Generative dynamical models for classification of rsfMRI data
Grace Huckins, Russell A Poldrack · 2024
Read Generative dynamical models for classification of rsfMRI data by Grace Huckins, Russell A Poldrack (2024) 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-11675094.txt.
Description
Grace Huckins and Russell Poldrack test a new way to sort brain scans by what a person is doing or experiencing, in a 2024 paper. Most studies read resting-state brain scans as still pictures and ignore how activity shifts over time. The authors instead fit hidden Markov models, which track hidden states and the odds of moving between them. One model is fit for each class, and new scans are labeled by which model fits them best.
The method worked on the MyConnectome dataset, sorting scans from the same person using only the shift patterns between states. The result shows that timing patterns alone carry useful signal for sorting scans. The approach also avoids some statistical limits that block other dynamic methods.
Catalog record
| CREATOR | Grace Huckins, Russell A Poldrack |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 58 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |