About
Grand Challenge is a platform for collaborative AI development in medical imaging. Built to support researchers, clinicians, and developers worldwide, Grand Challenge enables the creation, evaluation, and deployment of medical imaging algorithms—all in one secure, cloud-based environment.
Whether you're running a global reader study, hosting an AI challenge, or sharing your algorithm with the world, Grand Challenge provides the tools to accelerate innovation while keeping your data safe. Our mission is to make cutting-edge medical AI accessible, reproducible, and impactful through collaboration and robust infrastructure.
Developing and benchmarking algorithms demands expertise, secure data storage, hardware access, and attention to security, performance, and community trust. The Grand Challenge platform addresses these needs by providing a secure, user-friendly environment with automated features to streamline the process.
With Grand Challenge, you can
Securely store and share your data
Validate and compare algorithms
Offer your algorithms to the world
Connect with a large community
High-profile contributions
The Pi-cai challenge
A challenge to validate modern AI algorithms and estimate radiologists’ performance at csPCa detection and diagnosis, using a large dataset of over 10,000 carefully curated MRI exams.
Saha et al., Lancet Oncology 2024
The Project AIR challenges
Two challenges to perform an independent, stand-alone validation of commercially available algorithms for bone age prediction on hand radiographs and lung nodule detection on chest radiographs. It showcases the comparison of commercial AI products to help healthcare objectively choose the best AI products
Leeuwen et al., Radiology 2024.
The TIGER challenge
Tiger: a challenge on fully automated assessment of tumor-infiltrating lymphocytes (TILs) in H&E breast cancer slides. It is the largest comprehensive multi-centric validation of multiple cTILs methods on surgical resections and biopsies using 3,708 Triple Negative Breast Cancer (TNBC) and human epidermal growth factor receptor 2 positive (HER2+) breast cancers from clinical practice and phase 3 clinical trials.
M. van Rijthoven et al., Preprint 2025.
The Team
The software behind Grand Challenge is open source. It was largely written by the team of Research Software Engineers from the Diagnostic Image Analysis Group at Radboud University Medical Center. Radboud University Medical Center is also the responsible entity for the website.