A deep learning model for radiological measurement of adolescent idiopathic scoliosis using biplanar radiographs
Abstract Background Accurate measurement of the spinal alignment parameters is crucial for diagnosing and evaluating adolescent idiopathic scoliosis (AIS). Manual measurement is subjective and time-consuming. The recently developed artificial intelligence models mainly focused on measuring the coron...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-03-01
|
| Series: | Journal of Orthopaedic Surgery and Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13018-025-05620-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849762143711264768 |
|---|---|
| author | Kunjie Xie Suping Zhu Jincong Lin Yi Li Jinghui Huang Wei Lei Yabo Yan |
| author_facet | Kunjie Xie Suping Zhu Jincong Lin Yi Li Jinghui Huang Wei Lei Yabo Yan |
| author_sort | Kunjie Xie |
| collection | DOAJ |
| description | Abstract Background Accurate measurement of the spinal alignment parameters is crucial for diagnosing and evaluating adolescent idiopathic scoliosis (AIS). Manual measurement is subjective and time-consuming. The recently developed artificial intelligence models mainly focused on measuring the coronal Cobb angle (CA) and ignored the evaluation of the sagittal plane. We developed a deep-learning model that could automatically measure spinal alignment parameters in biplanar radiographs. Methods In this study, our model adopted ResNet34 as the backbone network, mainly consisting of keypoint detection and CA measurement. A total of 600 biplane radiographs were collected from our hospital and randomly divided into train and test sets in a 3:1 ratio. Two senior spinal surgeons independently manually measured and analyzed spinal alignment and recorded the time taken. The reliabilities of automatic measurement were evaluated by comparing them with the gold standard, using mean absolute difference (MAD), intraclass correlation coefficient (ICC), simple linear regression, and Bland-Altman plots. The diagnosis performance of the model was evaluated through the receiver operating characteristic (ROC) curve and area under the curve (AUC). Severity classification and sagittal abnormalities classification were visualized using a confusion matrix. Results Our AI model achieved the MAD of coronal and sagittal angle errors was 2.15° and 2.72°, and ICC was 0.985, 0.927. The simple linear regression showed a strong correction between all parameters and the gold standard (p < 0.001, r2 ≥ 0.686), the Bland-Altman plots showed that the mean difference of the model was within 2° and the automatic measurement time was 9.1 s. Our model demonstrated excellent diagnostic performance, with an accuracy of 97.2%, a sensitivity of 96.8%, a specificity of 97.6%, and an AUC of 0.972 (0.940–1.000).For severity classification, the overall accuracy was 94.5%. All accuracy of sagittal abnormalities classification was greater than 91.8%. Conclusions This deep learning model can accurately and automatically measure spinal alignment parameters with reliable results, significantly reducing diagnostic time, and might provide the potential to assist clinicians. |
| format | Article |
| id | doaj-art-eae551a92f6c4541a80f13454a0757c0 |
| institution | DOAJ |
| issn | 1749-799X |
| language | English |
| publishDate | 2025-03-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Orthopaedic Surgery and Research |
| spelling | doaj-art-eae551a92f6c4541a80f13454a0757c02025-08-20T03:05:49ZengBMCJournal of Orthopaedic Surgery and Research1749-799X2025-03-0120111010.1186/s13018-025-05620-7A deep learning model for radiological measurement of adolescent idiopathic scoliosis using biplanar radiographsKunjie Xie0Suping Zhu1Jincong Lin2Yi Li3Jinghui Huang4Wei Lei5Yabo Yan6Department of Orthopedics, Xijing Hospital, Air Force Military Medical UniversitySchool of Telecommunications Engineering, Xidian UniversityDepartment of Orthopedics, Xijing Hospital, Air Force Military Medical UniversitySchool of Telecommunications Engineering, Xidian UniversityDepartment of Orthopedics, Xijing Hospital, Air Force Military Medical UniversityDepartment of Orthopedics, Xijing Hospital, Air Force Military Medical UniversityDepartment of Orthopedics, Xijing Hospital, Air Force Military Medical UniversityAbstract Background Accurate measurement of the spinal alignment parameters is crucial for diagnosing and evaluating adolescent idiopathic scoliosis (AIS). Manual measurement is subjective and time-consuming. The recently developed artificial intelligence models mainly focused on measuring the coronal Cobb angle (CA) and ignored the evaluation of the sagittal plane. We developed a deep-learning model that could automatically measure spinal alignment parameters in biplanar radiographs. Methods