Sādhanā

, 43:39 | Cite as

An approach for classification of malignant and benign microcalcification clusters

Article
  • 50 Downloads

Abstract

The only reliable and successful treatment of breast cancer is its detection through mammography at initial stage. Clusters of microcalcifications are important signs of breast cancer. Manual interpretation of mammographic images, in which the suspicious regions are indicated as areas of varying intensities, is not error free due to a number of reasons. These errors can be reduced by using computer-aided diagnosis systems that result in reduction of either false positives or true negatives. The purpose of the study in this paper is to develop a methodology for distinguishing malignant microcalcification clusters from benign microcalcification clusters. The proposed approach first enhances the region of interest by using morphological operations. Then, two types of features, cluster shape features and cluster texture features, are extracted. A Support Vector Machine is used for classification. A new set of shape features based on the recursive subsampling method is added to the feature set, which improves the classification accuracy of the system. It has been found that these features are capable of differentiating malignant and benign tissue regions. To investigate the performance of the proposed approach, mammogram images are taken from Digital Database for Screening Mammography database and an accuracy of 94.25% has been achieved. The experiments have shown that the proposed classification system minimizes the classification errors and is more efficient in correct diagnosis.

Keywords

Microcalcifications texture features shape features hierarchical centroid Support Vector Machine 

Notes

Acknowledgement

Our thanks to Dr. Thomas Deserno, Department of Medical Informatics, Aachen University of Technology, Aachen, North Rhine-Westphalia, Germany, for providing the IRMA (Image Retrieval in Medical Applications) version of DDSM Database.

