Morphological procedure for mammogram enhancement and registration

Screening mammography often incorporates a computer aided diagnosis (CAD) scheme in its procedure to increase the detection rates of gradual changes in breast tissues. One method for detecting gradual changes in temporal mammograms is through the use of registration algorithms. Images of degraded resolution present an obstacle to accurate registration, however. The performance of registration algorithms and, hence, the performance of the CADs are directly proportional to the quality of the input mammograms. In this paper, we present a novel approach for increasing the quality of the mammograms based on morphological operations and contrast enhancement prior to performing the registration step. The registration algorithm is applied using a structural similarity (SSIM) index. Based on the radiologist’s evaluation, this work provided accurate results that were more helpful in detecting changes over time in the registered mammogram pair.