Skip to main content
SpringerLink
Log in

Development of Local Software for Automatic Measurement of Geometric Parameters in the Proximal Femur Using a Combination of a Deep Learning Approach and an Active Shape Model on X-ray Images

  • Published:
Journal of Imaging Informatics in Medicine Aims and scope Submit manuscript

Abstract

Proximal femur geometry is an important risk factor for diagnosing and predicting hip and femur injuries. Hence, the development of an automated approach for measuring these parameters could help physicians with the early identification of hip and femur ailments. This paper presents a technique that combines the active shape model (ASM) and deep learning methodologies. First, the femur boundary is extracted by a deep learning neural network. Then, the femur’s anatomical landmarks are fitted to the extracted border using the ASM method. Finally, the geometric parameters of the proximal femur, including femur neck axis length (FNAL), femur head diameter (FHD), femur neck width (FNW), shaft width (SW), neck shaft angle (NSA), and alpha angle (AA), are calculated by measuring the distances and angles between the landmarks. The dataset of hip radiographic images consisted of 428 images, with 208 men and 220 women. These images were split into training and testing sets for analysis. The deep learning network and ASM were subsequently trained on the training dataset. In the testing dataset, the automatic measurement of FNAL, FHD, FNW, SW, NSA, and AA parameters resulted in mean errors of 1.19%, 1.46%, 2.28%, 2.43%, 1.95%, and 4.53%, respectively.

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
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Data Availability

The data that support the findings of this study are available from the corresponding author upon reasonable request.

Abbreviations

AA:

Alpha angle

AP:

Antero-posterior

ASM:

Active shape model

BMI:

Body mass index

FCNNs:

Fully convolutional neural networks

FHD:

Femur head diameter

FNAL:

Femur neck axis length

FNW:

Femur neck width

GT:

Ground truth

KNN:

K-nearest neighbors

LMSE:

Least mean squares error

NSA:

Neck shaft angle

OA:

Osteoarthritis

PCA:

Principal component analysis

ROI:

Region of interest

SSM:

Statistical shape model

SVD:

Singular value decomposition

SVM:

Support vector machines

SW:

Shaft width

References

  1. Williams A, Kamper SJ, Wiggers JH, O’Brien KM, Lee H, Wolfenden L, et al. Musculoskeletal conditions may increase the risk of chronic disease: a systematic review and meta-analysis of cohort studies. BMC medicine. 2018;16:1-9.

    Article  Google Scholar 

  2. Gregory JS, Testi D, Stewart A, Undrill PE, Reid DM, Aspden RM. A method for assessment of the shape of the proximal femur and its relationship to osteoporotic hip fracture. Osteoporosis International. 2004;15:5-11.

    Article  CAS  PubMed  Google Scholar 

  3. Gnudi S, Sitta E, Pignotti E. Prediction of incident hip fracture by femoral neck bone mineral density and neck–shaft angle: a 5-year longitudinal study in post-menopausal females. The British journal of radiology. 2012;85(1016):e467-e73.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. Hawellek T, Meier M-P, Seitz M-T, Uhlig J, Hosseini ASA, Beil FT, et al. Morphological Parameters of the Hip Joint and Its Relation to Gender, Joint Side and Age—A CT-Based Study. Diagnostics. 2022;12(8):1774.

    Article  PubMed  PubMed Central  Google Scholar 

  5. Heppenstall SV, Ebsim R, Saunders FR, Lindner C, Gregory JS, Harvey NC, et al. Hip geometric parameters are associated with radiographic and clinical hip osteoarthritis: findings from a cross-sectional study in uk biobank. Osteoarthritis and Cartilage. 2023;31(5):700.

    Article  Google Scholar 

  6. Gregory JS, Aspden RM. Femoral geometry as a risk factor for osteoporotic hip fracture in men and women. Medical engineering & physics. 2008;30(10):1275-86.

    Article  Google Scholar 

  7. Soodmand E, Zheng G, Steens W, Bader R, Nolte L, Kluess D. Surgically relevant morphological parameters of proximal human femur: a statistical analysis based on 3D reconstruction of CT data. Orthopaedic surgery. 2019;11(1):135-42.

    Article  PubMed  PubMed Central  Google Scholar 

  8. Doherty M, Courtney P, Doherty S, Jenkins W, Maciewicz RA, Muir K, et al. Nonspherical femoral head shape (pistol grip deformity), neck shaft angle, and risk of hip osteoarthritis: a case–control study. Arthritis & Rheumatism: Official Journal of the American College of Rheumatology. 2008;58(10):3172-82.