References

  1. 1.
    Acharya U R, Ng E Y K, Tan J H and Sree S V 2012 Thermography based breast cancer detection using texture features and support vector machine. J. Med. Syst. 36: 1503–1510CrossRefGoogle Scholar
  2. 2.
    Cheng H D, Shi X J, Min R, Hu L M, Cai X P and Du H N 2006 Approaches for automated detection and classification of masses in mammograms. Pattern Recogn. 39(4): 646–668CrossRefGoogle Scholar
  3. 3.
    Sree S V, Ng E Y K, Acharya U R and Faust O 2011 Breast imaging: a survey. World J. Clin. Oncol. 2(4): 171–178CrossRefGoogle Scholar
  4. 4.
    Papadopoulos A, Fotiadis D I and Likas A 2005 Characterization of clustered microcalcifications in digitized mammograms using neural networks and support vector machines. Artif. Intell. Med. 34(2): 141–150CrossRefGoogle Scholar
  5. 5.
    Ganesan K, Acharya U R, Chua C K, Min L C, Mathew B and Thomas A K 2013 Decision support system for breast cancer detection using mammograms. Proc. Inst. Mech. Eng. Part H: J. Eng. Med. 227(7): 721–732CrossRefGoogle Scholar
  6. 6.
    Tiedeu A, Daul C, Kentsop A, Graebling P and Wolf D 2012 Texture-based analysis of clustered microcalcifications detected on mammograms. Digit. Signal Process. 22(1): 124–132MathSciNetCrossRefGoogle Scholar
  7. 7.
    Muttarak M, Kongmebhol P and Sukhamwang N 2009 Breast calcifications: which are malignant? Singapore Med. J. 50(9): 907–913Google Scholar
  8. 8.
    Wei L, Yang Y, Nishikawa R M and Jiang Y 2005 A study on several machine learning methods for classification of malignant and benign clustered microcalcifications. IEEE Trans. Med. Imag. 24(3): 371–380CrossRefGoogle Scholar
  9. 9.
    Shanthi S and Bhaskaran V M 2014 A novel approach for classification of abnormalities in digitized mammograms. Sadhana 39(5): 1141–1150CrossRefMATHGoogle Scholar
  10. 10.
    Karahaliou A, Skiadopoulos S, Boniatis I, Sakellaropoulos P, Likaki E, Panayiotakis G and Costaridou L 2007 Texture analysis of tissue surrounding microcalcifications on mammograms for breast cancer diagnosis. Br. J. Radiol. 80(956): 648–656CrossRefGoogle Scholar
  11. 11.
    Hamdi N, Auhmani K and Hassani M M R 2008 Design of a high-accuracy classifier based on Fisher discriminant analysis: application to computer-aided diagnosis of microcalcifications. In: Proceedings of the IEEE International Conference on Computational Sciences and its Applications (ICCSA’08), June 30–July 3, Perugia, pp. 267–273Google Scholar
  12. 12.
    Tirtajaya A and Santika D D 2010 Classification of microcalcification using dual-tree complex wavelet transform and support vector machine. In: Proceedings of the IEEE 2 nd International Conference on Advances in Computing, Control and Telecommunication Technologies (ACT 2010), 2–3 December, Jakarta, pp. 164–166Google Scholar
  13. 13.
    Zyout I and Abdel-Qader I 2011 Classification of microcalcification clusters via PSO-KNN Heuristic parameter selection and GLCM features. Int. J. Comput. Appl. 31(2): 34–39Google Scholar
  14. 14.
    Farzana N and Rathnakara S 2011 Detection of micro-calcifications in mammogram images using probabilistic neural network. Elixir Comput. Sci. Eng. 38: 4404–4408Google Scholar
  15. 15.
    Bhanumathi R and Suresh G R 2013 Detection of microcalcification in mammogram images using support vector machine based classifier. ITSI Trans. Electr. Electron. Eng. 1(2): 27–32Google Scholar
  16. 16.
    Jenifer S, Parasuraman S and Kadirvel A 2014 An efficient biomedical imaging technique for automatic detection of abnormalities in digital mammograms. J. Med. Imag. Health Informat. 4(2): 291–296CrossRefGoogle Scholar
  17. 17.
    Strange H, Chen Z, Denton E R and Zwiggelaar R 2014 Modelling mammographic microcalcification clusters using persistent mereotopology. Pattern Recogn. Lett. 47: 157–163CrossRefGoogle Scholar
  18. 18.
    Lee S K, Chung P C, Chang C I, Lo C S, Lee T, Hsu G C and Yang C W 2003 Classification of clustered microcalcifications using a shape cognitron neural network. Neural Netw. 16(1): 121–132CrossRefGoogle Scholar
  19. 19.
    Soltanian-Zadeh H, Rafiee-Rad F and Pourabdollah-Nejad D S 2004 Comparison of multiwavelet, wavelet, Haralick, and shape features for microcalcification classification in mammograms. Pattern Recogn. 37(10): 1973–1986CrossRefGoogle Scholar
