Metraipolis › archive › dc_ec70ea8d3dfb

Inference-Time Orthogonal Seeding Enables Geometry-Aligned 3D Organ Segmentation for Slice-Propagation Methods — arXiv:2608.12658

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.12658
License (as archived): CC0-1.0
Archived: 2026-10-19T04:55:32.602Z
SHA-256 of the archived text: 6a980b948ea8211aa382fe9d686b6097dfebd306092fdeadf7cd476bd2dfb1dc
Stable URL of this page: https://metraipolis.com/documento/dc_ec70ea8d3dfb

How to cite

Inference-Time Orthogonal Seeding Enables Geometry-Aligned 3D Organ Segmentation for Slice-Propagation Methods — arXiv:2608.12658 — arXiv (en), https://arxiv.org/abs/2608.12658 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec70ea8d3dfb (Metraipolis archive dc_ec70ea8d3dfb, sha256 6a980b948ea8211aa382fe9d686b6097dfebd306092fdeadf7cd476bd2dfb1dc)

BibTeX

@misc{dcec70ea8d3dfb,
  title = {Inference-Time Orthogonal Seeding Enables Geometry-Aligned 3D Organ Segmentation for Slice-Propagation Methods — arXiv:2608.12658},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12658},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec70ea8d3dfb; sha256 6a980b948ea8211aa382fe9d686b6097dfebd306092fdeadf7cd476bd2dfb1dc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12658. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Dense voxel-level annotation remains a major bottleneck in 3D medical image segmentation. Single-slice propagation methods such as Sli2Vol reduce this burden by propagating one annotated seed slice through a volume using label-free registration. However, axial-only propagation accumulates errors with distance from the seed, especially in surface-distance metrics, because it ignores coronal and sagittal evidence and therefore underuses the 3D information available in CT/MRI volumes. To better leverage volumetric geometry, we study how key training and inference choices affect slice-propagation models, including single-axis versus multi-axis label-free registration, single-seed versus multi-seed propagation, and orthogonal seed configurations. Instead of propagating from a single axial seed, we use three orthogonal seeds---one axial, one coronal, and one sagittal---and fuse their propagated labels with a simple label-free rule. Our results show that the training paradigm has limited impact: an axially trained network applied to off-axis seeds captures nearly all the improvement, while explicit three-axis training adds little. Instead, performance is driven by inference-time seed geometry, especially orthogonality rather than the number of annotated slices, as a budget-matched three-axial control provides no benefit and can even degrade performance. On a multi-organ CT cohort, orthogonal seeding with the axial Sli2Vol backbone improves Dice by 21.9%, Normalized Surface Dice by 25.5%, and reduces Average Hausdorff Distance by 53.5% over the single-axis baseline.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.12658 — 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 2026-10-19T04:46:30.054Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).