Skip to content

PyTorch Implementation for Fracture Detection in Wrist X-ray Images

License

Notifications You must be signed in to change notification settings

fatihuysal88/wrist-d

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

72 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

wrist-d

LICENSE

PWC
PyTorch Implementation for Fracture Detection in Wrist X-ray Images

note:

Published: 8 February 2022, Hardalaç, F.; Uysal, F.; Peker, O.; Çiçeklidağ, M.; Tolunay, T.; Tokgöz, N.; Kutbay, U.; Demirciler, B.; Mert, F. Fracture Detection in Wrist X-ray Images Using Deep Learning-Based Object Detection Models. Sensors 2022, 22, 1285. https://doi.org/10.3390/s22031285 IF 2020: 3.576, Index: SCIE, JCR: Q1, EF: 0.10094, AI: 0.584

abstract

Hospitals, especially their emergency services, receive a high number of wrist fracture cases. For correct diagnosis and proper treatment of these, images obtained from various medical equipment must be viewed by physicians, along with the patient’s medical records and physical examination. The aim of this study is to perform fracture detection by use of deep-learning on wrist X-ray images to support physicians in the diagnosis of these fractures, particularly in the emergency services. Using SABL, RegNet, RetinaNet, PAA, Libra R-CNN, FSAF, Faster R-CNN, Dynamic R-CNN and DCN deep-learning-based object detection models with various backbones, 20 different fracture detection procedures were performed on Gazi University Hospital’s dataset of wrist X-ray images. To further improve these procedures, five different ensemble models were developed and then used to reform an ensemble model to develop a unique detection model, ‘wrist fracture detection-combo (WFD-C).’ From 26 different models for fracture detection, the highest detection result obtained was 0.8639 average precision (AP50) in the WFD-C model. Huawei Turkey R&D Center supports this study within the scope of the ongoing cooperation project coded 071813 between Gazi University, Huawei and Medskor.

Keywords: artificial intelligence; biomedical image processing; bone fractures; deep learning; fracture detection; object detection; transfer learning; wrist; X-ray

paper links

Paper: https://www.mdpi.com/1424-8220/22/3/1285

Preprint: https://arxiv.org/abs/2111.07355

Papers With Code: https://paperswithcode.com/paper/fracture-detection-in-wrist-x-ray-images

GitHub: https://github.com/fatihuysal88/wrist-d

citation

please cite the paper if you benefit from our paper:

@Article{s22031285,
AUTHOR = {Hardalaç, Fırat and Uysal, Fatih and Peker, Ozan and Çiçeklidağ, Murat and Tolunay, Tolga and Tokgöz, Nil and Kutbay, Uğurhan and Demirciler, Boran and Mert, Fatih},
TITLE = {Fracture Detection in Wrist X-ray Images Using Deep Learning-Based Object Detection Models},
JOURNAL = {Sensors},
VOLUME = {22},
YEAR = {2022},
NUMBER = {3},
ARTICLE-NUMBER = {1285},
URL = {https://www.mdpi.com/1424-8220/22/3/1285},
ISSN = {1424-8220},
ABSTRACT = {Hospitals, especially their emergency services, receive a high number of wrist fracture cases. For correct diagnosis and proper treatment of these, images obtained from various medical equipment must be viewed by physicians, along with the patient’s medical records and physical examination. The aim of this study is to perform fracture detection by use of deep-learning on wrist X-ray images to support physicians in the diagnosis of these fractures, particularly in the emergency services. Using SABL, RegNet, RetinaNet, PAA, Libra R-CNN, FSAF, Faster R-CNN, Dynamic R-CNN and DCN deep-learning-based object detection models with various backbones, 20 different fracture detection procedures were performed on Gazi University Hospital’s dataset of wrist X-ray images. To further improve these procedures, five different ensemble models were developed and then used to reform an ensemble model to develop a unique detection model, ‘wrist fracture detection-combo (WFD-C).’ From 26 different models for fracture detection, the highest detection result obtained was 0.8639 average precision (AP50) in the WFD-C model. Huawei Turkey R&D Center supports this study within the scope of the ongoing cooperation project coded 071813 between Gazi University, Huawei and Medskor.},
DOI = {10.3390/s22031285}
}

authors

proposed detection models

models

proposed ensemble models

models

model performance

models

sample of wrist fracture results

models

Note: ground-truth bounding box (green), predicted bounding box (red)

requirements

About

PyTorch Implementation for Fracture Detection in Wrist X-ray Images

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published