Skip to main content

Advertisement

SpringerLink
Log in

An interval prototype classifier based on a parameterized distance applied to breast thermographic images

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

Abstract

Breast cancer is one of the leading causes of death in women. Because of this, thermographic images have received a refocus for diagnosing this cancer type. This work proposes an innovative approach to classify breast abnormalities (malignant, benignant and cyst), employing interval temperature data in order to detect breast cancer. The learning step takes into account the internal variation of the intervals when describing breast abnormalities and uses a way to map these intervals into a space where they can be more easily separated. The method builds class prototypes, and the allocation step is based on a parameterized Mahalanobis distance for interval-valued data. The proposed classifier is applied to a breast thermography dataset from Brazil with 50 patients. We investigate two different scenarios for parameter configuration. The first scenario focuses on the overall misclassification rate and achieves 16 % misclassification rate and 93 % sensitivity to the malignant class. The second scenario maximizes the sensitivity to the malignant class, achieving 100 % sensitivity to this specific class, along with 20 % overall misclassification rate. We compare the performances of our approach and of many methods taken from the literature of interval data classification for the breast thermography task. Results show that our method outperforms competing algorithms.

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

Similar content being viewed by others

References

  1. Acharya UR, Ng EYK, Tan J-H, Sree SV (2012) Thermography based breast cancer detection using texture features and support vector machine. J Med Syst 36:1503–1510

    Article  PubMed  Google Scholar 

  2. Appice A, D’Amato C, Esposito F, Malerba D (2006) Classification of symbolic objects: a lazy learning approach. Intell Data Anal 10(4):301–324

    Google Scholar 

  3. Araújo MC, Lima RCF, Souza RMCR (2014) Interval symbolic feature extraction for thermography breast cancer detection. Exp Syst Appl 41:6728–6737

    Article  Google Scholar 

  4. Wahab AA, Salim MIM, Ahamat MA, Manaf NA, Yunus J, Lai KW (2015) Thermal distribution analysis of three-dimensional tumor-embedded breast models with different breast density compositions. Med Biol Eng Comput 1–11

  5. Bezerra LA, Oliveira MM, Araújo MC, Viana MJA, Santos LC, Santos FGS, Rolim TL, Lyra PRM, Lima RCF, Borschartt TB, Resmini R, Conci A (2013). Multimodality breast imaging: diagnosis and treatment. Vol. 1. SPIE PRESS, Ch. infrared imaging for breast cancer detection with proper selection of properties: from acquisition protocol to numerical simulation

  6. Borschartt TB, Conci A, Lima RCF, Resmini R, Sanchez A (2013) Breast thermography from an image processing viewpoint: a survey. Signal Process 93(10):2785–2803

    Article  Google Scholar 

  7. Ciampi A, Diday E, Lebbe J, Prinel E, Vignes R (2000) Growing a tree classifier with imprecise data. Pattern Recognit Lett 21(9):787–803

    Article  Google Scholar 

  8. Diday E, Noirhomme-Fraiture M (2008) Symbolic data analysis and the SODAS software. Wiley, England

    Google Scholar 

  9. D’Oliveira ST, de Carvalho FA, Souza RM (2004) Classification of SAR images through a convex hull region oriented approach. In: Pal N, Kasabov N, Mudi R, Pal S, Parui S (eds) Neural information processing. Lecture Notes in Computer ScienceSpringer, Berlin, pp 769–774

    Chapter  Google Scholar 

  10. Francis SV, Sasikala M (2013) Automatic detection of abnormal breast thermograms using asymmetry analysis of texture features. J Med Eng Technol 37(1):17–21

    Article  PubMed  Google Scholar 

  11. Ichino M, Yaguchi H, Diday E (1996) A fuzzy symbolic pattern classifier. In: Ordinal and symbolic data analysis, pp 92–102

  12. Kapoor P, Prasad SVAV (2010) Image processing for early diagnosis of breast cancer using infrared images. In: Proceedings of the 2010 IEEE computer and automation engineering 2nd international conference 3, 564–566

  13. Krawczyk B, Schaefer G, Wozniak M (2012) Breast thermogram analysis using a cost-sensitive multiple classifier system. In: Proceedings of the IEEE-EMBS international conference on biomedical and health informatics (BHI 2012). pp 507–510

  14. Kuruganti PT, Qi H (2002) Asymmetry analysis in breast cancer detection using thermal infrared images. In: Proceedings of the second joint EMBS/BMES Conference. Houston, TX, USA

  15. Mali K, Mitra S (2005) Symbolic classification, clustering and fuzzy radial basis function network. Fuzzy Sets Syst 152(3):553–564

