no code implementations • 2 Apr 2024 • Pierre Rougé, Pierre-Henri Conze, Nicolas Passat, Odyssée Merveille
Based on these experiments, we provide guidelines for the annotation and training of cerebrovascular segmentation models.
1 code implementation • 21 Jul 2023 • Pierre Rougé, Nicolas Passat, Odyssée Merveille
To overcome these limitations, the clDice loss, a topological loss that focuses on the vessel centerlines, has been recently proposed.
1 code implementation • 20 Jan 2022 • Méghane Decroocq, Carole Frindel, Pierre Rougé, Makoto Ohta, Guillaume Lavoué
We proposed a vessel model based on penalized splines to overcome the limitations inherent to the centerline representation, such as noise and sparsity.