Doctoral Dissertations

Keywords and Phrases

Dermatology; Fusion; Machine Learning

Abstract

"The realm of melanoma diagnosis has been significantly advanced by deep learning (DL) techniques, yet the current approaches are not without limitations, including missed diagnoses and the challenge of interpreting these "black box" models. The research is comprised of three studies, each contributing uniquely towards advancing melanoma detection accuracy and interpretability. The first study focuses on improving the detection of specific dermoscopic structures through a deep learning-based segmentation approach, while the second study builds upon this by employing a fusion technique that combines traditional image features with advanced deep learning models. This method significantly improves melanoma detection, particularly in recall and accuracy. The third study expands the scope by exploring the fusion of deep learning with conventional imaging processing methods, emphasizing the enhancement of diagnostic specificity, and addressing the critical aspect of explainability in AI diagnostics" -- Abstract, p. iv

Advisor(s)

Stanley, R. Joe

Committee Member(s)

Stoecker, William V.
Kosbar, Kurt Louis
Samaranayake, V. A.
Moss, Randy H., 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

xiii, 94 pages

Note about bibliography

Includes_bibliographical_references_(pages 29, 65, 79 & 92-93)

Rights

©2024 Anand Krishnadas Nambisan , All Rights Reserved

Document Type

Dissertation - Open Access

File Type

text

Language

English

Thesis Number

T 12400

Electronic OCLC #

1477929740

Download

Share

 
COinS