    Article  Google Scholar 

  9. Boese CK, Dargel J, Oppermann J, Eysel P, Scheyerer MJ, Bredow J, et al. The femoral neck-shaft angle on plain radiographs: a systematic review. Skeletal Radiology. 2016;45:19-28.

    Article  PubMed  Google Scholar 

  10. Srisaarn T, Salang K, Klawson B, Vipulakorn K, Chalayon O, Eamsobhana P. Surgical correction of coxa vara: Evaluation of neck shaft angle, Hilgenreiner-epiphyseal angle for indication of recurrence. Journal of Clinical Orthopaedics and Trauma. 2019;10(3):593-8.

    Article  PubMed  Google Scholar 

  11. Laborie LB, Lehmann TG, Engesæter I, Sera F, Engesæter LB, Rosendahl K. The alpha angle in cam-type femoroacetabular impingement: new reference intervals based on 2038 healthy young adults. The bone & joint journal. 2014;96(4):449-54.

    Article  Google Scholar 

  12. Siebelt M, Agricola R, Weinans H, Kim YJ. The role of imaging in early hip OA. Osteoarthritis and cartilage. 2014;22(10):1470-80.

    Article  CAS  PubMed  Google Scholar 

  13. Lamo-Espinosa JM, Alfonso A, Pascual E, García-Ausín J, Sánchez-Gordoa M, Blanco A, et al. Hip Preservation Surgery in Osteoarthritis Prevention: Potential Benefits of the Radiographic Angular Correction. Diagnostics. 2022;12(5):1128.

    Article  PubMed  PubMed Central  Google Scholar 

  14. Thiagarajah S, MacInnes S, Yang L, Doherty M, Wilkinson JM. Quantifying the characteristics of the acetabulum and proximal femur using a semi-automated hip morphology software programme (SHIPS). Hip International. 2013;23(3):330-6.

    Article  PubMed  Google Scholar 

  15. Cootes TF, Taylor CJ, Cooper DH, Graham J. Active shape models-their training and application. Computer vision and image understanding. 1995;61(1):38-59.

    Article  Google Scholar 

  16. Smith R, Najarian K, Ward K. A hierarchical method based on active shape models and directed Hough transform for segmentation of noisy biomedical images; application in segmentation of pelvic X-ray images. BMC Medical Informatics and Decision Making. 2009;9:1-11.

    Article  Google Scholar 

  17. Cheng R, Roth HR, Lay N, Lu L, Turkbey B, Gandler W, et al. Automatic magnetic resonance prostate segmentation by deep learning with holistically nested networks. Journal of medical imaging. 2017;4(4):041302-.

  18. Cheng R, Roth HR, Lu L, Wang S, Turkbey B, Gandler W, et al., editors. Active appearance model and deep learning for more accurate prostate segmentation on MRI2016: SPIE.

  19. Zadeh A, Chong Lim Y, Baltrusaitis T, Morency L-P, editors. Convolutional experts constrained local model for 3d facial landmark detection2016 2017.

  20. Pilgram R, Walch C, Blauth M, Jaschke W, Schubert R, Kuhn V. Knowledge-based femur detection in conventional radiographs of the pelvis. Computers in biology and medicine. 2008;38(5):535-44.

    Article  PubMed  Google Scholar 

  21. Hussain D, Han S-M, Kim T-S. Automatic hip geometric feature extraction in DXA imaging using regional random forest. Journal of X-ray Science and Technology. 2019;27(2):207-36.

    Article  PubMed  Google Scholar 

  22. Lindner C, Thiagarajah S, Wilkinson JM, Wallis GA, Cootes TF, arc OC. Fully automatic segmentation of the proximal femur using random forest regression voting. IEEE transactions on medical imaging. 2013;32(8):1462–72.

  23. Wei Q, Han J, Jia Y, Zhu L, Zhang S, Lu Y, et al. An approach for fully automatic femoral neck-shaft angle evaluation on radiographs. Review of Scientific Instruments. 2020;91(1).

  24. Pries A, Schreier PJ, Lamm A, Pede S, Schmidt J. Deep morphing: Detecting bone structures in fluoroscopic x-ray images with prior knowledge. arXiv preprint arXiv:180804441. 2018.

  25. Lianghui F, Gang HJ, Yang J, Bin Y, editors. Femur segmentation in X-ray image based on improved U-Net2019: IOP Publishing; 2019.

  26. Ronneberger O, Fischer P, Brox T, editors. U-net: Convolutional networks for biomedical image segmentation2015 2015: Springer.

