Skip to content
/ AVAF Public

An automatic video analysis framework for exposure region recognition in X-ray examination

Notifications You must be signed in to change notification settings

JiaRuiS/AVAF

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

81 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Automatic video analysis framework for exposure region recognition in X-ray imaging automation

We propose an automatic video analysis framework (AVAF) for exposure region recognition in X-ray examination. In this work, we have constructed a large dataset including body keypoint and body Bbox annotation images. Currently, we are further expanding the annotation categories of the basic version dataset so that it can be close to the real clinical scenario in the X-Ray imaging process.

Dataset

The following are some samples in basic version dataset.

Annotation categories

微信小程序

Annotion Demo

微信小程序

Results

In the work, we propose a new solution to recognize the exposure region better for X-ray imaging protocols and conduct extensive experiments to test the performance of the proposed method. We present qualitative visualization results of Body Structure Detection and video detection. Among them, Body Structure Detection gives the performance evaluation of the two body detection models, and video detection is used to evaluate the overall performance of the proposed framework. Finally, we also hope to help optimize the workflow in conventional X-ray imaging and facilitate decreasing the radiographer's workload.

Result of Body Structure Detection

微信小程序

Result of video detection

image image

Citation

If you find our approaches useful in your research, please consider citing:

@article{sun2022automatic,
  title={Automatic video analysis framework for exposure region recognition in X-ray imaging automation},
  author={Sun, Jiarui and Wu, Zhan and Yu, Zechen and Chen, Huanji and Du, Changping and Xu, Liang and Zhong, Jian and Feng, Juan and Coatrieux, Gouenou and Coatrieux, Jean-Louis and others},
  journal={IEEE Journal of Biomedical and Health Informatics},
  volume={26},
  number={9},
  pages={4359--4370},
  year={2022},
  publisher={IEEE}
}

About

An automatic video analysis framework for exposure region recognition in X-ray examination

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published