Addressing Limited Generalizability in Artificial Intelligence–Based Brain Aneurysm Detection for Computed Tomography Angiography: Development of an Externally Validated Artificial Intelligence Screening Platform
The authors developed the first publicly testable artificial intelligence model for aneurysm detection on CTA scans, demonstrating generalizability and state-of-the-art performance in external validation. The model addresses key limitations of previous efforts and enables broader validation through a web-based platform.
Authors
- Jean Filo
- Yu‐Ming Chang (ORCID: https://orcid.org/0000-0003-2431-1164)
- Christopher S. Ogilvy (ORCID: https://orcid.org/0000-0003-4600-8545)
- Felipe Ramirez‐Velandia (ORCID: https://orcid.org/0000-0003-1041-6360)
- Paulina Skrzypkowska (ORCID: https://orcid.org/0000-0002-7724-1334)
- Piotr Zieliński (ORCID: https://orcid.org/0000-0002-2085-4308)
- T Fodor (ORCID: https://orcid.org/0009-0002-0212-0543)
- Tomasz Szmuda (ORCID: https://orcid.org/0000-0003-1904-6773)
- Tomasz Klepinowski (ORCID: https://orcid.org/0000-0003-4806-2094)
- Philipp Taussky (ORCID: https://orcid.org/0000-0001-9247-0146)
- Samuel D. Pettersson (ORCID: https://orcid.org/0000-0003-4703-1624)
- Peter K. Liaw
Institutions
- Beth Israel Deaconess Medical Center (US)
- Harvard University (US)
- Gdańsk Medical University (PL)
Publication Details
- Journal
- Neurosurgery
- Published
- 2025-06-09
- DOI
- https://doi.org/10.1227/neu.0000000000003549
- Primary Topic
- Intracranial Aneurysms: Treatment and Complications
- Type
- article
- Field-Weighted Citation Impact
- 0.00