Masters Theses

Abstract

"Seborrheic keratoses are the most common benign tumors found in older individuals. Seborrheic keratoses are normally benign in nature, but sometimes in a large lesion area of seborrheic keratoses, secondary tumors, or squamous cell carcinoma in situ or malignant melanoma may occur. It has been found that seborrheic keratoses have a few features that distinguish them from melanomas. Milia-like cysts, comedo-like openings and network-like structures are the most prominent features found in seborrheic keratoses. Comedo-like openings are pigmented structures and are mostly oval yellowish, brown or black in appearance. They can also be observed in melanocytic lesions and melanomas. Milia-like cysts (MLCs) are structures which are mostly white or yellowish in color, vary in size and are mostly seen in seborrheic keratoses and in certain congenital melanocytic nevi. MLCs are very useful in classifying a skin lesion as a seborrheic keratosis and hence are also useful in differentiating between seborrheic keratoses and melanomas. MLCs are classified into two categories depending on the size and shape of the MLC. The two types of MLCs are starry MLCs and cloudy MLCs. This research project gives a method to automatically identify starry milia-like cysts in any image. The aim of the research is to identify starry milia-like cysts accurately and to distinguish starry MLCs from competing structures like skin pores, bubbles from dermoscopy fluids and keratin scales"--Abstract, page iii.

Advisor(s)

Moss, Randy Hays, 1953-

Committee Member(s)

Kosbar, Kurt Louis
Sedigh, Sahra

Department(s)

Electrical and Computer Engineering

Degree Name

M.S. in Electrical Engineering

Sponsor(s)

Missouri University of Science and Technology. Department of Electrical and Computer Engineering

Publisher

Missouri University of Science and Technology

Publication Date

Fall 2012

Pagination

ix, 75 pages

Note about bibliography

Includes bibliographical references.

Rights

© 2012 Viswanaath Subramanian, All rights reserved.

Document Type

Thesis - Open Access

File Type

text

Language

English

Library of Congress Subject Headings

Keratosis
Skin -- Tumors
Skin -- Tumors -- Diagnosis -- Computer programs
Image processing -- Computer programs

Thesis Number

T 9990

Print OCLC #

852158694

Electronic OCLC #

852150887

Share

 
COinS