Can Artificial Intelligence Reliably and Accurately Measure Lower Limb Alignment: A Systematic Review and Meta-Analysis

Document Type : SYSTEMATIC REVIEW

Authors

1 Student Research Committee, Shahid Beheshti University of Medical Sciences, Tehran, Iran

2 Department of Orthopedic Surgery, Akhtar Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran

3 Student Research Committee, Shahid Sadoughi University of Medical Sciences, Yazd, Iran

4 Student Research Committee, School of Medicine, Shahed University, Tehran, Iran

5 Clinical Research Development Unit (CRDU), Shohada-eTajrish Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran

6 Birjand University of Medical Sciences and Health Services, Birjand, Iran

7 Joint Reconstruction Research Center, Tehran University of Medical Sciences, Tehran, Iran

10.22038/abjs.2025.84846.3864

Abstract

Objectives: Lower limb alignment (LLA) measurements are vital for pre-operative assessments and 
surgical planning in orthopedics. Artificial intelligence (AI) can enhance the precision and consistency 
of these measurements. This systematic review and meta -analysis evaluates the accuracy and 
reliability of AI-based approaches in detecting anatomical landmarks and measuring LLA angles, 
highlighting both their strengths and limitations.
Methods: Adhering to PRISMA guidelines, we searched PubMed, Scopus, Embase, and Web of Science on July 
2024 and included observational studies validating AI-driven LLA measurements. Pooled intraclass correlation 
coefficients (ICCs) were computed to assess inter-rater reliability between AI and manual measurements. The 
Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool was used to assess study quality.
Results: We reviewed 28 studies with 47,200 patients and 61,253 images; AI demonstrated high reliability in 
measuring 15 lower limb angles, with pooled ICCs ranging from 0.9811 to 1.0597. Angles like the hip-knee-ankle 
(HKA; ICC = 0.9987, 95% CI: 0.9975–0.9998) and the mechanical tibiofemoral angle (mTFA; ICC = 1.0001, 95% 
CI: 1.0001–1.0001) showed near-perfect agreement. In contrast, the joint line convergence angle (JLCA) and 
femoral anatomical-mechanical angle (FAMA) exhibited lower reliability and significant publication bias. 
Heterogeneity was substantial across most angles (I² = 63%–100%). These findings highlight the potential of AI for 
clinical applications while also identifying areas that require refinement and standardization.
Conclusion: AI exhibits high reliability and accuracy in measuring key LLA angles, often outperforming manual 
techniques in both speed and consistency. It holds significant promise as a clinical tool, though challenges with less 
reliable angles warrant further refinement. Future studies should focus on standardizing landmark definitions and 
addressing implementation barriers to maximize AI’s potential in orthopedic practice.
 Level of evidence: IV

