Preprint
Sep 2026
ConPro: Contrast Projection Pretraining for Label-Efficient Vessel Segmentation in DSA Sequences
Dense vessel annotation in digital subtraction angiography (DSA) is labor-intensive, yet every unlabeled sequence records how contrast passes through the vessels. Semi-supervised methods take their targets from the current model, and generic self-supervised pretexts reconstruct static appearance, so this signal goes un...
Xin-Ge Guo, Yuan-Hao Wang, Liao Shu et al.
· 0 citations