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

Grand Challenge embraces the FAIR principles for data, algorithms, and challenges. Whether your data is from Radiology, Pathology, or Ophthalmology, we validate and convert it into standardized formats, enabling seamless sharing and reuse across the platform. We’re also expanding to support additional medical data modalities, such as Genomics and Cardiology. Beyond medical data, the platform accommodates various formats, including PDF, JSON, and MP4. Our custom viewer lets you explore data in Archives, create annotations in Reader Studies, and review Algorithm results effortlessly.

Validate and compare algorithms

Host a Challenge to test and compare algorithms developed by the research community or commercial parties. Grand Challenge will run the algorithms on the secret test data, allowing for fair comparison of performance without exposing this data. Design custom metrics specific to your data and algorithms to create a meaningful leaderboard.

Offer your algorithms to the world

Share your algorithm, either by granting access to specific users or by making it public and allow these users to try your algorithm on their own data. This approach promotes open science, facilitates collaboration, and encourages the sharing of research results.

Connect with a large community

Join the global Grand Challenge community that currently consists of over 100.000 users with a shared interest: AI in medical imaging. Connect with users through MICCAI, RSNA, MIDL, IDC and SPIE Medical Imaging. Invite community members to contribute, whether you are interested in hosting your own challenge, offering data, or providing access to your algorithm.

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.