Safe/Surg, First Workshop on AI for Safe Surgery

Surgical data science has achieved considerable progress in recent years, with increasingly capable methods tackling novel application areas in surgery. As the field moves forward from proof-of-concept methods towards clinical translation, developing clinically meaningful surgical applications requires us to address the multi-faceted nature of surgery, with surgical safety at its core. SafeSurg aims to create a space to address questions about how we collect and annotate data, what we choose to model, how we evaluate generalization, and how AI systems behave in the operating room.

These challenges cut across subfields that are usually treated in isolation: annotation quality, rare event detection, robustness, calibration, skill assessment, human-AI interaction. SafeSurg brings together clinicians, academics, industry, and regulators to concretely discuss what safety-aware AI actually looks like for surgery. Through this inaugural workshop, we aim to direct the community’s attention to the hard, cross-cutting research questions that are essential to improving surgical quality and safety.

Learn more on the Safe/Surg website

---

This event is organized by University of Strasbourg, CNRS, INSERM, ICube & IHU Strasbourg. It will take place within the framework of the MICCAI 2026 conference and it is supported by the AI Grand Est ENACT Cluster.