DeepSUVR: Using temporal constraints to improve SUVR and Centiloid quantification
Pierrick Bourgeat, Jurgen Fripp, Ashley G Gillman, Timothy Cox, Manu S Goyal, Duygu Tosun, Pamela LaMontagne, Tammie LS Benzinger, Michael S W Weiner, Victor L Villemagne, Colin L Masters, Christopher C Rowe, Vincent Dore · 2025
Read DeepSUVR: Using temporal constraints to improve SUVR and Centiloid quantification by Pierrick Bourgeat, Jurgen Fripp, Ashley G Gillman, Timothy Cox, Manu S Goyal, Duygu Tosun, Pamela LaMontagne, Tammie LS Benzinger, Michael S W Weiner, Victor L Villemagne, Colin L Masters, Christopher C Rowe, Vincent Dore (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-11713578.txt.
Description
Pierrick Bourgeat and co-authors clean up brain amyloid measurements with a learning method that watches change over time, in this 2025 paper. PET scans gauge amyloid with a ratio that leans on a reference brain region, and noise there corrupts the score. Their network, DeepSUVR, learns a per-scan correction by penalizing changes that make no biological sense, like amyloid shrinking over time.
Trained on thousands of repeated scans, the method tightened agreement between different tracers and steadied each person's trend across visits. Corrections run on single scans, so clinics need no history to use it.
Catalog record
| CREATOR | Pierrick Bourgeat, Jurgen Fripp, Ashley G Gillman, Timothy Cox, Manu S Goyal, Duygu Tosun, Pamela LaMontagne, Tammie LS Benzinger, Michael S W Weiner, Victor L Villemagne, Colin L Masters, Christopher C Rowe, Vincent Dore |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |