Abstract
Medical imaging artificial intelligence (AI) produces methods competitive on retrospective, public benchmarks yet rarely reaches validated, deployable clinical use. This gap persists in large part because the communities best placed to close it – clinician-scientists who understand workflow, regulatory, and validation constraints, and computational researchers who build the underlying methods – remain organisationally siloed. To this end, we organized the Multidisciplinary Evaluation & Translation in Imaging & Surgery (METIS) workshop, in conjunction with the 2026 Annual Meeting of the Medical Image Computing and Computer Assisted Intervention (MICCAI) Society, in Strasbourg, France, in our attempt to bridge clinical and computational communities for the next generation of medical imaging AI. METIS 2026 was organised in direct partnership with the Medical Image Understanding and Analysis (MIUA) 2026 conference and building upon prior accumulated efforts from the American Society for NeuroRadiology (ASNR) and the American Society of Functional Neuroradiology (ASFNR). Here we report the motivation, design, and inaugural programme of METIS 2026, as well as its roadmap for the MICCAI METIS 2027. We summarise the seven accepted contributions to METIS’ inaugural programme, spanning surgical, radiation-oncology, pathology, neuroradiology, paediatric-neurology, and gynaecological-oncology/global-health applications across seven countries, and show that cross-site generalisation, privacy-preserving validation, adaptation of large pretrained models, and interpretability for clinician trust recur independently across the cohort as shared computational themes – alongside a shared reflection that most lead applicants are computational researchers actively seeking the clinical partnership METIS is designed to supply. Finally, we set out the expectations for the next METIS iteration: a structured, approximately nine-month mentoring pathway for accepted authors culminating in independent submission opportunities to MICCAI 2027 in Auckland, New Zealand, with an explicit finalist/award track, a sharpened focus on clinical translation and computational themes, and deeper cross-society engagement. We position METIS as a seed for a sustained, multi-society translational pipeline rather than a single-session event.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/METIS_001.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: https://papers.miccai.org/miccai-2026-sat/supp/METIS_001_supp.pdf
Link to Open Review
Open Review Page: Not Available
BibTex
@InProceedings{NavAli_Multidisciplinary_MICCAISAT2026,
author = { Navas, Alin AND Astaraki, Mehdi AND Bazay, Fatima Ez-Zahraa AND Chiumento, Francesco AND Kachole, Sanket AND Lee, Jongwoon AND Oladejo, Ezekiel Ayodeji AND Soares, Antonio S. AND Rudie, Jeffrey D. AND Calabrese, Evan AND Aboian, Mariam S. AND Safdar, Aon AND Saadeldin, Mohamed AND Healy, Nuala A. AND Ochoa-Ruiz, Gilberto AND Ali, Sharib AND Yilmaz, Bulent AND Papież, Bartłomiej W. AND Bakas, Spyridon AND Curran, Kathleen M.},
title = { { Multidisciplinary Evaluation and Translation in Imaging and Surgery (METIS) 2026: Bridging Clinical and Computational Communities for the Next Generation of Medical Imaging AI } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17266},
month = {pending},
page = {pending}
}