Skip to main content

Advertisement

SpringerLink
Log in

A convolutional neural network to detect scoliosis treatment in radiographs

  • Short communication
  • Published:
International Journal of Computer Assisted Radiology and Surgery Aims and scope Submit manuscript

Abstract

Purpose

The aim of this work is to propose a classification algorithm to automatically detect treatment for scoliosis (brace, implant or no treatment) in postero-anterior radiographs. Such automatic labelling of radiographs could represent a step towards global automatic radiological analysis.

Methods

Seven hundred and ninety-six frontal radiographies of adolescents were collected (84 patients wearing a brace, 325 with a spinal implant and 387 reference images with no treatment). The dataset was augmented to a total of 2096 images. A classification model was built, composed by a forward convolutional neural network (CNN) followed by a discriminant analysis; the output was a probability for a given image to contain a brace, a spinal implant or none. The model was validated with a stratified tenfold cross-validation procedure. Performance was estimated by calculating the average accuracy.

Results

98.3% of the radiographs were correctly classified as either reference, brace or implant, excluding 2.0% unclassified images. 99.7% of brace radiographs were correctly detected, while most of the errors occurred in the reference group (i.e. 2.1% of reference images were wrongly classified).

Conclusion

The proposed classification model, the originality of which is the coupling of a CNN with discriminant analysis, can be used to automatically label radiographs for the presence of scoliosis treatment. This information is usually missing from DICOM metadata, so such method could facilitate the use of large databases. Furthermore, the same model architecture could potentially be applied for other radiograph classifications, such as sex and presence of scoliotic deformity.

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

References

  1. Cheng JC, Castelein RM, Chu WC, Danielsson AJ, Dobbs MB, Grivas TB, Gurnett CA, Luk KD, Moreau A, Newton PO, Stokes IA, Weinstein SL, Burwell RG (2015) Adolescent idiopathic scoliosis. Nat Rev Dis Primers 1:15030. https://doi.org/10.1038/nrdp.2015.30

    Article  PubMed  Google Scholar 

  2. Negrini S, Donzelli S, Aulisa AG, Czaprowski D, Schreiber S, de Mauroy JC, Diers H, Grivas TB, Knott P, Kotwicki T, Lebel A, Marti C, Maruyama T, O’Brien J, Price N, Parent E, Rigo M, Romano M, Stikeleather L, Wynne J, Zaina F (2018) 2016 SOSORT guidelines: orthopaedic and rehabilitation treatment of idiopathic scoliosis during growth. Scoliosis Spinal Disord 13:3. https://doi.org/10.1186/s13013-017-0145-8

    Article  PubMed  PubMed Central  Google Scholar 

  3. Weinstein SL, Dolan LA, Wright JG, Dobbs MB (2013) Effects of bracing in adolescents with idiopathic scoliosis. N Engl J Med 369:1512–1521. https://doi.org/10.1056/NEJMoa1307337

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. Bunnell WP (1986) The natural history of idiopathic scoliosis before skeletal maturity. Spine (Phila Pa 1976) 11:773–776

    Article  CAS  Google Scholar 

  5. Galbusera F, Casaroli G, Bassani T (2019) Artificial intelligence and machine learning in spine research. Jor Spine 2:e1044. https://doi.org/10.1002/jsp2.1044

    Article  PubMed  PubMed Central  Google Scholar 

  6. Bakhous C, Aubert B, Vazquez C, Cresson T, Parent S, Guise J De (2018) Automatic pedicles detection using convolutional neural network in a 3D spine reconstruction from biplanar radiographs. In: Proc SPIE

  7. Ebrahimi S, Gajny L, Skalli W, Angelini E (2019) Vertebral corners detection on sagittal X-rays based on shape modelling, random forest classifiers and dedicated visual features. Comput Methods Biomech Biomed Eng Imaging Vis 7:132–144. https://doi.org/10.1080/21681163.2018.1463174

    Article  Google Scholar 

  8. Aubert B, Vazquez C, Cresson T, Parent S, de Guise JA (2019) Toward automated 3D spine reconstruction from biplanar radiographs using CNN for statistical spine model fitting. IEEE Trans Med Imaging 38:2796–2806. https://doi.org/10.1109/TMI.2019.2914400

    Article  CAS  PubMed  Google Scholar 

  9. Yang Z, Skalli W, Vergari C, Angelini ED, Gajny L (2019) Automated spinal midline delineation on biplanar x-rays using mask R-CNN - VipIMAGE. In: Natal Jorge RM (ed) Tavares JMRS. Springer International Publishing, Cham, pp 307–316

    Google Scholar 

  10. Zhang J, Li H, Lv L, Zhang Y (2017) Computer-aided Cobb measurement based on automatic detection of vertebral slopes using deep neural network. Int J Biomed Imaging 2017:9083916. https://doi.org/10.1155/2017/9083916