  27. Lim S-J, Park Y-S. Plain radiography of the hip: a review of radiographic techniques and image features. Hip & pelvis. 2015;27(3):125-34.

    Article  Google Scholar 

  28. Rafati M, Kalantari N, Azadbakht J, Nickfarjam AM, Hosseini F. Performance evaluation of fuzzy genetic, fuzzy particle swarm and similar insects’ optimization algorithms on denoising problem based on novel combined filter for digital X-ray and CT images in Pelvic Region. Multimedia Tools and Applications. 2023:1–49.

  29. Pauchard Y, Fitze T, Browarnik D, Eskandari A, Pauchard I, Enns-Bray W, et al. Interactive graph-cut segmentation for fast creation of finite element models from clinical ct data for hip fracture prediction. Computer methods in biomechanics and biomedical engineering. 2016;19(16):1693-703.

    Article  PubMed  PubMed Central  Google Scholar 

  30. Nai Y-H, Teo BW, Tan NL, O'Doherty S, Stephenson MC, Thian YL, et al. Comparison of metrics for the evaluation of medical segmentations using prostate MRI dataset. Computers in Biology and Medicine. 2021;134:104497.

    Article  PubMed  Google Scholar 

  31. Goodall C. Procrustes methods in the statistical analysis of shape. Journal of the Royal Statistical Society: Series B (Methodological). 1991;53(2):285-321.

    Article  Google Scholar 

  32. Bland JM, Altman D. Statistical methods for assessing agreement between two methods of clinical measurement. The lancet. 1986;327(8476):307-10.

    Article  Google Scholar 

  33. LERA—Lower extremity radiographs [Internet]. Available from: https://aimi.stanford.edu/lera-lower-extremity-radiographs. Accessed 11 November 2023.

  34. Lindner C, Thiagarajah S, Wilkinson JM, Wallis GA, Cootes TF, arc OC. Development of a fully automatic shape model matching (FASMM) system to derive statistical shape models from radiographs: application to the accurate capture and global representation of proximal femur shape. Osteoarthritis and cartilage. 2013;21(10):1537–44.

  35. Nihat A, ÜNal AM. Türk Toplumunda Proksimal Femurun Geometrik Özelliklerinin Radyolojik Değerlendirilmesi. SDÜ Tıp Fakültesi Dergisi. 2016;24(4):127–34.

  36. Center JR, Nguyen TV, Pocock NA, Noakes KA, Kelly PJ, Eisman JA, et al. Femoral neck axis length, height loss and risk of hip fracture in males and females. Osteoporosis international. 1998;8:75-81.

    Article  CAS  PubMed  Google Scholar 

  37. Farias THSd, Borges VQ, Souza ESd, Miki N, Abdala F. Radiographic study on the anatomical characteristics of the proximal femur in Brazilian adults. Revista Brasileira de Ortopedia. 2015;50:16–21.

  38. Fischer CS, Kühn J-P, Völzke H, Ittermann T, Gümbel D, Kasch R, et al. The neck–shaft angle: an update on reference values and associated factors. Acta orthopaedica. 2020;91(1):53-7.

    Article  PubMed  Google Scholar 

  39. Meeusen RA, Christensen AM, Hefner JT. The use of femoral neck axis length to estimate sex and ancestry. Journal of Forensic Sciences. 2015;60(5):1300-4.

    Article  PubMed  Google Scholar 

  40. Nötzli HP, Wyss TF, Stoecklin CH, Schmid MR, Treiber K, Hodler J. The contour of the femoral head-neck junction as a predictor for the risk of anterior impingement. The Journal of Bone & Joint Surgery British Volume. 2002;84(4):556-60.

    Article  Google Scholar 

  41. Pathak SK, Maheshwari P, Ughareja P, Gadi D, Prashanth RM, Gour SK. Evaluation of femoral neck shaft angle on plain radiographs and its clinical implications. Int J Res Orthop. 2016;2(4):383.

    Article  Google Scholar 

  42. Roy S, Kundu R, Medda S, Gupta A, Nanrah BK. Evaluation of proximal femoral geometry in plain anterior-posterior radiograph in eastern-Indian population. Journal of clinical and diagnostic research: JCDR. 2014;8(9):AC01.

  43. Shen W, Xu W, Zhang H, Sun Z, Ma J, Ma X, et al. Automatic segmentation of the femur and tibia bones from X-ray images based on pure dilated residual U-Net. Inverse Problems and Imaging. 2020;15(6):1333-46.

    Article  Google Scholar 

  44. Chen C, Zheng G, editors. Fully automatic segmentation of AP pelvis X-rays via random forest regression and hierarchical sparse shape composition2014 2013: Springer.

