A differentiable voxelization loss lets neural networks fit B-spline centerline-and-radius vessel models directly to segmentations, giving sparse editable meshes with Dice scores around 95, 86, and 82 percent on the three tested datasets.
Radiology: Artificial Intelligence (2022)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Parametric shape models for vessels learned from segmentations via differentiable voxelization
A differentiable voxelization loss lets neural networks fit B-spline centerline-and-radius vessel models directly to segmentations, giving sparse editable meshes with Dice scores around 95, 86, and 82 percent on the three tested datasets.