Automated analysis of knee joint alignment using detailed angular values in long leg radiographs based on deep learning
Abstract Malalignment in the lower limb structure occurs due to various causes. Accurately evaluating limb alignment in situations where malalignment needs correction is necessary. To create an automated support system to evaluate lower limb alignment by quantifying mechanical tibiofemoral angle (mT...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-03-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-57887-1 |
| _version_ | 1827301131855855616 |
|---|---|
| author | Hong Seon Lee Sangchul Hwang Sung-Hwan Kim Nam Bum Joon Hyeongmin Kim Yeong Sang Hong Sungjun Kim |
| author_facet | Hong Seon Lee Sangchul Hwang Sung-Hwan Kim Nam Bum Joon Hyeongmin Kim Yeong Sang Hong Sungjun Kim |
| author_sort | Hong Seon Lee |
| collection | DOAJ |
| description | Abstract Malalignment in the lower limb structure occurs due to various causes. Accurately evaluating limb alignment in situations where malalignment needs correction is necessary. To create an automated support system to evaluate lower limb alignment by quantifying mechanical tibiofemoral angle (mTFA), mechanical lateral distal femoral angle (mLDFA), medial proximal tibial angle (MPTA), and joint line convergence angle (JLCA) on full-length weight-bearing radiographs of both lower extremities. In this retrospective study, we analysed 404 radiographs from one hospital for algorithm development and testing and 30 radiographs from another hospital for external validation. The performance of segmentation algorithm was compared to that of manual segmentation using the dice similarity coefficient (DSC). The agreement of alignment parameters was assessed using the intraclass correlation coefficient (ICC) for internal and external validation. The time taken to load the data and measure the four alignment parameters was recorded. The segmentation algorithm demonstrated excellent agreement with human-annotated segmentation for all anatomical regions (average similarity: 89–97%). Internal validation yielded good to very good agreement for all the alignment parameters (ICC ranges: 0.7213–0.9865). Interobserver correlations between manual and automatic measurements in external validation were good to very good (ICC scores: 0.7126–0.9695). The computer-aided measurement was 3.44 times faster than was the manual measurement. Our deep learning-based automated measurement algorithm accurately quantified lower limb alignment from radiographs and was faster than manual measurement. |
| first_indexed | 2024-04-24T16:17:52Z |
| format | Article |
| id | doaj.art-a4f1e56b008f4fa0861933e77b678d39 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-24T16:17:52Z |
| publishDate | 2024-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-a4f1e56b008f4fa0861933e77b678d392024-03-31T11:21:07ZengNature PortfolioScientific Reports2045-23222024-03-0114111010.1038/s41598-024-57887-1Automated analysis of knee joint alignment using detailed angular values in long leg radiographs based on deep learningHong Seon Lee0Sangchul Hwang1Sung-Hwan Kim2Nam Bum Joon3Hyeongmin Kim4Yeong Sang Hong5Sungjun Kim6Department of Radiology, Gangnam Severance Hospital, Yonsei University College of MedicineResearch Institute of Radiological Science, Center for Clinical Imaging Data Science, Yonsei University College of MedicineDepartment of Orthopedic Surgery, Gangnam Severance Hospital, Yonsei University College of MedicineDepartment of Orthopedic Surgery, Gangnam Severance Hospital, Yonsei University College of MedicineDepartment of Radiology, Gangnam Severance Hospital, Yonsei University College of MedicineDepartment of Radiology, Gangnam Severance Hospital, Yonsei University College of MedicineDepartment of Radiology, Gangnam Severance Hospital, Yonsei University College of MedicineAbstract Malalignment in the lower limb structure occurs due to various causes. Accurately evaluating limb alignment in situations where malalignment needs correction is necessary. To create an automated support system to evaluate lower limb alignment by quantifying mechanical tibiofemoral angle (mTFA), mechanical lateral distal femoral angle (mLDFA), medial proximal tibial angle (MPTA), and joint line convergence angle (JLCA) on full-length weight-bearing radiographs of both lower extremities. In this retrospective study, we analysed 404 radiographs from one hospital for algorithm development and testing and 30 radiographs from another hospital for external validation. The performance of segmentation algorithm was compared to that of manual segmentation using the dice similarity coefficient (DSC). The agreement of alignment parameters was assessed using the intraclass correlation coefficient (ICC) for internal and external validation. The time taken to load the data and measure the four alignment parameters was recorded. The segmentation algorithm demonstrated excellent agreement with human-annotated segmentation for all anatomical regions (average similarity: 89–97%). Internal validation yielded good to very good agreement for all the alignment parameters (ICC ranges: 0.7213–0.9865). Interobserver correlations between manual and automatic measurements in external validation were good to very good (ICC scores: 0.7126–0.9695). The computer-aided measurement was 3.44 times faster than was the manual measurement. Our deep learning-based automated measurement algorithm accurately quantified lower limb alignment from radiographs and was faster than manual measurement.https://doi.org/10.1038/s41598-024-57887-1Knee joint alignmentRadiographDeep learningOsteoarthritis |
| spellingShingle | Hong Seon Lee Sangchul Hwang Sung-Hwan Kim Nam Bum Joon Hyeongmin Kim Yeong Sang Hong Sungjun Kim Automated analysis of knee joint alignment using detailed angular values in long leg radiographs based on deep learning Scientific Reports Knee joint alignment Radiograph Deep learning Osteoarthritis |
| title | Automated analysis of knee joint alignment using detailed angular values in long leg radiographs based on deep learning |
| title_full | Automated analysis of knee joint alignment using detailed angular values in long leg radiographs based on deep learning |
| title_fullStr | Automated analysis of knee joint alignment using detailed angular values in long leg radiographs based on deep learning |
| title_full_unstemmed | Automated analysis of knee joint alignment using detailed angular values in long leg radiographs based on deep learning |
| title_short | Automated analysis of knee joint alignment using detailed angular values in long leg radiographs based on deep learning |
| title_sort | automated analysis of knee joint alignment using detailed angular values in long leg radiographs based on deep learning |
| topic | Knee joint alignment Radiograph Deep learning Osteoarthritis |
| url | https://doi.org/10.1038/s41598-024-57887-1 |
| work_keys_str_mv | AT hongseonlee automatedanalysisofkneejointalignmentusingdetailedangularvaluesinlonglegradiographsbasedondeeplearning AT sangchulhwang automatedanalysisofkneejointalignmentusingdetailedangularvaluesinlonglegradiographsbasedondeeplearning AT sunghwankim automatedanalysisofkneejointalignmentusingdetailedangularvaluesinlonglegradiographsbasedondeeplearning AT nambumjoon automatedanalysisofkneejointalignmentusingdetailedangularvaluesinlonglegradiographsbasedondeeplearning AT hyeongminkim automatedanalysisofkneejointalignmentusingdetailedangularvaluesinlonglegradiographsbasedondeeplearning AT yeongsanghong automatedanalysisofkneejointalignmentusingdetailedangularvaluesinlonglegradiographsbasedondeeplearning AT sungjunkim automatedanalysisofkneejointalignmentusingdetailedangularvaluesinlonglegradiographsbasedondeeplearning |