Document Type

Thesis - University Access Only

Award Date

2012

Degree Name

Master of Science (MS)

Department / School

Electrical Engineering and Computer Science

First Advisor

Sung Y. Shin

Abstract

About 1 in 8 women in the United States is expected to develop breast cancer over the course of her entire lifetime but a few medical imaging techniques have been applied for breast cancer screening [ 1]. In addition, the feature extraction and comparison in medical images for breast cancer detection have rarely been reported in literature. This study proposes a new framework to extract abnormal features in medical images and compare them by relating original characteristic patterns thereof. This method concentrates on two key aspects: (1) Extracting an abnormal feature from a medical image by Support Vector Machine (SVM) classifier and (2) Generating a parametric shape pattern of the extracted feature. The main contribution of the proposed approach is improving a method of identifying features which is less sensitive to noise in medical images for breast cancer detection and presenting an original design of relating features which is invariant to the orientation and size of the feature. Experimental results demonstrate that the proposed approach is accurate and tolerant of an image noise and generates an invariant characteristic pattern of various orientations and sizes.

Publisher

South Dakota State University

Download

Share

COinS
 

Rights Statement

In Copyright