Bridging the gap between research innovation and clinical impact in medical imaging AI
Rapid advances in medical imaging AI and computer-assisted intervention (CAI) have produced highly accurate algorithms, yet their translation into clinical practice remains limited. A major barrier is the gap between technical evaluation in research and the requirements of clinical validation, regulatory approval, and deployment.
The MÉTIS Workshop addresses this challenge by uniting clinical and computational communities to develop shared standards for evaluation, validation, and translation of AI and CAI systems. It provides a platform for case studies and technical contributions that emphasize clinically meaningful evaluation strategies, reproducibility, robustness, and regulatory considerations.
By fostering collaboration among radiology, pathology, surgery, and medical image computing communities, MÉTIS aims to train a new generation of researchers capable of delivering clinically robust, reproducible, and deployable AI technologies.
🏛️ Metis — the ancient Greek goddess of wisdom, practical intelligence, and strategic thinking — embodies exactly what is needed for the translation of MICCAI methods into the clinic. She is a symbol for bringing together different forms of knowledge, aligned with our workshop's goal of uniting clinical practice, imaging, AI, and computational science.
Submit your work across three complementary contribution tracks
Key milestones for the MÉTIS workshop at MICCAI 2026
A half-day workshop packed with presentations, panels, and collaborative sessions
Addressing the clinical–AI gap and translational readiness in medical imaging & CAI
Selected papers and case studies from Tracks 1 & 2
Clinicians, computational scientists, and regulatory experts on interdisciplinary validation
Collaborative evaluation outcomes from Track 3 (MIUA–MICCAI collaborations)
Co-designing joint educational and evaluation frameworks
Synthesizing outcomes and proposing multi-society steering committee
Top AI imaging systems will be recognized based on transparent, pre-defined criteria
Number and diversity of clinician collaborations formed
Quality and completeness of evaluation across institutions
Clinical relevance and translational impact of the system
Ease of use, openness, practicality, and integration
An interdisciplinary team spanning clinical imaging, computational AI, and translational research
