Graduate Studies

 

First Advisor

Chi Zhang

Degree Name

Doctor of Philosophy (Ph.D.)

Department

Complex Biosystems

Date of this Version

8-2024

Document Type

Dissertation

Citation

A dissertation presented to the faculty of the Graduate College of the University of Nebraska in partial fulfillment of requirements for the degree of Doctor of Philosophy

Major: Complex Biosystems (Systems Analysis)

Under the supervision of Professor Chi Zhang

Lincoln, Nebraska, August 2024

Comments

Copyright 2024, Yu Shi. Used by permission

Abstract

Cancer poses a significant global health challenge. With an estimated 20 million new cases diagnosed worldwide in 2022 and 9.7 million fatalities attributable to the disease, the economic burden of cancer is immense. It impacts healthcare systems and imposes substantial costs for its care on patients and their families. Despite advancements in early detection, prevention, and treatment that have reduced overall cancer mortality rates, the growing prevalence of cancer, particularly among younger individuals, remains a pressing issue.

Recent advancements in medical imaging technology have progressed significantly with the help of emerging computer vision and artificial intelligence (AI) technology. Despite these advancements, medical imaging analysis in cancer research and clinical settings faces significant challenges. Analyzing data produced by sophisticated imaging technologies, such as CT or MRI, is still labor-intensive, limiting its usability and contributing to disparities in cancer care and data hungriness for researchers. AI-assisted analysis has the potential not only to reduce cost and turnover time but also to increase the accuracy of clinical applications. Furthermore, it provides opportunities to integrate various types of data and information for better prediction, benefiting both patients and physicians.

The research described in this dissertation aims to improve cancer imaging analysis by presenting the design and implementation of novel AI architectures. In this dissertation, I developed AI-based algorithms focused on two primary objectives. (1) Develop feature extraction methods to improve model accuracy. I applied advanced techniques to extract and learn critical image features associated with cancer prognosis to improve diagnostic tool accuracy and reliability. (2) Develop advanced generative models to synthesize high-quality image data. I developed deep-learning-based methods to learn latent representations and synthesize high-quality 3D images of tumor sites, facilitating better visualization and assessment of cancerous tissues.

This dissertation showcases the immense potential of AI in revolutionizing cancer diagnostics, providing a foundation for further research and development in this critical healthcare field. The proposed AI frameworks, incorporating innovative applications of machine learning and deep learning methods, will undoubtedly drive ongoing efforts to reduce cancer worldwide and tackle major challenges in this area.

Advisor: Chi Zhang

Download

Share

COinS