YOLOX-SwinT algorithm improves the accuracy of AO/OTA classification of intertrochanteric fractures by orthopedic trauma surgeons
Purpose: Intertrochanteric fracture (ITF) classification is crucial for surgical decision-making. However, orthopedic trauma surgeons have shown lower accuracy in ITF classification than expected. The objective of this study was to utilize an artificial intelligence (AI) method to improve the accura...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Chinese Journal of Traumatology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1008127524000518 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586258434490368 |
|---|---|
| author | Xue-Si Liu Rui Nie Ao-Wen Duan Li Yang Xiang Li Le-Tian Zhang Guang-Kuo Guo Qing-Shan Guo Dong-Chu Zhao Yang Li He-Hua Zhang |
| author_facet | Xue-Si Liu Rui Nie Ao-Wen Duan Li Yang Xiang Li Le-Tian Zhang Guang-Kuo Guo Qing-Shan Guo Dong-Chu Zhao Yang Li He-Hua Zhang |
| author_sort | Xue-Si Liu |
| collection | DOAJ |
| description | Purpose: Intertrochanteric fracture (ITF) classification is crucial for surgical decision-making. However, orthopedic trauma surgeons have shown lower accuracy in ITF classification than expected. The objective of this study was to utilize an artificial intelligence (AI) method to improve the accuracy of ITF classification. Methods: We trained a network called YOLOX-SwinT, which is based on the You Only Look Once X (YOLOX) object detection network with Swin Transformer (SwinT) as the backbone architecture, using 762 radiographic ITF examinations as the training set. Subsequently, we recruited 5 senior orthopedic trauma surgeons (SOTS) and 5 junior orthopedic trauma surgeons (JOTS) to classify the 85 original images in the test set, as well as the images with the prediction results of the network model in sequence. Statistical analysis was performed using the SPSS 20.0 (IBM Corp., Armonk, NY, USA) to compare the differences among the SOTS, JOTS, SOTS + AI, JOTS + AI, SOTS + JOTS, and SOTS + JOTS + AI groups. All images were classified according to the AO/OTA 2018 classification system by 2 experienced trauma surgeons and verified by another expert in this field. Based on the actual clinical needs, after discussion, we integrated 8 subgroups into 5 new subgroups, and the dataset was divided into training, validation, and test sets by the ratio of 8:1:1. Results: The mean average precision at the intersection over union (IoU) of 0.5 (mAP50) for subgroup detection reached 90.29%. The classification accuracy values of SOTS, JOTS, SOTS + AI, and JOTS + AI groups were 56.24% ± 4.02%, 35.29% ± 18.07%, 79.53% ± 7.14%, and 71.53% ± 5.22%, respectively. The paired t-test results showed that the difference between the SOTS and SOTS + AI groups was statistically significant, as well as the difference between the JOTS and JOTS + AI groups, and the SOTS + JOTS and SOTS + JOTS + AI groups. Moreover, the difference between the SOTS + JOTS and SOTS + JOTS + AI groups in each subgroup was statistically significant, with all p < 0.05. The independent samples t-test results showed that the difference between the SOTS and JOTS groups was statistically significant, while the difference between the SOTS + AI and JOTS + AI groups was not statistically significant. With the assistance of AI, the subgroup classification accuracy of both SOTS and JOTS was significantly improved, and JOTS achieved the same level as SOTS. Conclusion: In conclusion, the YOLOX-SwinT network algorithm enhances the accuracy of AO/OTA subgroups classification of ITF by orthopedic trauma surgeons. |
| format | Article |
| id | doaj-art-4e1f91855ab243d8938794f34a8bb081 |
| institution | Kabale University |
