Abstract #1357

Intrinsic functional connectivity of spinal cord can be used to differentiate injured monkeys from normal using machine learning

Anirban Sengupta¹, Arabinda Mishra^1,2, Feng Wang^1,2, Li Min Chen^1,2,3, and John C Gore^1,2,4,5,6

¹Institute of Imaging Science, Vanderbilt University Medical Center, Nashville, TN, United States, ²Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, TN, United States, ³Psychology, Vanderbilt University Medical Center, Nashville, TN, United States, ⁴Physics and Astronomy, Vanderbilt University Medical Center, Nashville, TN, United States, ⁵Molecular Physiology and Biophysics, Vanderbilt University Medical Center, Nashville, TN, United States, ⁶Biomedical Engineering, Vanderbilt University Medical Center, Nashville, TN, United States

The objective of this study was to investigate the presence of robust intrinsic networks inside the spinal cord of squirrel monkey and whether connectivity measures of these networks can detect injury in spinal cord. We used Independent Component Analysis of resting state fMRI data to obtain dorsal and ventral networks within the gray-matter of spinal cord. Within Horn Connectivity and Between Horn Connectivity measures were calculated based on the time course of Independent Components. A Support-Vector-Machine classifier could differentiate a spinal cord injured monkey from a control monkey using these connectivity measures with a low classification error of 6.67 %.

This abstract and the presentation materials are available to members only; a login is required.

Join Here