SURF Research Bootcamp 2025

ℹ️ About the tutorial¶

Grand-Challenge.org is an open platform for hosting AI benchmarks in medical imaging. During this 2-hour, hands-on tutorial, we will cover the core components of the platform. Through so-called Challenges, we will examine algorithms and evaluations.

Participants will learn:

• how to integrate containerized algorithms.
• configure custom evaluation metrics.
• interpret leaderboard results on the platform.

Through guided mini-lectures and hands-on tutorials, attendees will debug, adapt, and test their own benchmarking!

By the end of the session, participants will understand how Grand Challenge manages algorithm execution and evaluation in a reproducible way. They will leave with a clearer mental model of how submissions are processed, and the confidence to understand or design their own benchmarking workflows.

Whether you’re developing models, supporting challenge organizers, or simply curious about how large-scale benchmarking is automated, this tutorial offers a compact but practical introduction to the infrastructure behind AI validation!

🧑‍💻 Prepare for the tutorial¶

You will be expected to bring:

• a laptop
• some minimal Python-programming experience