Meeting Banner
Abstract #3492

Perfusion MRI in stroke as a regional spatio-temporal texture

Noëlie Debs1, Mathilde Giacalone1, Pejman Rasti2, Tae-Hee Cho1, Carole Frindel1, and David Rousseau2

1CREATIS UMR 5220, U1206, University of Lyon, Lyon, France, 2LARIS, UMR INRA IRHS, Université d'Angers, Angers, France

We tackle the clinical issue of predicting the final lesion in stroke from early perfusion magnetic resonance imaging. We demonstrate here the value of exploiting directly the raw perfusion data by encoding the local environment of each voxel as a spatio-temporal texture. As an illustration for this approach, the textures are characterized with Haralick coefficients computed on co-occurrence matrices and a standard support vector machine classifier is used for the classification. This simple machine learning classification scheme demonstrates good results while working on raw perfusion data.

This abstract and the presentation materials are available to members only; a login is required.

Join Here