Uncertainty for Safe Utilization of Machine Learning in Medical Imaging

Recent Updates

Important Dates

  • July 1, 2022 Extended Paper Submission Deadline (23:59 PST)
  • June 24, 2022 Paper Submission Deadline (23:59 PST)
  • July 14, 2022 Reviews due
  • July 22, 2022 Publication of decisions
  • July 28, 2022 Camera ready submissions due
  • September 18, 2022 Workshop date
Note: Those are preliminary dates and may be subject to change.

About the MICCAI UNSURE Workshop


With the rise and influence of machine learning (ML) in medical application and the need to translate newly developed techniques into clinical practice, questions about safety and uncertainty over measurements and reported quantities have gained importance. Obtaining accurate measurements is insufficient, as one needs to establish the circumstances under which these values generalize, or give appropriate error bounds for these measures. This is becoming particularly relevant to patient safety as many research groups and companies have deployed or are aiming to deploy ML technology in clinical practice.

The purpose of this workshop is to develop awareness and encourage research on uncertainty modelling to ensure safety for applications spanning both the MIC and CAI fields. In particular, this workshop invites submissions to cover different facets of this topic, including but not limited to: detection and quantification of algorithmic failures; processes of healthcare risk management (e.g. CAD systems); robustness and adaptation to domain shifts; evaluation of uncertainty estimates; defence against noise and mistakes in data (e.g. bias, label mistakes, measurement noise, inter/intra-observer variability). The workshop aims to encourage contributions in a wide range of applications and types of ML algorithms. The use or development of any relevant ML methods are welcomed, including, but not limited to, probabilistic deep learning, Bayesian nonparametric statistics, graphical models and Gaussian processes. We also aim to ensure broad coverage of applications in the context of both MIC and CAI, which are categorized into reporting problems (descriptions of image contents) such as diagnosis, measurements, segmentation, detection, and enhancement problems (addition of information) such as image synthesis, registration, reconstruction, super-resolution, harmonisation, inpainting and augmented display.


In the last few years, machine learning (ML) techniques have permeated many aspects of the MICCAI community, leading to substantial progress in a wide range of applications ranging from image analysis to surgical assistance. However, in medical applications, algorithms ultimately assist life and death decisions, and translation of such innovations into practice requires a measure of safety. In practice, ML systems often face situations where the correct decision is ambiguous, and therefore principled mechanisms for quantifying uncertainty are required to envision potential practical deployment.

Safety is indeed paramount in medical imaging applications, where images inform scientific conclusions in research, and diagnostic, prognostic or interventional decisions in clinics. However, efforts have mostly focused on improving the accuracy, while systematic approaches ensuring safety of medical imaging-derived automated systems are largely lacking in the existing body of research.

Uncertainty quantification has recently attracted attention in the MICCAI community as a promising approach to provide a reliability metric of the output, and as a mechanism to communicate the knowledge boundary of such ML systems. Spurred on by this emergent interest, the workshop will encourage discussions on the topic of uncertainty modelling and alternative approaches for risk management in a wide range of medical applications. It aims thereby to highlight both fundamental and practical challenges that need to be addressed to achieve safer implementations of ML systems in the clinical world.

Call for Papers


We accept submissions of original, unpublished work on safety and uncertainty in medical imaging, including (but not limited to) the following areas:

  • Uncertainty quantification in any MIC or CAI applications
  • Risk management of ML systems in clinical pipelines
  • Out-of-distribution and anomaly detection
  • Defending against hallucinations in enhancement tasks (e.g. super-resolution, reconstruction, modality translation)
  • Robustness to domain shifts
  • Measurement errors
  • Modelling noise in data (e.g. labels, measurements, inter/intra-observer variability)
  • Validation of uncertainty estimates
  • Active Learning
  • Confidence bounds
  • Posterior inference over point estimates
  • Bayesian deep learning
  • Graphical models
  • Gaussian processes
  • Calibration of uncertainty measures
  • Bayesian decision theory

Submission Format

Submissions must be 8-page papers (excluding references) following the Springer LNCS format. 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 8 page limit refers only to the main content. Including references and acknowledgements the submission may exceed 8 pages.

How to submit?

The system is now open for submissions! Please submit papers using the paper submission system.
Submission Deadline: June 24, 2022 - 23:59 (PST)
Extended Submission Deadline: July 1, 2022 - 23:59 (PST)


All accepted papers will be published as part of the MICCAI Satellite Events joint LNCS proceedings to be published by Springer Nature.


Date and Location

Date: 18. September, 08:00-15:00 Singapore Time.
Location: Room Aquarius 2, or virtually on Pathable.


Timezone Information: All times below are given in Singapore Time (SGT). Please be mindful of time zone conversions when planning your attendance.
  • 08:00-08:05 Introduction
  • 08:05-08:50 Keynote - Prof. Dr. Ben Glocker
  • 08:50-09:25 Spotlight Session 1
    • 08:50-08:55
      On the pitfalls of entropy based uncertainty for multi-class semi-supervised segmentation (virtual), Martin van Waerebeke et al.