  45. Clohisy JC, Nunley RM, Otto RJ, Schoenecker PL. The frog-leg lateral radiograph accurately visualized hip cam impingement abnormalities. Clinical Orthopaedics and Related Research®. 2007;462:115–21.

  46. Konan S, Rayan F, Haddad FS. Is the frog lateral plain radiograph a reliable predictor of the alpha angle in femoroacetabular impingement? The Journal of Bone & Joint Surgery British Volume. 2010;92(1):47-50.

    Article  CAS  Google Scholar 

  47. Gregory JS, Waarsing JH, Day J, Pols HA, Reijman M, Weinans H, et al. Early identification of radiographic osteoarthritis of the hip using an active shape model to quantify changes in bone morphometric features: can hip shape tell us anything about the progression of osteoarthritis? Arthritis & Rheumatism: Official Journal of the American College of Rheumatology. 2007;56(11):3634-43.

    Article  Google Scholar 

  48. Lynch JA, Parimi N, Chaganti RK, Nevitt MC, Lane NE, Study of Osteoporotic Fractures Research G. The association of proximal femoral shape and incident radiographic hip OA in elderly women. Osteoarthritis and Cartilage. 2009;17(10):1313–8.

  49. Barr RJ, Gregory JS, Reid DM, Aspden RM, Yoshida K, Hosie G, et al. Predicting OA progression to total hip replacement: can we do better than risk factors alone using active shape modelling as an imaging biomarker? Rheumatology. 2012;51(3):562-70.

    Article  PubMed  Google Scholar 

  50. Nelson AE, Liu F, Lynch JA, Renner JB, Schwartz TA, Lane NE, et al. Association of incident symptomatic hip osteoarthritis with differences in hip shape by active shape modeling: the Johnston County Osteoarthritis Project. Arthritis care & research. 2014;66(1):74-81.

    Article  Google Scholar 

  51. Agricola R, Leyland KM, Bierma-Zeinstra SMA, Thomas GE, Emans PJ, Spector TD, et al. Validation of statistical shape modelling to predict hip osteoarthritis in females: data from two prospective cohort studies (Cohort Hip and Cohort Knee and Chingford). Rheumatology. 2015;54(11):2033-41.

    Article  PubMed  Google Scholar 

  52. Van Buuren MMA, Arden NK, Bierma-Zeinstra SMA, Bramer WM, Casartelli NC, Felson DT, et al. Statistical shape modeling of the hip and the association with hip osteoarthritis: a systematic review. Osteoarthritis and cartilage. 2021;29(5):607-18.

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

The authors would like to thank the Clinical Research Development Unit of Baqiyatallah Hospital, for all their support and guidance during carrying out this study.

Funding

None.

Author information

Authors and Affiliations

  1. Department of Radiology, Health Research Center, Life Style Institute, Baqiyatallah University of Medical Sciences, Tehran, Iran

    Hamid Alavi & Mehdi Seifi

  2. School of Health Management and Information Sciences, Iran University of Medical Sciences, Tehran, Iran

    Mahboubeh Rouhollahei

  3. Chemical Injuries Research Center, Systems Biology and Poisonings Institute, Baqiyatallah University of Medical Sciences, Tehran, Iran

    Mahboubeh Rouhollahei & Masoud Arabfard

  4. Department of Medical Physics and Radiology, Faculty of Paramedicine, Kashan University of Medical Sciences, Kashan, Iran

    Mehravar Rafati

Authors
  1. Hamid Alavi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mehdi Seifi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mahboubeh Rouhollahei
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mehravar Rafati
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Masoud Arabfard
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization: MA and MRa. Methodology: MA and HA. Investigation: MA, MS, MRa, and MRo. Visualization: HA. Project administration: MA and MRa. Supervision: MA. Writing—original draft: MA and HA. Writing—review and editing: MA and HA.

Corresponding authors

Correspondence to Mehravar Rafati or Masoud Arabfard.

Ethics declarations

Conflict of Interest

The authors declare no competing interests.

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.

Supplementary file1 (DOCX 18.8 KB)

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

Alavi, H., Seifi, M., Rouhollahei, M. et al. Development of Local Software for Automatic Measurement of Geometric Parameters in the Proximal Femur Using a Combination of a Deep Learning Approach and an Active Shape Model on X-ray Images. J Digit Imaging. Inform. med. 37, 633–652 (2024). https://doi.org/10.1007/s10278-023-00953-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10278-023-00953-3

Keywords

Search

Navigation