Automatic extraction of corresponding points for the registration of medical images

In this paper we address the problem of finding corresponding points in a r eference and its subsequent image with the aim of registering the images. A whole-image-content-based automatic algorithm for extracting point pairs f rom 2-D monomodal medical images has been developed. The properties of poin t distinctiveness, point pair similarity, and point pair consistency have b een incorporated into the steps which lead to the automatic extraction and weighting of point pairs. The selection of the most distinctive points of t he reference image, and the search for their corresponding points in the su bsequent image, have two things in common. First, the local operator by whi ch the distinctive points are selected mimics the template matching used to find the corresponding points. Second, the same similarity measure is used for both tasks. We have applied the algorithm to a variety of computer-gen erated and real medical images, and have both qualitatively and quantitativ ely evaluated its performance. The results show that the proposed automatic algorithm for point extraction is accurate and robust and that it may sign ificantly improve on the accuracy, reproducibility, and speed of the manual extraction of corresponding points. (C) 1999 American Association of Physi cists in Medicine. [S0094-2405(99)02708-X].