  20. 20.
    D’Aloia M, Rizzi M and Bari P D 2013 A second opinion system for microcalcification diagnosis. World Appl. Sci. J. 23(3): 289–295Google Scholar
  21. 21.
    Karssemeijer N 1993 Recognition of microcalcification clusters in mammograms. Int. J. Pattern Recogn. Artif. Intell. 7(6): 1357–1376CrossRefGoogle Scholar
  22. 22.
    Zhang L, Qian W, Sankar R, Song D and Clark R 2001 A new false positive reduction method for MCCs detection in digital mammography. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 7–11 May, Salt Lake City, UT, pp. 1033–1036Google Scholar
  23. 23.
    Cordella L P, Tortorella F and Vento M 2000 Combing experts with different features for classifying clustered microcalcifications in mammograms. In: Proceedings of the IEEE 15 th International Conference on Patten Recognition, 3–7 September, Barcelona, Spain, pp. 324–327Google Scholar
  24. 24.
    De Oliveira J E, Deserno T M and Araújo A D A 2008 Breast lesions classification applied to a reference database. In: Proceedings of the 2 nd International Conference on E-Medical Systems, 29–31 October, Tunisia, pp. 1–7Google Scholar
  25. 25.
    Kimori Y 2011 Mathematical morphology-based approach to the enhancement of morphological features in medical images. J. Clin. Bioinformat. 1(1): 1–10CrossRefGoogle Scholar
  26. 26.
    Stojić T and Reljin B 2010 Enhancement of microcalcifications in digitized mammograms: multifractal and mathematical morphology approach. FME Trans. 38(1): 1–9Google Scholar
  27. 27.
    Vega-Corona A, Quintanilla-Domínguez J, Ojeda-Magaña B, Cortina-Januchs M G, Marcano-Cedeño A, Ruelas R and Andina D 2011 Microcalcifications detection using PFCM and ANN. In: Pattern Recognition. Berlin–Heidelberg: Springer, pp. 260–268Google Scholar
  28. 28.
    Mustra M, Grgic M and Delac K 2012 Enhancement of microcalcifications in digital mammograms. In: Proceedings of the IEEE 19 th International Conference on Systems, Signals and Image Processing (IWSSIP), 11–13 April, Vienna, pp. 248–251Google Scholar
  29. 29.
    Zhang X, Homma N, Goto S, Kawasumi Y, Ishibashi T, Abe M, Sugita N and Yoshizawa M 2013 A hybrid image filtering method for computer-aided detection of microcalcification clusters in mammograms. J. Med. Eng. Article ID 615254, pp. 1–8Google Scholar
  30. 30.
    Quintanilla-Dominguez J, Ojeda-Magana B, Cortina-Januchs M C, Ruelas R, Vega-Corona A and Andina D 2011 Image segmentation by fuzzy and possibilistic clustering algorithms for identification of microcalcifications. Sci. Iran. 18(3): 580–589CrossRefMATHGoogle Scholar
  31. 31.
    Nishikawa R M, Jiang Y, Giger M L, Doi K, Vyborny C J and Schmidt R A 1992 Computer-aided detection of clustered microcalcifications. In: Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, 18–21 October, Chicago, pp. 1375–1378Google Scholar
  32. 32.
    Mossi J M and Albiol A 1999 Improving detection of clustered microcalcifications using morphological connected operators. In: Proceedings of the IEEE 7 th International Conference on Image Processing and its Applications, 13–15 July, Manchester, pp. 498–501Google Scholar
  33. 33.
    Pereira Jr R R, Marques P M A, Honda M O, Kinoshita S K, Engelmann R, Muramatsu C and Doi K 2007 Usefulness of texture analysis for computerized classification of breast lesions on mammograms. J. Digit. Imag. 20(3): 248–255CrossRefGoogle Scholar
  34. 34.
    Armon S 2011 Handwriting recognition and fast retrieval for Hebrew historical manuscripts. MTech Thesis, The Hebrew University of JerusalemGoogle Scholar
  35. 35.
    Vamvakas G, Gatos B and Perantonis S J 2010 Handwritten character recognition through two-stage foreground sub-sampling. Pattern Recogn. 43(8): 2807–2816CrossRefMATHGoogle Scholar
  36. 36.
    Wu C M and Chen Y C 1992 Statistical feature matrix for texture analysis. CVGIP: Graph. Models Image Process. 54(5): 407–419Google Scholar
  37. 37.
    Haralick R M, Shanmugam K and Dinstein I 1973 Textural features for image classification. IEEE Trans. Syst. Man Cybern. SMC-3: 610–621Google Scholar
  38. 38.
    Laws K I 1980 Textured image segmentation. PhD Thesis, University of Southern California, Electrical EngineeringGoogle Scholar
  39. 39.
