Methods Overview.  1) Raw T1, T2, and FLAIR images were intensity corrected, 2) local image filters were computed in the volume then 3) sampled onto the gray-white junction surface; each feature was standardized within each subject.   4) Across healthy volunteers, dimensionality reduction was carried out using PCA, resulting in 14 features explaining 90% of the variance.  5) Iterative Gaussianization was used to nonlinearly convert each feature to a Gaussian distribution, creating a normative model of cortical variability.  6)  An average FCD vector was computed across all visually identifiable FCDs in our patient sample.  Similarity to the average FCD vector was assessed by projecting each patch onto the average FCD unit vector.  Local normalization was performed for each cortical location by subtracting the mean across homotopic patches in healthy volunteers at each location.  The purple HV homotopic patches can be seen to become centered around 0 following local normalization, while the FCD location becomes more atypical along both the FCD PC1 and PC2 directions.  7)  Following local normalization, the similarity maps were created based on the projection onto the mean FCD unit vector at each cortical location.  These maps were thresholded at 1%, retaining clusters of > 5 vertices, then an optimal threshold for mean cluster similarity was defined to distinguish between true positive FCD clusters and false positive clusters in healthy volunteers.  Clusters above this threshold are detected as FCDs.