A generalizable foundation model for intraoperative understanding across surgical procedures
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914329681461248 |
|---|---|
| author | Park, Kanggil Jeon, Yongjun Lim, Soyoung Park, Seonmin Shin, Jongmin Kim, Jung Yong An, Sehyeon Rhu, Jinsoo Kim, Jongman Choi, Gyu-Seong Oh, Namkee Jung, Kyu-Hwan |
| author_facet | Park, Kanggil Jeon, Yongjun Lim, Soyoung Park, Seonmin Shin, Jongmin Kim, Jung Yong An, Sehyeon Rhu, Jinsoo Kim, Jongman Choi, Gyu-Seong Oh, Namkee Jung, Kyu-Hwan |
| contents | In minimally invasive surgery, clinical decisions depend on real-time visual interpretation, yet intraoperative perception varies substantially across surgeons and procedures. This variability limits consistent assessment, training, and the development of reliable artificial intelligence systems, as most surgical AI models are designed for narrowly defined tasks and do not generalize across procedures or institutions. Here we introduce ZEN, a generalizable foundation model for intraoperative surgical video understanding trained on more than 4 million frames from over 21 procedures using a self-supervised multi-teacher distillation framework. We curated a large and diverse dataset and systematically evaluated multiple representation learning strategies within a unified benchmark. Across 20 downstream tasks and full fine-tuning, frozen-backbone, few-shot and zero-shot settings, ZEN consistently outperforms existing surgical foundation models and demonstrates robust cross-procedure generalization. These results suggest a step toward unified representations for surgical scene understanding and support future applications in intraoperative assistance and surgical training assessment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13633 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A generalizable foundation model for intraoperative understanding across surgical procedures Park, Kanggil Jeon, Yongjun Lim, Soyoung Park, Seonmin Shin, Jongmin Kim, Jung Yong An, Sehyeon Rhu, Jinsoo Kim, Jongman Choi, Gyu-Seong Oh, Namkee Jung, Kyu-Hwan Computer Vision and Pattern Recognition In minimally invasive surgery, clinical decisions depend on real-time visual interpretation, yet intraoperative perception varies substantially across surgeons and procedures. This variability limits consistent assessment, training, and the development of reliable artificial intelligence systems, as most surgical AI models are designed for narrowly defined tasks and do not generalize across procedures or institutions. Here we introduce ZEN, a generalizable foundation model for intraoperative surgical video understanding trained on more than 4 million frames from over 21 procedures using a self-supervised multi-teacher distillation framework. We curated a large and diverse dataset and systematically evaluated multiple representation learning strategies within a unified benchmark. Across 20 downstream tasks and full fine-tuning, frozen-backbone, few-shot and zero-shot settings, ZEN consistently outperforms existing surgical foundation models and demonstrates robust cross-procedure generalization. These results suggest a step toward unified representations for surgical scene understanding and support future applications in intraoperative assistance and surgical training assessment. |
| title | A generalizable foundation model for intraoperative understanding across surgical procedures |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.13633 |