Top

Journal of Orthopaedic Surgery and Research

Published in:

Open Access 01-12-2024 | Knee Osteoarthritis | Research article

Automatic measurement of lower limb alignment in portable devices based on deep learning for knee osteoarthritis

Authors: Jianfeng Yang, Peng Ren, Peng Xin, Yiming Wang, Yonglei Ma, Wei Liu, Yu Wang, Yan Wang, Guoqiang Zhang

Published in: Journal of Orthopaedic Surgery and Research | Issue 1/2024

Abstract

Background

For knee osteoarthritis patients, analyzing alignment of lower limbs is essential for therapy, which is currently measured from standing long-leg radiographs of anteroposterior X-ray (LLR) manually. To address the time wasting, poor reproducibility and inconvenience of use caused by existing methods, we present an automated measurement model in portable devices for assessing knee alignment from LLRs.

Method

We created a model and trained it with 837 conforming LLRs, and tested it using 204 LLRs without duplicates in a portable device. Both manual and model measurements were conducted independently, then we recorded knee alignment parameters such as Hip knee ankle angle (HKA), Joint line convergence angle (JCLA), Anatomical mechanical angle (AMA), mechanical Lateral distal femoral angle (mLDFA), mechanical Medial proximal tibial angle (mMPTA), and the time required. We evaluated the model’s performance compared with manual results in various metrics.

Result

In both the validation and test sets, the average mean radial errors were 2.778 and 2.447 (P<0.05). The test results for native knee joints showed that 92.22%, 79.38%, 87.94%, 79.82%, and 80.16% of the joints reached angle deviation<1° for HKA, JCLA, AMA, mLDFA, and mMPTA. Additionally, for joints with prostheses, 90.14%, 93.66%, 86.62%, 83.80%, and 85.92% of the joints reached that. The Chi-square test did not reveal any significant differences between the manual and model measurements in subgroups (P>0.05). Furthermore, the Bland-Altman 95% limits of agreement were less than ± 2° for HKA, JCLA, AMA, and mLDFA, and slightly more than ± 2 degrees for mMPTA.

Conclusion

The automatic measurement tool can assess the alignment of lower limbs in portable devices for knee osteoarthritis patients. The results are reliable, reproducible, and time-saving.

Conaghan PG, Porcheret M, Kingsbury SR, et al. Impact and therapy of osteoarthritis: the Arthritis Care OA Nation 2012 survey. Clin Rheumatol. 2015;34:1581–8. https://doi.org/10.1007/s10067-014-2692-1.CrossRefPubMed

Sasek C. An update on primary care management of knee osteoarthritis. JAAPA. 2015;28:37–43. https://doi.org/10.1097/01.JAA.0000458853.38655.02.CrossRefPubMed

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;51:1249–59. https://doi.org/10.1007/s00256-021-03948-9.CrossRefPubMed

Bouché P-A, Aubert T, Corsia S, et al. Systematic alignments yield balanced knees without additional releases in only 11% of knee arthroplasties: a prospective study. Knee Surg Sports Traumatol Arthrosc. 2022. https://doi.org/10.1007/s00167-022-07252-4.CrossRefPubMedPubMedCentral

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;98:250–3. https://doi.org/10.1177/145749690909800411.CrossRefPubMed

Langenbach MR, Dohle J, Zirngibl H. [Determination of the axis after totalendoprosthesis of the knee: functional X-ray photography as golden standard]. Z Orthop Ihre Grenzgeb. 2002;140:32–6. https://doi.org/10.1055/s-2002-22088.CrossRefPubMed

Paley D, Herzenberg JE, Tetsworth K, et al. Deformity planning for frontal and sagittal plane corrective osteotomies. Orthop Clin North Am. 1994;25:425–65.CrossRefPubMed

Rozzanigo U, Pizzoli A, Minari C, Caudana R. Alignment and articular orientation of lower limbs: manual vs computer-aided measurements on digital radiograms. Radiol Med. 2005;109:234–8.PubMed

Takahashi T, Yamanaka N, Komatsu M, et al. A new computer-assisted method for measuring the tibio-femoral angle in patients with osteoarthritis of the knee. Osteoarthritis Cartilage. 2004;12:256–9. https://doi.org/10.1016/j.joca.2003.10.005.CrossRefPubMed

10.

Sled EA, Sheehy LM, Felson DT, et al. Reliability of lower limb alignment measures using an established landmark-based method with a customized computer software program. Rheumatol Int. 2011;31:71–7. https://doi.org/10.1007/s00296-009-1236-5.CrossRefPubMed

11.

Zahn RK, Renner L, Perka C, Hommel H. Weight-bearing radiography depends on limb loading. Knee Surg Sports Traumatol Arthrosc. 2019;27:1470–6. https://doi.org/10.1007/s00167-018-5056-6.CrossRefPubMed

12.

Kannan A, Hawdon G, McMahon SJ. Effect of flexion and rotation on measures of coronal alignment after TKA. J Knee Surg. 2012;25:407–10. https://doi.org/10.1055/s-0032-1313756.CrossRefPubMed

13.

Maderbacher G, Baier C, Benditz A, et al. Presence of rotational errors in long leg radiographs after total knee arthroplasty and impact on measured lower limb and component alignment. Int Orthop. 2017;41:1553–60. https://doi.org/10.1007/s00264-017-3408-3.CrossRefPubMed

14.

Feldman DS, Henderson ER, Levine HB, et al. Interobserver and intraobserver reliability in lower-limb deformity correction measurements. J Pediatr Orthop. 2007;27:204–8. https://doi.org/10.1097/01.bpb.0000242441.96434.6f.CrossRefPubMed

15.

Akhmedov B, Sung KH, Chung CY, et al. Reliability of lower-limb alignment measurements in patients with multiple epiphyseal dysplasia. Clin Orthop Relat Res. 2012;470:3566–76. https://doi.org/10.1007/s11999-012-2548-4.CrossRefPubMedPubMedCentral

16.

Pavlovic N, Harris IA, Boland R, et al. The effect of body mass index and preoperative weight loss in people with obesity on postoperative outcomes to 6 months following total hip or knee arthroplasty: a retrospective study. Arthroplasty. 2023;5:48. https://doi.org/10.1186/s42836-023-00203-5.CrossRefPubMedPubMedCentral

17.

Bowman A, Shunmugam M, Watts AR, et al. Inter-observer and intra-observer reliability of mechanical axis alignment before and after total knee arthroplasty using long leg radiographs. Knee. 2016;23:203–8. https://doi.org/10.1016/j.knee.2015.11.013.CrossRefPubMed

18.

Finsterwald MA, Lu V, Andronic O, et al. Popliteal tendon impingement as a cause of pain following total knee arthroplasty: a systematic review. Arthroplasty. 2023;5:45. https://doi.org/10.1186/s42836-023-00201-7.CrossRefPubMedPubMedCentral

19.

Cho BW, Lee T-H, Kim S, et al. Evaluation of the reliability of lower extremity alignment measurements using EOS imaging system while standing in an even weight-bearing posture. Sci Rep. 2021;11:22039. https://doi.org/10.1038/s41598-021-01646-z.CrossRefPubMedPubMedCentral

20.

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. https://doi.org/10.1016/j.cmpb.2021.106080.CrossRefPubMed

21.

Zhang Z, Huang C, Jiang Q, et al. Guidelines for the diagnosis and treatment of osteoarthritis in China (2019 edition). Ann Transl Med. 2020;8:1213. https://doi.org/10.21037/atm-20-4665.CrossRefPubMedPubMedCentral

22.

Liu W, Wang Y, Jiang T, et al. Landmarks detection with anatomical constraints for total hip arthroplasty preoperative measurements. In: Martel AL, Abolmaesumi P, Stoyanov D, et al. editors. Medical Image Computing and Computer assisted intervention – MICCAI 2020. Cham: Springer International Publishing; 2020. pp. 670–9.CrossRef

23.

Sun K, Xiao B, Liu D, Wang J. (2019) Deep High-Resolution Representation Learning for Human Pose Estimation.

24.

ImageNet Large Scale Visual Recognition Challenge | SpringerLink. https://link.springer.com/article/10.1007/s11263-015-0816-y. Accessed 6 Nov 2022.

25.

Liu W, Anguelov D, Erhan D, et al. SSD: single shot MultiBox detector. In: Leibe B, Matas J, Sebe N, Welling M, editors. Computer vision – ECCV 2016. Cham: Springer International Publishing; 2016. pp. 21–37.CrossRef

26.

Kingma DP, Ba J. (2017) Adam: A Method for Stochastic Optimization.

27.

Nguyen TP, Chae D-S, Park S-J, et al. Intelligent analysis of coronal alignment in lower limbs based on radiographic image with convolutional neural network. Comput Biol Med. 2020;120:103732. https://doi.org/10.1016/j.compbiomed.2020.103732.CrossRefPubMed

28.

Ramazanian T, Yan S, Rouzrokh P, et al. Distribution and correlates of hip-knee-ankle Angle in early osteoarthritis and preoperative total knee arthroplasty patients. J Arthroplasty. 2022;37:170–S175. https://doi.org/10.1016/j.arth.2021.12.009.CrossRef

29.

Bayramoglu N, Nieminen MT, Saarakkala S. Automated detection of patellofemoral osteoarthritis from knee lateral view radiographs using deep learning: data from the Multicenter Osteoarthritis Study (MOST). Osteoarthritis Cartilage. 2021;29:1432–47. https://doi.org/10.1016/j.joca.2021.06.011.CrossRefPubMed

30.

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;44:53–62. https://doi.org/10.1007/s13246-020-00951-7.CrossRefPubMed

Title: Automatic measurement of lower limb alignment in portable devices based on deep learning for knee osteoarthritis
Authors: Jianfeng Yang
Peng Ren
Peng Xin
Yiming Wang
Yonglei Ma
Wei Liu
Yu Wang
Yan Wang
Guoqiang Zhang
Publication date: 01-12-2024
Publisher: BioMed Central
Keywords: Knee Osteoarthritis
Knee Osteoarthritis
Published in: Journal of Orthopaedic Surgery and Research / Issue 1/2024
Electronic ISSN: 1749-799X
DOI: https://doi.org/10.1186/s13018-024-04658-3

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Automatic measurement of lower limb alignment in portable devices based on deep learning for knee osteoarthritis

Abstract

Background

Method

Result

Conclusion

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Background

Method

Result

Conclusion

Please log in to get access to this content

Other articles of this Issue 1/2024

Comparison of minimally invasive transforaminal lumbar interbody fusion and midline lumbar interbody fusion in patients with spondylolisthesis

Navigation versus fluoroscopy in minimalinvasive iliosacral screw placement

Modified Bilhaut–Cloquet procedure for Wassel type III–IV polydactyly

Application of machine learning-based multi-sequence MRI radiomics in diagnosing anterior cruciate ligament tears

The outcome of conversion total hip arthroplasty following acetabular fractures: a systematic review and meta-analysis of comparative studies

Percutaneous kyphoplasty combined with pediculoplasty for the surgical treatment of osteoporotic thoracolumbar burst fractures