RSNA launches a global AI challenge to develop models for detecting and localizing intracranial aneurysms in CT and MRI scans.
Key Details
- 1RSNA launches 2025 Intracranial Aneurysm Detection AI Challenge in collaboration with major neuroradiology societies.
- 2AI models will target identifying aneurysms in 13 anatomical locations using CT angiography, MR angiography, and MRI sequences.
- 3The dataset includes imaging from 18 sites across five continents, annotated by over 60 expert radiologists.
- 4A subset includes 3D segmentations for specific vascular locations in MRI.
- 5Challenge is open globally via Kaggle, with $50,000 in prizes for top nine competitors.
- 6Winners will be announced at RSNA’s annual meeting; top-performing models released under open licenses.
Why It Matters
This challenge is significant as it will drive innovation in AI solutions for neurovascular disease detection, leveraging diverse, expertly annotated datasets. The open licensing of top models will help propel further research, validation, and potential clinical adoption in radiology.
Source
AuntMinnie
Related News
•AuntMinnie
Paul Chang Discusses Foundation Models and Agentic AI at RSNA 2025
Dr. Paul Chang shares his insights on the role of foundation models and agentic AI in radiology at RSNA 2025.
•AuntMinnie
Toronto Study: LLMs Must Cite Sources for Radiology Decision Support
University of Toronto researchers found that large language models (LLMs) such as DeepSeek V3 and GPT-4o offer promising support for radiology decision-making in pancreatic cancer when their recommendations cite guideline sources.
•AI in Healthcare
Nvidia, Amazon Drive AI Expansion Across Genomics and Radiology
Major healthcare and technology companies partner to push AI advancements in genomics, radiology, and broader healthcare.