Masters Theses

Keywords and Phrases

Live wire segmentation tool; Osteophytes

Abstract

"Computer-assisted image segmentation can be a challenging problem. In previous research, manual segmentation was used for the detection of key features in cervical and lumbar x-ray images. In this research, a semi-automated live wire technique is investigated and is evaluated for the detection of anterior osteophytes in lumbar vertebrae. Convex hull-based features are extracted from manual and live wire segmented vertebrae for anterior osteophyte discrimination over 405 lumbar vertebrae, 204 abnormal vertebrae with anterior osteophytes and 201 normal vertebrae. A leave-one-out standard back propagation neural network was used for vertebrae classification. Experimental results show that manual segmentation yielded slightly better discrimination results than the live wire technique."--Abstract, page iii.

Advisor(s)

Stanley, R. Joe

Committee Member(s)

Moss, Randy Hays, 1953-
Agarwal, Sanjeev, 1971-

Department(s)

Electrical and Computer Engineering

Degree Name

M.S. in Electrical Engineering

Publisher

University of Missouri--Rolla

Publication Date

Fall 2004

Pagination

viii, 40 pages

Note about bibliography

Includes bibliographical references (pages 38-39).

Rights

© 2004 Suren Eda Naarayana Kulothungan, All rights reserved.

Document Type

Thesis - Restricted Access

File Type

text

Language

English

Subject Headings

Osteoarthritis -- Diagnosis -- Research
Lumbar vertebrae -- Imaging
Computer vision in medicine
Image analysis

Thesis Number

T 8673

Print OCLC #

62349672

Link to Catalog Record

Electronic access to the full-text of this document is restricted to Missouri S&T users. Otherwise, request this publication directly from Missouri S&T Library or contact your local library.

http://merlin.lib.umsystem.edu/record=b5409709~S5

Share My Thesis If you are the author of this work and would like to grant permission to make it openly accessible to all, please click the button above.

Share

 
COinS