NORMA eResearch @NCI Library

Recognition and Classification of Knee Osteoporosis and Osteoarthritis Severity using Deep Learning Techniques

Yang, Tsai Shih (2022) Recognition and Classification of Knee Osteoporosis and Osteoarthritis Severity using Deep Learning Techniques. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (2MB) | Preview


The Knee pain which is the common complaint and it affects different ages also is an irreversible disease cause problems and influence our life and future. There are two cases of knee disease in this study are the first case Knee Osteoarthritis which is the most common joint disorder based on Kellgren-Lawrence grading to distinguish from 0 to 4 levels of the severity and the second case is the Knee Osteoporosis which can progress without symptoms until a broken bone occurs. These two diseases the current diagnostic knee problems diagnostic systems are usually use X-ray, MRI, CT scan which require time and experienced physicians to identity knee diseases and diagnose X-Ray images from clinical data to prevent or early treatment also provide the appropriate medical diagnosis and treatment. This study aim to identify and classify knee diseases X-Ray images by using deep learning technique CNN, VGG16 and Late-Fusion model which methods this author had found great performance from researches of knee Osteoarthritis Severity X-ray images detection but in the Knee Osteoporosis case there is no research use deep learning method to do the X-ray image detective so this researcher assume the same method would bring the great performance assist the physicians identify the X-ray images and evaluate. This researcher had compared the results of models the Late-Fusion model bring the 77% accuracy for the OA dataset and the VGG16 model brings the 82% accuracy for OS data and propose the knee osteoporosis detection by using deep learning techniques.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QP Physiology
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 14 Mar 2023 15:35
Last Modified: 14 Mar 2023 15:35

Actions (login required)

View Item View Item