Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Jun;51(6):1249-1259.
doi: 10.1007/s00256-021-03948-9. Epub 2021 Nov 13.

Fully automated deep learning for knee alignment assessment in lower extremity radiographs: a cross-sectional diagnostic study

Sebastian Simon  1   2 , Gilbert M Schwarz  1   3 , Alexander Aichmair  1   2 , Bernhard J H Frank  1 , Allan Hummer  4 , Matthew D DiFranco  4 , Martin Dominkus  2   5 , Jochen G Hofstaetter  6   7
Affiliations

Fully automated deep learning for knee alignment assessment in lower extremity radiographs: a cross-sectional diagnostic study

Sebastian Simon et al. Skeletal Radiol. 2022 Jun.

Abstract

Objectives: Accurate assessment of knee alignment and leg length discrepancy is currently measured manually from standing long-leg radiographs (LLR), a process that is both time consuming and poorly reproducible. The aim was to assess the performance of a commercial available AI software by comparing its outputs with manually performed measurements.

Materials and methods: The AI was trained on over 15,000 radiographs to measure various clinical angles and lengths from LLRs. We performed a retrospective single-center analysis on 295 LLRs obtained between 2015 and 2020 from male and female patients over 18 years. AI and expert measurements were performed independently. Kellgren-Lawrence score and reading time were assessed. All measurements were compared and non-inferiority, mean-absolute-deviation (sMAD), and intra-class-correlation (ICC) were calculated.

Results: A total of 295 LLRs from 284 patients (mean age, 65 years (18; 90); 97 (34.2%) men) were analyzed. The AI model produces outputs on 98.0% of the LLRs. Manually annotations were considered as 100% accurate. For each measurement, its divergence was calculated, resulting in an overall accuracy of 89.2% when comparing the AI outputs to the manually measured. AI vs. mean observer revealed an sMAD between 0.39 and 2.19° for angles and 1.45-5.00 mm for lengths. AI showed good reliability in all lengths and angles (ICC ≥ 0.87). Non-inferiority comparing AI to the mean observer revealed an equivalence-index (γ) between 0.54 and 3.03° for angles and - 0.70-1.95 mm for lengths. On average, AI was 130 s faster than clinicians.

Conclusion: Automated measurements of knee alignment and length measurements produced with an AI tool result in reproducible, accurate measures with a time savings compared to manually acquired measurements.

Keywords: Artificial intelligence; Big data; Knee alignment; Long-leg radiographs; Standardization.

PubMed Disclaimer

References

    1. Skyttä ET, Lohman M, Tallroth K, Remes V. Comparison of standard anteroposterior knee and hip-to-ankle radiographs in determining the lower limb and implant alignment after total knee arthroplasty. Scand J Surg. 2009 [cited 2021 Jun 8];98:250–3. Available from: http://journals.sagepub.com/doi/10.1177/145749690909800411
    1. Zheng Q, Shellikeri S, Huang H, Hwang M, Sze RW. Deep learning measurement of leg length discrepancy in children based on radiographs. Radiology. 2020 [cited 2021 Jun 8];296:152–8. Available from: http://pubs.rsna.org/doi/10.1148/radiol.2020192003
    1. Hankemeier S, Gosling T, Richter M, Hufner T, Hochhausen C, Krettek C. Computer-assisted analysis of lower limb geometry: higher intraobserver reliability compared to conventional method. Comput Aided Surg. 2006 [cited 2021 Jun 8];11:81–6. Available from: http://www.tandfonline.com/doi/full/10.3109/10929080600628985
    1. Schmidt G, Altman G, Dougherty J, DeMeo P. Reproducibility and reliability of the anatomic axis of the lower extremity. J Knee Surg. 2010 [cited 2020 Sep 8];17:140–3. Available from: http://www.thieme-connect.de/DOI/DOI?10.1055/s-0030-1248212
    1. McDaniel G, Mitchell KL, Charles C, Kraus VB. A comparison of five approaches to measurement of anatomic knee alignment from radiographs. Osteoarthr Cartil. NIH Public Access; 2010 [cited 2020 Sep 8];18:273–7. Available from:/pmc/articles/PMC2818371/?report=abstract

LinkOut - more resources