Detection of Cerebral Vessels in MRA Using 3D Steerable Filters

This paper describes a fully automatic method for enhancement and segmentation of three-dimensional(3D) cerebral vessels in MRA. We obtain the 3D dyadic B-spline wavelets by extending corresponding 1D wavelet. A 3D steerable filter is then developed based on 3D dyadic B-spline wavelets. One can adaptively steer the filter to an arbitrary direction. The oriented energy of filter response is introduced for detecting orientation strength of vessels in that direction. The points with maximum of local oriented energy across multiple scales are regarded as vessel points. This method was tested on real MRA data and promising results have been obtained. It could be suitable for other types of curvilinear structures such as cardiovascular vessels, bronchial tree.