Skip to main content

Advertisement

SpringerLink
Log in

Dynamic ensemble selection of learner-descriptor classifiers to assess curve types in adolescent idiopathic scoliosis

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

While classification is important for assessing adolescent idiopathic scoliosis (AIS), it however suffers from low interobserver and intraobserver reliability. Classification using ensemble methods may contribute to improving reliability using the proper 2D and 3D images of spine curvature features. In this study, we present two new techniques to describe the spine, namely, leave-one-out and fan leave-one-out. Using these techniques, three descriptors are computed from a stereoradiographic 3D reconstruction to describe the relationship between a vertebra and its neighbors. A dynamic ensemble selection method is introduced for automatic spine classification. The performance of the method is evaluated on a dataset containing 962 3D spine models categorized according to three curve types. With a log loss of 0.5623, the dynamic ensemble selection outperforms voting and stacking ensemble learning techniques. This method can improve intraobserver and interobserver reliability, identify the best combination of descriptors for characterizing spine curve types, and provide assistance to clinicians in the form of information to classify borderline curvature types.

ᅟ

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

Similar content being viewed by others

References

  1. Breiman L (2001) Random forests. Mach Learn 45:5–32. https://doi.org/10.1023/A:1010933404324

    Article  Google Scholar 

  2. Britto AS, Sabourin R, Oliveira LES (2014) Dynamic selection of classifiers—a comprehensive review. Pattern Recogn 47:3665–3680. https://doi.org/10.1016/j.patcog.2014.05.003

    Article  Google Scholar 

  3. Delorme S, Petit Y, De Guise JA, Labelle H, Aubin C-E, Dansereau J (2003) Assessment of the 3-d reconstruction and high-resolution geometrical modeling of the human skeletal trunk from 2-D radiographic images. IEEE Trans Biomed Eng 50:989–998. https://doi.org/10.1109/TBME.2003.814525

    Article  CAS  PubMed  Google Scholar 

  4. Dietterich TG (2000) Ensemble methods in machine learning. In: Multiple classifier systems. MCS 2000. Lecture Notes in Computer Science, vol 1857. Springer, Berlin

    Google Scholar 

  5. Donzelli S, Poma S, Balzarini L, Borboni A, Respizzi S, Villafane JH, Zaina F, Negrini S (2015) State of the art of current 3-D scoliosis classifications: a systematic review from a clinical perspective. J Neuroeng Rehabil 12:1–11. https://doi.org/10.1186/s12984-015-0083-8

    Article  Google Scholar 

  6. Duong L, Cheriet F, Labelle H (2006) Three-dimensional classification of spinal deformities using fuzzy clustering. Spine (Phila Pa 1976) 31:923–930. https://doi.org/10.1097/01.brs.0000209312.62384.c1

    Article  Google Scholar 

  7. Duong L, Mac-Thiong J-M, Cheriet F, Labelle H (2009) Three-dimensional subclassification of Lenke type 1 scoliotic curves. J Spinal Disord Tech 22:135–143. https://doi.org/10.1097/BSD.0b013e31816845bc

    Article  PubMed  Google Scholar 

  8. Duong L, Cheriet F, Labelle H (2010) Automatic classification of spinal deformities using support vector machines. IEEE Trans Biomed Eng 57:1143–1151

    Article  Google Scholar 

  9. Fernández-Delgado M, Cernadas E, Barro S, Amorim D (2014) Do we need hundreds of classifiers to solve real world classification problems? J Mach Learn Res 15:3133–3181

    Google Scholar 

  10. Garcia-Cano E, Arambula-Cosio F, Duong L, Bellefleur C, Roy-Beaudry M, Joncas J, Parent S, Labelle H (2016) Dynamic ensemble selection of learner-descriptor classifiers to assess curve types in adolescent idiopathic scoliosis : a preliminary study. Communication lors de la conférence : 46e Réunion Annuelle de la Société de la Scoliose du Québec, Estérel, QC, Canada, 20–22 Oct. 2016

  11. Kadoury S, Labelle H (2012) Classification of three-dimensional thoracic deformities in adolescent idiopathic scoliosis from a multivariate analysis. Eur Spine J 21:40–49. https://doi.org/10.1007/s00586-011-2004-2

    Article  PubMed  Google Scholar 

  12. Kadoury S, Shen J, Parent S (2014) Global geometric torsion estimation in adolescent idiopathic scoliosis. Med Biol Eng Comput 52:309–319. https://doi.org/10.1007/s11517-013-1132-8

    Article  PubMed  Google Scholar 

  13. King HA, Moe JH, Bradford DS, Winter RB (1983) The selection of fusion levels in thoracic idiopathic scoliosis. J Bone Joint Surg Am 65:1302–1313

    Article  CAS  Google Scholar 

  14. Kittler J, Hatef M, Duin RPW, Matas J (1998) On combining classifiers. IEEE Trans Pattern Anal Mach Intell 20:226–239. https://doi.org/10.1109/34.667881

