RSNA Intracranial Aneurysm Detection

Overview

This competition challenges you to build machine learning models to detect and locate intracranial aneurysms in multimodal medical images like CTA, MRA, and MRI. The models will need to handle real-world clinical variations from different institutions and scanners to accurately diagnose these potentially life-threatening conditions.

Requirements

Your submission should be a Kaggle Notebook that uses the provided evaluation API to detect aneurysms. The notebook must have a runtime of 12 hours or less for both CPU and GPU, with internet access disabled. Freely available external data and pre-trained models are allowed. The submission file must be named submission.csv. Winners are also required to provide their training code, a video presentation, and a method description.

Prizes

The competition offers a total of $50,000 in prizes, with $12,000 for first place, $10,000 for second, $8,000 for third, $5,000 for fourth, and $3,000 for places 5th through 9th. Winners will also be invited to attend the AI Challenge Recognition Event at the RSNA Annual Meeting.