VesselSim trains a 3D vessel segmentation model exclusively on 16,500 synthetic angiographic volumes generated by stochastic branching simulation and achieves competitive zero-shot performance on real clinical datasets via test-time mask reconstruction adaptation.
IEEE transactions on bio-medical engineeringPP(11 2023)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
VesselSim: learning 3D blood vessel segmentation without expert annotations
VesselSim trains a 3D vessel segmentation model exclusively on 16,500 synthetic angiographic volumes generated by stochastic branching simulation and achieves competitive zero-shot performance on real clinical datasets via test-time mask reconstruction adaptation.