A feature selection framework for white matter fiber clustering based on normalized cuts

Abstract

Due to its ability to automatically identify spatially and functionally related white matter fiber bundles, fiber clustering has the potential to improve our understanding of white matter anatomy. The normalized cuts (NCut) criterion has proven to be a suitable method for clustering fiber tracts. In this work, we show that the NCut value can be used for unsupervised feature selection as a measure for the quality of clustering. We further present a method how feature selection can be improved by penalizing spatially illogical clustering results, which is achieved by employing the Silhouette index for a fixed set of geometric features.