Diagnostic accuracy of deep learning for evaluation of C-spine injury from lateral neck radiographs
Background: Traumatic spinal cord injury (TSI) is a leading cause of morbidity and mortality worldwide, with the cervical spine being the most affected. Delayed diagnosis carries a risk of morbidity and mortality. However, cervical spine CT scans are time-consuming, costly, and not always available...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-08-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844022016607 |
| _version_ | 1818010296846909440 |
|---|---|
| author | Arunnit Boonrod Artit Boonrod Atthaphon Meethawolgul Prin Twinprai |
| author_facet | Arunnit Boonrod Artit Boonrod Atthaphon Meethawolgul Prin Twinprai |
| author_sort | Arunnit Boonrod |
| collection | DOAJ |
| description | Background: Traumatic spinal cord injury (TSI) is a leading cause of morbidity and mortality worldwide, with the cervical spine being the most affected. Delayed diagnosis carries a risk of morbidity and mortality. However, cervical spine CT scans are time-consuming, costly, and not always available in general care. In this study, deep learning was used to assess and improve the detection of cervical spine injuries on lateral radiographs, the most widely used screening method to help physicians triage patients quickly and avoid unnecessary CT scans. Materials and methods: Lateral neck or lateral cervical spine radiographs were obtained for patients who underwent CT scan of cervical spine. Ground truth was determined based on CT reports. CiRA CORE, a codeless deep learning program, was used as a training and testing platform. YOLO network models, including V2, V3, and V4, were trained to detect cervical spine injury. The diagnostic accuracy, sensitivity, and specificity of the model were calculated. Results: A total of 229 radiographs (129 negative and 100 positive) were selected for inclusion in our study from a list of 625 patients with cervical spine CT scans, 181 (28.9%) of whom had cervical spine injury. The YOLO V4 model performed better than the V2 or V3 (AUC = 0.743), with sensitivity, specificity, and accuracy of 80%, 72% and 75% respectively. Conclusion: Deep learning can improve the accuracy of lateral c-spine or neck radiographs. We anticipate that this will assist clinicians in quickly triaging patients and help to minimize the number of unnecessary CT scans. |
| first_indexed | 2024-04-14T05:53:35Z |
| format | Article |
| id | doaj.art-b6918083737b47c1bad38a6785cda985 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-04-14T05:53:35Z |
| publishDate | 2022-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-b6918083737b47c1bad38a6785cda9852022-12-22T02:09:01ZengElsevierHeliyon2405-84402022-08-0188e10372Diagnostic accuracy of deep learning for evaluation of C-spine injury from lateral neck radiographsArunnit Boonrod0Artit Boonrod1Atthaphon Meethawolgul2Prin Twinprai3Department of Radiology, Khon Kaen University, Khon Kaen, 40002, Thailand; AI and Informatics in Medical Imaging (AIIMI) Research Group, Faculty of Medicine, Khon Kaen University, Khon Kaen, 40002, ThailandDepartment of Orthopedics, Khon Kaen University, Khon Kaen, 40002, Thailand; AI and Informatics in Medical Imaging (AIIMI) Research Group, Faculty of Medicine, Khon Kaen University, Khon Kaen, 40002, Thailand; Corresponding author.Department of Radiology, Khon Kaen University, Khon Kaen, 40002, ThailandDepartment of Radiology, Khon Kaen University, Khon Kaen, 40002, ThailandBackground: Traumatic spinal cord injury (TSI) is a leading cause of morbidity and mortality worldwide, with the cervical spine being the most affected. Delayed diagnosis carries a risk of morbidity and mortality. However, cervical spine CT scans are time-consuming, costly, and not always available in general care. In this study, deep learning was used to assess and improve the detection of cervical spine injuries on lateral radiographs, the most widely used screening method to help physicians triage patients quickly and avoid unnecessary CT scans. Materials and methods: Lateral neck or lateral cervical spine radiographs were obtained for patients who underwent CT scan of cervical spine. Ground truth was determined based on CT reports. CiRA CORE, a codeless deep learning program, was used as a training and testing platform. YOLO network models, including V2, V3, and V4, were trained to detect cervical spine injury. The diagnostic accuracy, sensitivity, and specificity of the model were calculated. Results: A total of 229 radiographs (129 negative and 100 positive) were selected for inclusion in our study from a list of 625 patients with cervical spine CT scans, 181 (28.9%) of whom had cervical spine injury. The YOLO V4 model performed better than the V2 or V3 (AUC = 0.743), with sensitivity, specificity, and accuracy of 80%, 72% and 75% respectively. Conclusion: Deep learning can improve the accuracy of lateral c-spine or neck radiographs. We anticipate that this will assist clinicians in quickly triaging patients and help to minimize the number of unnecessary CT scans.http://www.sciencedirect.com/science/article/pii/S2405844022016607Cervical spine injuryLateral radiographsCervical spine CTDeep learning |
| spellingShingle | Arunnit Boonrod Artit Boonrod Atthaphon Meethawolgul Prin Twinprai Diagnostic accuracy of deep learning for evaluation of C-spine injury from lateral neck radiographs Heliyon Cervical spine injury Lateral radiographs Cervical spine CT Deep learning |
| title | Diagnostic accuracy of deep learning for evaluation of C-spine injury from lateral neck radiographs |
| title_full | Diagnostic accuracy of deep learning for evaluation of C-spine injury from lateral neck radiographs |
| title_fullStr | Diagnostic accuracy of deep learning for evaluation of C-spine injury from lateral neck radiographs |
| title_full_unstemmed | Diagnostic accuracy of deep learning for evaluation of C-spine injury from lateral neck radiographs |
| title_short | Diagnostic accuracy of deep learning for evaluation of C-spine injury from lateral neck radiographs |
| title_sort | diagnostic accuracy of deep learning for evaluation of c spine injury from lateral neck radiographs |
| topic | Cervical spine injury Lateral radiographs Cervical spine CT Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S2405844022016607 |
| work_keys_str_mv | AT arunnitboonrod diagnosticaccuracyofdeeplearningforevaluationofcspineinjuryfromlateralneckradiographs AT artitboonrod diagnosticaccuracyofdeeplearningforevaluationofcspineinjuryfromlateralneckradiographs AT atthaphonmeethawolgul diagnosticaccuracyofdeeplearningforevaluationofcspineinjuryfromlateralneckradiographs AT printwinprai diagnosticaccuracyofdeeplearningforevaluationofcspineinjuryfromlateralneckradiographs |