sign in
english version rss feed

hal-00717990, version 2

Learning to rank from medical imaging data

Fabian Pedregosa (, http://fseoane.net) 12, Elodie Cauvet 3, Gaël Varoquaux (, http://gael-varoquaux.info) 24, Christophe Pallier 23, Bertrand Thirion (, http://parietal.saclay.inria.fr/Members/bertrand-thirion) 2, Alexandre Gramfort (, http://alexandre.gramfort.net/) 24

Third International Workshop on Machine Learning in Medical Imaging - MLMI 2012 (2012)

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.

  • Domain : Computer Science/Machine Learning
  • Keywords : fMRI – supervised learning – decoding – ranking
  • Available versions :  v1 (2012-07-16) v2 (2012-09-30)
 
  • hal-00717990, version 2
  • oai:hal.inria.fr:hal-00717990
  • From: 
  • Submitted on: Sunday, 30 September 2012 14:11:59
  • Updated on: Sunday, 1 September 2013 22:19:50
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...
all articles on CCSd database...