Automatic Detection of Cortical Thickness Measurement Errors using Support Vector Regression

Vitali Zagorodnov¹, Kallam Hanimi Reddy

Despite steady improvements in automated brain structural measurement algorithms (FreeSurfer, VBM, CLASP) over recent years, segmentation errors still frequently occur and require tedious manual review and editing of the segmentation results. We propose a framework based on Support Vector Regression to automatically highlight the errors in cortical thickness measurements, obtained using FreeSurfer segmentation pipeline. Our approach exploits high correlations between regional cortical thicknesses , which allows guessing what the correct measurement should be for a specific region, based on the rest of the brain measurements.