27 September 2026 · Strasbourg, France
Co-organized the MICCAI 2026 SAFER Workshop on Trustworthy Medical Foundation Models
SAFER — Stable Adaptation and Faithful Evaluation of Reasoning, MICCAI 2026 Workshop ↗
On 27 September 2026 we held the first SAFER workshop — Stable Adaptation and Faithful Evaluation of Reasoning — at MICCAI 2026 in Strasbourg. As medical AI moves beyond performance-driven optimisation, SAFER brings together researchers from academia, industry and clinical practice around medical foundation and vision–language models that explain their reasoning transparently, ground their outputs in verifiable medical evidence and adapt reliably across imaging domains and modalities. Key themes are hallucination detection and grounding in radiology and surgical vision, trust and evaluation of reasoning for image-based diagnosis, and stable adaptation to unseen imaging domains.
Programme (Room Curie B)
| Time (CEST) | Session |
|---|---|
| 08:00 | Opening remarks |
| 08:15 | Oral session 1: Robust adaptation and grounding in medical foundation models (4 papers) |
| 09:15 | Keynote 1: Beyond Performance: Evaluating Foundation Models for Trustworthy Medical AI — Annika Reinke, German Cancer Research Center (DKFZ) |
| 10:00 | Coffee break |
| 10:30 | Keynote 2: Promise Versus Performance: A Faithful Benchmark of Vision-Language Foundation Models Against Specialized AI for Lung Cancer Prediction — Pierre Baudot, Median Technologies |
| 11:15 | Oral session 2: Trustworthy reasoning and evaluation in medical VLMs (5 papers) |
| 12:15 | Closing remarks |
| 12:30 | Lunch and poster session |
Organisers: Dwarikanath Mahapatra (Khalifa University), Imran Razzak (MBZUAI), Miguel O. Bernabeu (University of Edinburgh), Shadi Albarqouni (University of Bonn) and Yasmeen George (Monash University). Outreach committee: Hongxi Yang, Jianghao Wu, Jiayi Chen and Trang Pham (Monash University) and Malek Al Abed (University of Bonn). Details: safer-workshop.github.io.
Photos
