Similarity measures for subtraction methods in medical imaging

The authors recommend the use of an entropy similarity measure for the registration of image pairs prior to subtraction in medical imaging (e.g. digital subtraction angiography (DSA) or MR mammography). A comparison of cross-correlation function, cross-structure function and deterministic sign change to the new entropy similarity measure reveals the advantages of the latter. The data driven approach is especially suitable for registration of two images which are identical except for some structures visible in one but not in the other image