Skip to main content

Advertisement

Springer Nature Link
Log in

Automatic classification of thyroid histopathology images using multi-classifier system

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

A computer aided diagnosis system supports doctors by providing quantitative diagnostic clues from medical data. In this paper, we propose a computer aided diagnosis (CAD) system to automatically discriminate hematoxylin and eosin (H&E)-stained thyroid histopathology images either as normal thyroid (NT) images or as papillary thyroid carcinoma (PTC) images. The CAD system incorporates a multi-classifier system to maximize the diagnostic accuracy of classification. Thyroid histopathology images are provided as input to the CAD system. The input images are enhanced and the nuclei present in the images are segmented automatically. Shape and texture features are extracted from the segmented images. Classification of the features is studied using classifiers such as support vector machine (SVM), naive Bayes (NB), K-nearest neighbor (K-nn) and closest matching rule (CMR) either as stand alone classifiers or as combinations to form multi-classifier systems. The multi-classifier system which provides the best accuracy is found out experimentally. The CAD system thus formed can be used as a second opinion to assist pathologists.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Similar content being viewed by others

References

  1. Al-Brahim N, Asa S (2006) Papillary thyroid carcinoma: an overview. Arch Pathol Lab Med 130(7):1057–1062

    Google Scholar 

  2. Belsare A, Mushrif M (2012) Histopathological image analysis using image processing techniques: an overview. Signal Image Process Int J 3(4):23–36

    Article  Google Scholar 

  3. Chen C, Wang W, Ozolek J, Rohde G (2013) A flexible and robust approach for segmenting cell nuclei from 2D microscopy images using supervised learning and template matching. J Int Soc Adv Cytom Cytom Part A 83(5):495–507

    Article  Google Scholar 

  4. Chu A, Sehgal C, Greenleaf J (1990) Use of gray value distribution of run lengths for texture analysis. Pattern Recogn Lett 11(6):415–420

    Article  MATH  Google Scholar 

  5. Dasarathy B, Holder E (1991) Image characterizations based on joint gray-level run-length distributions. Pattern Recogn Lett 12(8):497–502

    Article  Google Scholar 

  6. Daskalakis A, Kostopoulos S, Spyridonos P, Glotsos D, Ravazoula P, Kardari M, Kalatzis I, Cavouras D, Nikiforidis G (2008) Design of a multi-classifier system for discriminating benign from malignant thyroid nodules using routinely H&E-stained cytological images. Comput Biol Med 38(2):196–203

    Article  Google Scholar 

  7. Demir C, Yener B (2005) Automated cancer diagnosis based on histopathological images: a systematic survey. Technical report, Department of Computer Science, Rensselaer Polytechnic Institute, USA

  8. Galloway M (1975) Texture analysis using gray level run lengths. Comput Graph Image Process 4(2):172–179

    Article  Google Scholar 

  9. Gopinath B, Gupta B (2010) Majority voting based classification of thyroid carcinoma. Proced Comput Sci 2:265–271

    Article  Google Scholar 

  10. Gopinath B, Shanthi N (2013) Computer-aided diagnosis system for classifying benign and malignant thyroid nodules in multi-stained FNAB cytological images. Aust Phys Eng Sci Med 36(2):219–230

    Article  Google Scholar 

  11. Gopinath B, Shanthi N (2015) Development of an automated medical diagnosis system for classifying thyroid tumor cells using multiple classifier fusion. Technol Cancer Res Treat 14(5):653–662

    Article  Google Scholar 

  12. Gurcan M, Boucheron L, Can A, Madabhushi A, Rajpoot N, Yener B (2009) Histopathological image analysis: a review. IEEE Rev Biomed Eng 2:147–171

    Article  Google Scholar 

  13. Han J, Kamber M (2006) Data mining concepts and techniques. Elsevier

  14. Haralick R M, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern SMC-3(6):610–621

    Article  Google Scholar 

  15. Huang P, Lee C (2009) Automatic classification for pathological prostate images based on fractal analysis. IEEE Trans Med Imag 28(7):1037–1050

    Article  Google Scholar 

  16. Huang H, Tosun A, Guo J, Chen C, Wang W, Ozolek J, Rohde G (2014) Cancer diagnosis by nuclear morphometry using spatial information. Pattern Recogn Lett 42:115–121

    Article  Google Scholar 

  17. Jothi J, Rajam V (2014) Segmentation of nuclei from breast histopathology images using PSO-based Otsu’s multilevel thresholding. In: Suresh L, Dash S, Panigrahi B (eds) Artificial intelligence and evolutionary algorithms in engineering systems, advances in intelligent and soft computing, vol 325, pp 835–843

    Google Scholar 

  18. Jothi J, Rajam V (2016a) Effective segmentation and classification of thyroid histopathology images. Appl Soft Comput 46:652–664

    Article  Google Scholar 

  19. Jothi J, Rajam V (2016b) A survey on automated cancer diagnosis from histopathology images. Artif Intell Rev. doi:10.1007/s10462-016-9494-6

  20. Kennedy K, Eberhart R (1995) Particle swarm optimization. In: Proceedings of the IEEE international conference on neural networks, vol 4, pp 1942–1948

  21. Kulkarni R, Venayagamoorthy G (2010) Bio-inspired algorithms for autonomous deployment and localization of sensor nodes. IEEE Trans Syst Man Cybern Part C: Appl Rev 40(6):663–675

    Article  Google Scholar 

  22. LiVolsi V (2011) Papillary thyroid carcinoma: an update. Modern Pathol 24:S1–S9. doi:10.1038/modpathol.2010.129

    Article  Google Scholar 

  23. Lloyd R, Buehler D, Khanafshar E (2011) Papillary thyroid carcinoma variants. Head Neck Pathol 5(1):51–56

    Article  Google Scholar 

  24. National Cancer Institute (2016) National cancer institute - cancer topics. http://www.cancer.gov/cancertopics

  25. Norman J (2015a) Incidence and types of thyroid cancer. http://www.endocrineweb.com/guides/thyroid-cancer/incidence-types-thyroid-cancer

  26. Norman J (2015b) Thyroid cancer symptoms, diagnosis, and treatments. http://www.endocrineweb.com/conditions/thyroid-cancer/thyroid-cancer/

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

    Article  Google Scholar 

  28. Ozolek J, Tosun A, Wang W, Chen C, Kolouri S, Basu S, Huang H, Rohde G (2014) Accurate diagnosis of thyroid follicular lesions from nuclear morphology using supervised learning. Med Image Anal 18(5):772–780

    Article  Google Scholar 

  29. Pawlak Z, Grzymala-Busse J, Slowinski R, Ziarko W (1995) Rough sets. Commun ACM 38(11):88–95

    Article  Google Scholar 

  30. Pedram G, Micael S, Atli B, Nuno M (2012) An efficient method for segmentation of images based on fractional calculus and natural selection. Expert Syst Appl 39(16):12,407–12,417

    Article  Google Scholar 

  31. Polikar R (2006) Ensemble based systems in decision making. IEEE Circ Syst Mag 6(3):21–45

    Article  Google Scholar 

  32. Rokach L (2010) Ensemble-based classifiers. Artif Intell Rev 33(1):1–39

    Article  MathSciNet  Google Scholar 

  33. Scopa C (2004) Histopathology of thyroid tumors. An overview. Hormones 3 (2):100–110

    Article  Google Scholar 

  34. Sridhar S (2011) Digital image processing. Oxford University Press

  35. Wang W, Ozolek J, Rohde G (2010) Detection and classification of thyroid follicular lesions based on nuclear structure from histopathology images. J Int Soc Adv Cytom Cytom Part A 77A(5):485–494

    Google Scholar 

  36. Xu L, Krzyzak A, Suen C (1992) Methods of combining multiple classifiers and their applications to handwriting recognition. IEEE Trans Syst Man Cybern 22 (3):418–435

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. College of Engineering Guindy, Anna University, Chennai, Tamil Nadu, India

    Angel Arul Jothi J & Mary Anita Rajam V

Authors
  1. Angel Arul Jothi J
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Mary Anita Rajam V
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Mary Anita Rajam V.

Electronic supplementary material

Below is the link to the electronic supplementary material.

(PDF 53.1 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

J, A.A.J., V, M.A.R. Automatic classification of thyroid histopathology images using multi-classifier system. Multimed Tools Appl 76, 18711–18730 (2017). https://doi.org/10.1007/s11042-017-4363-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-017-4363-0

Keywords