Date of Award


Document Type


Degree Name

Master of Science in Computer Science


School of Computer Science and Engineering

First Reader/Committee Chair

Dr. Jennifer Jin


Chest X-ray images are crucial for medical decisions and patient care. However, their manual interpretation is time-consuming and prone to human error. This project aims to create an automated system that uses deep learning techniques to classify thorax disease from chest X-ray images. We are using the NIH Chest X-Ray Dataset, which contains many annotated images, as input data for this project. This approach uses UNet architecture as its classification layer. UNet architecture is well-known for its efficiency in image segmentation. Adding residual blocks enhances this approach's ability to classify images. The goal of this project is to create a robust and accurate classification model that uses UNet’s unique capabilities for feature representation and extraction. This would allow accurate discrimination between different forms of thorax diseases with high precision. This project shows the effectiveness of UNet architecture with residual block for accurately classifying thorax disease types. These techniques combined produced superior results to many other architectures for medical image analysis, underscoring their importance.