot. Multilevel Modeling with Structured Penalties for Classification from Imaging Genetics data. 3rd MICCAI Workshop on Imaging Genetics (MICGen 2017), Sep 2017, Québec City, Canada. Springer, Lecture Notes in Computer Science, 1 (21), pp.230-240, 2017, Graphs in Biomedical Image Analysis, Computational Anatomy and Imaging Genetics. 〈http://www.springer.com/us/book/9783319676746〉. 〈hal-01578441〉

Partager

Métriques

Consultations de la notice

220

Téléchargements de fichiers

19