Validation of QyScore® White Matter Hyperintensity (WMH) U‐Net segmentation algorithm against expert manual consensus and comparison with currently available state‐of‐the‐art methods
Elizabeth Gordon, Luca Villa, Nicolas Guizard, Philippe Tran · 2025
Read Validation of QyScore® White Matter Hyperintensity (WMH) U‐Net segmentation algorithm against expert manual consensus and comparison with currently available state‐of‐the‐art methods by Elizabeth Gordon, Luca Villa, Nicolas Guizard, Philippe Tran (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-11716598.txt.
Description
Elizabeth Gordon and co-authors validate an automated tool that outlines white matter bright spots on brain scans. Those spots matter across dementia and multiple sclerosis care, yet hand tracing is far too slow for routine use. The tool, a U-Net inside an approved imaging platform, promises expert-grade maps at machine speed.
The test set holds one hundred twenty-nine people scanned on three makers' machines. Patient groups span Alzheimer's disease, frontotemporal dementia, and multiple sclerosis. Three expert readers set the gold standard by consensus. The tool's maps are scored against theirs, then against six rival methods on a shared sclerosis set, at default and tuned settings. Overlap and volume scores carry the verdict. Solid marks would clear the tool for wider clinic trials.
Catalog record
| CREATOR | Elizabeth Gordon, Luca Villa, Nicolas Guizard, Philippe Tran |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |