Impact of AI‐based segmentation on PET analyses
Luc Bracoud, Thomas Cajgfinger, Olivier Rousset, Madhura Ingalhalikar, Chris Conklin, Manja Lehmann, Joel Schaerer, David Scott, Joyce Suhy, the Alzheimer's Disease Neuroimaging Initiative · 2025
Read Impact of AI‐based segmentation on PET analyses by Luc Bracoud, Thomas Cajgfinger, Olivier Rousset, Madhura Ingalhalikar, Chris Conklin, Manja Lehmann, Joel Schaerer, David Scott, Joyce Suhy, the Alzheimer's Disease Neuroimaging Initiative (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-11715471.txt.
Description
Measuring Alzheimer's plaques in a scan requires outlining the brain's regions on an MRI first, and the standard outlining tool is slow and dated. Luc Bracoud and co-authors test whether a new AI outlining method can take over without bending the plaque numbers. Their 2025 study uses five hundred and seven volunteers from a national imaging archive. Each brain was outlined both ways and the plaque readings compared.
The sample spans healthy minds through full disease, and two hundred and ten people had repeat scans to check steadiness. Uptake values in four cortical regions and two reference regions were set side by side, then converted to a common scale. Bland-Altman and correlation checks judged agreement. Swapping the engine that draws the map, the study asks, must not move the territory: a quiet but necessary validation for faster trial pipelines.
Catalog record
| CREATOR | Luc Bracoud, Thomas Cajgfinger, Olivier Rousset, Madhura Ingalhalikar, Chris Conklin, Manja Lehmann, Joel Schaerer, David Scott, Joyce Suhy, the Alzheimer's Disease Neuroimaging Initiative |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |