Meeting Banner
Abstract #3329

Fully automated spatio-temporal segmentation approach for myocardium ischemic lesions detection and tissue classification

Clément Daviller1, Thomas Grenier1, Shivraman Giri2, Pierre Croisille3, and Magalie Viallon3

1Univ Lyon, INSA‐Lyon, Université Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, CREATIS UMR 5220, U1206, F-69621, Villeurbanne, France, Villeurbanne, France, 2Siemens Medical Solutions USA, Inc. Boston, USA., Boston, MA, United States, 3Univ Lyon, INSA‐Lyon, UJM-Saint Etienne, Université Claude Bernard Lyon 1,CNRS, Inserm, CREATIS UMR 5220, U1206, F-42023, SAINT-ETIENNE, France, Saint-Etienne, France

CMR Perfusion Imaging proved its role in patient triage, identifying visually ischemia and its capability in quantifying heart perfusion1,2, but failed to transfer this technology to clinical routine and to show how this worth information could be used to improve tissue lesions comprehension. Deconvolution techniques are sensitive to noise present on time intensity curves S(t), when observation scale decreases. Automated segmentation prior modelling would be a powerful adjunct. Indeed, prior tissue classification would optimize perfusion quantification accuracy since enabling advanced modelling leading to additional markers while reducing processing time. Such automated method is proposed here.

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

Join Here