Meeting Banner
Abstract #3907

Automatic seed selection for resting state fMRI data analysis by using machine learning

Mingyi Li1, Katherine Koenig1, Jian Lin1, and Mark Lowe1

1Diagnostic Radiology, Cleveland Clinic, Cleveland, OH, United States

To facilitate seed-based resting state fMRI (rs-fMRI) data analysis, we have been developing a method to automatically compute the seed location by using anatomical and rs-fMRI data. In the method, self-organizing map (SOM) is used to cluster voxels within searching ROI and then the seed locations are derived from the voxel clusters. The methods were tested on ten subjects to find seed in the motor cortex. The computed seeds successfully matched unilateral finger tapping fMRI maps in eight out of ten subjects.

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

Join Here