Masters Theses

Abstract

"The current study presents the investigation and development of image processing, computational intelligence, fuzzy logic, and statistical techniques for different types of data fusion for a varied range of applications. Raw data, decision level and feature level fusion techniques are explored for detection of pre Cervical cancer (CIN) grades from digital histology images of the cervical epithelium tissues.

In previous research, an automated, localized, fusion-based approach was investigated for classifying squamous epithelium into Normal, CIN1, CIN2, and CIN3 grades of cervical intraepithelial neoplasia (CIN) based on image analysis. The approach included medial axis determination, vertical segment partitioning as medial axis orthogonal cuts, individual vertical segment feature extraction and classification, and image-based classification using a voting scheme to fuse the vertical segment CIN grades. This paper presents advances in medial axis determination, epithelium atypical cell concentration feature development and a particle swarm optimization neural network and receiver operating characteristic curve technique for individual vertical segment-based classification. Combining individual vertical segment classification confidence values using a weighted sum fusion approach for image-based classification, exact grade labeling accuracy was as high as 90% for a 62-image data set"--Abstract, page iii.

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 Computer Engineering

Sponsor(s)

National Library of Medicine (U.S.)

Publisher

Missouri University of Science and Technology

Publication Date

Fall 2014

Pagination

viii, 75 pages

Note about bibliography

Includes bibliographical references (pages 72-74).

Rights

© 2014 Koyel Banerjee, All rights reserved.

Document Type

Thesis - Open Access

File Type

text

Language

English

Thesis Number

T 11357

Electronic OCLC #

1041856242

Download

Share

 
COinS