Harnessing ResNet50 and SENet for enhanced ankle fracture identification
Abstract Background Ankle fractures are prevalent injuries that necessitate precise diagnostic tools. Traditional diagnostic methods have limitations that can be addressed using machine learning techniques, with the potential to improve accuracy and expedite diagnoses. Methods We trained various dee...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-04-01
|
| Series: | BMC Musculoskeletal Disorders |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12891-024-07355-8 |
| _version_ | 1797220058975436800 |
|---|---|
| author | Hua Wang Jichong Ying Jianlei Liu Tianming Yu Dichao Huang |
| author_facet | Hua Wang Jichong Ying Jianlei Liu Tianming Yu Dichao Huang |
| author_sort | Hua Wang |
| collection | DOAJ |
| description | Abstract Background Ankle fractures are prevalent injuries that necessitate precise diagnostic tools. Traditional diagnostic methods have limitations that can be addressed using machine learning techniques, with the potential to improve accuracy and expedite diagnoses. Methods We trained various deep learning architectures, notably the Adapted ResNet50 with SENet capabilities, to identify ankle fractures using a curated dataset of radiographic images. Model performance was evaluated using common metrics like accuracy, precision, and recall. Additionally, Grad-CAM visualizations were employed to interpret model decisions. Results The Adapted ResNet50 with SENet capabilities consistently outperformed other models, achieving an accuracy of 93%, AUC of 95%, and recall of 92%. Grad-CAM visualizations provided insights into areas of the radiographs that the model deemed significant in its decisions. Conclusions The Adapted ResNet50 model enhanced with SENet capabilities demonstrated superior performance in detecting ankle fractures, offering a promising tool to complement traditional diagnostic methods. However, continuous refinement and expert validation are essential to ensure optimal application in clinical settings. |
| first_indexed | 2024-04-24T12:43:31Z |
| format | Article |
| id | doaj.art-4a1f290403924586998b708f302c7e23 |
| institution | Directory Open Access Journal |
| issn | 1471-2474 |
| language | English |
| last_indexed | 2024-04-24T12:43:31Z |
| publishDate | 2024-04-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Musculoskeletal Disorders |
| spelling | doaj.art-4a1f290403924586998b708f302c7e232024-04-07T11:05:44ZengBMCBMC Musculoskeletal Disorders1471-24742024-04-0125111110.1186/s12891-024-07355-8Harnessing ResNet50 and SENet for enhanced ankle fracture identificationHua Wang0Jichong Ying1Jianlei Liu2Tianming Yu3Dichao Huang4Department of Medical Imaging, Ningbo No. 6 HospitalDepartment of Orthopedics, Ningbo No. 6 HospitalDepartment of Orthopedics, Ningbo No. 6 HospitalDepartment of Orthopedics, Ningbo No. 6 HospitalDepartment of Orthopedics, Ningbo No. 6 HospitalAbstract Background Ankle fractures are prevalent injuries that necessitate precise diagnostic tools. Traditional diagnostic methods have limitations that can be addressed using machine learning techniques, with the potential to improve accuracy and expedite diagnoses. Methods We trained various deep learning architectures, notably the Adapted ResNet50 with SENet capabilities, to identify ankle fractures using a curated dataset of radiographic images. Model performance was evaluated using common metrics like accuracy, precision, and recall. Additionally, Grad-CAM visualizations were employed to interpret model decisions. Results The Adapted ResNet50 with SENet capabilities consistently outperformed other models, achieving an accuracy of 93%, AUC of 95%, and recall of 92%. Grad-CAM visualizations provided insights into areas of the radiographs that the model deemed significant in its decisions. Conclusions The Adapted ResNet50 model enhanced with SENet capabilities demonstrated superior performance in detecting ankle fractures, offering a promising tool to complement traditional diagnostic methods. However, continuous refinement and expert validation are essential to ensure optimal application in clinical settings.https://doi.org/10.1186/s12891-024-07355-8Ankle fracturesDeep learningResNet50SENetRadiographic imagesGrad-CAM |
| spellingShingle | Hua Wang Jichong Ying Jianlei Liu Tianming Yu Dichao Huang Harnessing ResNet50 and SENet for enhanced ankle fracture identification BMC Musculoskeletal Disorders Ankle fractures Deep learning ResNet50 SENet Radiographic images Grad-CAM |
| title | Harnessing ResNet50 and SENet for enhanced ankle fracture identification |
| title_full | Harnessing ResNet50 and SENet for enhanced ankle fracture identification |
| title_fullStr | Harnessing ResNet50 and SENet for enhanced ankle fracture identification |
| title_full_unstemmed | Harnessing ResNet50 and SENet for enhanced ankle fracture identification |
| title_short | Harnessing ResNet50 and SENet for enhanced ankle fracture identification |
| title_sort | harnessing resnet50 and senet for enhanced ankle fracture identification |
| topic | Ankle fractures Deep learning ResNet50 SENet Radiographic images Grad-CAM |
| url | https://doi.org/10.1186/s12891-024-07355-8 |
| work_keys_str_mv | AT huawang harnessingresnet50andsenetforenhancedanklefractureidentification AT jichongying harnessingresnet50andsenetforenhancedanklefractureidentification AT jianleiliu harnessingresnet50andsenetforenhancedanklefractureidentification AT tianmingyu harnessingresnet50andsenetforenhancedanklefractureidentification AT dichaohuang harnessingresnet50andsenetforenhancedanklefractureidentification |