Meeting Banner
Abstract #4844

Unsupervised learning with multi-parametric diffusion MRI to detect brain injury in concussed athletes

L. Tugan Muftuler1, Timothy B. Meier 1, and Michael A. McCrea1
1Neurosurgery, Medical College of Wisconsin, Milwaukee, WI, United States


Despite high prevalence of concussion in contact sports, there is still a lack of reliable, unbiased biomarkers of brain injury and recovery following sport-related concussion. The changes in imaging biomarkers after concussion are generally subtle such that signs of abnormalities are detected only in group analyses with large cohorts. Although diffusion MRI techniques show promise, detecting injury in individual subjects is still a challenge. The goal of this project is to identify potential signatures of brain injury in an individual subject with concussion using an unsupervised learning method using parameters derived from diffusion kurtosis imaging (DKI).

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

Join Here