Embedded Files
MICCAI 2025 Tutorial
3rd edition
27th September 8AM-12PM
About
About
This MICCAI 2025 full-day 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, model calibration, and multi-rater modeling techniques necessary for making reliable decisions.
This MICCAI 2025 full-day 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, model calibration, and multi-rater modeling techniques necessary for making reliable decisions.
This third edition of the tutorial will be focused on the topic of uncertainty quantification, model calibration, and conformal prediction. This year's tutorial is conducted in a joint event with the 7th edition of the UNSURE Workshop, combining talks from experts, hands-on materials, modern research presentations, an invited lecturer presentation, and a panel discussion.
This third edition of the tutorial will be focused on the topic of uncertainty quantification, model calibration, and conformal prediction. This year's tutorial is conducted in a joint event with the 7th edition of the UNSURE Workshop, combining talks from experts, hands-on materials, modern research presentations, an invited lecturer presentation, and a panel discussion.
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.
This tutorial is an essential resource for scientists, clinicians, and industry professionals aiming to enhance the robustness and trustworthiness of their DL models.
This tutorial is an essential resource for scientists, clinicians, and industry professionals aiming to enhance the robustness and trustworthiness of their DL models.
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 techniques for model calibration and its relationship with predictive uncertainty.
• Knowledge of uncertainty quantification through the basics of conformal prediction.
• Label uncertainty and multi-rater modeling techniques and practical utilization in medical imaging.
• Quantifying uncertainty for medical foundational models.
Program
Program
8:00-8:05: Opening remarks on the event organization
8:05-8:35: Part 1: General Introduction to Uncertainty & Domain Shift by Vatsal Raina
8:35-9:05: Part 2: Uncertainty for Medical Image Analysis by Nataliia Molchanova
9:05-9:15: Q&A
9:15-9:45: Part 3: Multi-Rater Modeling by Meritxell Riera i Marín
9:45-9:55: Q&A
Coffee break with a poster session
10:30-11:20: Part 4: Model Calibration & Conformal Prediction by Adrian Galdran
11:20-11:30: Q&A
11:30-12:00: Invited Lecture by Julio Silva-Rodriguez on Uncertainty Quantification for Medical Foundation Models
12:00-12:10: Q&A
12:10-12:30 Spotlight presentation session by UNSURE Workshop participants
Lunch
Afternoon UNSURE Workshop presentations and panel discussion
Invited Lecturer Julio Silva-Rodriguez
Invited Lecturer Julio Silva-Rodriguez
Postdoctoral researcher at ÉTS Montréal specializing in computer vision and medical imaging. Currently developing foundation models tailored for medical image analysis — exploring few-shot, parameter-efficient adaptation and uncertainty quantification. Passionate about building scalable, real-world AI systems that push the boundaries of healthcare and imaging.
Personal webpage: https://jusiro.github.io/
Minimal required skills
Minimal required skills
This tutorial does not require any prior skills in uncertainty or model calibration, however 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.
Contacts
Contacts
In case of questions about the tutorial, please contact:
nataliia(dot)molchanova(at)unil(dot)ch 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
Computer Vision Center, Universitat Autònoma de Barcelona
Nataliia Molchanova
University of Lausanne and Lausanne University Hospital, Switzerland
University of Applied Sciences of Western Switzerland, Switzerland
Meritxell Riera i Marín
Sycai Medical
Vatsal Raina
University of Cambridge,
Apta AI
Page updated
Google Sites
Report abuse