GRAZPEDWRI-DX Dataset (Split By Ju)

National Taiwan University
The left side is the original X-ray image and the right side is the image from the expert's manual labelling.

Original Dataset

GRAZPEDWRI-DX [Nagy et al. 2022] is a public dataset of 20,327 pediatric wrist trauma X-ray images released by the University of Medicine of Graz. These X-ray images were collected by multiple pediatric radiologists at the Department for Pediatric Surgery of the University Hospital Graz between 2008 and 2018, involving 6,091 patients and a total of 10,643 studies. This dataset is annotated with 74,459 image labels, featuring a total of 67,771 labeled objects. You can find the original GRAZPEDWRI-DX dataset here (unsplit).

Splitting Strategy

In our study [Ju et al. 2023], we first divided the GRAZPEDWRI-DX dataset randomly into three sets: training set, validation set, and test set. The sizes of these sets are approximately 70%, 20%, and 10% of the original dataset, respectively. Specifically, our training set consists of 14,204 images (69.88%), our validation set consists of 4,094 images (20.14%), and our test set consists of 2,029 images (9.98%). In the later studies [Ju et al. 2024][Chien et al. 2024a][Chien et al. 2024b], we all followed to use this dataset.

Application

You can access our web application here. This website is hosted by Streamlit. In addition, we have also designed the Graphical User Interface, more information about this you can find here.

Reference

[Nagy et al. 2022] Eszter Nagy, Michael Janisch, Franko Hržić, Erich Sorantin, Sebastian Tschauner. 2022. A pediatric wrist trauma X-ray dataset (GRAZPEDWRI-DX) for machine learning. Scientific Data.

[Ju et al. 2023] Rui-Yang Ju, Weiming Cai. 2023. Fracture detection in pediatric wrist trauma X-ray images using YOLOv8 algorithm. Scientific Reports.

[Ju et al. 2024] Rui-Yang Ju, Chun-Tse Chien, Enkaer Xieerke, Jen-Shiun Chiang. 2024. Pediatric Wrist Fracture Detection Using Feature Context Excitation Modules in X-ray Images. arXiv preprint.

[Chien et al. 2024a] Chun-Tse Chien, Rui-Yang Ju, Kuang-Yi Chou, Jen-Shiun Chiang. 2024. YOLOv9 for fracture detection in pediatric wrist trauma X-ray images. Electronics Letters.

[Chien et al. 2024b] Chun-Tse Chien, Rui-Yang Ju, Kuang-Yi Chou, Enkaer Xieerke, Jen-Shiun Chiang. 2024. YOLOv8-AM: YOLOv8 Based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detection. arXiv preprint.

BibTeX

If you use our split dataset, please cite some of the papers below:

  @article{ju2023fracture,
    title={Fracture detection in pediatric wrist trauma X-ray images using YOLOv8 algorithm},
    author={Ju, Rui-Yang and Cai, Weiming},
    journal={Scientific Reports},
    volume={13},
    number={1},
    pages={20077},
    year={2023}
  }
    
  @article{chien2024yolov9,
    title={YOLOv9 for fracture detection in pediatric wrist trauma X-ray images},
    author={Chien, Chun-Tse and Ju, Rui-Yang and Chou, Kuang-Yi and Chiang, Jen-Shiun},
    journal={Electronics Letters},
    volume={60},
    number={11},
    pages={e13248},
    year={2024}
  }

  @article{chien2024yolov8,
    title={YOLOv8-AM: YOLOv8 Based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detection}, 
    author={Chien, Chun-Tse and Ju, Rui-Yang and Chou, Kuang-Yi and Xieerke, Enkaer and Chiang, Jen-Shiun},
    journal={arXiv preprint arXiv:2402.09329},
    year={2024}
  }

  @article{ju2024pediatric,
    title={Pediatric Wrist Fracture Detection Using Feature Context Excitation Modules in X-ray Images},
    author={Ju, Rui-Yang and Chien, Chun-Tse and Xieerke, Enkaer and Chiang, Jen-Shiun},
    journal={arXiv preprint arXiv:2410.01031},
    year={2024}
  }