Keywords

Main Subjects


  1. Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts H. Artificial intelligence in radiology. Nat Rev Cancer. 2018; 18(8):500-510. doi:10.1038/s41568-018-0016-5.
  2. Felson DT, Niu J, Gross KD, et al. Valgus malalignment is a risk factor for lateral knee osteoarthritis incidence and progression: findings from the Multicenter Osteoarthritis Study and the Osteoarthritis Initiative. Arthritis Rheum. 2013; 65(2):355-62. doi: 10.1002/art.37726.
  3. Sharma L, Chmiel JS, Almagor O, et al. The role of varus and valgus alignment in the initial development of knee cartilage damage by MRI: the MOST study. Ann Rheum Dis. 2013; 72(2):235-40. doi: 10.1136/annrheumdis-2011-201070.
  4. Choong PF, Dowsey MM, Stoney JD. Does accurate anatomical alignment result in better function and quality of life? Comparing conventional and computer-assisted total knee arthroplasty. J Arthroplasty. 2009; 24(4):560-9. doi: 10.1016/j.arth.2008.02.018.
  5. Tew M, Waugh W. Tibiofemoral alignment and the results of knee replacement. J Bone Joint Surg Br. 1985; 67(4):551-6. doi: 10.1302/0301-620X.67B4.4030849.
  6. Laskin RS. Alignment of total knee components. Orthopedics. 1984; 7(1):62-72. doi: 10.3928/0147-7447-19840101-09.
  7. Wright JG, Treble N, Feinstein AR. Measurement of lower limb alignment using long radiographs. J Bone Joint Surg Br. 1991; 73(5):721-3. doi: 10.1302/0301-620X.73B5.1894657.
  8. Gitto S, Serpi F, Albano D, et al. AI applications in musculoskeletal imaging: a narrative review. Eur Radiol Exp. 2024; 8(1):22. doi:10.1186/s41747-024-00422-8.
  9. Jung J, Dai J, Liu B, Wu Q. Artificial intelligence in fracture detection with different image modalities and data types: A systematic review and meta-analysis. PLOS Digit Health. 2024; 3(1):e0000438. doi:10.1371/journal.pdig.0000438.
  10. Ren M, Yi PH. Artificial intelligence in orthopedic implant model classification: a systematic review. Skeletal Radiol. 2022; 51(2):407-416. doi:10.1007/s00256-021-03884-8.
  11. Simon S, Schwarz GM, Aichmair A, et al. Fully automated deep learning for knee alignment assessment in lower extremity radiographs: a cross-sectional diagnostic study. Skeletal Radiol. 2022; 51(6):1249-1259. doi: 10.1007/s00256-021-03948-9.
  12. Li Z, Liu F, Yang W, Peng S, Zhou J. A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects. IEEE Trans Neural Netw Learn Syst. 2022; 33(12):6999-7019. doi: 10.1109/TNNLS.2021.3084827.
  13. Page MJ, McKenzie JE, Bossuyt PM, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ. 2021:372:n71. doi: 10.1136/bmj.n71.
  14. Marques Luís N, Varatojo R. Radiological assessment of lower limb alignment. EFORT Open Rev. 2021; 6(6):487-494. doi: 10.1302/2058-5241.6.210015.
  15. Whiting PF, Rutjes AW, Westwood ME, et al. QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies. Ann Intern Med. 2011; 155(8):529-36. doi: 10.7326/0003-4819-155-8-201110180-00009.
  16. Mongan J, Moy L, Kahn Jr CE. Checklist for artificial intelligence in medical imaging (CLAIM): a guide for authors and reviewers. Radiol Artif Intell. 2020; 2(2):e200029. doi: 10.1148/ryai.2020200029.
  17. Yang J, Ren P, Xin P, et al. Automatic measurement of lower limb alignment in portable devices based on deep learning for knee osteoarthritis. J Orthop Surg Res. 2024; 19(1):232. doi: 10.1186/s13018-024-04658-3.
  18. Archer H, Reine S, Xia S, et al. Deep learning generated lower extremity radiographic measurements are adequate for quick assessment of knee angular alignment and leg length determination. Skeletal Radiol. 2024; 53(5):923-933. doi:10.1007/s00256-023-04502-5.
  19. Bernard de Villeneuve F, Jacquet C, El Kadim B, et al. An artificial intelligence based on a convolutional neural network allows a precise analysis of the alignment of the lower limb. Int Orthop. 2023; 47(2):511-518. doi:10.1007/s00264-022-05634-4.
  20. Erne F, Grover P, Dreischarf M, et al. Automated Artificial Intelligence-Based Assessment of Lower Limb Alignment Validated on Weight-Bearing Pre- and Postoperative Full-Leg Radiographs. Diagnostics (Basel). 2022; 12(11):2679. doi: 10.3390/diagnostics12112679.
  21. Gielis WP, Rayegan H, Arbabi V, et al. Predicting the mechanical hip-knee-ankle angle accurately from standard knee radiographs: a cross-validation experiment in 100 patients. Acta Orthop. 2020; 91(6):732-737. doi:10.1080/17453674.2020.1779516.
  22. Jang SJ, Kunze KN, Casey JC, et al. Variability of the femoral mechanical-anatomical axis angle and its implications in primary and revision total knee arthroplasty. Bone Jt Open. 2024; 5(2):101-108. doi:10.1302/2633-1462.52.Bjo-2023-0056.R1.
  23. Jo C, Hwang D, Ko S, et al. Deep learning-based landmark recognition and angle measurement of full-leg plain radiographs can be adopted to assess lower extremity alignment. Knee Surg Sports Traumatol Arthrosc. 2023; 31(4):1388-1397. doi:10.1007/s00167-022-07124-x.
