Doctoral Dissertations

Keywords and Phrases

Deep Learning; Dermoscopy; Image Analysis; Machine Learning; Medical Imaging; Melanoma

Abstract

"Melanoma is recognized as the most lethal type of skin cancer, responsible for a significant proportion of skin cancer-related deaths. However, early detection of melanoma is essential for successful treatment outcomes. Computer-aided skin cancer diagnosis tools can save lives by enabling earlier detection of skin cancer. Image segmentation is a crucial step in computer-aided diagnosis as it allows the detection of critical features or regions in an image. Thus, an accurate image segmentation method is necessary to create a more precise computer-aided diagnostic tool for skin cancer diagnosis. This dissertation includes investigating and developing deep learning techniques to improve image segmentation in dermoscoopic skin lesion images.

First, a novel deep neural architecture is proposed for hair and ruler mark detection in skin lesion images. Second, a new deep learning approach is developed to segment lesion borders. Third, a novel data augmentation technique is developed to generate synthetic multi-lesion images to train a robust deep neural network for multi-lesion segmentation. The experimental results from this research achieved state-of-the-art performance on hair and ruler mark segmentation and lesion segmentation in skin lesion images" -- Abstract, p. iv

Advisor(s)

Stanley, R. Joe

Committee Member(s)

Stoecker, William V.
Kosbar, Kurt Louis
Zawodniok, Maciej Jan, 1975-
Samaranayake, V. A.

Department(s)

Electrical and Computer Engineering

Degree Name

Ph. D. in Computer Engineering

Publisher

Missouri University of Science and Technology

Publication Date

Summer 2024

Pagination

xiv, 95 pages

Note about bibliography

Includes_bibliographical_references_(pages 28, 57, 84, 91-94)

Rights

©2024 Norsang Lama , All Rights Reserved

Document Type

Dissertation - Open Access

File Type

text

Language

English

Thesis Number

T 12425

Electronic OCLC #

1477828197

Download

Share

 
COinS