Metraipolis › archive › dc_0956b09f4ff5

woma: a real-time foundation model and its fine-tuned models for endoscopy — arXiv:2609.15130

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.15130
License (as archived)
CC0-1.0
Archived
2026-10-16T00:15:44.885Z
SHA-256 of the archived text
7b38d0da7cf4258a30c931a5f9e62751ec1d68ae22d48ff3353ebef1d801229f
Stable URL of this page
https://metraipolis.com/documento/dc_0956b09f4ff5

How to cite

woma: a real-time foundation model and its fine-tuned models for endoscopy — arXiv:2609.15130 — arXiv (en), https://arxiv.org/abs/2609.15130 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0956b09f4ff5 (Metraipolis archive dc_0956b09f4ff5, sha256 7b38d0da7cf4258a30c931a5f9e62751ec1d68ae22d48ff3353ebef1d801229f)
BibTeX
@misc{dc0956b09f4ff5,
  title = {woma: a real-time foundation model and its fine-tuned models for endoscopy — arXiv:2609.15130},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15130},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0956b09f4ff5; sha256 7b38d0da7cf4258a30c931a5f9e62751ec1d68ae22d48ff3353ebef1d801229f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15130. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

woma is a real-time foundation model for gastrointestinal endoscopy: a network trained without labels on about a million endoscopy frames, from which task models are fine-tuned. We contribute a systematic design for production. Requirements and pass marks were fixed before any run, eight candidates screened under pre-registered rules, self-supervised training taken to a stopping rule, then fine-tuning and deployment optimisation, all on one self-contained library, numbat. We also contribute woma itself with two fine-tuned models, every outcome reported met or missed. Our colonoscopy model finds and outlines polyps, names which colon segment is in view, suggests polyp type and grades bowel preparation. Our gastroscopy model names a station out of 22 protocol sites, flags and outlines lesions, and names one of seven findings. Every number was read on data never seen in training, and shipped weights were chosen on that record. In colonoscopy, 96% of polyps in a six-hospital PolypGen set are found at precision >=0.85, and 19 of 19 polyps across fifteen full REAL-Colon videos at 1.6 false alarms per procedure. In gastroscopy, landmark region is named correctly on 92% of frames from unseen patients, and 37 of 39 held-out neoplasia frames are flagged at specificity 0.91. On one workstation GPU every task runs over 1080p video at about 100 frames per second, faster than PyTorch, ONNX Runtime and TensorRT in all four precision regimes tested. TensorRT comes closest: one pass of our foundation model takes it 3 to 27% longer than ours, and we deliver 6 to 31% more frames per second from frame to results. A second build links no vendor library at all -- our own kernels over Vulkan -- so a site deploys two files and needs no toolkit, no cuDNN and no framework; in f32 it beats the CUDA build on the same card.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG).
Categorie arXiv: Software Engineering (cs.SE) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.15130 — 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 2026-10-15T23:54:14.947Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).