Date of Award

12-1-1994

Document Type

Thesis

Degree Name

Master of Science

Department

Department of Electrical and Computer Engineering

First Advisor

Steven K. Rogers, PhD

Abstract

Breast cancer is a disease that accounts for a disturbingly large number of deaths in females each year. Its prevalence is a topic of concern to all of us since it can affect our families, friends, and coworkers. Although mammographic screening is the most effective method currently available for the early detection of breast cancer, it is far from being an infallible procedure. Mammographic reading is error prone, partly because of the complexity of the task and partly because of the variability in human performance. Computers offer high reproducibility, and when used as an adjunct by the radiologist, may improve diagnostic accuracy and thus the mammographic screening process. The goal of this research was to create using MATLAB version 4.2 (UNIX) and the MATLAB Image Processing Toolbox a menu-based, mouse-driven, and keyboard interactive Mammography Image Processing Program that would support the future research and development of complex segmentation, feature extraction, and classification algorithms. McCall's software quality factors are used on a general level to assess the program's operational characteristics, ability to undergo change, and adaptability to new environments. An important criteria driving this research was to build a platform that would provide full source code accountability so that errors in earlier image processing stages could be fixed and not allowed to propagate through to later stages.

AFIT Designator

AFIT-GCS-ENG-94D-12

DTIC Accession Number

ADA289228

Comments

The author's Vita page is omitted.

Share

COinS