Fully automated measurement on coronal alignment of lower limbs using deep convolutional neural networks on radiographic images
Abstract Background A deep convolutional neural network (DCNN) system is proposed to measure the lower limb parameters of the mechanical lateral distal femur angle (mLDFA), medial proximal tibial angle (MPTA), lateral distal tibial angle (LDTA), joint line convergence angle (JLCA), and mechanical ax...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-09-01
|
| Series: | BMC Musculoskeletal Disorders |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12891-022-05818-4 |
| _version_ | 1828104859895726080 |
|---|---|
| author | Xianghong Meng Zhi Wang Xinlong Ma Xiaoming Liu Hong Ji Jie-zhi Cheng Pei Dong |
| author_facet | Xianghong Meng Zhi Wang Xinlong Ma Xiaoming Liu Hong Ji Jie-zhi Cheng Pei Dong |
| author_sort | Xianghong Meng |
| collection | DOAJ |
| description | Abstract Background A deep convolutional neural network (DCNN) system is proposed to measure the lower limb parameters of the mechanical lateral distal femur angle (mLDFA), medial proximal tibial angle (MPTA), lateral distal tibial angle (LDTA), joint line convergence angle (JLCA), and mechanical axis of the lower limbs. Methods Standing X-rays of 1000 patients’ lower limbs were examined for the DCNN and assigned to training, validation, and test sets. A coarse-to-fine network was employed to locate 20 key landmarks on both limbs that first recognised the regions of hip, knee, and ankle, and subsequently outputted the key points in each sub-region from a full-length X-ray. Finally, information from these key landmark locations was used to calculate the above five parameters. Results The DCNN system showed high consistency (intraclass correlation coefficient > 0.91) for all five lower limb parameters. Additionally, the mean absolute error (MAE) and root mean squared error (RMSE) of all angle predictions were lower than 3° for both the left and right limbs. The MAE of the mechanical axis of the lower limbs was 1.124 mm and 1.416 mm and the RMSE was 1.032 mm and 1.321 mm, for the right and left limbs, respectively. The measurement time of the DCNN system was 1.8 ± 1.3 s, which was significantly shorter than that of experienced radiologists (616.8 ± 48.2 s, t = -180.4, P < 0.001). Conclusions The proposed DCNN system can automatically measure mLDFA, MPTA, LDTA, JLCA, and the mechanical axis of the lower limbs, thus helping physicians manage lower limb alignment accurately and efficiently. |
| first_indexed | 2024-04-11T09:54:34Z |
| format | Article |
| id | doaj.art-eff9f5487d4c4336a7e7a8707ea12085 |
| institution | Directory Open Access Journal |
| issn | 1471-2474 |
| language | English |
| last_indexed | 2024-04-11T09:54:34Z |
| publishDate | 2022-09-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Musculoskeletal Disorders |
| spelling | doaj.art-eff9f5487d4c4336a7e7a8707ea120852022-12-22T04:30:42ZengBMCBMC Musculoskeletal Disorders1471-24742022-09-0123111110.1186/s12891-022-05818-4Fully automated measurement on coronal alignment of lower limbs using deep convolutional neural networks on radiographic imagesXianghong Meng0Zhi Wang1Xinlong Ma2Xiaoming Liu3Hong Ji4Jie-zhi Cheng5Pei Dong6Department of Radiology, Tianjin HospitalDepartment of Radiology, Tianjin HospitalDepartment of Orthopaedics, Tianjin HospitalBeijing United Imaging Research Institute of Intelligent Imaging, Haidian DistrictUnited Imaging Intelligence (Beijing) Co., Ltd, Haidian DistrictShanghai United Imaging Intelligence Co., Ltd, Xuhui DistrictUnited Imaging Intelligence (Beijing) Co., Ltd, Haidian DistrictAbstract Background A deep convolutional neural network (DCNN) system is proposed to measure the lower limb parameters of the mechanical lateral distal femur angle (mLDFA), medial proximal