TReNDS Neuroimaging Competition

In this competition, you will predict multiple assessments plus age from multimodal brain MRI features. You will be working from existing results from other data scientists, doing the important work of validating the utility of multimodal features in a normative population of unaffected subjects. Due to the complexity of the brain and differences between scanners, generalized approaches will be essential to effectively propel multimodal neuroimaging research forward.

The dataset consists of unbiased multimodal neuroimaging features from nearly 12K unaffected subjects and their associated age and assessment values (using 50/50 train/test split to minimize the test set prediction error). The competition will be hosted with Kaggle in a joint collaborative effort by OHBM, the IEEE SPS Data Science Initiative, and the IEEE Challenges and Data Collections Program.

Interested teams and participants will be considered for presenting/publishing their methods in a peer reviewed venue at the discretion of the competition evaluation committee. Special attention will be given to submissions achieving good prediction on the data subset coming from a second scanner, with the goal of encouraging methods unbiased by site/scanner effects.

We hope to stir interest and bring together non-imagers and imagers alike towards this common goal, pushing the envelope to assess the limits of current predictive technologies and gauge the clinical usefulness of neuroimaging features for personalized treatment.

Join the Competition: https://www.kaggle.com/c/trends-assessment-prediction/