Abstract #1724

Classification Technique to Detect Activation Patterns in Pain FMRI Data

Loan Vo^1,2, Harish A. Sharma³, Y. Michelle Wang^1,4, Dirk B. Walther¹, Arthur F. Kramer^1,4, William Olivero⁵

¹Beckman Institute, University of Illinois at Urbana-Champaign, Urbana, IL, USA; ²Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA; ³Biomedical Imaging Center, University of Illinois at Urbana-Champaign, Urbana, IL, USA; ⁴Department of Psychology, University of Illinois at Urbana-Champaign, Urbana, IL, USA; ⁵Carle Foundation Hospital, Urbana, IL, USA

Traditional univariate GLM (General Linear Model) in fMRI analysis has its weakness as not taking into account the relationship between data from different (but adjacent or physiology related) voxels. In this back-pain study, we use classification method i.e multi-voxel pattern analysis to find the brain activation regions involved in pain processing. Using this technique we successfully detect the activations in the motor cortex, insula and thalamus region in the patients with low back pain.