SIG-xMedIA aims to strengthen the exchange between research groups focused on explainable AI for real-world medical image analysis. Through its initiatives, the group aspires to make significant contributions to the development of XAI, promoting openness, transparency, and community-driven progress in this field.
Mission
By organizing satellite events at MICCAI conferences and biennial international workshops, SIG-xMedIA aims to:
Facilitate Collaboration: Provide platforms for researchers to collaborate, share insights, and collectively drive advancements in XAI.
Curate Datasets: Organize challenges like CARE 2024 and CARE 2025, curating standard and public real-world medical image datasets for model development and evaluation.
Financial Support for Education: Support tutorials, workshops, and educational initiatives to encourage diverse participation and foster best practices in the field.
Goals for Explainable AI for Medical Image Analysis
Establish a Specialized Community
Create a global community of researchers and clinicians dedicated to advancing XAI in medical image analysis.
Connect diverse perspectives and disciplines to collectively address challenges and opportunities in the field.
Promote XAI in MedIA
Facilitate collaboration among research groups to advance the development of explainable AI in real-world medical image analysis, which also sustains high consensus with clinicians.
Encourage consensus-building on principles guiding model design and evaluation.
Provide a Platform for Collaboration and Education
Create a platform for the exchange of ideas of explaining AI, methodologies of understanding decision-making process, and clinical practices of interpreting disease causes.
Foster collaboration through satellite events, workshops, and challenges, ensuring an open and reliable stage for evaluations and training.
Promote educational initiatives and opportunities in xMedIA to student communities by Student Board
Board Members
Shangqi Gao
PresidentUniversity of Cambridge
Shangqi Gao
Dr. Shangqi Gao is doing research on AI for Cancer Imaging. This focuses on applying advanced machine learning techniques to enhance the understanding and treatment of ovarian cancer. It is aimed to integrate and analyse diverse data types, including radiological imaging, genomics, liquid biopsies, and digital pathology, to define new biomarkers.
Read MoreNannan Shi
SecretaryShanghai Public Health Clinical Center
Fuping Wu
TreasurerUniversity of Oxford
Fuping Wu
Fuping Wu is now a postdoc researcher in medical image analysis, working at the Nuffield Department of Population Health.
Read MoreFreddy Odille
Clinical Translation ChairUniversity of Lorraine
Freddy Odille
Freddy Odille holds a degree in electrical engineering from ENSEM (2003) and a Ph.D. in control theory and signal processing from Henri Poincaré University in Nancy (2007). From 2007 to 2010, he completed a postdoctoral fellowship at University College London (UK).
Read MoreYufei Chen
Education ChairTongji University
Hangqi Zhou
Education ChairFudan University
Sihan Wang
Education ChairFudan University
Murtaza Taj
Technical ChairLahore University of Management Sciences
Murtaza Taj
Murtaza Taj earned his Ph.D. and M.Sc. degrees in electronic engineering and computer science from the Queen Mary University of London (QMUL), United Kingdom, in 2009 and 2005, respectively. Currently, he is an Assistant Professor at the Lahore University of Management Sciences, Syed Babar Ali School of Science and Engineering, Pakistan.
Read MoreAlejandro Frangi
AdvisorUniversity of Manchester
Alejandro Frangi
Activities
May 8 - September 27 2025 Toward real world medical image analysis
This challenge consists of four challenging tracks and encompasses imaging data from over 1300 patients collected across three continents
View Details
June 23 2025 Explainable AI for Medical Image Analysis
MICCAI Special Interest Group on Explainable AI for Medical Image Analysis
View Details
May 20 - October 10 2024 Toward real world medical image analysis
In this challenge, we set up a fair and public stage for developing and validating algorithms and applications of transferring foundation models to diverse real-world medical images to address specific practical medical image analysis problems
View Details