sepehrband/Mining_NeuroAnat

Neuroanatomical morphometric characterization of sex differences using univariate linear regression and multivariate statistical learning

Neuroanatomical Morphometric Characterization of Sex Differences

This repository accompanies below paper:

Sepehrband, F., Lynch, K.M., Cabeen, R.P., González-Zacarías, C., Zhao, L., D’Arcy, M., Kesselman, C., Herting, M.M., Dinov, I.D., Toga, A.W., Clark, K.A., 2018
Neuroanatomical Morphometric Characterization of Sex Differences in Youth Using Multivariate Statistical Learning
NeuroImage, 172:217–227. https://doi.org/10.1016/j.neuroimage.2018.01.065.

Source codes

• NeuroAnat_SexDiff/code contains source codes
• NeuroAnat_SexDiff/demo contains .html files of the same codes (compiled and static presentation)

Source codes include:

• Explatory analysis
• Linear regression
  • Ordinary least square implementation
  • Robust linear modeling with Huber's loss function using least trimmed squares estimator
• Non-parameteric correlation analysis
  • Spearman's rank correlation
• Multivariate logistic regression
• Statistical learning
  • Support vector machine
• Inferential analysis
  • Mapping between-group differences
  • Plotting statistical summeries

Raw data and preparation

• Strucutral MRI of the PNC study were used for this study.
• Morphological features of the strucutral images were derived using FreeSurfer toolkit.
• FreeSurfer analysis was performed using LONI pipeline on high performance computing of USC Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck school of Medicine of USC. The outputs were QC'ed and used in this study.
• Data is available upon request and approval. See LICENSE for more information.

---

author:
Farshid Sepehrband,
Laboratory of Neuro Imaging,
Mark and Mary Stevens Neuroimaging and Informatics Institute,
Keck School of Medicine,
University of Southern California, Los Angeles, CA, USA
farshid.sepehrband@loni.usc.edu
@fsepehrband