Comparison of tibial alignment parameters based on clinically relevant anatomical landmarks <subtitle>a deep learning radiological analysis</subtitle>
AimsAccurate identification of the ankle joint centre is critical for estimating tibial coronal alignment in total knee arthroplasty (TKA). The purpose of the current study was to leverage artificial intelligence (AI) to determine the accuracy and effect of using different radiological anatomical la...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The British Editorial Society of Bone & Joint Surgery
2022-10-01
|
| Series: | Bone & Joint Open |
| Subjects: | |
| Online Access: | https://online.boneandjoint.org.uk/doi/10.1302/2633-1462.310.BJO-2022-0082.R1 |
| _version_ | 1811246590562664448 |
|---|---|
| author | Seong J. Jang Kyle N. Kunze Zachary R. Brilliant Melissa Henson David J. Mayman Seth A. Jerabek Jonathan M. Vigdorchik Peter K. Sculco |
| author_facet | Seong J. Jang Kyle N. Kunze Zachary R. Brilliant Melissa Henson David J. Mayman Seth A. Jerabek Jonathan M. Vigdorchik Peter K. Sculco |
| author_sort | Seong J. Jang |
| collection | DOAJ |
| description | AimsAccurate identification of the ankle joint centre is critical for estimating tibial coronal alignment in total knee arthroplasty (TKA). The purpose of the current study was to leverage artificial intelligence (AI) to determine the accuracy and effect of using different radiological anatomical landmarks to quantify mechanical alignment in relation to a traditionally defined radiological ankle centre.MethodsPatients with full-limb radiographs from the Osteoarthritis Initiative were included. A sub-cohort of 250 radiographs were annotated for landmarks relevant to knee alignment and used to train a deep learning (U-Net) workflow for angle calculation on the entire database. The radiological ankle centre was defined as the midpoint of the superior talus edge/tibial plafond. Knee alignment (hip-knee-ankle angle) was compared against 1) midpoint of the most prominent malleoli points, 2) midpoint of the soft-tissue overlying malleoli, and 3) midpoint of the soft-tissue sulcus above the malleoli.ResultsA total of 932 bilateral full-limb radiographs (1,864 knees) were measured at a rate of 20.63 seconds/image. The knee alignment using the radiological ankle centre was accurate against ground truth radiologist measurements (inter-class correlation coefficient (ICC) = 0.99 (0.98 to 0.99)). Compared to the radiological ankle centre, the mean midpoint of the malleoli was 2.3 mm (SD 1.3) lateral and 5.2 mm (SD 2.4) distal, shifting alignment by 0.34o (SD 2.4o) valgus, whereas the midpoint of the soft-tissue sulcus was 4.69 mm (SD 3.55) lateral and 32.4 mm (SD 12.4) proximal, shifting alignment by 0.65o (SD 0.55o) valgus. On the intermalleolar line, measuring a point at 46% (SD 2%) of the intermalleolar width from the medial malleoli (2.38 mm medial adjustment from midpoint) resulted in knee alignment identical to using the radiological ankle centre.ConclusionThe current study leveraged AI to create a consistent and objective model that can estimate patient-specific adjustments necessary for optimal landmark usage in extramedullary and computer-guided navigation for tibial coronal alignment to match radiological planning.Cite this article: Bone Jt Open 2022;3(10):767–776. |
| first_indexed | 2024-04-12T14:55:33Z |
| format | Article |
| id | doaj.art-b34a9749dedd42019c82fc118cf572e0 |
| institution | Directory Open Access Journal |
| issn | 2633-1462 |
| language | English |
| last_indexed | 2024-04-12T14:55:33Z |
| publishDate | 2022-10-01 |
| publisher | The British Editorial Society of Bone & Joint Surgery |
| record_format | Article |
| series | Bone & Joint Open |
| spelling | doaj.art-b34a9749dedd42019c82fc118cf572e02022-12-22T03:28:15ZengThe British Editorial Society of Bone & Joint SurgeryBone & Joint Open2633-14622022-10-0131076777610.1302/2633-1462.310.BJO-2022-0082.R1Comparison of tibial alignment parameters based on clinically relevant anatomical landmarks <subtitle>a deep learning radiological analysis</subtitle>Seong J. Jang0Kyle N. Kunze1Zachary R. Brilliant2Melissa Henson3David J. Mayman4Seth A. Jerabek5Jonathan M. Vigdorchik6Peter K. Sculco7Weill Cornell Medical College, New York, New York, USADepartment of Orthopedic Surgery, Hospital for Special Surgery, New York, New York, USAAdult Reconstruction and Joint Replacement Service, Hospital for Special Surgery, New York, New York, USADepartment of Orthopedic Surgery, Hospital for Special Surgery, New York, New York, USADepartment of Orthopedic Surgery, Hospital for Special Surgery, New York, New York, USADepartment of Orthopedic Surgery, Hospital for Special Surgery, New York, New York, USADepartment of Orthopedic Surgery, Hospital for Special Surgery, New York, New York, USADepartment of Orthopedic Surgery, Hospital for Special Surgery, New York, New York, USAAimsAccurate identification of the ankle joint centre is critical for estimating tibial coronal alignment in total knee arthroplasty (TKA). The purpose