Vessel enhancement in angiography images using decimation-free directional filter bank

Vessel enhancement is an important preprocessing step in accurate vessel tree reconstruction which is necessary in many medical imaging applications. Conventional vessel enhancement approaches used in literature are Hessian-based filters, which are found to be sensitive to noise and sometimes give discontinued vessels due to junction suppression. In this paper, we propose a new structure of Directional Filter Bank (DFB), named Decimation-free DFB, to decompose an input image into several directional images. In each directional image, due to the directional information known in advance, Hessian analysis is then performed less noise-sensitively. Also, the directional image decomposition helps to avoid junction suppression, which in turn, yields continuous vessel tree. Qualitative and quantitative evaluations performed on both synthetic and real angiography images show that the proposed filter generates better performance in comparison against the conventional approaches.