Date of Award

2025

Document Type

Thesis

Degree Name

Master of Science in Engineering (MSE)

Department

Electrical and Computer Engineering

Committee Chair

David Pan

Committee Member

Laurie Joiner

Committee Member

Dongsheng Wu

Research Advisor

David Pan

Subject(s)

Data compression (Computer science), Diagnostic imaging, Deep learning (Machine learning), Computer vision, Malaria--Diagnosis

Abstract

In the field of medical imaging, lossless compression techniques play a critical role in maintaining the fidelity of medical data, while improving the efficiency of data storage and transmission, especially in telemedicine applications. This thesis addresses the development of a novel machine learning-based method for lossless compression of images of erythrocytes infected with malaria. The proposed method has two stages. In the first stage, a Vision Transformer, a computer vision model that can learn long-range dependence, is employed to separate erythrocyte images into two categories: infected and uninfected. This classification stage is essential as it allows the subsequent compression approaches to be tailored for each category. In the second stage, the compression of these images is conducted using two dedicated deep autoencoders—one for each category. These autoencoders are specifically trained to significantly reduce the dimensionality of the input data. To achieve lossless compression, the residue, which is the difference between the original images and the images reconstructed by the autoencoder, undergoes further compression through Huffman coding. Simulation results demonstrate that the proposed compression method can achieve lower bit rates and greater compression ratios than conventional compression techniques like JPEG 2000, JPEG-LS, and CALIC. The thesis provides detailed descriptions and thorough analysis of each component of the proposed data compression system, while discussing the broader impacts of further development of the techniques for malaria health informatics.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.