Knee Osteoarthritis: Automatic Grading with Deep Learning
Junru Zhong1, Yongcheng Yao1, Sheheryar Khan2, Fan Xiao1, Dόnal G. Cahill1, James F. Griffith1, and Weitian Chen1
1Department of Imaging and Interventional Radiology, The Chinese University of Hong Kong, Sha Tin, NT, Hong Kong, 2School of Professional Education & Executive Development, The Hong Kong Polytechnic University, Kowloon, Hong Kong
We present a deep learning-based knee osteoarthritis grading system that automatically provides a binary classification for cartilage degeneration. The system was trained on MRI data sets applying MOAKS grading from the Osteoarthritis Initiative (OAI). The proposed method achieved an accuracy of 0.75 to 0.83, despite being conducted on highly imbalanced data sets. Significant improvement in accuracy is expected with more balanced data sets.
This abstract and the presentation materials are available to members only;
a login is required.