Aim:

This workshop aims to connect researchers, medical experts, policymakers, regulators, and industry partners from around the world who are working on translational ML solutions for real-world medical imaging in resource-constrained settings (RCS). This workshop builds on the successful MICCAI Meets Africa Workshop, organized in 2024 for the Morrocco meeting. While the 2024 workshop focused on ML solutions for Africa-specific healthcare challenges, this year’s workshop will broaden the scope to medical imaging challenges in countries and clinical practices with limited infrastructure, personnel, and funding resources.

Research and ML methods on optimization of imaging systems (e.g., accelerated imaging, low-resolution image enhancement, denoising, missing sequences), improvement in human resources (e.g., rapid diagnosis, reporting), and policy efforts for translation of ML from concept to clinic in RCS will be highlighted. The workshop will foster ML imaging innovations that address the general challenge of fewer datasets in RCS and inspire the wider MICCAI community to develop methods in a sustainability conscious and cost-effective manner (do more with little).

Workshop Focus Area

We are looking for long and short papers that will be presented as contributed talks. Specifically, we encourage contributions that highlight issues related to:

Theoretical and practical advances in machine learning algorithms and methods for medical imaging tailored for monitoring disease progression in settings with data scarcity, imbalanced representations, and limited computational resources.
Clinical outcome prediction and forecasting methods in multimodal healthcare data.
Societal and policy impacts of healthcare ML solutions in the global South focused on insights obtained via pilot studies, qualitative research, and human-in-the-loop settings.
Approaches to build and rapidly scale capacity for ML innovations in health in RCS, particularly in LMICs.

See the Call for Papers for details of core focus areas and topics