Classification of Shoulder X-ray Images with Deep Learning Ensemble Models
Fractures occur in the shoulder area, which has a wider range of motion than other joints in the body, for various reasons. To diagnose these fractures, data gathered from X-radiation (X-ray), magnetic resonance imaging (MRI), or computed tomography (CT) are used. This study aims to help physicians...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/6/2723 |
| _version_ | 1797540894999576576 |
|---|---|
| author | Fatih Uysal Fırat Hardalaç Ozan Peker Tolga Tolunay Nil Tokgöz |
| author_facet | Fatih Uysal Fırat Hardalaç Ozan Peker Tolga Tolunay Nil Tokgöz |
| author_sort | Fatih Uysal |
| collection | DOAJ |
| description | Fractures occur in the shoulder area, which has a wider range of motion than other joints in the body, for various reasons. To diagnose these fractures, data gathered from X-radiation (X-ray), magnetic resonance imaging (MRI), or computed tomography (CT) are used. This study aims to help physicians by classifying shoulder images taken from X-ray devices as fracture/non-fracture with artificial intelligence. For this purpose, the performances of 26 deep learning-based pre-trained models in the detection of shoulder fractures were evaluated on the musculoskeletal radiographs (MURA) dataset, and two ensemble learning models (EL1 and EL2) were developed. The pre-trained models used are ResNet, ResNeXt, DenseNet, VGG, Inception, MobileNet, and their spinal fully connected (Spinal FC) versions. In the EL1 and EL2 models developed using pre-trained models with the best performance, test accuracy was 0.8455, 0.8472, Cohen’s kappa was 0.6907, 0.6942 and the area that was related with fracture class under the receiver operating characteristic (ROC) curve (AUC) was 0.8862, 0.8695. As a result of 28 different classifications in total, the highest test accuracy and Cohen’s kappa values were obtained in the EL2 model, and the highest AUC value was obtained in the EL1 model. |
| first_indexed | 2024-03-10T13:07:33Z |
| format | Article |
| id | doaj.art-389ead98109245fca1ebbf2ad001528c |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T13:07:33Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-389ead98109245fca1ebbf2ad001528c2023-11-21T10:58:44ZengMDPI AGApplied Sciences2076-34172021-03-01116272310.3390/app11062723Classification of Shoulder X-ray Images with Deep Learning Ensemble ModelsFatih Uysal0Fırat Hardalaç1Ozan Peker2Tolga Tolunay3Nil Tokgöz4Department of Electrical and Electronics Engineering, Faculty of Engineering, Gazi University, TR 06570 Ankara, TurkeyDepartment of Electrical and Electronics Engineering, Faculty of Engineering, Gazi University, TR 06570 Ankara, TurkeyDepartment of Electrical and Electronics Engineering, Faculty of Engineering, Gazi University, TR 06570 Ankara, TurkeyDepartment of Orthopaedics and Traumatology, Faculty of Medicine, Gazi University, TR 06570 Ankara, TurkeyDepartment of Radiology, Faculty of Medicine, Gazi University, TR 06570 Ankara, TurkeyFractures occur in the shoulder area, which has a wider range of motion than other joints in the body, for various reasons. To diagnose these fractures, data gathered from X-radiation (X-ray), magnetic resonance imaging (MRI), or computed tomography (CT) are used. This study aims to help physicians by classifying shoulder images taken from X-ray devices as fracture/non-fracture with artificial intelligence. For this purpose, the performances of 26 deep learning-based pre-trained models in the detection of shoulder fractures were evaluated on the musculoskeletal radiographs (MURA) dataset, and two ensemble learning models (EL1 and EL2) were developed. The pre-trained models used are ResNet, ResNeXt, DenseNet, VGG, Inception, MobileNet, and their spinal fully connected (Spinal FC) versions. In the EL1 and EL2 models developed using pre-trained models with the best performance, test accuracy was 0.8455, 0.8472, Cohen’s kappa was 0.6907, 0.6942 and the area that was related with fracture class under the receiver operating characteristic (ROC) curve (AUC) was 0.8862, 0.8695. As a result of 28 different classifications in total, the highest test accuracy and Cohen’s kappa values were obtained in the EL2 model, and the highest AUC value was obtained in the EL1 model.https://www.mdpi.com/2076-3417/11/6/2723biomedical image classificationbone fracturesdeep learningensemble learningshouldertransfer learning |
| spellingShingle | Fatih Uysal Fırat Hardalaç Ozan Peker Tolga Tolunay Nil Tokgöz Classification of Shoulder X-ray Images with Deep Learning Ensemble Models Applied Sciences biomedical image classification bone fractures deep learning ensemble learning shoulder transfer learning |
| title | Classification of Shoulder X-ray Images with Deep Learning Ensemble Models |
| title_full | Classification of Shoulder X-ray Images with Deep Learning Ensemble Models |
| title_fullStr | Classification of Shoulder X-ray Images with Deep Learning Ensemble Models |
| title_full_unstemmed | Classification of Shoulder X-ray Images with Deep Learning Ensemble Models |
| title_short | Classification of Shoulder X-ray Images with Deep Learning Ensemble Models |
| title_sort | classification of shoulder x ray images with deep learning ensemble models |
| topic | biomedical image classification bone fractures deep learning ensemble learning shoulder transfer learning |
| url | https://www.mdpi.com/2076-3417/11/6/2723 |
| work_keys_str_mv | AT fatihuysal classificationofshoulderxrayimageswithdeeplearningensemblemodels AT fırathardalac classificationofshoulderxrayimageswithdeeplearningensemblemodels AT ozanpeker classificationofshoulderxrayimageswithdeeplearningensemblemodels AT tolgatolunay classificationofshoulderxrayimageswithdeeplearningensemblemodels AT niltokgoz classificationofshoulderxrayimageswithdeeplearningensemblemodels |