      Uncertainty Categories in medical image segmentation a study of source related diversity (virtual), Luke Whitbread et al.

      Calibration of deep medical image classifiers: an empirical comparison using dermatology and histopathology datasets (virtual), Jacob Carse et al.

      Joint paraspinal muscle segmentation and inter-rater labeling variability prediction with multi-task TransUNet (virtual), Parinaz Roshanzamir et al.

      Generalised probabilistic U-Net for medical image segmentation (in-person), Ishaan Bhat et al.

      nnOOD: A framework for benchmarking self-supervised anomaly localisation methods (in-person), Matthew Baugh et al.

      Information Gain Sampling for active learning in medical image classification (in-person), Raghav Mehta et al.
  • 09:30-10:00 Break
  • 10:00-11:20 Long Oral Session 1
    • 10:00-10:20
      Improved post-hoc probability calibration for out-of-domain MRI segmentation (in-person), Cheng Ouyang et al.

      Morphologically aware Jaccard based iterative optimization (MOJITO) for Consensus segmentation (in-person), Dimitri Hamzaoui et al.

      Improving Error detection in deep learning based radiotherapy autocontouring using Bayesian uncertainty (in-person), Prerak Mody et al.

      What do untargeted adversarial examples reveal in medical image segmentation (in person), Gangin Park et al.
  • 11:20-12:30 Lunch Break
  • 12:30-13:10 Long Oral Session 2
    • 12:30-12:50
      Quantification of Predictive Uncertainty via Inference Time Sampling (in-person), Katarina Tothova et al.

      Stochastic Weight Perturbations along the hessian: a plug-and-play method to compute uncertainty (virtual), Rahul Venkataramani et al.
  • 13:10-13:45 In-Person Poster Session
  • 13:45-14:10 Virtual Poster Session
  • 14:10-14:55 Keynote - Prof. Dr. med. Sergios Gatidis
  • 14:55-15:00 Concluding Remarks & Best paper award
  • Note regarding poster sessions: To accommodate virtual as well as in-person visitors of UNSURE 2022, we divided our poster session into two corresponding parts. All presenters (in-person and virtual) are asked to log on to the virtual poster session which will be implemented as breakout rooms from the main UNSURE Zoom room. This will give virtual attendees the opportunity to interact with all authors.

Keynote Speakers

Prof. Dr. Ben Glocker

Co-Lead of the Biomedical Image Analysis Group at Imperial College London. Lead of the HeartFlow-Imperial Research Team and Head of ML Research at Kheiron Medical Technologies.

Prof. Dr. med. Sergios Gatidis

Radiologist and Senior Researcher at the Empirical Inference Group at the Max Planck Institute for Intelligent Systems.

UNSURE2022 Organizing Committee


In alphabetical order

Christian Baumgartner

Cluster of Excellence: Machine Learning for Science, University of Tubingen

Adrian Dalca

MGH, Harvard Medical School

Koen Van Leemput

Technical University of Denmark and
Harvard Medical School

Raghav Mehta

Probabilistic Vision Group, Centre for Intelligent Machines, McGill University

Chen Qin

The University of Edinburgh

Carole Sudre

MRC Unit for Lifelong Health and Ageing, University College London / Centre for Medical Image Computing, University College London / Department of Biomedical Engineering, King's College London

Ryutaro Tanno

Department of Computer Science, University College London

William (Sandy) Wells

Radiology, BWH, Harvard Medical School

Program Committee

  • Adrian Galdran (Universitat Pompeu Fabra)
  • Alejandro Granados (King's College London)
  • Di Qiu (The Chinese University of Hong Kong)
  • Daniel Grzech (Imperial College London)
  • Evan Yu (Cornell University)
  • Fons van der Sommen (Eindhoven University of Technology)
  • Hongwei Li (Technical University of Munich)
  • Hongxiang Lin (University College London / Zheijiang Lab)
  • Irina Grigorescu (King's College London)
  • Jinwei Zhang (Cornell University)
  • Jorge Cardoso (King's College London)
  • Leo Joskowicz (Hebrew University of Jerusalem)
  • Liane Canas (King's College London)
  • Mark Graham (King's College London)
  • Max-Heinrich Laves (Leibniz Universitat Hannover)
  • Melanie Bernhardt (Imperial College London)
  • Pedro Borges (King's College London)
  • Raghav Mehta (McGill University)
  • Riccardo Barbano (University College London)
  • Robin Camarasa (Erasmus Medical Centre)
  • Stephen J. McKenna (University of Dundee)
  • Tanya Nair (McGill University)
  • Tewodros Arega (University of Bourgogne)
  • Tim Adler (DKFZ)
  • Tristan Glatard (Concordia University)
  • Contact

    For general inquiries please send an email to: unsure@mit.edu