Graduate Studies

 

First Advisor

Dongming Peng

Degree Name

Doctor of Philosophy (Ph.D.)

Department

Electrical Engineering

Date of this Version

8-2025

Document Type

Dissertation

Citation

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

Major: Engineering (Computer Engineering)

Under the supervision of Professor Dongming Peng

Lincoln, Nebraska, August 2025

Comments

Copyright 2025, Adarsha Bhattarai. Used by permission

Abstract

This dissertation investigates the application of artificial intelligence in biomedical data acquisition, communication, and analysis to advance neurological research and to enable the early detection of cardiovascular conditions. Despite significant advances in imaging and physiological modalities, challenges persist. Imaging modalities, such as the chemical exchange saturation transfer magnetic resonance imaging (CEST MRI) technique are challenged by a prolonged data acquisition time and high operational costs. In addition, physiological modalities such as electrocardiogram (ECG) sensors face constraints in providing uninterrupted signal monitoring which is crucial for the timely detection of premature cardiac abnormalities. The primary goal of this work is to lay the foundation for developing an AI-powered infrastructure to advance biomedical technologies. To address the prolonged acquisition time for the CEST MRI technique, we propose an innovative method to reduce the number of frequency offsets followed by data reconstruction. Likewise, we propose a unique system architecture that enables the division of biomedical data analysis among heterogeneous computing platforms. In the proposed architectures, deep learning algorithms are utilized for multiple functions, including detecting abnormalities in physiological signals and accelerating medical imaging. In the first study on CEST MRI, a methodological framework to optimize the number of frequency offsets followed by deep learning-based reconstruction is presented. The results show that the percentage of optimally selected frequency offsets can be as low as 10% of the total offsets. These findings have significant implications for the development of an efficient biomedical imaging method. In the second study involving a physiological modality, namely ECG, we present novel open-loop and closed-loop communication switch modes, a resource-aware machine learning approach, a sparse embedding technique, and a medical virtual chain framework. These components together facilitate secure and efficient real-time assessment of physiological signals. The simulation results of the R-peak detection algorithm, 2D- 2D-CNN-based analysis, and open-loop/closed-loop supervision demonstrate the feasibility of the proposed method for deployment in telemedicine applications. Together, this dissertation presents original research that offers new insights into real-time biomedical data communication and analysis frameworks. The work has implications for basic science, clinical research, clinical theranostic applications, and remote healthcare. The findings of this study provide a solid foundation for future research by enabling the development of the proposed platform with a larger biomedical dataset, robust deep learning algorithms, and validation using experimental testbeds.

Advisor: Dongming Peng

Download

Share

COinS