Local normalization allows for the detection of differences from the expected appearance at any given cortical location.  Following local normalization, as expected, we found that patches in the outlier ROIs appeared more "typical" for their location, now with a similar Mahalanobis distance to randomly selected cortical patches (random cortex MD = \(1.86\pm0.52\) versus precentral MD = \(1.92\pm0.52\)\(d=0.10\), and insula MD = \(1.59\pm0.36\)\(d=0.63\)).  In contrast, following local normalization, FCDs remained as significant outliers (MD = \(3.55\pm0.81\)) compared to both normal cortex and the previously outlying ROIs (versus normal cortex  \(d=2.81\),  precentral \(d=2.78\), insula \(d=4.09\)) (Figure 4B).  Cosine similarity between FCD patches also became significantly higher following local normalization (\(0.40\pm 0.26\)) compared to non-lesional patches at any location (to homotopic patches \(cos=0.00\pm 0.30\)\(p<0.001\)\(d=1.40\), and to heterotopic patches \(cos=0.00\pm 0.28\)\(p<0.001\)\(d=1.44\), with no difference between the two, \(p=0.54\), ) (Figure 4B, left).  Local normalization, therefore, not only aids with global outlier detection by decreasing the "outlierness" of normal cortical regions, but also with local outlier detection, by further distancing FCDs from the expected appearance in their homotopic regions.