Date of Award
Spring 2020
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Mathematics, Statistics and Computer Science
First Advisor
Bansal, Naveen
Second Advisor
Rowe, Daniel
Third Advisor
Sheng, Wenhui
Abstract
Knee osteoarthritis(OA) is a very general joint disease that disturb many people especially people over 60. The severity of pain caused by knee OA is the most important portent to disable. Until now, the bad impact of osteoarthritis on health care and public health systems is still increasing.In this paper, we will build a machine learning model to detect the edge of the knee based on the X-ray image and predict the severity of OA. We use a clustering algorithm and machine learning tools to predict the severity of OA in knee X-ray images. The data is coming from the OsteoArthritis Initiative (OAI). To process the data, we use the clustering method as the first step to do unsupervised learning on the dataset and get clusters from each single X-ray image. For every single image, we can get features. Therefore, we transfer complicate image data into simple data, a vector. Then, we use machine learning tools to analyze the extracted feature data and detect the severity of knee OA. We also built a convolutional neural network (CNN) model to make a comparison between the method we used and deep learning algorithm.