of the current study was to leverage artificial intelligence (AI) to determine the accuracy and effect of using different radiological anatomical landmarks to quantify mechanical alignment in relation to a traditionally defined radiological ankle centre.MethodsPatients with full-limb radiographs from the Osteoarthritis Initiative were included. A sub-cohort of 250 radiographs were annotated for landmarks relevant to knee alignment and used to train a deep learning (U-Net) workflow for angle calculation on the entire database. The radiological ankle centre was defined as the midpoint of the superior talus edge/tibial plafond. Knee alignment (hip-knee-ankle angle) was compared against 1) midpoint of the most prominent malleoli points, 2) midpoint of the soft-tissue overlying malleoli, and 3) midpoint of the soft-tissue sulcus above the malleoli.ResultsA total of 932 bilateral full-limb radiographs (1,864 knees) were measured at a rate of 20.63 seconds/image. The knee alignment using the radiological ankle centre was accurate against ground truth radiologist measurements (inter-class correlation coefficient (ICC) = 0.99 (0.98 to 0.99)). Compared to the radiological ankle centre, the mean midpoint of the malleoli was 2.3 mm (SD 1.3) lateral and 5.2 mm (SD 2.4) distal, shifting alignment by 0.34o (SD 2.4o) valgus, whereas the midpoint of the soft-tissue sulcus was 4.69 mm (SD 3.55) lateral and 32.4 mm (SD 12.4) proximal, shifting alignment by 0.65o (SD 0.55o) valgus. On the intermalleolar line, measuring a point at 46% (SD 2%) of the intermalleolar width from the medial malleoli (2.38 mm medial adjustment from midpoint) resulted in knee alignment identical to using the radiological ankle centre.ConclusionThe current study leveraged AI to create a consistent and objective model that can estimate patient-specific adjustments necessary for optimal landmark usage in extramedullary and computer-guided navigation for tibial coronal alignment to match radiological planning.Cite this article: Bone Jt Open 2022;3(10):767–776.https://online.boneandjoint.org.uk/doi/10.1302/2633-1462.310.BJO-2022-0082.R1Knee alignmentArtificial intelligenceMachine learningMechanical alignmentTibial alignmentknees |
| spellingShingle | Seong J. Jang Kyle N. Kunze Zachary R. Brilliant Melissa Henson David J. Mayman Seth A. Jerabek Jonathan M. Vigdorchik Peter K. Sculco Comparison of tibial alignment parameters based on clinically relevant anatomical landmarks <subtitle>a deep learning radiological analysis</subtitle> Bone & Joint Open Knee alignment Artificial intelligence Machine learning Mechanical alignment Tibial alignment knees |
| title | Comparison of tibial alignment parameters based on clinically relevant anatomical landmarks <subtitle>a deep learning radiological analysis</subtitle> |
| title_full | Comparison of tibial alignment parameters based on clinically relevant anatomical landmarks <subtitle>a deep learning radiological analysis</subtitle> |
| title_fullStr | Comparison of tibial alignment parameters based on clinically relevant anatomical landmarks <subtitle>a deep learning radiological analysis</subtitle> |
| title_full_unstemmed | Comparison of tibial alignment parameters based on clinically relevant anatomical landmarks <subtitle>a deep learning radiological analysis</subtitle> |
| title_short | Comparison of tibial alignment parameters based on clinically relevant anatomical landmarks <subtitle>a deep learning radiological analysis</subtitle> |
| title_sort | comparison of tibial alignment parameters based on clinically relevant anatomical landmarks subtitle a deep learning radiological analysis subtitle |
| topic | Knee alignment Artificial intelligence Machine learning Mechanical alignment Tibial alignment knees |
| url | https://online.boneandjoint.org.uk/doi/10.1302/2633-1462.310.BJO-2022-0082.R1 |
| work_keys_str_mv | AT seongjjang comparisonoftibialalignmentparametersbasedonclinicallyrelevantanatomicallandmarkssubtitleadeeplearningradiologicalanalysissubtitle AT kylenkunze comparisonoftibialalignmentparametersbasedonclinicallyrelevantanatomicallandmarkssubtitleadeeplearningradiologicalanalysissubtitle AT zacharyrbrilliant comparisonoftibialalignmentparametersbasedonclinicallyrelevantanatomicallandmarkssubtitleadeeplearningradiologicalanalysissubtitle AT melissahenson comparisonoftibialalignmentparametersbasedonclinicallyrelevantanatomicallandmarkssubtitleadeeplearningradiologicalanalysissubtitle AT davidjmayman comparisonoftibialalignmentparametersbasedonclinicallyrelevantanatomicallandmarkssubtitleadeeplearningradiologicalanalysissubtitle AT sethajerabek comparisonoftibialalignmentparametersbasedonclinicallyrelevantanatomicallandmarkssubtitleadeeplearningradiologicalanalysissubtitle AT jonathanmvigdorchik comparisonoftibialalignmentparametersbasedonclinicallyrelevantanatomicallandmarkssubtitleadeeplearningradiologicalanalysissubtitle AT peterksculco comparisonoftibialalignmentparametersbasedonclinicallyrelevantanatomicallandmarkssubtitleadeeplearningradiologicalanalysissubtitle |