Cargando…
Functional connectome fingerprinting using shallow feedforward neural networks
Although individual subjects can be identified with high accuracy using correlation matrices computed from resting-state functional MRI (rsfMRI) data, the performance significantly degrades as the scan duration is decreased. Recurrent neural networks can achieve high accuracy with short-duration (72...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
National Academy of Sciences
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8053937/ https://www.ncbi.nlm.nih.gov/pubmed/33827923 http://dx.doi.org/10.1073/pnas.2021852118 |
Sumario: | Although individual subjects can be identified with high accuracy using correlation matrices computed from resting-state functional MRI (rsfMRI) data, the performance significantly degrades as the scan duration is decreased. Recurrent neural networks can achieve high accuracy with short-duration (72 s) data segments but are designed to use temporal features not present in the correlation matrices. Here we show that shallow feedforward neural networks that rely solely on the information in rsfMRI correlation matrices can achieve state-of-the-art identification accuracies ([Formula: see text]) with data segments as short as 20 s and across a range of input data size combinations when the total number of data points (number of regions [Formula: see text] number of time points) is on the order of [Formula: see text]. |
---|