Learning to rank from medical imaging data

Fabian Pedregosa; Elodie Cauvet; Gaël Varoquaux; Christophe Pallier; Bertrand Thirion; Alexandre Gramfort

Learning to rank from medical imaging data

Fabian Pedregosa ^{1, 2} Elodie Cauvet ³ Gaël Varoquaux ^{1, 4} Christophe Pallier ^{1, 3} Bertrand Thirion ¹ Alexandre Gramfort ^{1, 4}

1 PARIETAL - Modelling brain structure, function and variability based on high-field MRI data

Inria Saclay - Ile de France

2 SIERRA - Statistical Machine Learning and Parsimony

DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548

3 NEUROSPIN - Service NEUROSPIN

4 LNAO - Laboratoire de Neuroimagerie Assistée par Ordinateur

Abstract : Medical images can be used to predict a clinical score coding for the severity of a disease, a pain level or the complexity of a cognitive task. In all these cases, the predicted variable has a natural order. While a standard classifier discards this information, we would like to take it into account in order to improve prediction performance. A standard linear regression does model such information, however the linearity assumption is likely not be satisfied when predicting from pixel intensities in an image. In this paper we address these modeling challenges with a supervised learning procedure where the model aims to order or rank images. We use a linear model for its robustness in high dimension and its possible interpretation. We show on simulations and two fMRI datasets that this approach is able to predict the correct ordering on pairs of images, yielding higher prediction accuracy than standard regression and multiclass classification techniques.

Keywords : fMRI supervised learning decoding ranking

Type de document :

Communication dans un congrès

Third International Workshop on Machine Learning in Medical Imaging - MLMI 2012, Oct 2012, Nice, France. 2012

Domaine :

Informatique [cs] / Apprentissage [cs.LG]

Liste complète des métadonnées

Littérature citée [17 références] Voir Masquer Télécharger

https://hal.inria.fr/hal-00717990
Contributeur : Fabian Pedregosa <>
Soumis le : dimanche 30 septembre 2012 - 14:11:59
Dernière modification le : mardi 17 avril 2018 - 11:32:09
Document(s) archivé(s) le : vendredi 16 décembre 2016 - 18:17:12

paper.pdf

Fichiers produits par l'(les) auteur(s)

Learning to rank from medical imaging data

Fichiers

Identifiants

Collections

Citation

Exporter

Métriques

2648

382

Contact

Learning to rank from medical imaging data

Fichiers

Identifiants

Collections

Citation

Exporter

Partager

Métriques

2648

382

Contact