Integration of Probabilistic Atlas and Graph Cuts for Automated Segmentation of Multiple Sclerosis lesions

Francesca Galassi (1) , Olivier Commowick (1) , Christian Barillot (1)

1 VisAGeS - Vision, Action et Gestion d'informations en Santé

We propose a framework for automated segmentation of Multiple Sclerosis (MS) lesions from MR brain images. It integrates a priori tissues and MS lesions information into a GraphCuts algorithm for improved segmentation results.

Mots clés: Graph Cuts; Multiple Sclerosis lesions; Automated Segmentation

Domaines: Ingénierie biomédicale; Imagerie médicale

Francesca Galassi, Olivier Commowick, Christian Barillot. Integration of Probabilistic Atlas and Graph Cuts for Automated Segmentation of Multiple Sclerosis lesions. International Society for Magnetic Resonance in Medicine (ISMRM 2018), Jun 2018, Paris, France. pp.1-6. ⟨hal-01823801⟩