tibial angle (MPTA), lateral distal tibial angle (LDTA), joint line convergence angle (JLCA), and mechanical axis of the lower limbs. Methods Standing X-rays of 1000 patients’ lower limbs were examined for the DCNN and assigned to training, validation, and test sets. A coarse-to-fine network was employed to locate 20 key landmarks on both limbs that first recognised the regions of hip, knee, and ankle, and subsequently outputted the key points in each sub-region from a full-length X-ray. Finally, information from these key landmark locations was used to calculate the above five parameters. Results The DCNN system showed high consistency (intraclass correlation coefficient > 0.91) for all five lower limb parameters. Additionally, the mean absolute error (MAE) and root mean squared error (RMSE) of all angle predictions were lower than 3° for both the left and right limbs. The MAE of the mechanical axis of the lower limbs was 1.124 mm and 1.416 mm and the RMSE was 1.032 mm and 1.321 mm, for the right and left limbs, respectively. The measurement time of the DCNN system was 1.8 ± 1.3 s, which was significantly shorter than that of experienced radiologists (616.8 ± 48.2 s, t = -180.4, P < 0.001). Conclusions The proposed DCNN system can automatically measure mLDFA, MPTA, LDTA, JLCA, and the mechanical axis of the lower limbs, thus helping physicians manage lower limb alignment accurately and efficiently.https://doi.org/10.1186/s12891-022-05818-4Lower limbsFull-length X-rayAlignment measurementDeep convolutional neural networks |
| spellingShingle | Xianghong Meng Zhi Wang Xinlong Ma Xiaoming Liu Hong Ji Jie-zhi Cheng Pei Dong Fully automated measurement on coronal alignment of lower limbs using deep convolutional neural networks on radiographic images BMC Musculoskeletal Disorders Lower limbs Full-length X-ray Alignment measurement Deep convolutional neural networks |
| title | Fully automated measurement on coronal alignment of lower limbs using deep convolutional neural networks on radiographic images |
| title_full | Fully automated measurement on coronal alignment of lower limbs using deep convolutional neural networks on radiographic images |
| title_fullStr | Fully automated measurement on coronal alignment of lower limbs using deep convolutional neural networks on radiographic images |
| title_full_unstemmed | Fully automated measurement on coronal alignment of lower limbs using deep convolutional neural networks on radiographic images |
| title_short | Fully automated measurement on coronal alignment of lower limbs using deep convolutional neural networks on radiographic images |
| title_sort | fully automated measurement on coronal alignment of lower limbs using deep convolutional neural networks on radiographic images |
| topic | Lower limbs Full-length X-ray Alignment measurement Deep convolutional neural networks |
| url | https://doi.org/10.1186/s12891-022-05818-4 |
| work_keys_str_mv | AT xianghongmeng fullyautomatedmeasurementoncoronalalignmentoflowerlimbsusingdeepconvolutionalneuralnetworksonradiographicimages AT zhiwang fullyautomatedmeasurementoncoronalalignmentoflowerlimbsusingdeepconvolutionalneuralnetworksonradiographicimages AT xinlongma fullyautomatedmeasurementoncoronalalignmentoflowerlimbsusingdeepconvolutionalneuralnetworksonradiographicimages AT xiaomingliu fullyautomatedmeasurementoncoronalalignmentoflowerlimbsusingdeepconvolutionalneuralnetworksonradiographicimages AT hongji fullyautomatedmeasurementoncoronalalignmentoflowerlimbsusingdeepconvolutionalneuralnetworksonradiographicimages AT jiezhicheng fullyautomatedmeasurementoncoronalalignmentoflowerlimbsusingdeepconvolutionalneuralnetworksonradiographicimages AT peidong fullyautomatedmeasurementoncoronalalignmentoflowerlimbsusingdeepconvolutionalneuralnetworksonradiographicimages |