Embedded Files
MICCAI 2026 Tutorial
4th edition
4th or 8th October 8AM-12PM
About
About
This MICCAI 2026 satellite event aims to foster discussions within the scientific community regarding the trustworthiness of deep learning model predictions by providing valuable insights into uncertainty quantification. This fourth edition of the tutorial will be focused on relevant computational techniques to support uncertainty quantification in medical image analysis: Bayesian models, Out-of-Distribution analysis, Conformal Prediction, and Multi-Rater Ambiguity, plus a keynote talk by Olivier Colliot about Uncertainty in Performance Estimation.
This MICCAI 2026 satellite event aims to foster discussions within the scientific community regarding the trustworthiness of deep learning model predictions by providing valuable insights into uncertainty quantification. This fourth edition of the tutorial will be focused on relevant computational techniques to support uncertainty quantification in medical image analysis: Bayesian models, Out-of-Distribution analysis, Conformal Prediction, and Multi-Rater Ambiguity, plus a keynote talk by Olivier Colliot about Uncertainty in Performance Estimation.
Participants will have an opportunity to gain a comprehensive understanding of uncertainty quantification, covering mathematical foundations and cutting-edge research questions while acquiring practical tools for deriving state-of-the-art uncertainty estimates in medical image analysis.
Participants will have an opportunity to gain a comprehensive understanding of uncertainty quantification, covering mathematical foundations and cutting-edge research questions while acquiring practical tools for deriving state-of-the-art uncertainty estimates in medical image analysis.
We are pleased to announce that this year's tutorial will be a full-day joint event combined with the 8th edition of the UNSURE Workshop and the 9th edition of the iMIMIC Workshop, gathering engaging lectures from experts in the field, hands-on materials, research presentations, two keynote talks, and a panel discussion.
We are pleased to announce that this year's tutorial will be a full-day joint event combined with the 8th edition of the UNSURE Workshop and the 9th edition of the iMIMIC Workshop, gathering engaging lectures from experts in the field, hands-on materials, research presentations, two keynote talks, and a panel discussion.
Learning objectives
Learning objectives
This tutorial will enable participants to gain knowledge about topics ranging from the very fundamentals of uncertainty quantification to cutting-edge recent methods in the field. We expect tutorial attendees to develop:
• A solid understanding of the basic concepts around uncertainty quantification in machine learning and of a taxonomical map of the field.
• The ability to discriminate between different sources of uncertainty.
• Fundamentals for understanding and implementing several well-established uncertainty quantification techniques.
• Understanding of the probabilistic uncertainty quantification methods used for the medical image analysis tasks.
• Mathematical basis and practical tips for Bayesian modeling uncertainty in medical image analysis.
• Knowledge of uncertainty quantification through the basics of conformal prediction.
• Label uncertainty and multi-rater modeling techniques and practical utilization in medical imaging.
• Understanding of uncertainty in performance estimation.
Program
Program
UQinMIA Tutorial - UNSURE Workshop - iMIMIC Workshop
8:00-8:30: Part 1: Introduction and Taxonomy of Uncertainty Quantification - Gabriel Oliveira-Stahl, University College London
8:30-9:00: Part 2: Basics of Bayesian Models of Uncertainty - Zeinab Abboud, Polytechnique Montreal
9:00-9:30: Part 3: Fundamentals of Out-of-Distribution Analysis - Anna Wundram, University of Lucerne
9:30-10:00: Part 4: Multi-Rater Modeling in Medical Image Analysis - Meritxell Riera Marín, Sycai Medical
10.00-10.30 - Coffee break
10.30-11.00: Part 5: Introduction to Conformal Prediction - Adrian Galdran, Tecnalia
11.00-11.30: Keynote Presentation: Oliver Coilliot, Uncertainty in Performance Estimates (preliminary title)
11.30 - 12.30: UNSURE – Part I
11.30 - 13.30 - Lunch break
13.30 - 14.30 - UNSURE – Part II
14.30 - 15.30 iMIMIC – Part I
15.30 - 16.00 - Coffee break + Joint poster session UNSURE + iMIMIC
16.00 - 17.00 iMIMIC – Part II
17.00 - 18.00 - Joint panel discussion UQinMIA + UNSURE + iMIMIC
Invited Lecturer: Olivier Coilliot
Invited Lecturer: Olivier Coilliot
Dr. Olivier Colliot is a Research Director at CNRS (Division of Computer Science) and the co-head of the ARAMIS team (www.aramislab.fr) at the Paris Brain Institute (www.icm-institute.org), a team with joint affiliation between CNRS, Inria, Inserm, Sorbonne University and the Paris Brain Institute. He also holds a chair at the PRAIRIE Institute for Artificial Intelligence, a center of excellence created as part of the French strategic plan for AI. He has twenty years of experience working on the design and validation of innovative machine learning approaches to better understand, model, diagnose, predict and prevent brain disorders from multimodal data including neuroimaging, genomic and clinical data
Personal webpage: https://oliviercolliot.github.io/
Minimal required skills
Minimal required skills
This tutorial does not require prior skills in uncertainty quantification (that's the point), but some background in deep learning may be needed.
Materials
Materials
All materials from previous years and this year are available on our GitHub repository.
Several lectures and hands-on sessions were pre-recorded and are available on our YouTube playlist.
References on UQ can be found in the UQ in MIA Cookbook. More materials will be provided closer to the tutorial date.
Contact
Contact
In case of questions about the tutorial, please contact:
adrian(dot)galdran(at)tecnalia(dot)com or meritxell(dot)bachcuadra(at)unil(dot)ch
Organizers
Organizers
Meritxell
Bach Cuadra
CIBM Center for Biomedical Imaing
University of Lausanne and Lausanne University Hospital
Adrian Galdran
Tecnalia, Spain
Meritxell
Riera i Marín
Sycai Medical, Barcelona
Gabriel
Oliveira-Stahl
University College London
Zeinab Abboud
Polytechnique Montréal
Anna Wundram
University of Lucerne
Page updated
Google Sites
Report abuse