Comparison of rigid and elastic matching of dynamic magnetic resonance mammographic images by mutual information

Abstract
The present study aims at (i) the evaluation of the performance of a rigid and of an elastic matching algorithm for the coregistration of dynamic magnetic resonance (MR) images visualizing the female breast, and (ii) the evaluation of the mutual information (MI) as a matching criterion. To this end, ten patient data sets were analyzed. The comparison was performed with respect to the achieved increase in the MI and by visual inspection of the dynamic image series in a continuous film sequence (cine mode). In most cases, the achieved increase in MI by elastic image registration is much higher than that achieved by rigid registration. Only for three of the ten data sets could the MI be increased by rigid image registration to a similar or even larger degree than by elastic image registration. Taking into account the results of the visual inspection of the rigid and elastic matched data sets, however, the elastic match leads to equal or better results for all data sets. Therefore, elastic matching is the gold standard for the registration of dynamic MR mammographic images of the female breast. The comparison of the increase in MI and the visual inspection further shows that the visual impression agrees in most cases with the result of the calculation of the MI. Therefore, the MI proves to be a suitable matching criterion for the type of data sets studied.