Skip to content

Knee Osteoarthritis Analysis with X-ray Images using CNN

License

Notifications You must be signed in to change notification settings

PingjunChen/GradingKneeOA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

dc19c24 · Feb 9, 2022

History

31 Commits
May 21, 2019
May 16, 2019
Aug 28, 2018
Aug 27, 2018
Feb 9, 2022
Sep 3, 2019

Repository files navigation

Knee Osteoarthritis Analysis

Pipeline of knee osteoarthritis grading pipeline, which includes knee joints detection and knee OA grading.

klg_pipeline

DetJoint

  • Detecting two knee joints in X-ray images using a customized YOLOv2 model.

ClsKL

  • Classifying the KL grade of detected knee joints with a novel ordinal loss.

Data & Models

Knee joint detection (DetJoint) and KL grading (ClsKL) training/testing datasets, as well as best models, can be downloaded from KneeXrayData, around 7G.

Citation

Please consider cite the paper if you use the code or data for your research.

@article{chen2019fully,
  title={Fully Automatic Knee Osteoarthritis Severity Grading Using Deep Neural Networks with a Novel Ordinal Loss},
  author={Chen, Pingjun and Gao, Linlin and Shi, Xiaoshuang and Allen, Kyle and Yang Lin},
  journal={Computerized Medical Imaging and Graphics},,
  volume={75},
  pages={84--92},
  year={2019},
  doi={https://doi.org/10.1016/j.compmedimag.2019.06.002},
  publisher={Elsevier}  
}