Cancer is the second leading cause of death in Europe1. With 3.7 million new cancer cases in Europe each year, it is clear that clinicians require innovative tools and resources to improve cancer diagnosis, therapy, patient selection, and prediction. Artificial intelligence (AI) has emerged as a promising technology that can support these goals. In the search for new AI opportunities to advance medical research and improve patient outcomes, the consortium partners of the EU-funded CHAIMELEON Project have created the CHAIMELEON Open Challenges.
The CHAIMELEON Open Challenges is a competition designed to train and refine AI models to answer clinical questions about five types of cancer: prostate, lung, breast, colon, and rectal. Participants are challenged to collaborate and develop innovative AI-powered solutions that can significantly impact cancer diagnosis, management, and treatment. They will be evaluated considering a balance between the performance of their AI algorithms to predict different clinical endpoints such as disease staging, treatment response or progression free survival and their trustworthiness. Those who take on the challenge can win a total prize pool of €20,000 per challenge, split amongst the winners, with €100,000 in prizes.
The CHAIMELEON Open Challenges offers a unique opportunity for researchers to collaborate and develop new solutions that can have a significant impact on cancer diagnosis and treatment. The registration for the challenges will open on July 3rd, 2023 and will be available until the end of August 2023. The challenges will be divided in two phases: the Classification Phase and the Championship Phase.
The Classification Phase will extend from July to September 2023. In this phase, any participant can join and download a highly controlled cancer dataset. The dataset will consist of post-processed (i.e., harmonised) images associated with specific clinical variables, ensuring a level playing field for all participants. The participants will train their AI models and compete to be among the top on the leaderboard.
The Championship Phase will extend from October to December 2023. In this phase the top 40 participants from the previous phase will be invited to compete on an even grander stage, using the CHAIMELEON platform to train their algorithms. This phase will include five different challenges, one for each cancer type (prostate, lung, breast, colon, and rectal), with a total prize pool of 20.000€ per challenge, split among the winners. Original images and associated clinical data, along with different image pre-processing and harmonization tools, will be available to participants who have passed the qualifying round cut-off point. The same computational resources will be assigned to each participant; therefore, each participant can decide which challenges to tackle and apply their strategies accordingly.
Quibim will be the leading specialised company managing the challenges, as it has vast experience in cancer research through AI. Ángel Alberich-Bayarri, CEO and co-founder of Quibim, says, “The excitement of being part of this one-of-a-kind project is immense; we get to participate in what will be a significant step forward in cancer research. The CHAIMELEON Open Challenges are an encouraging opportunity for the scientific community because they will enable researchers to leverage the power of AI to develop new solutions.”
The challenges are open to the whole scientific and tech community interested in AI. They are a unique opportunity to showcase how AI can be used to advance medical research and improve patient outcomes within the CHAIMELEON project.