    Article  Google Scholar 

  15. Ko AHR, Sabourin R, Britto AS (2008) From dynamic classifier selection to dynamic ensemble selection. Pattern Recogn 41:1735–1748. https://doi.org/10.1016/j.patcog.2007.10.015

    Article  Google Scholar 

  16. Lenke LG, Betz RR, Harms J, Bridwell KH, Clements DH, Lowe TG, Blanke KM (2001) Adolescent idiopathic scoliosis. A new classification to determine extent of spinal arthrodesis. J Bone Joint Surg Am 83–A:1169–1181

    Article  Google Scholar 

  17. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:1825–2830

    Google Scholar 

  18. Phan P, Mezghani N, Wai EK, De Guise JA, Labelle H (2013) Artificial neural networks assessing adolescent idiopathic scoliosis: comparison with Lenke classification. Spine J 13:1527–1533. https://doi.org/10.1016/j.spinee.2013.07.449

    Article  PubMed  Google Scholar 

  19. Sangole AP, Aubin C-E, Labelle H, Stokes IAF, Lenke LG, Jackson R, Newton PO (2009) Three-dimensional classification of thoracic scoliotic curves. Spine (Phila Pa 1976) 34:91–99. https://doi.org/10.1097/BRS.0b013e3181877bbb

    Article  Google Scholar 

  20. Shen J, Parent S, Kadoury S (2014) Classification of spinal deformities using a parametric torsion estimator. In: Yao J, Klinder T, Li S (eds) Computational methods and clinical applications for spine imaging. Lecture Notes in Computational Vision and Biomechanics, vol 17. Springer, Cham

    Google Scholar 

  21. Stokes IAF (1994) Three-dimensional terminology of spinal deformity. A report presented to the Scoliosis Research Society by the Scoliosis Research Society Working Group on 3-D terminology of spinal deformity. Spine (Phila Pa 1976) 19:236–248

    Article  CAS  Google Scholar 

  22. Stokes IA, Bigalow LC, Moreland MS (1986) Measurement of axial rotation of vertebrae in scoliosis. Spine (Phila Pa 1976) 11:213–218. https://doi.org/10.1097/00007632-198604000-00006

    Article  CAS  Google Scholar 

  23. Thong WE, Labelle H, Shen J, Parent S, Kadoury S (2015) Stacked auto-encoders for classification of 3D spine models in adolescent idiopathic scoliosis. In: Yao J, Glocker B, Klinder T, Li S (eds) Recent advances in computational methods and clinical applications for spine imaging. Lecture Notes in Computational Vision and Biomechanics, vol 20. Springer, Cham

    Chapter  Google Scholar 

  24. Thong W, Parent S, Wu J, Aubin C-E, Labelle H, Kadoury S (2016) Three-dimensional morphology study of surgical adolescent idiopathic scoliosis patient from encoded geometric models. Eur Spine J 25:3104–3113. https://doi.org/10.1007/s00586-016-4426-3

    Article  PubMed  Google Scholar 

  25. Woźniak M, Graña M, Corchado E (2014) A survey of multiple classifier systems as hybrid systems. Information Fusion 16:3–17. https://doi.org/10.1016/j.inffus.2013.04.006

    Article  Google Scholar 

Download references

Acknowledgments

A preliminary short abstract of this work was presented in [10].

Funding

This research was funded by CONACYT CVU 323619 in Mexico, Fonds de recherche du Québec – Nature et technologies (FRQNT), file 194703, and the Ministère des Relations internationales et de la Francophonie.

Author information

Authors and Affiliations

  1. École de technologie supérieure, 1100 Notre-Dame Street West, Montreal, Quebec, H3C 1K3, Canada

    Edgar García-Cano & Luc Duong

  2. Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas, Universidad Nacional Autónoma de México, Circuito Escolar S/N. Ciudad Universitaria, C.P. 04510, Mexico, D.F., Mexico

    Fernando Arámbula Cosío

  3. Research Center, Sainte-Justine Hospital, 3175 Côte-Sainte-Catherine, Montreal, Quebec, Canada

    Christian Bellefleur, Marjolaine Roy-Beaudry, Julie Joncas, Stefan Parent & Hubert Labelle

Authors
  1. Edgar García-Cano
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fernando Arámbula Cosío
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Luc Duong
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Christian Bellefleur
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Marjolaine Roy-Beaudry
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Julie Joncas
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Stefan Parent
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Hubert Labelle
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Edgar García-Cano.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

García-Cano, E., Arámbula Cosío, F., Duong, L. et al. Dynamic ensemble selection of learner-descriptor classifiers to assess curve types in adolescent idiopathic scoliosis. Med Biol Eng Comput 56, 2221–2231 (2018). https://doi.org/10.1007/s11517-018-1853-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-018-1853-9

Keywords

Search

Navigation