Metraipolis › archive › dc_6fbbfa70d0f8

Beyond Volume Overlap: Surface Matching for Topology-Aware Coronary Artery Segmentation — arXiv:2609.31740

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31740
License (as archived)
CC0-1.0
Archived
2026-10-07T23:50:33.699Z
SHA-256 of the archived text
bb43628e1e4bb77eebed3de4641b00cec58e3d3ebf6a886baa7cf1018e770789
Stable URL of this page
https://metraipolis.com/documento/dc_6fbbfa70d0f8

How to cite

Beyond Volume Overlap: Surface Matching for Topology-Aware Coronary Artery Segmentation — arXiv:2609.31740 — arXiv (en), https://arxiv.org/abs/2609.31740 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6fbbfa70d0f8 (Metraipolis archive dc_6fbbfa70d0f8, sha256 bb43628e1e4bb77eebed3de4641b00cec58e3d3ebf6a886baa7cf1018e770789)
BibTeX
@misc{dc6fbbfa70d0f8,
  title = {Beyond Volume Overlap: Surface Matching for Topology-Aware Coronary Artery Segmentation — arXiv:2609.31740},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31740},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6fbbfa70d0f8; sha256 bb43628e1e4bb77eebed3de4641b00cec58e3d3ebf6a886baa7cf1018e770789},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31740. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accurate coronary artery segmentation on coronary computed tomography angiography (CCTA) is essential for diagnosing coronary artery disease. Deep networks are conventionally trained and evaluated with the Dice coefficient, but volume-overlap metrics are poorly suited to thin, tubular anatomy: since most voxels belong to a few thickproximal segments, a missing distal branch barely affects Dice despite severely disrupting the connectivity required for clinical use. We introduce a surface metric that matches predicted and reference surface points via bipartite assignment under a localized, vessel-radius tolerance, reporting precision, recall, and F1 with decoupled false positives (spurious branches) and false negatives (missed branches) a distinction the symmetric Dice cannot make. With it we show that a strong Dice-trained baseline omits far more vessel surface than it hallucinates, an asymmetry its high Dice hides. Building on this, we propose a differentiable surface loss that simultaneously suppresses spurious mass and recovers absent structure, validated by fine-tuning three backbones (nnU-Net, SwinUNETR, NexToU) on two public benchmarks (Image-CAS, ASOCA). Against a matched-epoch control, it significantly improves surface F1 by recovering missed distal vessels at comparable Dice. Our findings argue for measuring and optimizing the vessel surface, not the volume it overlaps. Code

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.31740 — 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 2026-10-07T23:29:26.908Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).