Skip to main content

Advertisement

SpringerLink
Log in

Deep learning generated lower extremity radiographic measurements are adequate for quick assessment of knee angular alignment and leg length determination

  • Scientific Article
  • Published:
Skeletal Radiology Aims and scope Submit manuscript

Abstract

Purpose

Angular and longitudinal deformities of leg alignment create excessive stresses across joints, leading to pain and impaired function. Multiple measurements are used to assess these deformities on anteroposterior (AP) full-length radiographs. An artificial intelligence (AI) software automatically locates anatomical landmarks on AP full-length radiographs and performs 13 measurements to assess knee angular alignment and leg length. The primary aim of this study was to evaluate the agreements in LLD and knee alignment measurements between an AI software and two board-certified radiologists in patients without metal implants. The secondary aim was to assess time savings achieved by AI.

Methods

The measurements assessed in the study were hip-knee-angle (HKA), anatomical-tibiofemoral angle (aTFA), anatomical-mechanical-axis angle (AMA), joint-line-convergence angle (JLCA), mechanical-lateral-proximal-femur-angle (mLPFA), mechanical-lateral-distal-femur-angle (mLDFA), mechanical-medial-proximal-tibia-angle (mMPTA), mechanical-lateral-distal-tibia- angle (mLDTA), femur length, tibia length, full leg length, leg length discrepancy (LLD), and mechanical axis deviation (MAD). These measurements were performed by two radiologists and the AI software on 164 legs. Intraclass-correlation-coefficients (ICC) and Bland–Altman analyses were used to assess the AI’s performance.

Results

The AI software set incorrect landmarks for 11/164 legs. Excluding these cases, ICCs between the software and radiologists were excellent for 12/13 variables (11/13 with outliers included), and the AI software met performance targets for 11/13 variables (9/13 with outliers included). The mean reading time for the AI algorithm and two readers, respectively, was 38.3, 435.0, and 625.0 s.

Conclusion

This study demonstrated that, with few exceptions, this AI-based software reliably generated measurements for most variables in the study and provided substantial time savings.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Gordon JE, Davis LE. Leg length discrepancy: the natural history (and what do we really know). J Pediatr Orthop. 2019;39(Issue 6, Supplement 1 Suppl 1):S10-s13.

    Article  PubMed  Google Scholar 

  2. Siffert RS. Lower limb-length discrepancy. J Bone Joint Surg Am. 1987;69(7):1100–6.

    Article  CAS  PubMed  Google Scholar 

  3. Gurney B. Leg length discrepancy. Gait Posture. 2002;15(2):195–206.

    Article  PubMed  Google Scholar 

  4. Gofton JP, Trueman GE. Studies in osteoarthritis of the hip. II. Osteoarthritis of the hip and leg-length disparity. Can Med Assoc J. 1971;104(9):791–9.

    CAS  PubMed  PubMed Central  Google Scholar 

  5. Applebaum A, Nessim A, Cho W. Overview and spinal implications of leg length discrepancy: narrative review. Clin Orthop Surg. 2021;13(2):127–34.

    Article  PubMed  PubMed Central  Google Scholar 

  6. Raczkowski JW, Daniszewska B, Zolynski K. Functional scoliosis caused by leg length discrepancy. Arch Med Sci. 2010;6(3):393–8.

    Article  PubMed  PubMed Central  Google Scholar 

  7. Ghanem I, Karam JA, Widmann RF. Surgical epiphysiodesis indications and techniques: update. Curr Opin Pediatr. 2011;23(1):53–9.

    Article  PubMed  Google Scholar 

  8. Thienpont E, et al. Bone morphotypes of the varus and valgus knee. Arch Orthop Trauma Surg. 2017;137(3):393–400.

    Article  CAS  PubMed  Google Scholar 

  9. Wang B, et al. Valgus malalignment and prevalence of lateral compartmental radiographic knee osteoarthritis (OA): the Wuchuan OA study. Int J Rheum Dis. 2018;21(7):1385–90.

    Article  PubMed  Google Scholar 

  10. Sharma L, et al. Varus and valgus alignment and incident and progressive knee osteoarthritis. Ann Rheum Dis. 2010;69(11):1940–5.

    Article  PubMed  Google Scholar 

  11. Schwarz GM, 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):2538–47.

    Article  PubMed  Google Scholar 

  12. Simon S, et al. Fully automated deep learning for knee alignment assessment in lower extremity radiographs: a cross-sectional diagnostic study. Skeletal Radiol. 2022;51(6):1249–59.

    Article  PubMed  Google Scholar 

  13. Kallogjeri D, Spitznagel EL Jr, Piccirillo JF. Importance of defining and interpreting a clinically meaningful difference in clinical research. JAMA Otolaryngol-Head Neck Surg. 2020;146(2):101–2.

    Article  PubMed  Google Scholar 

  14. Martin Bland J, Altman D. Statistical methods for assessing agreement between two methods of clinical measurement. Lancet. 1986;327(8476):307–10.

    Article  Google Scholar 

  15. Hodson TO. Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not. Geosci Model Dev. 2022;15(14):5481–7.

    Article  Google Scholar 

  16. Obuchowski NA, Subhas N, Schoenhagen P. Testing for interchangeability of imaging tests. Acad Radiol. 2014;21(11):1483–9.

    Article  PubMed  Google Scholar 

  17. Cicchetti DV. Guidelines, criteria, and rules of thumb for evaluating normed and standardized assessment instruments in psychology. Psychol Assess. 1994;6:284–90.

    Article  Google Scholar 

  18. Lu MJ, Zhong WH, Liu YX, Miao HZ, Li YC, Ji MH. Sample size for assessing agreement between two methods of measurement by Bland-Altman method. Int J Biostat. 2016;12(2):/j/ijb.2016.12.issue-2/ijb-2015-0039/ijb-2015-0039.xml. https://doi.org/10.1515/ijb-2015-0039.

  19. Lin YH, Chang FS, Chen KH, Huang KC, Su KC. Mismatch between femur and tibia coronal alignment in the knee joint: classification of five lower limb types according to femoral and tibial mechanical alignment. BMC Musculoskelet Disord. 2018;19(1):411. https://doi.org/10.1186/s12891-018-2335-9.

  20. Marques Luis N, Varatojo R. Radiological assessment of lower limb alignment. EFORT Open Rev. 2021;6(6):487–94.

    Article  PubMed  PubMed Central  Google Scholar 

  21. Bellemans J, et al. The Chitranjan Ranawat Award: is neutral mechanical alignment normal for all patients?: the concept of constitutional varus. Clin Orthop Relat Res. 2012;470(1):45–53.

    Article  PubMed  Google Scholar 

  22. Shimizu M, et al. Examination of the changes in lower extremities related to progression of adult spinal deformity: a longitudinal study of over 22 years. Sci Rep. 2020;10(1):11605.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX, 75390, USA

    Holden Archer, Seth Reine, Shuda Xia, Louis Camilo Vazquez, Oganes Ashikyan, Parham Pezeshk, Ajay Kohli, Yin Xi & Avneesh Chhabra

  2. Baylor, Scott, & White, Dallas, TX, USA

    Joel E. Wells

  3. IB Lab GmbH, Zehetnergasse 6/2/2, 1140, Vienna, Austria

    Allan Hummer & Matthew Difranco

  4. Adjunct Faculty, Johns Hopkins University, Baltimore, MD, USA

    Avneesh Chhabra

  5. University of Dallas, Richardson, TX, USA

    Avneesh Chhabra

  6. Walton Centre for Neurosciences, Liverpool, UK

    Avneesh Chhabra

Authors
  1. Holden Archer
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Seth Reine
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shuda Xia
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Louis Camilo Vazquez
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Oganes Ashikyan
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Parham Pezeshk
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Ajay Kohli
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Yin Xi
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Joel E. Wells
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Allan Hummer
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Matthew Difranco
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Avneesh Chhabra
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Avneesh Chhabra.

Ethics declarations

Conflict of interest

AC: consultant: ICON Medical and TREACE Medical Concepts Inc.; book royalties: Jaypee, Wolters; speaker: Siemens; medical advisor: Imagebiopsy Lab Inc.; research grant: Imagebiopsy Lab Inc.

OA: consultant: ImageBiopsy Lab.

PP: consultant: ImageBiopsy Lab.

JW: consultant: Ethicon.

MD: employee: ImageBiopsy Lab GmbH.

AH: employee: ImageBiopsy Lab GmbH.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Summary statement

Our study showed that, with the exception of outlier cases, AI-based software demonstrated reliable radiographic assessment of knee angular alignment and leg length determination for most measurements along with significant time savings.

Key points

1. The artificial intelligence algorithm demonstrated excellent agreement (intraclass correlation coefficients > 0.75) for 12/13 measurements used in the study when outlier cases were excluded.

2. Artificial intelligence met the performance targets based on Bland-Altman analysis for 11/13 variables when outlier cases were excluded.

3. The artificial intelligence system generated measurements more than 90% faster than the expert readers.

Supplementary Information

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

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 53, 923–933 (2024). https://doi.org/10.1007/s00256-023-04502-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00256-023-04502-5

Keywords

Search

Navigation