Structural MRI‐Based AD Score using Bayesian VAEs
Aditya Nemali, Jose Bernal Moyano, Renat Yakupov, Hartmut Schütze, Annika Spottke, Alfredo Ramirez, Anja Schneider, Coraline D Metzger, Christoph Laske, Daniel Bittner, Michael T Heneka, Oliver Peters, Oliver Speck, Wenzel Glanz, Michael Wagner, Frank Jessen, Emrah Düzel, Gabriel Ziegler · 2025
Read Structural MRI‐Based AD Score using Bayesian VAEs by Aditya Nemali, Jose Bernal Moyano, Renat Yakupov, Hartmut Schütze, Annika Spottke, Alfredo Ramirez, Anja Schneider, Coraline D Metzger, Christoph Laske, Daniel Bittner, Michael T Heneka, Oliver Peters, Oliver Speck, Wenzel Glanz, Michael Wagner, Frank Jessen, Emrah Düzel, Gabriel Ziegler (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-11713417.txt.
Description
Aditya Nemali and co-authors build an Alzheimer score from brain scans that also states its own doubt. Their twenty twenty-five paper uses structural MRI and a Bayesian variational autoencoder. Standard scores give one number with no sense of how much to trust it.
The model learns a compressed picture of each brain and maps it to disease state, with uncertainty attached. Patients progress at wildly different speeds, which a doubt-aware score can respect. Clinicians weighing early treatment need to know when a scan read is firm and when it is a coin toss. A score that confesses its limits is safer than false precision.
Catalog record
| CREATOR | Aditya Nemali, Jose Bernal Moyano, Renat Yakupov, Hartmut Schütze, Annika Spottke, Alfredo Ramirez, Anja Schneider, Coraline D Metzger, Christoph Laske, Daniel Bittner, Michael T Heneka, Oliver Peters, Oliver Speck, Wenzel Glanz, Michael Wagner, Frank Jessen, Emrah Düzel, Gabriel Ziegler |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |