Skip to main content

Advertisement

Log in

Cooperative strategy for a dynamic ensemble of classification models in clinical applications: the case of MRI vertebral compression fractures

  • Original Article
  • Published:
International Journal of Computer Assisted Radiology and Surgery Aims and scope Submit manuscript

Abstract

Purpose

In clinical practice, the constructive consultation among experts improves the reliability of the diagnosis and leads to the definition of the treatment plan for the patient. Aggregation of the different opinions collected by many experts can be performed at the level of patient information, abnormality delineation, or final assessment.

Methods

In this study, we present a novel cooperative strategy that exploits the dynamic contribution of the classification models composing the ensemble to make the final class assignment. As a proof of concept, we applied the proposed approach to the assessment of malignant infiltration in 103 vertebral compression fractures in magnetic resonance images.

Results

The results obtained with repeated random subsampling and receiver operating characteristic analysis indicate that the cooperative system statistically improved (\(p<0.01\)) the classification accuracy of individual modules as well as of that based on the manual segmentation of the fractures provided by the experts.

Conclusions

The performances have been also compared with those obtained with those of standard ensemble classification algorithms showing superior results.

This is a preview of subscription content, log in via an institution to check access.

Access this article

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

Similar content being viewed by others

References

  1. Rokach L (2010) Pattern classification using ensemble methods, vol 75. World Scientific, Singapore

    Google Scholar 

  2. Dastgheib ZA, Pouya OR, Lithgow B, Moussavi Z (2016) Comparison of a new ad-hoc classification method with support vector machine and ensemble classifiers for the diagnosis of Meniere’s disease using EVestG signals. In: 2016 IEEE Canadian conference on electrical and computer engineering (CCECE). IEEE, pp 1–4

  3. Da Silva LA, Hernandez EDM, Rangayyan RM (2008) ’Classification of breast masses using a committee machine of artificial neural networks. J Electron Imaging 17(1):013017

    Article  Google Scholar 

  4. Kuncheva LI (2012) Switching between selection and fusion in combining classifiers: an experiment. IEEE Trans Syst Man Cybern B 32(2):146–156

    Article  Google Scholar 

  5. Antunes S, Esposito A, Palmisano A, Colantoni C, Cerutti S, Rizzo G (2016) Cardiac multi-detector CT segmentation based on multiscale directional edge detector and 3D level set. Ann Biomed Eng 44(5):1487–1501

    Article  PubMed  Google Scholar 

  6. Zhao Y, Rada L, Chen K, Harding SP, Zheng Y (2015) Automated vessel segmentation using infinite perimeter active contour model with hybrid region information with application to retinal images. IEEE Trans Med Imaging 34(9):1797–1807

    Article  PubMed  Google Scholar 

  7. Siefert AW, Icenogle DA, Rabbah JPM, Saikrishnan N, Rossignac J, Lerakis S, Yoganathan AP (2013) Accuracy of a mitral valve segmentation method using J-splines for real-time 3D echocardiography data. Ann Biomed Eng 41(6):1258–1268

    Article  PubMed  PubMed Central  Google Scholar 

  8. Guliato D, Rangayyan RM, Carnielli WA, Desautels JL (2003) Fuzzy fusion operators to combine results of complementary medical image segmentation techniques. J Electron Imaging 12(3):379–389

    Article  Google Scholar 

  9. He R, Sajja BR, Datta S, Narayana PA (2008) Volume and shape in feature space on adaptive FCM in MRI segmentation. Ann Biomed Eng 36(9):1580–1593

    Article  PubMed  PubMed Central  Google Scholar 

  10. Melkemi KE, Batouche M, Foufou S (2006) A multiagent system approach for image segmentation using genetic algorithms and extremal optimization heuristics. Pattern Recognit Lett 27(11):1230–1238

    Article  Google Scholar 

  11. Benamrane N, Nassane S (2007) Medical image segmentation by a multi-agent system approach. In: Multiagent system technologies. Springer, Berlin, pp 49–60

  12. Bovenkamp EG, Dijkstra J, Bosch JG, Reiber JH (2009) User-agent cooperation in multiagent IVUS image segmentation. IEEE Trans Med Imaging 28(1):94–105

    Article  CAS  PubMed  Google Scholar 

  13. Chen X, Udupa JK, Bagci U, Zhuge Y, Yao J (2012) Medical image segmentation by combining graph cuts and oriented active appearance models. IEEE Trans Image Process 21(4):2035–2046

    Article  PubMed  PubMed Central  Google Scholar 

  14. Lê M, Unkelbach J, Ayache N, Delingette H (2016) Sampling image segmentations for uncertainty quantification. Med Image Anal 34:42–51

    Article  PubMed  Google Scholar 

  15. Warfield SK, Zou KH, Wells WM (2004) Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. IEEE Trans Med Imaging 23(7):903–921

    Article  PubMed  PubMed Central  Google Scholar 

  16. Kohlberger T, Singh V, Alvino C, Bahlmann C, Grady L (2012) Evaluating segmentation error without ground truth. In: International conference on medical image computing and computer-assisted intervention. Springer, Berlin, pp 528–536

  17. Casti P, Mencattini A, Salmeri M, Ancona A, Mangeri F, Pepe ML, Rangayyan RM (2016) Contour-independent detection and classification of mammographic lesions. Biomed Signal Process Control 25:165–177

    Article  Google Scholar 

  18. Martinelli E, Magna G, Vergara A, Di Natale C (2014) Cooperative classifiers for reconfigurable sensor arrays. Sens Actuator B Chem 199:83–92

    Article  CAS  Google Scholar 

  19. Magna G, Casti P, Jayaraman SV, Salmeri M, Mencattini A, Martinelli E, Di Natale C (2016) Identification of mammography anomalies for breast cancer detection by an ensemble of classification models based on artificial immune system. Knowl Based Syst 101:60–70

    Article  Google Scholar 

  20. Brejl M, Sonka M (2000) Object localization and border detection criteria design in edge-based image segmentation: automated learning from examples. IEEE Trans Med Imaging 19(10):973–985

    Article  CAS  PubMed  Google Scholar 

  21. Peng Z, Zhong J, Wee W, Lee JH (2006) Automated vertebra detection and segmentation from the whole spine MR images. In: Proceedings of IEEE EMBS, pp 2527–2530

  22. Huang SH, Chu YH, Lai SH, Novak CL (2009) Learning-based vertebra detection and iterative normalized-cut segmentation for spinal MRI. IEEE Trans Med Imaging 28(10):1595–1605

    Article  PubMed  Google Scholar 

  23. Kelm BM, Wels M, Zhou SK, Seifert S, Suehling M, Zheng Y, Comaniciu D (2013) Spine detection in CT and MR using iterated marginal space learning. Med Image Anal 17(8):1283–1292

    Article  Google Scholar 

  24. Barbieri PD, Pedrosa GV, Traina AJM, Nogueira-Barbosa MH (2015) Vertebral body segmentation of spine MR images using superpixels. In: Proceedings of IEEE CBMS

  25. Frighetto-Pereira L, Rangayyan RM, Metzner GA, de Azevedo-Marques PM, Nogueira-Barbosa MH (2016) Shape, texture, and statistical features for classification of benign and malignant vertebral compression fractures in magnetic resonance images. Comput Biol Med 73(1):147–156

    Article  PubMed  Google Scholar 

  26. Pizer S, Amburn E, Austin J, Cromartie AR, Geselowitz A, Greer T, Romeny BTH, Zimmerman JB, Zuiderveld K (1987) Adaptative histogram equalization and its varations. Comput Vis Graph Image Process 39:355–368

    Article  Google Scholar 

  27. Zhao Y, Liu Y, Wu X, Harding SP, Zheng Y (2015) Correction: retinal vessel segmentation: an efficient graph cut approach with retinex and local phase. PLoS ONE 10(4):e0127486

    Article  PubMed  PubMed Central  Google Scholar 

  28. Rosenfeld A, Kak A (1982) Digital picture processing, vol 2, 2nd edn. Academic Press, New York

    Google Scholar 

  29. Chan TF, Vese LA (2001) Active contours without edges. IEEE Trans Image Proc 10(2):266–277

    Article  CAS  Google Scholar 

  30. Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62–66

    Article  Google Scholar 

  31. Bezdek JC (1981) Pattern recognition with fuzzy objective function algorithms. Plenum Press, New York

    Book  Google Scholar 

  32. Adams R, Bischof L (1994) Seeded region growing. IEEE Trans Pattern Anal Mach Intell 16(6):641–647

    Article  Google Scholar 

  33. Rangayyan RM (2005) Biomedical image analysis. CRC Press, Boca Raton

    Google Scholar 

  34. Davies ER (2004) Machine vision: theory, algorithms, practicalities. Elsevier, Amsterdam

    Google Scholar 

  35. Weinstein RS, Majumdar S (1994) Fractal geometry and vertebral compression fractures. J Bone Miner Res 9(1):1797–1802

    CAS  PubMed  Google Scholar 

  36. Draper NR, Smith H (1998) Regression analysis. Wiley-Interscience, Hoboken

    Google Scholar 

  37. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444

    Article  CAS  PubMed  Google Scholar 

Download references

Acknowledgements

This work was supported, in part, by grants from the São Paulo Research Foundation (FAPESP), from the Financing of Studies and Projects (FINEP), and from the National Council of Technological and Scientific Development (CNPq). The authors thank Prof. R.M. Rangayyan, University of Calgary, for his encouragement and fruitful discussions.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Arianna Mencattini.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

This work was supported, in part, by grants from the São Paulo Research Foundation, FAPESP (2014/12135-0), from the Financing of Studies and Projects, FINEP(01/2006, 0184/07), and from the National Council of Technological and Scientific Development, CNPq (306576/2014-7).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Casti, P., Mencattini, A., Nogueira-Barbosa, M.H. et al. Cooperative strategy for a dynamic ensemble of classification models in clinical applications: the case of MRI vertebral compression fractures. Int J CARS 12, 1971–1983 (2017). https://doi.org/10.1007/s11548-017-1625-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-017-1625-2

Keywords

Navigation