Spatially regularized SVM for the detection of brain areas associated with stroke outcome

Authors:
Rémi Cuingnet;Charlotte Rosso;Stéphane Lehéricy;Didier Dormont;Habib Benali;Yves Samson;Olivier Colliot
Affiliations:
Université Pierre et Marie Curie-Paris 6, CNRS UMR Inserm Centre de Recherche de l'Institut Cerveau-Moelle, Paris, France and Inserm, UMR, LIF, Paris, France;Université Pierre et Marie Curie-Paris 6, CNRS UMR Inserm, Centre de Recherche de l'Institut Cerveau-Moelle, Paris, France and AP-HP, Urgences Cérébro-Vasculaires, Paris, France;Univ. Pierre et Marie Curie-Paris 6, CNRS UMR Inserm, Centre de Recherche de l'Institut Cerveau-Moelle, Paris, France and AP-HP, Urgences Cérébro-Vasculaires, Pitié-Salpêtri ...;Université Pierre et Marie Curie-Paris 6, CNRS UMR Inserm, Centre de Recherche de l'Institut Cerveau-Moelle, Paris, France and Université Pierre et Marie Curie-Paris, Centre de Recherche ...;Inserm, UMR, LIF, Paris, France;Université Pierre et Marie Curie-Paris 6, CNRS, UMR Inserm, Centre de Recherche de l'Institut Cerveau-Moelle, Paris, France and AP-HP, Urgences Cérébro-Vasculaires, Paris, France;Université Pierre et Marie Curie-Paris 6, CNRS UMR Inserm, Centre de Recherche de l'Institut Cerveau-Moelle, Paris, France
Venue:
MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part I
Year:
2010

Citing 2
Cited 1

The nature of statistical learning theory

The nature of statistical learning theory
Diffusion Kernels on Graphs and Other Discrete Input Spaces

ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning

Anatomical regularization on statistical manifolds for the classification of patients with Alzheimer's disease

MLMI'11 Proceedings of the Second international conference on Machine learning in medical imaging

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper introduces a new method to detect group differences in brain images based on spatially regularized support vector machines (SVM). First, we propose to spatially regularize the SVM using a graph encoding the voxels' proximity. Two examples of regularization graphs are provided. Significant differences between two populations are detected using statistical tests on the margins of the SVM. We first tested our method on synthetic examples. We then applied it to 72 stroke patients to detect brain areas associated with motor outcome at 90 days, based on diffusion-weighted images acquired at the acute stage (one day delay). The proposed method showed that poor motor outcome is associated to changes in the corticospinal bundle and white matter tracts originating from the premotor cortex. Standard mass univariate analyses failed to detect any difference.