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 Aug;18(4):e2394.
doi: 10.1002/rcs.2394. Epub 2022 Apr 4.

Automatic prosthetic-parameter estimation from anteroposterior pelvic radiographs after total hip arthroplasty using deep learning-based keypoint detection

Tsung-Wei Tseng  1   2 , Yueh-Peng Chen  3 , Yu-Cheng Yeh  1   2 , Chang-Fu Kuo  3 , Tzuo-Yau Fan  3 , Yu-Chih Lin  1   2
Affiliations

Automatic prosthetic-parameter estimation from anteroposterior pelvic radiographs after total hip arthroplasty using deep learning-based keypoint detection

Tsung-Wei Tseng et al. Int J Med Robot. 2022 Aug.

Abstract

Background: X-ray is a necessary tool for post-total hip arthroplasty (THA) check-ups; however, parameter measurements are time-consuming. We proposed a deep learning tool, BKNet that automates localization of landmarks with parameter measurements.

Methods: About 3072 radiographs from 3021 patients who underwent THA at our institute between 2013 and 2017 were used. We employed BKNet to perform landmark localization with parameter measurements in these radiographs. The performance of BKNet was assessed and compared with that of human observers.

Results: The 75-percentile cut-off errors were <0.5 cm in all key points. The Bland-Altman methods show the agreement between the predicted and ground truth parameters. Human and BKNet comparison revealed the model could match the repeatability for 7/10 of the parameters.

Conclusions: The accuracy of BKNet is equivalent to that of human observers, and BKNet was able to perform prosthetic-parameter estimation from keypoint detection with superior cost-effectiveness, repeatability, and timesaving compared to human observers.

Keywords: artificial intelligence; landmark identification; parameter estimation; total hip arthroplasty.

PubMed Disclaimer

References

REFERENCES

    1. Schwartz AM, Farley KX, Guild GN, Bradbury TL, Jr. Projections and epidemiology of revision hip and knee arthroplasty in the United States to 2030. J Arthroplasty 2020;35(6S):S79-S85. https://doi.org/10.1016/j.arth.2020.02.030
    1. Lim SJ, Park YS. Plain radiography of the hip: a review of radiographic techniques and image features. Hip Pelvis. 2015;27(3):125-134. https://doi.org/10.5371/hp.2015.27.3.125
    1. Vanrusselt J, Vansevenant M, Vanderschueren G, Vanhoenacker F. Postoperative radiograph of the hip arthroplasty: what the radiologist should know. Insights Imaging. 2015;6(6):591-600. https://doi.org/10.1007/s13244-015-0438-5
    1. Sariali E, Mauprivez R, Khiami F, Pascal-Mousselard H, Catonné Y. Accuracy of the preoperative planning for cementless total hip arthroplasty. A randomised comparison between three-dimensional computerised planning and conventional templating. Orthop Traumatol Surg Res. 2012;98(2):151-158. https://doi.org/10.1016/j.otsr.2011.09.023
    1. Nomura T, Naito M, Nakamura Y, et al. An analysis of the best method for evaluating anteversion of the acetabular component after total hip replacement on plain radiographs. Bone Jt Lett J. 2014;96-B(5):597-603. https://doi.org/10.1302/0301-620X.96B.33013

LinkOut - more resources