    Mavroforakis M E, Georgiou H V, Dimitropoulos N, Cavouras D and Theodoridis S 2006 Mammographic masses characterization based on localized texture and dataset fractal analysis using linear, neural and support vector machine classifiers. Artif. Intell. Med. 37(2): 145–162CrossRefGoogle Scholar
  40. 40.
    Wu C M, Chen Y C and Hsieh K S 1992 Texture features for classification of ultrasonic liver images. IEEE Trans. Med. Imag. 11(2): 141–152CrossRefGoogle Scholar
  41. 41.
    Guo Z, Zhang I, Zhang D and Zhang S 2010 Rotation invariant texture classification using adaptive LBP with directional statistical features. In: Proceedings of the IEEE 17 th International Conference on Image Processing, 26–29 September, Hong Kong, pp. 285–288Google Scholar
  42. 42.
    Thangavel K and Velayutham C 2012 Rough set based unsupervised feature selection in mammogram image classification using entropy measure. J. Med. Imag. Health Informat. 2(3): 320–326CrossRefGoogle Scholar
  43. 43.
    Wang J and Zhao Y 2011 Differential evolution algorithm based one dimension real valued searching for feature selection. In: Future intelligent information systems. Berlin–Heidelberg: Springer, 127–134Google Scholar
  44. 44.
    Das S and Suganthan P N 2011 Differential evolution: a survey of the state-of-the-art. IEEE Trans. Evol. Comput. 15(1): 4–31CrossRefGoogle Scholar
  45. 45.
    Mala S and Latha K 2014 Feature selection in classification of eye movements using electrooculography for activity recognition. Comput. Math. Methods Med. Article ID 713818, pp. 1–9Google Scholar
  46. 46.
    Bharathi P T and Subashini P 2014 Optimal feature subset selection using differential evolution and extreme learning machine. Int. J. Sci. Res. 3(7): 1898–1905Google Scholar
  47. 47.
    Singh B, Jain V K and Singh S 2014 Mammogram mass classification using support vector machine with texture, shape features and hierarchical centroid method. J. Med. Imag. Health Inf. 4(5): 687–696CrossRefGoogle Scholar
  48. 48.
    Khushaba R N, Al-Ani A and Al-Jumaily A 2011 Feature subset selection using differential evolution and a statistical repair mechanism. Expert Syst. Appl. 38(9): 11515–11526CrossRefGoogle Scholar
  49. 49.
    Zyout I, Abdel-Qader I and Jacobs C 2009 Bayesian classifier with simplified learning phase for detecting microcalcifications in digital mammograms. Int. J. Biomed. Imag. Article ID 767805, pp. 1–13Google Scholar
  50. 50.
    Bhateja V and Devi S 2010 Mammographic image enhancement using double sigmoid transformation function. In: Proceedings of the International Conference on Computer Applications (ICCA-2010), 24–27 December, Pondicherry, India, pp. 259–264Google Scholar
  51. 51.
    Singh S, Yadav A and Singh B K 2011 Performance analysis of mammographic image enhancement techniques for early detection of breast cancer. In: Advances in parallel distributed computing. Berlin–Heidelberg: Springer, pp. 439–448Google Scholar
  52. 52.
    Saleem A, Beghdadi A and Boashash B 2012 Image fusion-based contrast enhancement. EURASIP J. Image Video Process. 2012(1): 1–17Google Scholar
  53. 53.
    Panetta K, Samani A and Agaian S 2014 Choosing the optimal spatial domain measure of enhancement for mammogram images. J. Biomed. Imag. Article ID 937849, pp. 1–8Google Scholar
  54. 54.
    Gorgel P, Sertbas A, Kilic N and Ucan O N 2013 Mammographical mass detection and classification using local seed region growing-spherical wavelet transform hybrid scheme. Comput. Biol. Med. 43(6): 765–774CrossRefGoogle Scholar
  55. 55.
    Tang X, Ding H, Yuan Y E and Wang Q 2008 Morphological measurement of localized temperature increase amplitudes in breast infrared thermograms and its clinical application. Biomed. Signal Process. Control 3(4): 312–318CrossRefGoogle Scholar
  56. 56.
    Chen Z, Strange H, Oliver A, Denton E R, Boggis C and Zwiggelaar R 2015 Topological modeling and classification of mammographic microcalcification clusters. IEEE Trans. Biomed. Eng. 62(4): 1203–1214CrossRefGoogle Scholar

Copyright information

© Indian Academy of Sciences 2018

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringSant Longowal Institute of Engineering and TechnologyLongowalIndia
  2. 2.Department of Electrical and Instrumentation EngineeringSant Longowal Institute of Engineering and TechnologyLongowalIndia

Personalised recommendations