  24. Kim SE, Nam JW, Kim JI, Kim JK, Ro DH. Enhanced deep learning model enables accurate alignment measurement across diverse institutional imaging protocols. Knee Surg Relat Res. 2024; 36(1):4. doi:10.1186/s43019-023-00209-y.
  25. Kunze KN, Jang SJ, Li T, et al. Radiographic findings involved in knee osteoarthritis progression are associated with pain symptom frequency and baseline disease severity: a population-level analysis using deep learning. Knee Surg Sports Traumatol Arthrosc. 2023; 31(2):586-595. doi:10.1007/s00167-022-07213-x.
  26. Lee HS, Hwang S, Kim SH, et al. Automated analysis of knee joint alignment using detailed angular values in long leg radiographs based on deep learning. Sci Rep. 2024; 14(1):7226. doi:10.1038/s41598-024-57887-1.
  27. Meng X, Wang Z, Ma X, et al. Fully automated measurement on coronal alignment of lower limbs using deep convolutional neural networks on radiographic images. BMC Musculoskelet Disord. 2022; 23(1):869. doi:10.1186/s12891-022-05818-4.
  28. Mitterer JA, Huber S, Schwarz GM, et al. Fully automated assessment of the knee alignment on long leg radiographs following corrective knee osteotomies in patients with valgus or varus deformities. Arch Orthop Trauma Surg. 2024; 144(3):1029-1038. doi:10.1007/s00402-023-05151-y.
  29. Miyama K, Akiyama T, Bise R, Nakamura S, Nakashima Y, Uchida S. Development of an automatic surgical planning system for high tibial osteotomy using artificial intelligence. Knee. 2024; 48:128-137. doi:10.1016/j.knee.2024.03.008.
  30. Moon HD, Choi HG, Lee KJ, Choi DJ, Yoo HJ, Lee YS. Can Deep Learning Using Weight Bearing Knee Anterio-Posterior Radiograph Alone Replace a Whole-Leg Radiograph in the Interpretation of Weight Bearing Line Ratio? J Clin Med. 2021; 10(8). doi: 10.3390/jcm10081772.
  31. Murad Y, Chhina H, Cooper A. Fully Automated Analysis of the Anatomic and Mechanical Axes From Pediatric Standing Lower Limb Radiographs Using Convolutional Neural Networks. J Pediatr Orthop. 2024; 44(4):244-253. doi:10.1097/bpo.0000000000002611.
  32. Nam HS, Park SH, Ho JPY, Park SY, Cho JH, Lee YS. Key-Point Detection Algorithm of Deep Learning Can Predict Lower Limb Alignment with Simple Knee Radiographs. J Clin Med. 2023; 12(4).doi:10.3390/jcm12041455.
  33. Nguyen TP, Chae DS, Park SJ, Kang KY, Lee WS, Yoon J. Intelligent analysis of coronal alignment in lower limbs based on radiographic image with convolutional neural network. Comput Biol Med. 2020; 120:103732. doi:10.1016/j.compbiomed.2020.103732.
  34. Pagano S, Müller K, Götz J, et al. The Role and Efficiency of an AI-Powered Software in the Evaluation of Lower Limb Radiographs before and after Total Knee Arthroplasty. J Clin Med. 2023; 12(17). doi:10.3390/jcm12175498.
  35. Pei Y, Yang W, Wei S, et al. Automated measurement of hip–knee–ankle angle on the unilateral lower limb X-rays using deep learning. Phys Eng Sci Med. 2021; 44(1):53-62. doi: 10.1007/s13246-020-00951-7.
  36. Schock J, Truhn D, Abrar DB, et al. Automated Analysis of Alignment in Long-Leg Radiographs by Using a Fully Automated Support System Based on Artificial Intelligence. Radiol Artif Intell. 2021; 3(2):e200198. doi:10.1148/ryai.2020200198.
  37. Schwarz GM, Simon S, Mitterer JA, et al. Artificial intelligence enables reliable and standardized measurements of implant alignment in long leg radiographs with total knee arthroplasties. Knee Surg Sports Traumatol Arthrosc. 2022; 30(8):2538-2547. doi:10.1007/s00167-022-07037-9.
  38. Stotter C, Klestil T, Chen K, et al. Artificial intelligence-based analyses of varus leg alignment and after high tibial osteotomy show high accuracy and reproducibility. Knee Surg Sports Traumatol Arthrosc. 2023; 31(12):5885-5895. doi: 10.1007/s00167-023-07644-0.
  39. Tack A, Preim B, Zachow S. Fully automated Assessment of Knee Alignment from Full-Leg X-Rays employing a "YOLOv4 And Resnet Landmark regression Algorithm" (YARLA): Data from the Osteoarthritis Initiative. Comput Methods Programs Biomed. 2021:205:106080. doi: 10.1016/j.cmpb.2021.106080.
  40. Tanner IL, Ye K, Moore MS, et al. Developing a Computer Vision Model to Automate Quantitative Measurement of Hip-Knee-Ankle Angle in Total Hip and Knee Arthroplasty Patients. J Arthroplasty. 2024; 39(9):2225-2233. doi:10.1016/j.arth.2024.04.062.
  41. Tsai A. A deep learning approach to automatically quantify lower extremity alignment in children. Skeletal Radiol. 2022; 51(2):381-390. doi:10.1007/s00256-021-03844-2.
  42. Wang J, Hall TAG, Musbahi O, Jones GG, van Arkel RJ. Predicting hip-knee-ankle and femorotibial angles from knee radiographs with deep learning. Knee. 2023; 42:281-288.