In this study, our model adopted ResNet34 as the backbone network, mainly consisting of keypoint detection and CA measurement. A total of 600 biplane radiographs were collected from our hospital and randomly divided into train and test sets in a 3:1 ratio. Two senior spinal surgeons independently manually measured and analyzed spinal alignment and recorded the time taken. The reliabilities of automatic measurement were evaluated by comparing them with the gold standard, using mean absolute difference (MAD), intraclass correlation coefficient (ICC), simple linear regression, and Bland-Altman plots. The diagnosis performance of the model was evaluated through the receiver operating characteristic (ROC) curve and area under the curve (AUC). Severity classification and sagittal abnormalities classification were visualized using a confusion matrix. Results Our AI model achieved the MAD of coronal and sagittal angle errors was 2.15° and 2.72°, and ICC was 0.985, 0.927. The simple linear regression showed a strong correction between all parameters and the gold standard (p < 0.001, r2 ≥ 0.686), the Bland-Altman plots showed that the mean difference of the model was within 2° and the automatic measurement time was 9.1 s. Our model demonstrated excellent diagnostic performance, with an accuracy of 97.2%, a sensitivity of 96.8%, a specificity of 97.6%, and an AUC of 0.972 (0.940–1.000).For severity classification, the overall accuracy was 94.5%. All accuracy of sagittal abnormalities classification was greater than 91.8%. Conclusions This deep learning model can accurately and automatically measure spinal alignment parameters with reliable results, significantly reducing diagnostic time, and might provide the potential to assist clinicians.https://doi.org/10.1186/s13018-025-05620-7Adolescent idiopathic scoliosisDeep learningCobb angleSagittal alignment parameterBiplanar radiographs |
| spellingShingle | Kunjie Xie Suping Zhu Jincong Lin Yi Li Jinghui Huang Wei Lei Yabo Yan A deep learning model for radiological measurement of adolescent idiopathic scoliosis using biplanar radiographs Journal of Orthopaedic Surgery and Research Adolescent idiopathic scoliosis Deep learning Cobb angle Sagittal alignment parameter Biplanar radiographs |
| title | A deep learning model for radiological measurement of adolescent idiopathic scoliosis using biplanar radiographs |
| title_full | A deep learning model for radiological measurement of adolescent idiopathic scoliosis using biplanar radiographs |
| title_fullStr | A deep learning model for radiological measurement of adolescent idiopathic scoliosis using biplanar radiographs |
| title_full_unstemmed | A deep learning model for radiological measurement of adolescent idiopathic scoliosis using biplanar radiographs |
| title_short | A deep learning model for radiological measurement of adolescent idiopathic scoliosis using biplanar radiographs |
| title_sort | deep learning model for radiological measurement of adolescent idiopathic scoliosis using biplanar radiographs |
| topic | Adolescent idiopathic scoliosis Deep learning Cobb angle Sagittal alignment parameter Biplanar radiographs |
| url | https://doi.org/10.1186/s13018-025-05620-7 |
| work_keys_str_mv | AT kunjiexie adeeplearningmodelforradiologicalmeasurementofadolescentidiopathicscoliosisusingbiplanarradiographs AT supingzhu adeeplearningmodelforradiologicalmeasurementofadolescentidiopathicscoliosisusingbiplanarradiographs AT jinconglin adeeplearningmodelforradiologicalmeasurementofadolescentidiopathicscoliosisusingbiplanarradiographs AT yili adeeplearningmodelforradiologicalmeasurementofadolescentidiopathicscoliosisusingbiplanarradiographs AT jinghuihuang adeeplearningmodelforradiologicalmeasurementofadolescentidiopathicscoliosisusingbiplanarradiographs AT weilei adeeplearningmodelforradiologicalmeasurementofadolescentidiopathicscoliosisusingbiplanarradiographs AT yaboyan adeeplearningmodelforradiologicalmeasurementofadolescentidiopathicscoliosisusingbiplanarradiographs AT kunjiexie deeplearningmodelforradiologicalmeasurementofadolescentidiopathicscoliosisusingbiplanarradiographs AT supingzhu deeplearningmodelforradiologicalmeasurementofadolescentidiopathicscoliosisusingbiplanarradiographs AT jinconglin deeplearningmodelforradiologicalmeasurementofadolescentidiopathicscoliosisusingbiplanarradiographs AT yili deeplearningmodelforradiologicalmeasurementofadolescentidiopathicscoliosisusingbiplanarradiographs AT jinghuihuang deeplearningmodelforradiologicalmeasurementofadolescentidiopathicscoliosisusingbiplanarradiographs AT weilei deeplearningmodelforradiologicalmeasurementofadolescentidiopathicscoliosisusingbiplanarradiographs AT yaboyan deeplearningmodelforradiologicalmeasurementofadolescentidiopathicscoliosisusingbiplanarradiographs |