The RSNA has launched its 2025 Intracranial Aneurysm Detection AI Challenge to motivate the creation of AI tools for the detection and localization of intracranial aneurysms.
The goal of the challenge, developed in collaboration with the American Society of Neuroradiology, the European Society of Neuroradiology, and the Society of Neurointerventional Surgery, is to develop machine-learning models for identifying intracranial aneurysms across a variety of medical imaging modalities, including CT angiography, MR angiography, and T1 postcontrast and T2-weighted MRI.
The challenge is open to all researchers and will be conducted on a platform provided by Kaggle. Participants will be tasked with detecting and localizing aneurysms across 13 distinct anatomical locations within the intracranial circulation where aneurysms commonly arise. The reference dataset provided will include CT and MR imaging exams from 18 sites across five continents, annotated by more than 60 expert radiologists for the presence and location of aneurysms.
Additionally, a subset of MRI studies will be available that will include 3D segmentations of the same 13 vascular locations.
The competition is open through October 14, 2025. Winners will be announced in November, and winning teams will be recognized in the AI Theater during the RSNA's meeting in November/December. A total of $50,000 in prize money will be distributed to the top nine competitors. The highest performing models will be made available under open licenses to encourage additional research, the society said.
Information about the 2025 Intracranial Aneurysm Detection AI Challenge may be found on RSNA’s website. For more information on RSNA AI challenges, visit RSNA.org/AI-image-challenge or contact [email protected].
