Learning to rank from medical imaging data
This work addresses the need for better prediction of ordered clinical variables in medical imaging, though it is incremental as it adapts existing ranking methods to this domain.
The paper tackles the problem of predicting ordered clinical scores from medical images by using a ranking model instead of standard regression or classification, and shows that this approach yields higher prediction accuracy on fMRI datasets.
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.