Vessel enhancement filter using 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 the 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 novel framework for vessel enhancement for angiography images. The proposed approach incorporates the use of line-like directional features present in an image, extracted by a directional filter bank, to obtain more precise Hessian analysis in noisy environment and thus can correctly reveal small and thin vessels. 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 two Hessian-based approaches. In average, it is relatively 3.74% and 7.02% less noise-sensitive and performs 5.83% and 6.21% better compared to the two approaches, respectively.