    Article  PubMed  PubMed Central  Google Scholar 

  11. Cho BH, Kaji D, Cheung ZB, Ye IB, Tang R, Ahn A, Carrillo O, Schwartz JT, Valliani AA, Oermann EK, Arvind V, Ranti D, Sun L, Kim JS, Cho SK (2019) Automated measurement of lumbar lordosis on radiographs using machine learning and computer vision. Glob Spine J. https://doi.org/10.1177/2192568219868190

    Article  Google Scholar 

  12. Weng C-H, Wang C-L, Huang Y-J, Yeh Y-C, Fu C-J, Yeh C-Y, Tsai T-T (2019) Artificial intelligence for automatic measurement of sagittal vertical axis using ResUNet framework. J Clin Med 8(11):1826

    Article  Google Scholar 

  13. Klinder T, Ostermann J, Ehm M, Franz A, Kneser R, Lorenz C (2009) Automated model-based vertebra detection, identification, and segmentation in CT images. Med Image Anal 13:471–482. https://doi.org/10.1016/j.media.2009.02.004

    Article  PubMed  Google Scholar 

  14. Zheng G, Chu C, Belavý DL, Ibragimov B, Korez R, Vrtovec T, Hutt H, Everson R, Meakin J, Andrade IL, Glocker B, Chen H, Dou Q, Heng P-A, Wang C, Forsberg D, Neubert A, Fripp J, Urschler M, Stern D, Wimmer M, Novikov A, Cheng H, Armbrecht G, Felsenberg D, Li S (2017) Evaluation and comparison of 3D intervertebral disc localization and segmentation methods for 3D T2 MR data: a grand challenge. Med Image Anal 35:327–344. https://doi.org/10.1016/j.media.2016.08.005

    Article  PubMed  Google Scholar 

  15. Jamaludin A, Lootus M, Kadir T, Zisserman A, Urban J, Battié MC, Fairbank J, McCall I (2017) ISSLS PRIZE IN BIOENGINEERING SCIENCE 2017: automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist. Eur Spine J 26:1374–1383. https://doi.org/10.1007/s00586-017-4956-3

    Article  PubMed  Google Scholar 

  16. Faro FD, Marks MC, Pawelek J, Newton PO (2004) Evaluation of a functional position for lateral radiograph acquisition in adolescent idiopathic scoliosis. Spine (Phila Pa 1976) 29:2284–2289

    Article  Google Scholar 

  17. Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86:2278–2324. https://doi.org/10.1109/5.726791

    Article  Google Scholar 

  18. Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958

    Google Scholar 

  19. Vedaldi A, Lenc K (2015) MatConvNet—convolutional neural networks for MATLAB. In: Proceeding of the ACM Int Conf on Multimedia

  20. Pedersen PH, Vergari C, Alzakri A, Vialle R, Skalli W (2019) A reduced micro-dose protocol for 3D reconstruction of the spine in children with scoliosis: results of a phantom-based and clinically validated study using stereo-radiography. Eur Radiol 29:1874–1881. https://doi.org/10.1007/s00330-018-5749-8

    Article  PubMed  Google Scholar 

  21. Dubousset J, Ilharreborde B, Le Huec J-C (2014) Use of EOS imaging for the assessment of scoliosis deformities: application to postoperative 3D quantitative analysis of the trunk. Eur Spine J 23:397–405. https://doi.org/10.1007/s00586-014-3334-7

    Article  Google Scholar 

  22. Vergari C, Aubert B, Lallemant-Dudek P, Haen TX, Skalli W (2019) A novel method of anatomical landmark selection for rib cage 3D reconstruction from biplanar radiography. Comput Methods Biomech Biomed Eng Imaging Vis. https://doi.org/10.1080/21681163.2018.1537860

    Article  Google Scholar 

  23. Hirsch C, Ilharreborde B, Mazda K (2016) Flexibility analysis in adolescent idiopathic scoliosis on side-bending images using the EOS imaging system. Orthop Traumatol Surg Res 102:495–500. https://doi.org/10.1016/j.otsr.2016.01.021

    Article  CAS  PubMed  Google Scholar 

Download references

Acknowledgements

The authors are grateful to the ParisTech BiomecAM chair program on subject-specific musculoskeletal modelling (with the support of ParisTech and Yves Cotrel Foundations, Société Générale, Proteor and Covea).

Author information

Authors and Affiliations

  1. Arts et Métiers, Institut de Biomécanique Humaine Georges Charpak, 151 bd de l’Hôpital, 75013, Paris, France

    Claudio Vergari, Wafa Skalli & Laurent Gajny

Authors
  1. Claudio Vergari
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wafa Skalli
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Laurent Gajny
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Laurent Gajny.

Ethics declarations

Conflict of interest

Wafa Skalli holds patents related to the EOS system and associated 3D reconstruction methods, with no personal financial benefit (royalties rewarded for research and education). The other authors declare that they have no conflict of interest.

Ethical standards

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.

Informed consent

For this type of study, formal consent is not required.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Vergari, C., Skalli, W. & Gajny, L. A convolutional neural network to detect scoliosis treatment in radiographs. Int J CARS 15, 1069–1074 (2020). https://doi.org/10.1007/s11548-020-02173-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-020-02173-4

Keywords

Search

Navigation