Dissertation/Thesis Abstract

Applications of Operations Research Techniques for Detection of Anatomical Structures in Medical Images
by Balasooriya, Maduka, M.S., Southern Illinois University at Edwardsville, 2017, 78; 10603509
Abstract (Summary)

Segmentation of anatomical structures in medical images, such as MRI, CT scan and digital fundus photography, is still an ongoing research subject. In this work, the operations research techniques are used to segment the anatomical structures in medical images. We have developed two new models that can efficiently segment the medical images. First, we developed the dynamic identification and classification of edges (DICE) model that can automatically and simultaneously identify retinal structures such as macula and fovea in the eye fundus images. The DICE model comprises three sequential but entwined steps: (a) identifying potential edge points of a contour using moving range control charts; (b) extrapolating additional edge points of a contour over noise reduction; and (c) classifying potential points into different edges by neighborhood gradient search. Second, we developed a model that can segment the anatomical structures in magnetic resonance images (MRI) nonparametrically based on nonlinear programming optimization. The developed nonlinear program was solved using brute force search technique, and this model can be applied to any image datasets without using any pre-processing steps. Although this study focuses on the anatomical structures in medical images, the proposed models can be applied to any object detection problems in any image types.

Indexing (document details)
Advisor: Chew, Song F., Onal, Sinan
Commitee: Chen, Xin, Pailden, Junvie
School: Southern Illinois University at Edwardsville
Department: Mathematics and Statistics
School Location: United States -- Illinois
Source: MAI 57/01M(E), Masters Abstracts International
Source Type: DISSERTATION
Subjects: Medical imaging, Operations research
Keywords: Dynamic programming, Medical images, Nonlinear programming, Segmentation
Publication Number: 10603509
ISBN: 9780355229608
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest