Abstract
Purpose
The purpose of this study was to evaluate the reliability of a newly developed AI-algorithm for the evaluation of long leg radiographs (LLR) after total knee arthroplasties (TKA).
Methods
In the validation cohort 200 calibrated LLRs of eight different common unconstrained and constrained knee systems were analysed. Accuracy and reproducibility of the AI-algorithm were compared to manual reads regarding the hip–knee–ankle (HKA) as well as femoral (FCA) and tibial component (TCA) angles. In the evaluation cohort all institutional LLRs with TKAs in 2018 (n = 1312) were evaluated to assess the algorithms’ ability of handling large data sets. Intraclass correlation (ICC) coefficient and mean absolute deviation (sMAD) were calculated to assess conformity between the AI software and manual reads.
Results
Validation cohort: The AI-software was reproducible on 96% and reliable on 92.1% of LLRs with an output and showed excellent reliability in all measured angles (ICC > 0.97) compared to manual measurements. Excellent results were found for primary unconstrained TKAs. In constrained TKAs landmark setting on the femoral and tibial component failed in 12.5% of LLRs (n = 9). Evaluation cohort: Mean measurements for all postoperative TKAs (n = 1240) were 0.2° varus ± 2.5° (HKA), 89.3° ± 1.9° (FCA), and 89.1° ± 1.6° (TCA). Mean measurements on preoperative revision TKAs (n = 74) were 1.6 varus ± 6.4° (HKA), 90.5° ± 3.1° (FCA), and 88.9° ± 4.1° (TCA).
Conclusions
AI-powered applications are reliable for automated analysis of lower limb alignment on LLRs with TKAs. They are capable of handling large data sets and could, therefore, lead to more standardized and efficient postoperative quality controls.
Level of evidence
Diagnostic Level III.
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00167-022-07037-9/MediaObjects/167_2022_7037_Fig1_HTML.png)
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00167-022-07037-9/MediaObjects/167_2022_7037_Fig2_HTML.jpg)
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00167-022-07037-9/MediaObjects/167_2022_7037_Fig3_HTML.jpg)
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00167-022-07037-9/MediaObjects/167_2022_7037_Fig4_HTML.png)
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00167-022-07037-9/MediaObjects/167_2022_7037_Fig5_HTML.jpg)
![](https://cdn.statically.io/img/media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00167-022-07037-9/MediaObjects/167_2022_7037_Fig6_HTML.png)
Similar content being viewed by others
References
Franken M, Grimm B, Heyligers I (2010) A comparison of four systems for calibration when templating for total hip replacement with digital radiography. J Bone Joint Surg Br 92:136–141
Hankemeier S, Gosling T, Richter M, Hufner T, Hochhausen C, Krettek C (2006) Computer-assisted analysis of lower limb geometry: higher intraobserver reliability compared to conventional method. Comput Aided Surg 11:81–86
Hinterwimmer F, Lazic I, Suren C, Hirschmann MT, Pohlig F, Rueckert D et al (2022) Machine learning in knee arthroplasty: specific data are key—a systematic review. Knee Surg Sports Traumatol Arthrosc 30:376–388
Hirschmann A, Cyriac J, Stieltjes B, Kober T, Richiardi J, Omoumi P (2019) Artificial Intelligence in musculoskeletal imaging: review of current literature, challenges, and trends. Semin Musculoskelet Radiol 23:304–311
Howell SM, Shelton TJ, Hull ML (2018) Implant survival and function ten years after kinematically aligned total knee arthroplasty. J Arthroplasty 33:3678–3684
Huang NF, Dowsey MM, Ee E, Stoney JD, Babazadeh S, Choong PF (2012) Coronal alignment correlates with outcome after total knee arthroplasty: five-year follow-up of a randomized controlled trial. J Arthroplasty 27:1737–1741
Kiener M (2021) Artificial intelligence in medicine and the disclosure of risks. AI Soc 36:705–713
Kim TW, Park SH, Suh JT (2012) Comparison of mobile-bearing and fixed-bearing designs in high flexion total knee arthroplasty: using a navigation system. Knee Surg Relat Res 24:25–33
