Doctoral Dissertations

Keywords and Phrases

Basal Cell Carcinoma; Deep learning; Fusion; Machine learning; Skin cancer; Telangiectasia

Abstract

"An estimated 2 million new cases of basal cell carcinoma (BCC) are diagnosed each year in the United States, making it one of the most common skin cancers. Earlier detection of these cancers enables less invasive biopsies. Clinical detection consists of a preliminary visual observation of these skin lesions by an experienced dermatologist making it a specialized task highly dependent on their time, availability, and resources. Hence, there is a need for automating this process that can assist healthcare staff. In recent years, deep learning (DL) has been used extensively and successfully to diagnose different cancers in dermoscopic images. Telangiectasia or narrow blood vessels that typically appear serpiginous or arborizing, are a critical indicator of basal cell carcinoma (BCC), aiding dermatologists in BCC diagnosis. Most DL approaches lack such clinical inputs that could aid in higher accuracy and explainability. Hence, in this research, we exploit the following computational and data fusion techniques for BCC feature detection and diagnosis: 1. Automate the segmentation of telangiectasia with the application of image processing techniques and a semantic deep learning model. 2. Apply ensemble learning on a combination of Deep learning features and handcrafted features from semantically segmented telangiectasia masks for BCC diagnosis. 3. Explore topological data analysis (TDA) techniques to create a DL-TDA based hybrid classification model. Through this research we achieve state-of-the-art results in BCC diagnosis and provide pathways for automating diagnosis/classification for similar datasets and problem statements" -- Abstract, p. iv

Advisor(s)

Stanley, R. Joe

Committee Member(s)

Stoecker, William V.
Kosbar, Kurt Louis
Wunsch, Donald C.
Moss, Randy Hays, 1953-

Department(s)

Electrical and Computer Engineering

Degree Name

Ph. D. in Electrical Engineering

Publisher

Missouri University of Science and Technology

Publication Date

Summer 2024

Pagination

Xiv, 91 pages

Note about bibliography

Includes_bibliographical_references_(pages 18, 46, 79 & 85-90)

Rights

©2024 Akanksha Maurya , All Rights Reserved

Document Type

Dissertation - Open Access

File Type

text

Language

English

Thesis Number

T 12426

Electronic OCLC #

1477917115

Download

Share

 
COinS