| issn | 1008-1275 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Chinese Journal of Traumatology |
| spelling | doaj-art-4e1f91855ab243d8938794f34a8bb0812025-01-26T05:03:27ZengElsevierChinese Journal of Traumatology1008-12752025-01-012816975YOLOX-SwinT algorithm improves the accuracy of AO/OTA classification of intertrochanteric fractures by orthopedic trauma surgeonsXue-Si Liu0Rui Nie1Ao-Wen Duan2Li Yang3Xiang Li4Le-Tian Zhang5Guang-Kuo Guo6Qing-Shan Guo7Dong-Chu Zhao8Yang Li9He-Hua Zhang10Department of Medical Engineering, Daping Hospital, Army Medical University, Chongqing, 400042, ChinaDepartment of Medical Engineering, Daping Hospital, Army Medical University, Chongqing, 400042, ChinaDepartment of Medical Engineering, Daping Hospital, Army Medical University, Chongqing, 400042, ChinaDepartment of Medical Engineering, Daping Hospital, Army Medical University, Chongqing, 400042, ChinaDepartment of Information, Southwest Hospital, Army Medical University, Chongqing, 400038, ChinaDepartment of Radiology, Daping Hospital, Army Medical University, Chongqing, 400042, ChinaDepartment of Radiology, Daping Hospital, Army Medical University, Chongqing, 400042, ChinaDivision of Trauma and War Injury, Daping Hospital, Army Medical University of PLA, State Key Laboratory of Trauma and Chemical Poisoning, Chongqing, 400042, ChinaDivision of Trauma and War Injury, Daping Hospital, Army Medical University of PLA, State Key Laboratory of Trauma and Chemical Poisoning, Chongqing, 400042, ChinaDivision of Trauma and War Injury, Daping Hospital, Army Medical University of PLA, State Key Laboratory of Trauma and Chemical Poisoning, Chongqing, 400042, China; Corresponding author.Department of Medical Engineering, Daping Hospital, Army Medical University, Chongqing, 400042, China; Corresponding author.Purpose: Intertrochanteric fracture (ITF) classification is crucial for surgical decision-making. However, orthopedic trauma surgeons have shown lower accuracy in ITF classification than expected. The objective of this study was to utilize an artificial intelligence (AI) method to improve the accuracy of ITF classification. Methods: We trained a network called YOLOX-SwinT, which is based on the You Only Look Once X (YOLOX) object detection network with Swin Transformer (SwinT) as the backbone architecture, using 762 radiographic ITF examinations as the training set. Subsequently, we recruited 5 senior orthopedic trauma surgeons (SOTS) and 5 junior orthopedic trauma surgeons (JOTS) to classify the 85 original images in the test set, as well as the images with the prediction results of the network model in sequence. Statistical analysis was performed using the SPSS 20.0 (IBM Corp., Armonk, NY, USA) to compare the differences among the SOTS, JOTS, SOTS + AI, JOTS + AI, SOTS + JOTS, and SOTS + JOTS + AI groups. All images were classified according to the AO/OTA 2018 classification system by 2 experienced trauma surgeons and verified by another expert in this field. Based on the actual clinical needs, after discussion, we integrated 8 subgroups into 5 new subgroups, and the dataset was divided into training, validation, and test sets by the ratio of 8:1:1. Results: The mean average precision at the intersection over union (IoU) of 0.5 (mAP50) for subgroup detection reached 90.29%. The classification accuracy values of SOTS, JOTS, SOTS + AI, and JOTS + AI groups were 56.24% ± 4.02%, 35.29% ± 18.07%, 79.53% ± 7.14%, and 71.53% ± 5.22%, respectively. The paired t-test results showed that the difference between the SOTS and SOTS + AI groups was statistically significant, as well as the difference between the JOTS and JOTS + AI groups, and the SOTS + JOTS and SOTS + JOTS + AI groups. Moreover, the difference between the SOTS + JOTS