Feature coincidence trees for registration of ultrasound breast images

Registration of an image, the query or reference, to a database of rotated and translated exemplars constitutes an important image retrieval and indexing application which arises in biomedical imaging, digital libraries, georegistration, and other areas. Two important issues are the specification of a class of discriminatory and generalizable image features and determination of an appropriate image-dissimilarity measure to rank the closeness of the query image with respect to images in the database. The theoretically best set of features and dissimilarity measure are those which can be implemented with the lowest misregistration error rate. We study a method based on feature discrimination using feature coincidence trees and mutual /spl alpha/-information measures of feature correlation. Feature coincidence trees represent the commonality between pairs of images using joint histograms of many simple features, or tags, which are organized in a data structure similar to that of Y. Amit and D. Geman's randomized trees for shape recognition (see Neural Computation, vol.9, p.1545-88, 1997). The mutual alpha-information measure is a ranking discriminant applied to the joint histograms which is motivated by a large deviations framework for detection error rates. We illustrate the methodology in the context of registering ultrasound scans of human breast images.