Detection of Cerebral Vessels in MRA Based on 3D Steerable Filters
Shu Huazhong · Dianzi xuebao · 2006
A fully automatic method for enhancement and segmentation of three-dimensional cerebral vessels in low contrast MRA is presented.We obtain the 3D dyadic B-spline wavelets by extending the corresponding 1D wavelet.A 3D steerable filter is then developed based on 3D dyadic B-spline wavelets,it can be adapted 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 detected and then cerebral vessel tree can be extracted by simple thresholding.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.