A deep learning approach for fully automated measurements of lower extremity alignment in radiographic images
Abstract During clinical evaluation of patients and planning orthopedic treatments, the periodic assessment of lower limb alignment is critical. Currently, physicians use physical tools and radiographs to directly observe limb alignment. However, this process is manual, time consuming, and prone to...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-09-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-41380-2 |
| _version_ | 1827723157263351808 |
|---|---|
| author | Ki-Ryum Moon Byoung-Dai Lee Mu Sook Lee |
| author_facet | Ki-Ryum Moon Byoung-Dai Lee Mu Sook Lee |
| author_sort | Ki-Ryum Moon |
| collection | DOAJ |
| description | Abstract During clinical evaluation of patients and planning orthopedic treatments, the periodic assessment of lower limb alignment is critical. Currently, physicians use physical tools and radiographs to directly observe limb alignment. However, this process is manual, time consuming, and prone to human error. To this end, a deep-learning (DL)-based system was developed to automatically, rapidly, and accurately detect lower limb alignment by using anteroposterior standing X-ray medical imaging data of lower limbs. For this study, leg radiographs of non-overlapping 770 patients were collected from January 2016 to August 2020. To precisely detect necessary landmarks, a DL model was implemented stepwise. A radiologist compared the final calculated measurements with the observations in terms of the concordance correlation coefficient (CCC), Pearson correlation coefficient (PCC), and intraclass correlation coefficient (ICC). Based on the results and 250 frontal lower limb radiographs obtained from 250 patients, the system measurements for 16 indicators revealed superior reliability (CCC, PCC, and ICC ≤ 0.9; mean absolute error, mean square error, and root mean square error ≥ 0.9) for clinical observations. Furthermore, the average measurement speed was approximately 12 s. In conclusion, the analysis of anteroposterior standing X-ray medical imaging data by the DL-based lower limb alignment diagnostic support system produces measurement results similar to those obtained by radiologists. |
| first_indexed | 2024-03-10T21:55:23Z |
| format | Article |
| id | doaj.art-4254a7978cae4153a6828c2d2968e8c2 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-10T21:55:23Z |
| publishDate | 2023-09-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-4254a7978cae4153a6828c2d2968e8c22023-11-19T13:07:45ZengNature PortfolioScientific Reports2045-23222023-09-0113111110.1038/s41598-023-41380-2A deep learning approach for fully automated measurements of lower extremity alignment in radiographic imagesKi-Ryum Moon0Byoung-Dai Lee1Mu Sook Lee2Division of AI and Computer Engineering, Kyonggi UniversityDivision of AI and Computer Engineering, Kyonggi UniversityDepartment of Radiology, Keimyung University Dongsan HospitalAbstract During clinical evaluation of patients and planning orthopedic treatments, the periodic assessment of lower limb alignment is critical. Currently, physicians use physical tools and radiographs to directly observe limb alignment. However, this process is manual, time consuming, and prone to human error. To this end, a deep-learning (DL)-based system was developed to automatically, rapidly, and accurately detect lower limb alignment by using anteroposterior standing X-ray medical imaging data of lower limbs. For this study, leg radiographs of non-overlapping 770 patients were collected from January 2016 to August 2020. To precisely detect necessary landmarks, a DL model was implemented stepwise. A radiologist compared the final calculated measurements with the observations in terms of the concordance correlation coefficient (CCC), Pearson correlation coefficient (PCC), and intraclass correlation coefficient (ICC). Based on the results and 250 frontal lower limb radiographs obtained from 250 patients, the system measurements for 16 indicators revealed superior reliability (CCC, PCC, and ICC ≤ 0.9; mean absolute error, mean square error, and root mean square error ≥ 0.9) for clinical observations. Furthermore, the average measurement speed was approximately 12 s. In conclusion, the analysis of anteroposterior standing X-ray medical imaging data by the DL-based lower limb alignment diagnostic support system produces measurement results similar to those obtained by radiologists.https://doi.org/10.1038/s41598-023-41380-2 |
| spellingShingle | Ki-Ryum Moon Byoung-Dai Lee Mu Sook Lee A deep learning approach for fully automated measurements of lower extremity alignment in radiographic images Scientific Reports |
| title | A deep learning approach for fully automated measurements of lower extremity alignment in radiographic images |
| title_full | A deep learning approach for fully automated measurements of lower extremity alignment in radiographic images |
| title_fullStr | A deep learning approach for fully automated measurements of lower extremity alignment in radiographic images |
| title_full_unstemmed | A deep learning approach for fully automated measurements of lower extremity alignment in radiographic images |
| title_short | A deep learning approach for fully automated measurements of lower extremity alignment in radiographic images |
| title_sort | deep learning approach for fully automated measurements of lower extremity alignment in radiographic images |
| url | https://doi.org/10.1038/s41598-023-41380-2 |
| work_keys_str_mv | AT kiryummoon adeeplearningapproachforfullyautomatedmeasurementsoflowerextremityalignmentinradiographicimages AT byoungdailee adeeplearningapproachforfullyautomatedmeasurementsoflowerextremityalignmentinradiographicimages AT musooklee adeeplearningapproachforfullyautomatedmeasurementsoflowerextremityalignmentinradiographicimages AT kiryummoon deeplearningapproachforfullyautomatedmeasurementsoflowerextremityalignmentinradiographicimages AT byoungdailee deeplearningapproachforfullyautomatedmeasurementsoflowerextremityalignmentinradiographicimages AT musooklee deeplearningapproachforfullyautomatedmeasurementsoflowerextremityalignmentinradiographicimages |