Metraipolis › archive › dc_20dbb5b645aa

Artificial Intelligence for Workflow Analysis in Colorectal Surgery: A Multicentric, Cross-Procedural Development and Generalization Study — arXiv:2608.20154

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20154
License (as archived)
CC0-1.0
Archived
2026-10-18T12:04:49.060Z
SHA-256 of the archived text
3876b8beabc39eb6cbd714e34788802ea749563a7d17781784dba9d37c787d2b
Stable URL of this page
https://metraipolis.com/documento/dc_20dbb5b645aa

How to cite

Artificial Intelligence for Workflow Analysis in Colorectal Surgery: A Multicentric, Cross-Procedural Development and Generalization Study — arXiv:2608.20154 — arXiv (en), https://arxiv.org/abs/2608.20154 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_20dbb5b645aa (Metraipolis archive dc_20dbb5b645aa, sha256 3876b8beabc39eb6cbd714e34788802ea749563a7d17781784dba9d37c787d2b)
BibTeX
@misc{dc20dbb5b645aa,
  title = {Artificial Intelligence for Workflow Analysis in Colorectal Surgery: A Multicentric, Cross-Procedural Development and Generalization Study — arXiv:2608.20154},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20154},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_20dbb5b645aa; sha256 3876b8beabc39eb6cbd714e34788802ea749563a7d17781784dba9d37c787d2b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20154. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Minimally invasive colorectal surgeries (MIS-CRS) are characterised by significant variability and inconsistent outcomes. ColoWorkflow, a tool for the video-based assessment (VBA) of MIS-CRS workflow, was recently validated. However, manual VBA is time-consuming, limiting implementation. This study presents AI-ColoWorkflow, a deep learning model for automated surgical workflow analysis across MIS-CRS. Operative videos of MIS-CRS were collected from 4 centres and a publicly available dataset. Phases and steps were manually annotated according to ColoWorkflow. A deep learning model combining a fine-tuned DINOv3 vision transformer for per-frame visual feature extraction with a hierarchical multi-stage temporal convolutional network was jointly optimized for phase and step recognition. The model trained on pooled multicentric data, namely AI-ColoWorkflow was compared against centre-specific and procedure-specific models on a held-out test set. The following metrics were used for evaluation: macro F1 score, balanced accuracy, precision, and recall. AI-ColoWorkflow achieved a macro F1 of 73.01% $\pm$ 10.27 (balanced accuracy 73.43%) for phase recognition and 39.82% $\pm$ 7.06 (balanced accuracy 38.65%) for step recognition. The global model outperformed centre- and procedure-specific models in most experiments except procedure-specific step recognition. In the generalization analysis, mean F1 was 48.42% for phase recognition. AI-ColoWorkflow can reliably recognize MIS-CRS phases. A single model trained on pooled, multicentric, multi-procedural data generalises at least as well as and often better than centre- or procedure-specific models for phase recognition in MIS-CRS, while procedure-specific step models retain advantages for certain procedure types, motivating hybrid training strategies for future surgical AI development.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.20154 — 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 2026-10-18T12:01:57.742Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).