Simultaneous Manifold Learning and Clustering: Grouping White Matter Fiber Tracts Using a Volumetric White Matter Atlas

Demian Wassermann (1) , Rachid Deriche (1)

1 ODYSSEE - Computer and biological vision

We propose a new clustering algorithm. This algorithm performs clustering and manifold learning simultaneously by using a graph-theoretical approach to manifold learning. We apply this algorithm in order to cluster white matter fiber tracts obtained from Diffusion Tensor MRI (DT-MRI) through streamline tractography. Our algorithm is able perform clustering of these fiber tracts incorporating information about the shape of the fiber and a priori knowledge as the probability of the fiber belonging to known anatomical structures. This anatomical knowledge is incorporated as a volumetric white matter atlas, in this case LONI's ICBM DTI-81

Domaines: Imagerie médicale

Demian Wassermann, Rachid Deriche. Simultaneous Manifold Learning and Clustering: Grouping White Matter Fiber Tracts Using a Volumetric White Matter Atlas. MICCAI 2008 Workshop - Manifolds in Medical Imaging: Metrics, Learning and Beyond, Oct 2008, New-York, United States. ⟨inria-00430186⟩