Term of Award

Fall 2021

Degree Name

Master of Science, Electrical Engineering

Document Type and Release Option

Thesis (open access)

Copyright Statement / License for Reuse

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Department

Department of Electrical and Computer Engineering

Committee Chair

Rami Haddad

Committee Member 1

Mohammad Ahad

Committee Member 2

Seungmo Kim

Abstract

Pneumonia is one of the leading causes of infections in the lung area and deaths worldwide. The mortality rate is 24.8% for patients over 70 years of age due to other health complications present along with it. In least fortunate countries, pneumonia can often times go untreated because of how cost extensive it is to diagnose, especially severe cases that cannot be seen by a plain X-ray. Other scanning methods can find the lung abnormality but are time-extensive and not cost effective. An autonomous approach however can help aid diagnosing pneumonia with a plain X-ray scan due to the structural edging and feature mapping convolutions within them. Utilizing a fully-autonomous system can implement a practical classification process even with the presence of atypical X-ray images. The process implemented in this work uses an autonomous sorting process to classify between high-quality and low-quality X-rays using supervised deep-learning. The high-quality X-rays are immediately passed to the diagnostic network while the low-quality X-rays (Normal and Pneumonia) are inputted into a Cycle Generative Adversarial Network (CycleGAN) to be enhanced to high-quality. The data is split into composite sets to implement and evaluate a novel approach to binary pneumonia classification using primarily plain X-rays and a modifiable ResNetV2 architecture.

OCLC Number

1475302426

Research Data and Supplementary Material

No

Download

Share

COinS