    Article  Google Scholar 

  16. Mookiah MRK, Acharya UR, Ng E (2012) Data mining technique for breast cancer detection in thermograms using hybrid feature extraction strategy. Quantit InfraRed Thermogr J 9(2):151–165

    Article  Google Scholar 

  17. Mustra M, Grgic M, Rangayyan RM, (2015) Review of recent advances in segmentation of the breast boundary and the pectoral muscle in mammograms. Med Biol Eng Comput 1–22

  18. Nandi RJ, Nandi AK, Rangayyan RM, Scutt D (2006) Classification of breast masses in mammograms using genetic programming and feature selection. Med Biol Eng Comput 44(8):683–694

    Article  CAS  PubMed  Google Scholar 

  19. Ng EY-K (2009) A review of thermography as promising non-invasive detection modality for breast tumor. Int J Therm Sci 48:849–859

    Article  CAS  Google Scholar 

  20. Plewes DB, Sabol JM, Soutar I, Chevrier A, Shumak R (1995) Role of equalisation mammography of dense breasts. Med Biol Eng Comput 33(2):167–173

    Article  CAS  PubMed  Google Scholar 

  21. Roque AMS, Mate C, Arroyo J, Sarabia A (2007) imlp: applying multi-layer perceptrons to interval-valued data. Neural Process Lett 25:157–169

    Article  Google Scholar 

  22. Rossi F, Conan-guez B (2002) Multi-layer perceptron on interval data. In: Classification, clustering and data analysis (IFCS 2002), 427–434

  23. Schaefer G, Zviek M, Nakashima T (2009) Thermography based breast cancer analysis using statistical features and fuzzy classification. Pattern Recognit 47:1133–1137

    Article  Google Scholar 

  24. Silva APD, Brito P (2006) Linear discriminant analysis for interval data. Comput Stat 21:289–308

    Article  Google Scholar 

  25. Silva Filho TM, Souza RMCR (July 2013) Fuzzy learning vector quantization approaches for interval data. In: IEEE international conference on fuzzy systems (FUZZ)

  26. Souza RMCR, de Carvalho FAT, Frery AC (1999) Symbolic approach to sar image classification. In: IEEE international geoscience and remote sensing symposium

  27. Souza RMCR, Queiroz DCF, Cysneiros FJA (2011) Logistic regression-based pattern classifiers for symbolic interval data. Pattern Anal Appl 14:273–282

    Article  Google Scholar 

  28. de Souza RMCR, de Carvalho FAT, Tenorio CP (2004) Dynamic cluster methods for interval data based on Mahalanobis distances. In: Proceedings of the meeting of the international federation of classification societies (IFCS). Classification, clustering, and data mining applications. [S.l.], pp 351–360

  29. Tan T, Quek C, Ng G, Ng E (2007) A novel cognitive interpretation of breast cancer thermography with complementary learning fuzzy neural memory structure. Expert Syst Appl 33:652–666

    Article  Google Scholar 

  30. Tang X, Ding H, Yuan Y-E, Wang Q (2008) Morphological measurements of localized temperature increase amplitudes in breast infrared thermograms and its clinical application. Biomed Signal Process Control 3:312–318

    Article  Google Scholar 

  31. Webb AR (2002) Statistical pattern recognition, 2nd edn. Wiley, UK

    Book  Google Scholar 

Download references

Acknowledgments

The authors would like to thank Brazilian agencies CNPq (National Council for Scientific and Technological Development) and CAPES (Coordination for the Improvement of Higher Education Personnel) for financial support.

Author information

Authors and Affiliations

  1. Departamento de Engenharia Mecânica, Universidade Federal de Pernambuco, Av. Prof. Moraes Rego, 1235, Cidade Universitária, Recife, PE, 50670901, Brazil

    Marcus C. Araújo & Rita C. F. Lima

  2. Centro de Informática, Universidade Federal de Pernambuco, Av. Jornalista Aníbal Fernandes, Cidade Universitária, Recife, PE, 50740560, Brazil

    Renata M. C. R. Souza & Telmo M. Silva Filho

Authors
  1. Marcus C. Araújo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Renata M. C. R. Souza
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Rita C. F. Lima
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Telmo M. Silva Filho
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Renata M. C. R. Souza.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Araújo, M.C., Souza, R.M.C.R., Lima, R.C.F. et al. An interval prototype classifier based on a parameterized distance applied to breast thermographic images. Med Biol Eng Comput 55, 873–884 (2017). https://doi.org/10.1007/s11517-016-1565-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-016-1565-y

Keywords

Search

Navigation