Theses and Dissertations

ORCID

https://orcid.org/0009-0004-1343-5131

Advisor

Wang, Haifeng

Committee Member

He, Lu

Committee Member

Lee, Seunghan

Date of Degree

5-16-2025

Original embargo terms

Visible MSU Only 2 Years

Document Type

Graduate Thesis - Campus Access Only

Major

Industrial and Systems Engineering (Industrial Systems)

Degree Name

Master of Science (M.S.)

College

James Worth Bagley College of Engineering

Department

Department of Industrial and Systems Engineering

Abstract

Knowledge transferability is crucial for advancing computer-aided diagnosis (CAD), especially in complex tasks such as skin lesion diagnosis, where data variability and scarcity can challenge the effectiveness of traditional diagnostic models. This study introduces a novel approach to improving knowledge transfer in skin lesion diagnosis by leveraging Progressive Differentiable Architecture Search (P-DARTS). Our approach discovers neural network architectures that adapt well across diverse datasets, enhancing the model’s ability to generalize and transfer learned features to new contexts. The optimized architecture was evaluated using the publicly available ISIC-2019 and PAD-UFES-20 datasets, demonstrating competitive performance against established models such as InceptionNet, ResNet, and DenseNet. P-DARTS produced high-performing, transferable models with a diagnostic accuracy of 63.70% in multi-class classification and 97.71% in binary classification, underscoring its potential in creating robust artificial intelligence (AI) tools for accurate and timely skin lesion diagnosis. In addition, we observe that evaluation depth held more significance than the search-evaluation depth gap, and that architectures with a greater number of pooling operations resulted in a better performance. This approach addresses a key limitation in knowledge transfer for skin lesion diagnosis and fills the need for adaptable models capable of learning from limited, domain-specific data.

Download

Share

COinS