Contrast‐agnostic deep‐learning‐based detection of perivascular spaces in magnetic resonance imaging
Mario Díaz, Erelle Fuchs, Hendrik Mattern, Daniel Behme, Roberto Duarte, Maria del C. Valdes Hernandez, Joanna M Wardlaw, Stefanie Schreiber, Maria Trujillo, Jose Bernal Moyano · 2025
Read Contrast‐agnostic deep‐learning‐based detection of perivascular spaces in magnetic resonance imaging by Mario Díaz, Erelle Fuchs, Hendrik Mattern, Daniel Behme, Roberto Duarte, Maria del C. Valdes Hernandez, Joanna M Wardlaw, Stefanie Schreiber, Maria Trujillo, Jose Bernal Moyano (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11715394.txt.
Description
Mario Díaz and co-authors built a smart tool that finds tiny fluid gaps around brain vessels on any scan type. Older tools need hand tuning for each scan and often flag the wrong marks. Such gaps matter in vessel disease of the brain, where counts help grade harm. The new tool learned from fake scans built off brain maps, plus tube shapes that mimic the gaps.
The test set held scans from sixteen patients with bad vessel disease. An older sieve-style tool caught about eight in ten gaps but cried wolf a lot, with fewer than three in ten flags right. The new tool missed more on some scans yet was right nearly each time it flagged a gap. It kept that skill on both scan types with no fresh tuning. The team sees it as a step toward clinic-ready counts.
Catalog record
| CREATOR | Mario Díaz, Erelle Fuchs, Hendrik Mattern, Daniel Behme, Roberto Duarte, Maria del C. Valdes Hernandez, Joanna M Wardlaw, Stefanie Schreiber, Maria Trujillo, Jose Bernal Moyano |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |