Metraipolis › archive › dc_b032401013eb
PathCowork: Learning from real-world pathology practice to build AI copilots — arXiv:2610.39441
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39441
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:41:58.406Z
- SHA-256 of the archived text
701609f2be0dd2489895f8e8cfa97b916a2067b16300d2c2f54ba8338d731f66- Stable URL of this page
https://metraipolis.com/documento/dc_b032401013eb
How to cite
PathCowork: Learning from real-world pathology practice to build AI copilots — arXiv:2610.39441 — arXiv (en), https://arxiv.org/abs/2610.39441 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b032401013eb (Metraipolis archive dc_b032401013eb, sha256 701609f2be0dd2489895f8e8cfa97b916a2067b16300d2c2f54ba8338d731f66)
BibTeX
@misc{dcb032401013eb,
title = {PathCowork: Learning from real-world pathology practice to build AI copilots — arXiv:2610.39441},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39441},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b032401013eb; sha256 701609f2be0dd2489895f8e8cfa97b916a2067b16300d2c2f54ba8338d731f66},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39441. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Medical AI learns from the answers doctors record, but rarely from how they interpret the evidence to reach them. Here we introduce PathCowork, a framework that turns pathologists' narrated examinations into supervision for visual grounding and procedures that guide diagnostic AI agents. Synchronized gaze, narration and navigation link visual findings to the process of interpreting them. Across 48 sessions from 16 pathologists, the platform captured 1,028 minutes of slide review. Using these data, we trained PathCowork-1T for server deployment and PathCowork-27B for local deployment, with improved visual grounding. Across five organ-specific evaluations, agents combining this grounding with recorded diagnostic procedures achieved primary task scores averaging 17.9 and 24.1 percentage points higher than Claude Code and Codex, respectively, with shorter processing times and lower inference costs. Compared to the state-of-the-art multiple-instance learning AIs, the PathCowork agent-proposed regions achieved higher prostate-grading scores with limited slide labels. PathCowork can also help construct pathology AI benchmarks where questions derived from the recordings identified difficulties in recognizing viewing context and rejecting inapplicable premises. In summary, PathCowork proposes a new paradigm to scale up the data collection and train pathology AI through transparent reasoning from diagnostic sessions, opening a path towards systems that learn directly from routine clinical practice. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.39441 — 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 2026-11-01T02:16:43.928Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).