Multi-modal image registration using edge neighbourhood descriptor

Multi-modal medical image registration remains a challenging and active area of research owing to the difficulty of dealing with intensity distortions. Local patch-based entropy images were recently proposed to address this problem. However, this method suffers from the complexity of calculation of the entropy. Proposed is a new dense descriptor for an image, named the edge neighbourhood descriptor, which assigns different values to different image regions, namely the image background, image edges, edge neighbourhoods and the remaining area. The edge neighbourhood descriptor is faster than the entropy image. Experimental results show that this new descriptor can improve registration accuracy compared with the results of the entropy image and the mutual information method.