Abstract
Developing label-efficient models is a central challenge in surgical AI due to the high cost and scarcity of expert annotation. While self-supervised foundation models adapt well to new tasks with minimal data, how label efficiency varies across different surgical tasks remains largely unexplored. Here, we introduce SURGE, a surgical foundation model trained on SurgSpectrum-30M+, the largest pretraining dataset comprising over 30 million frames, with checkpoints released to enable further research. We systematically evaluate label efficiency across 5 task categories and 15 benchmarks. These range from temporal and spatial scene understanding to fine-grained reasoning tied to instrument-anatomy interactions and safety-critical maneuvers. SURGE outperforms prior state-of-the-art on all benchmarks, even surpassing task-specific models on complex reasoning tasks. Crucially, we reveal a task-dependent scaling behavior: while scene understanding tasks saturate with minimal supervision, fine-grained reasoning tasks continue improving with substantially larger annotation budgets, providing a blueprint for allocating expert effort in complex domains. Code: https://github.com/CAMMA-public/SURGE
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Stilz, F. P., Arboit, L., Srivastav, V., Partners, C. I. S., Marescaux, J., Alfieri, S., Mascagni, P., Navab, N., & Padoy, N. (2026). A Surgical Foundation Model Reveals Task-Dependent Label Efficiency. https://omanscience.com/en/articles/a-surgical-foundation-model-reveals-task-dependent-label-efficiency
MLA 9
Stilz, Florian Philipp, et al. "A Surgical Foundation Model Reveals Task-Dependent Label Efficiency." https://omanscience.com/en/articles/a-surgical-foundation-model-reveals-task-dependent-label-efficiency.
Chicago (author–date)
Stilz, Florian Philipp, Lorenzo Arboit, Vinkle Srivastav, CAMMA International Surgical Partners, Jacques Marescaux, Sergio Alfieri, Pietro Mascagni, Nassir Navab, and Nicolas Padoy. 2026. "A Surgical Foundation Model Reveals Task-Dependent Label Efficiency." https://omanscience.com/en/articles/a-surgical-foundation-model-reveals-task-dependent-label-efficiency.
Harvard
Stilz, F. P., Arboit, L., Srivastav, V., Partners, C. I. S., Marescaux, J., Alfieri, S., Mascagni, P., Navab, N. and Padoy, N. (2026) 'A Surgical Foundation Model Reveals Task-Dependent Label Efficiency', Available at: https://omanscience.com/en/articles/a-surgical-foundation-model-reveals-task-dependent-label-efficiency.
Vancouver
Stilz FP, Arboit L, Srivastav V, Partners CIS, Marescaux J, Alfieri S, et al. A Surgical Foundation Model Reveals Task-Dependent Label Efficiency. https://omanscience.com/en/articles/a-surgical-foundation-model-reveals-task-dependent-label-efficiency
IEEE
F. P. Stilz, L. Arboit, V. Srivastav, C. I. S. Partners, J. Marescaux, S. Alfieri, P. Mascagni, N. Navab, and N. Padoy, "A Surgical Foundation Model Reveals Task-Dependent Label Efficiency," https://omanscience.com/en/articles/a-surgical-foundation-model-reveals-task-dependent-label-efficiency.