HIGHLIGHTS
- What: In this article it is proposed that a U-Net be used to compute the vascular skeleton directly from the segmentation and the magnetic resonance angiography image. This study demonstrated that the proposed method provides segmentations with a more accurate topology while having a lower training time. To ensure a fair comparison across the experiments, the same data augmentation strategy (inspired by nnU-Net ) was used for all trained networks using the Python package batchgenerators :.
- Who: Pierre Rougé and collaborators from the France Editor:, University of Donja Gorica have published the paper: Topology aware . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.