Automated black-blood late gadolinium enhancement cardiac imaging through explainable user-independent inversion time selection
Aurelien Maillot1, Soumaya Sridi2, Xavier Pineau2, Amandine André-Billeau2, Stéphanie Hosteins2, Marta Nuñez-Garcia1, Maxime Sermesant1,3, Hubert Cochet1,2, Matthias Stuber1,4,5, and Aurelien Bustin1,2,4
1IHU LIRYC, Electrophysiology and Heart Modeling Institute, Université de Bordeaux – INSERM U1045, Bordeaux, France, 2Department of Cardiovascular Imaging, Hôpital Cardiologique du Haut-Lévêque, CHU de Bordeaux, Bordeaux, France, 3INRIA, Université Côte d’Azur, Sophia Antipolis, France, 4Department of Diagnostic and Interventional Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland, 5CIBM Center for Biomedical Imaging, Lausanne, Switzerland
Black-blood late gadolinium enhancement (LGE) imaging techniques have been introduced to improve the poor scar to blood contrast of bright-blood LGE, especially for subendocardial myocardial infarction. These techniques heavily rely on the manual selection of the optimal inversion time (TI) for blood nulling which makes them operator-dependent, reduce their reproducibility and decrease clinical workflow efficiency. In this work, we investigate whether an explainable image processing technique can be employed for automated TI selection to enable fully automated black-blood LGE.
This abstract and the presentation materials are available to members only;
a login is required.