Abstract #1294
Investigating Brain Connectomic Alterations in Autism using Reproducibility of Independent Components derived from Resting State fMRI
Mohammed Syed 1 , Zhi Yang 2 , and Gopikrishna Deshpande 3,4
1
Department of Computer Science and Software
Engineering, Auburn University, Auburn, AL, United
States,
2
Key
Laboratory of Behavioral Sciences, Institute of
Psychology, Chinese Academy of Sciences, Beijing, China,
3
Department
of Electrical and Computer Engineering, Auburn
University, Auburn, AL, United States,
4
Department
of Psychology, Auburn University, Auburn, AL, United
States
Autism is a heterogeneous spectrum disorder, hence fMRI
connectivity metrics derived from the autism group may
not be highly reproducible within that group, leading to
poor generalizability which in turn leads to lower
classification accuracies. We hypothesize that
functional brain networks that are most reproducible
within autism and healthy control groups separately, but
not when the two groups are merged, may possess the
ability to distinguish effectively between the groups.
We characterize reproducibility of networks using
generalized Ranking and Averaging Independent Component
Analysis by Reproducibility (gRAICAR) algorithm and
provide evidence in support of the above hypothesis.
This abstract and the presentation materials are available to members only;
a login is required.
Join Here