and SOTS + JOTS + AI groups in each subgroup was statistically significant, with all p < 0.05. The independent samples t-test results showed that the difference between the SOTS and JOTS groups was statistically significant, while the difference between the SOTS + AI and JOTS + AI groups was not statistically significant. With the assistance of AI, the subgroup classification accuracy of both SOTS and JOTS was significantly improved, and JOTS achieved the same level as SOTS. Conclusion: In conclusion, the YOLOX-SwinT network algorithm enhances the accuracy of AO/OTA subgroups classification of ITF by orthopedic trauma surgeons.http://www.sciencedirect.com/science/article/pii/S1008127524000518Artificial intelligenceIntertrochanteric fractureFracture classificationAssist diagnosisYOLOXSwin transformer |
| spellingShingle | Xue-Si Liu Rui Nie Ao-Wen Duan Li Yang Xiang Li Le-Tian Zhang Guang-Kuo Guo Qing-Shan Guo Dong-Chu Zhao Yang Li He-Hua Zhang YOLOX-SwinT algorithm improves the accuracy of AO/OTA classification of intertrochanteric fractures by orthopedic trauma surgeons Chinese Journal of Traumatology Artificial intelligence Intertrochanteric fracture Fracture classification Assist diagnosis YOLOX Swin transformer |
| title | YOLOX-SwinT algorithm improves the accuracy of AO/OTA classification of intertrochanteric fractures by orthopedic trauma surgeons |
| title_full | YOLOX-SwinT algorithm improves the accuracy of AO/OTA classification of intertrochanteric fractures by orthopedic trauma surgeons |
| title_fullStr | YOLOX-SwinT algorithm improves the accuracy of AO/OTA classification of intertrochanteric fractures by orthopedic trauma surgeons |
| title_full_unstemmed | YOLOX-SwinT algorithm improves the accuracy of AO/OTA classification of intertrochanteric fractures by orthopedic trauma surgeons |
| title_short | YOLOX-SwinT algorithm improves the accuracy of AO/OTA classification of intertrochanteric fractures by orthopedic trauma surgeons |
| title_sort | yolox swint algorithm improves the accuracy of ao ota classification of intertrochanteric fractures by orthopedic trauma surgeons |
| topic | Artificial intelligence Intertrochanteric fracture Fracture classification Assist diagnosis YOLOX Swin transformer |
| url | http://www.sciencedirect.com/science/article/pii/S1008127524000518 |
| work_keys_str_mv | AT xuesiliu yoloxswintalgorithmimprovestheaccuracyofaootaclassificationofintertrochantericfracturesbyorthopedictraumasurgeons AT ruinie yoloxswintalgorithmimprovestheaccuracyofaootaclassificationofintertrochantericfracturesbyorthopedictraumasurgeons AT aowenduan yoloxswintalgorithmimprovestheaccuracyofaootaclassificationofintertrochantericfracturesbyorthopedictraumasurgeons AT liyang yoloxswintalgorithmimprovestheaccuracyofaootaclassificationofintertrochantericfracturesbyorthopedictraumasurgeons AT xiangli yoloxswintalgorithmimprovestheaccuracyofaootaclassificationofintertrochantericfracturesbyorthopedictraumasurgeons AT letianzhang yoloxswintalgorithmimprovestheaccuracyofaootaclassificationofintertrochantericfracturesbyorthopedictraumasurgeons AT guangkuoguo yoloxswintalgorithmimprovestheaccuracyofaootaclassificationofintertrochantericfracturesbyorthopedictraumasurgeons AT qingshanguo yoloxswintalgorithmimprovestheaccuracyofaootaclassificationofintertrochantericfracturesbyorthopedictraumasurgeons AT dongchuzhao yoloxswintalgorithmimprovestheaccuracyofaootaclassificationofintertrochantericfracturesbyorthopedictraumasurgeons AT yangli yoloxswintalgorithmimprovestheaccuracyofaootaclassificationofintertrochantericfracturesbyorthopedictraumasurgeons AT hehuazhang yoloxswintalgorithmimprovestheaccuracyofaootaclassificationofintertrochantericfracturesbyorthopedictraumasurgeons |