Symposium on Artificial Intelligence in Medical Imaging SAIMI

Organised by researchers from multiple Swiss universities.

18.06.2026 in Bern

About SAIMI

Overview

Advances in the accuracy and reliability of artificial intelligence (AI) have substantially accelerated its adoption in healthcare. One particularly promising application area is the AI-assisted analysis of MRI, CT, X-ray, and other medical imaging modalities, which, under suitable conditions, can lead to significant savings in time and resources. At the same time, challenges related to transparency, interpretability and model reliability remain critical barriers to widespread clinical deployment. Furthermore, heterogeneity in image acquisition strategies and modalities across institutions and hospitals complicates both standardized evaluation and practical implementation.

This symposium aims to bring together research groups across Switzerland working on AI for medical imaging to present recent advances, exchange new ideas and discuss both institution-specific and overarching challenges, as well as potential future solutions. Early-career researchers and students are encouraged to present their work through oral presentations or poster sessions and to engage with peers from across the Swiss research community.

The program will be complemented by keynote talks from experienced researchers and representatives from industry and clinical practice, who will provide perspectives on the current state of the field and emerging future directions.

Format

This symposium will be held as an in-person event in Bern.

Important Dates

27.02.2026: Opening registration

19.03.2026: Opening abstract submission

30.04.2026: Abstract submission deadline

14.05.2026: Final decisions

18.06.2026: Event day

Call for Abstracts

Scope

The goal of SAIMI is to provide the opportunity to meet and discuss research ideas with the local MICCAI/MIDL community around Switzerland. To this end, we invite short abstract submissions on the topics related to AI for medical image analysis. Topics of interests include (but are not limited to):

Advancements to predictive models for medical imaging (e.g. segmentation, classification etc.)
Multi-modal models
Trustworthy AI and fairness
Generalizable AI in medical imaging
AI model monitoring
Image synthesis and generative modelling
Clinical translation

This symposium is non-archival, and we welcome submissions of preliminary results (work in progress), as well as work under submission or recently published work (publication date 2025 or 2026).Submissions will be reviewed in a double-blind manner. The aim of the review process is to determine (1) fit within the SAIMI scope, (2) quality of the abstract, (3) guide poster and spotlight talks selection.

Submission Format

We invite you to submit a 1-page abstract describing your work, following this structure: 1) Objective of the study, 2) Motivation & background, 3) Short description of methods, 4) Summary of main results, 5) Conclusion.

Please submit your abstract as a .pdf file, in Arial or Time New Roman, minimum 10pt font size. Figures or tables are allowed. Author names, affiliations and acknowledgements, as well as any obvious phrasings or clues that can identify authors must be removed to ensure anonymity.

Note that the 1 page limit refers only to the main content. Including references and acknowledgements the submission may exceed 1 page.

How to submit?

Please click here to submit an abstract. The Microsoft CMT service was used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft and they bore all expenses, including costs for Azure cloud services as well as for software development and support.

Presentation

All accepted abstracts will be presented as a poster during the symposium day. Additionally, we will select a number of papers for oral presentation based on the reviewers' suggestions.

Program

Date and Location

18.06.2026 in Bern

Schedule (preliminary)

09:00–09:15 Registration
09:15–09:30 Welcome words and DDM introduction
09:30–10:15 Keynote 1
10:15-11:00 6 x 5mins lightning talks
11:00-11:15 Coffee + poster setup
11:15-12:00 Poster session 1
12:00-13:00 Lunch
13:00-14:30 Keynote 2 & 3
14:30-15:00 6 x 5mins lightning talks
15:00-15:15 Coffee + poster setup
15:15-16:00 Poster session 2
16:00-16:45 Sponsor presentation
16:45-17:00 Closing words and goodbye + awards

Keynotes

Ender Konukoglu

Ender Konukoglu grew up in Istanbul, Turkey, where he completed his B.Sc. and M.Sc. degrees in Electrical and Electronics Engineering at Bogazici University. He received his PhD from INRIA Sophia Antipolis under the supervision of Nicholas Ayache. After postdoctoral positions at Microsoft Research Cambridge and the Athinoula A. Martinos Center for Biomedical Imaging at Massachusetts General Hospital and Harvard Medical School, he joined ETH Zurich in 2016 as an Assistant Professor. Since 2022, he has been an Associate Professor in the Department of Information Technology and Electrical Engineering at ETH Zurich, where he leads the Biomedical Image Computing (BMIC) group.

His research focuses on machine learning and computational methods for biomedical image analysis, including medical image segmentation, uncertainty quantification, anomaly detection, and AI-driven methods for improving medical imaging acquisition and analysis.

Meritxell Bach Cuadra

Meritxell Bach Cuadra has an electrical engineering background and graduated PhD from EPFL. Since October 2025, she is Associate Professor at the Faculty of Biology and Medicine of UNIL, Head of the CIBM Signal Processing CHUV-UNIL Trustworthy Medical Image Analysis Section, and leads the Medical Image Analysis Laboratory (MIAL) at CHUV since 2011. Her research focuses on the development of advanced image processing and machine learning techniques for medical image computing. Her team addresses challenges such as image quality assessment, super-resolution, registration, detection, segmentation and normative modelling with direct applications in computer-aided diagnosis and therapy planning. The group maintains a strong emphasis on translational research through collaborations with clinical partners in radiology, neurology, oncology, neuroscience and psychiatry. To support clinical integration, their methods are developed in alignment with emerging regulatory requirements for trustworthy and explainable AI in healthcare. Bach Cuadra's section focuses on uncertainty quantification and robust domain adaptation to ensure that AI systems deliver reliable, reproducible results across diverse clinical settings. In parallel, they emphasize human-centered AI design: promoting interpretability and effective communication of model outputs to support clinical decision-making and foster clinician trust.