Filament enhancement by non-linear volumetric filtering using clustering-based connectivity

Shape filters are a family of connected morphological operators that have been used for filament enhancement in biomedical imaging. They interact with connected image regions rather than individual pixels, which can either be removed or retained unmodified. This prevents edge distortion and noise amplification, a property particularly appreciated in filtering and segmentation. In this paper we investigate their performance using a generalized notion of connectivity that is referred to as "clustering-based connectivity". We show that we can capture thin fragmented structures which are filtered out with existing techniques.