Metraipolis › archive › dc_ddcf18420d89

ConPro: Contrast Projection Pretraining for Label-Efficient Vessel Segmentation in DSA Sequences — arXiv:2609.30043

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30043
License (as archived)
CC0-1.0
Archived
2026-10-08T06:44:41.619Z
SHA-256 of the archived text
ba00427aac3b65239f4b8e8c09791d77004e537d9154f7a7f369c2f42b3acbc8
Stable URL of this page
https://metraipolis.com/documento/dc_ddcf18420d89

How to cite

ConPro: Contrast Projection Pretraining for Label-Efficient Vessel Segmentation in DSA Sequences — arXiv:2609.30043 — arXiv (en), https://arxiv.org/abs/2609.30043 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ddcf18420d89 (Metraipolis archive dc_ddcf18420d89, sha256 ba00427aac3b65239f4b8e8c09791d77004e537d9154f7a7f369c2f42b3acbc8)
BibTeX
@misc{dcddcf18420d89,
  title = {ConPro: Contrast Projection Pretraining for Label-Efficient Vessel Segmentation in DSA Sequences — arXiv:2609.30043},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30043},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ddcf18420d89; sha256 ba00427aac3b65239f4b8e8c09791d77004e537d9154f7a7f369c2f42b3acbc8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30043. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 unused. We propose ConPro, a self-supervised pretraining scheme whose target is a contrast projection, the normalized drop of every pixel below its temporal median over the sequence. On DIAS and DSCA, with 10%, 20% and 50% of the training cases labeled, ConPro improves on training from scratch at every label fraction and is the best of the compared methods on DSCA at 20% and 50% labels. Controlled comparisons show that the gain comes from the target. A temporal-median target with the same input, loss and budget stays at scratch level, and using the projection directly instead of learning it, as an input channel or a pseudo-label, helps little or hurts. ConPro provides pretrained weights without changing the segmentation architecture, so it combines with semi-supervised training, and UniMatch, the strongest baseline, gains 0.5 to 2.0 Dice and 0.9 to 2.3 clDice at every label fraction when started from ConPro weights, reaching 75.4 Dice on DIAS and 81.3 on DSCA.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.30043 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T06:09:29.904Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).