 

        doi:10.1016/j.knee.2023.03.010.

  1. Wilhelm NJ, von Schacky CE, Lindner FJ, et al. Multicentric development and validation of a multi-scale and multi-task deep learning model for comprehensive lower extremity alignment analysis. Artif Intell Med. 2024; 150:102843. doi:10.1016/j.artmed.2024.102843.
  2. Kurmis AP, Ianunzio JR. Artificial intelligence in orthopedic surgery: evolution, current state and future directions. Arthroplasty. 2022;4(1):9. doi:10.1186/s42836-022-00112-z.
  3. Droppelmann G, Rodríguez C, Jorquera C, Feijoo F. Artificial intelligence in diagnosing upper limb musculoskeletal disorders: a systematic review and meta-analysis of diagnostic tests. EFORT Open Rev. 2024; 9(4):241-251. doi:10.1530/eor-23-0174.
  4. Gupta P, Haeberle HS, Zimmer ZR, Levine WN, Williams RJ, Ramkumar PN. Artificial intelligence-based applications in shoulder surgery leaves much to be desired: a systematic review. JSES Rev Rep Tech. 2023; 3(2):189-200. doi:10.1016/j.xrrt.2022.12.006.
  5. Morya VK, Lee HW, Shahid H, et al. Application of ChatGPT for Orthopedic Surgeries and Patient Care. Clin Orthop Surg. 2024; 16(3):347-356. doi:10.4055/cios23181.
  6. Joseph GB, McCulloch CE, Sohn JH, Pedoia V, Majumdar S, Link TM. AI MSK clinical applications: cartilage and osteoarthritis. Skeletal Radiol. 2022; 51(2):331-343. doi:10.1007/s00256-021-03909-2.
  7. Chong YY, Chan PK, Chan VWK, et al. Application of machine learning in the prevention of periprosthetic joint infection following total knee arthroplasty: a systematic review. Arthroplasty. 2023; 5(1):38. doi:10.1186/s42836-023-00195-2.
  8. Xu D, Lou W, Li M, Xiao J, Wu H, Chen J. Current status of robot-assisted surgery in the clinical application of trauma orthopedics in China: A systematic review. Health Sci Rep. 2022; 5(6):e930. doi:10.1002/hsr2.930.
  9. Zhang X, Yang Y, Shen YW, et al. Diagnostic accuracy and potential covariates of artificial intelligence for diagnosing orthopedic fractures: a systematic literature review and meta-analysis. Eur Radiol. 2022; 32(10):7196-7216. doi:10.1007/s00330-022-08956-4.
  10. Collins G, Dhiman P, Andaur Navarro C, et al. Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence. BMJ Open. 2021; 11(7):e048008. doi: 10.1136/bmjopen-2020-048008.
  11. Sounderajah V, Ashrafian H, Aggarwal R, et al. Developing specific reporting guidelines for diagnostic accuracy studies assessing AI interventions: The STARD-AI Steering Group. Nat Med. 2020; 26(6):807-808. doi: 10.1038/s41591-020-0941-1.
  12. Jayakumar S, Sounderajah V, Normahani P, et al. Quality assessment standards in artificial intelligence diagnostic accuracy systematic reviews: a meta-research study. NPJ Digit Med. 2022; 5(1):11. doi: 10.1038/s41746-021-00544-y.
  13. Collins GS, Moons KG, Dhiman P, et al. TRIPOD+ AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024:385:e078378. doi: 10.1136/bmj-2023-078378.