Klemt C, Tirumala V, Barghi A, Cohen-Levy WB, Robinson MG, Kwon YM (2022) Artificial intelligence algorithms accurately predict prolonged length of stay following revision total knee arthroplasty. Knee Surg Sports Traumatol Arthrosc. https://doi.org/10.1007/s00167-022-06894-8
Knutson GA (2005) Anatomic and functional leg-length inequality: a review and recommendation for clinical decision-making. Part I, anatomic leg-length inequality: prevalence, magnitude, effects and clinical significance. Chiropr Osteopat 13:11
Koo TK, Li MY (2016) A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J Chiropr Med 15:155–163
Kumar N, Yadav C, Raj R, Anand S (2014) How to interpret postoperative X-rays after total knee arthroplasty. Orthop Surg 6:179–186
Longstaff LM, Sloan K, Stamp N, Scaddan M, Beaver R (2009) Good alignment after total knee arthroplasty leads to faster rehabilitation and better function. J Arthroplasty 24:570–578
McDaniel G, Mitchell KL, Charles C, Kraus VB (2010) A comparison of five approaches to measurement of anatomic knee alignment from radiographs. Osteoarthritis Cartilage 18:273–277
Obuchowski NA, Subhas N, Schoenhagen P (2014) Testing for interchangeability of imaging tests. Acad Radiol 21:1483–1489
Schock J, Truhn D, Abrar DB, Merhof D, Conrad S, Post M et al (2021) Automated analysis of alignment in long-leg radiographs by using a fully automated support system based on artificial intelligence. Radiol Artif Intell 3:e200198
Simon S, Schwarz GM, Aichmair A, Frank BJH, Hummer A, DiFranco MD et al (2022) Fully automated deep learning for knee alignment assessment in lower extremity radiographs: a cross-sectional diagnostic study. Skeletal Radiol 51:1249–1259
Sled EA, Sheehy LM, Felson DT, Costigan PA, Lam M, Cooke TD (2011) Reliability of lower limb alignment measures using an established landmark-based method with a customized computer software program. Rheumatol Int 31:71–77
Tiulpin A, Thevenot J, Rahtu E, Lehenkari P, Saarakkala S (2018) Automatic knee osteoarthritis diagnosis from plain radiographs: a deep learning-based approach. Sci Rep 8:1727
Vaishya R, Vijay V, Birla VP, Agarwal AK (2016) Inter-observer variability and its correlation to experience in measurement of lower limb mechanical axis on long leg radiographs. J Clin Orthop Trauma 7:260–264
Zheng Q, Shellikeri S, Huang H, Hwang M, Sze RW (2020) Deep learning measurement of leg length discrepancy in children based on radiographs. Radiology 296:152–158
Acknowledgements
We would like to thank ImageBiopsy Lab (Allan Hummer and Matthew D. DiFranco) for the technical support and answering all our questions.
Funding
The Michael Ogon received a research grant from ImageBiopsy Lab. The collection, analysis, and interpretation of data, writing of the report, and the decision to submit the paper for publication were performed by the authors and not influenced by ImageBiopsy Lab.
Author information
Authors and Affiliations
Contributions
GMS: was responsible for conceptualization, data curation, formal analysis, investigation, methodology, project administration, visualization, and writing. GMS and SS: performed the manual measurements. JAM, BJHF, AA and MD: participated in conceptualization, methodology and editing. JGH: was the senior author and accountable for conceptualization, methodology, supervision, validation, writing as well as review & editing.
Corresponding author
Ethics declarations
Conflict of interest
We certify that we have not signed any agreement with commercial interest related to this study, which would in any way limit publication of any and all data generated for the study or to delay publication for any reason.
Ethical approval
This study was approved by the local ethics committee (No. 47/2020) and has been carried out in accordance with the ethical standards in the 1964 Declaration of Helsinki.
Informed consent
Individual informed consent was waived.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Schwarz, G.M., Simon, S., Mitterer, J.A. 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 30, 2538–2547 (2022). https://doi.org/10.1007/s00167-022-07037-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00167-022-07037-9