Date of Award
Master of Science (MS)
Electrical and Computer Engineering
Reza R. Adhami
Jennifer M. English
Laurie L. Joiner
Breast--Radiography., Breast--Cancer--Diagnosis., Breast--Imaging., Diagnostic imaging., Medical screening.
Accurate mammogram registration is vital to future breast cancer research. In order to detect changes over time and/or bilateral asymmetry, computer aided detection algorithms must first be able to accurately align two mammogram images. The registration algorithm in this thesis is a novel process designed to accurately register two mammogram images using the Pompeiu-Hausdorff distance as a similarity measure. The algorithm identifies the optimal translation and rotation that can be used to properly align the two mammogram images by computing the optimized Pompeiu-Hausdorff distance between extracted feature point-sets and adaptively fine tuning the parameters with each iteration. This automated algorithm, on average, is more accurate, efficient and robust than current mammographic registration techniques, such as registration based on mutual information.
Cunningham, Stephanie Cleveland, "A novel mammogram registration algorithm for improving breast cancer detection" (2013). Theses. 25.