Metraipolis › archive › dc_cbb79cb79966

WSPolypNet: Weakly Supervised Polyp Localization in Colonoscopy Videos — arXiv:2609.08182

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.08182
License (as archived): CC0-1.0
Archived: 2026-10-16T15:12:06.710Z
SHA-256 of the archived text: ff05dd42c44ce2cf6cf4a244fab22f09174fc5ff65308aa1dedd8d69de52eb71
Stable URL of this page: https://metraipolis.com/documento/dc_cbb79cb79966

How to cite

WSPolypNet: Weakly Supervised Polyp Localization in Colonoscopy Videos — arXiv:2609.08182 — arXiv (en), https://arxiv.org/abs/2609.08182 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cbb79cb79966 (Metraipolis archive dc_cbb79cb79966, sha256 ff05dd42c44ce2cf6cf4a244fab22f09174fc5ff65308aa1dedd8d69de52eb71)

BibTeX

@misc{dccbb79cb79966,
  title = {WSPolypNet: Weakly Supervised Polyp Localization in Colonoscopy Videos — arXiv:2609.08182},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.08182},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cbb79cb79966; sha256 ff05dd42c44ce2cf6cf4a244fab22f09174fc5ff65308aa1dedd8d69de52eb71},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08182. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Because dense frame-level annotation of colonoscopy videos is costly, we propose WSPolypNet, a weakly supervised framework for polyp localization using only video-level labels. WSPolypNet employs a 3D convolutional neural network trained with video-level supervision to generate class activation maps (CAMs), which identify candidate polyp regions without requiring frame-level spatial annotations. The CAM-derived localization cues are further enhanced using a multi-view strategy and provided to MedSAM2 as point prompts. MedSAM2 then propagates segmentation masks across the video, refining the coarse localization cues according to polyp boundaries. WSPolypNet achieved CorLoc scores of 47.80%, 43.68%, and 35.01% at IoU thresholds of 0.3, 0.5, and 0.7, respectively, compared with 36.87%, 33.72%, and 27.94% in the single-view setting. For small polyps, the multi-view strategy improved [email protected] from 16.01% to 30.97%. The framework also achieved a recall of 94.51%. These results demonstrate the potential of weakly supervised spatiotemporal learning to substantially reduce spatial annotation requirements for polyp localization in colonoscopy videos.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.08182 — 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 2026-10-16T14:49:57.284Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).