Attention mechanism‐based prediction of early tau accumulation using MRI
Jin‐Yang Kim, Yeong‐Hun Song, Wha Jin Lee, Joon‐Kyung Seong, ADNI · 2025
Read Attention mechanism‐based prediction of early tau accumulation using MRI by Jin‐Yang Kim, Yeong‐Hun Song, Wha Jin Lee, Joon‐Kyung Seong, ADNI (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-11710466.txt.
Description
Jin-Yang Kim, Yeong-Hun Song, Wha Jin Lee, and Joon-Kyung Seong train a model to spot early tau buildup from ordinary MRI scans. Their 2025 study uses data from the ADNI cohort. Tau scans predict Alzheimer's progression, but they cost much and expose patients to radiation. Two early-hit regions, the lateral entorhinal cortex and the inferior temporal gyrus, were the prediction targets.
The data set held 1,010 paired MRI and tau-PET scans, split into training, validation, and test portions. Software measured cortical thickness from the MRI side, while the PET side yielded tau values for sixty-six regions. Positivity was defined against cognitively normal subjects. An attention-based encoder-decoder, adapted from the Transformer family, learned to forecast the early regions' tau status from MRI alone.
Catalog record
| CREATOR | Jin‐Yang Kim, Yeong‐Hun Song, Wha Jin Lee, Joon‐Kyung Seong, ADNI |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |