Masters Theses

Abstract

"This paper deals with the automation of the detection of the cervical cancer through histology images. This process is divided into two parts, corresponding to segmentation and data fusion. The segmentation and classification of the cervical epithelium images is done using hybrid image processing techniques. The digitized histology images provided have a pre-cervical cancer condition called cervical intraepithelial neoplasia (CIN) by expert pathologists. Previously, image analysis studies focused on nuclei-level features to classify the epithelium into the CIN grades. The current study focuses on nuclei segmentation based on the level set segmentation and fuzzy c-means clustering methods. Morphological post-processing operations are used to smooth the image and to remove non-nuclei objects. This algorithm is evaluated on a 71-image dataset of digitized histology images for nuclei segmentation. Experimental results showed a nuclei detection accuracy of 99.53 percent. The second section of this thesis deals with the fusion of the 117 CIN features obtained after processing the input cervical images. Various data fusion techniques are tested using machine learning tools. For further research, the best algorithm from Weka is chosen"--Abstract, page iv.

Advisor(s)

Stanley, R. Joe

Committee Member(s)

Moss, Randy Hays, 1953-
Stoecker, William V.

Department(s)

Electrical and Computer Engineering

Degree Name

M.S. in Electrical Engineering

Sponsor(s)

Intramural Research Program of the National Institutes of Health
National Library of Medicine (U.S.)
Lister Hill National Center for Biomedical Communications

Publisher

Missouri University of Science and Technology

Publication Date

Spring 2017

Journal article titles appearing in thesis/dissertation

Nuclei segmentation using level set method and fuzzy c-means clustering

Pagination

x, 34 pages

Note about bibliography

Includes bibliographical references.

Rights

© 2017 Ravali Edulapuram, All rights reserved.

Document Type

Thesis - Open Access

File Type

text

Language

English

Thesis Number

T 11202

Print OCLC #

1022846449

Electronic OCLC #

1014181814

Download

Share

 
COinS