Date of Award

2013

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Electrical and Computer Engineering

Committee Chair

Reza R. Adhami

Committee Member

Jennifer M. English

Committee Member

Laurie L. Joiner

Subject(s)

Breast--Radiography, Breast--Cancer--Diagnosis, Breast--Imaging, Diagnostic imaging, Medical screening

Abstract

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.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.