Abstract

The aim of the study is to retrieve the similar mammographic images based on the type of breast tissue density of the given query image. Statistical descriptors were extracted from the candidate blocks of the breast parenchyma. The mean of extracted features are fed into the SVM classifier for classification of the tissue density into any of the three classes namely dense, glandular and fatty and the classification accuracy obtained is 91.54%. After classification the mammogram images along with its feature vector are stored into three separate databases based on tissue type. Then K-means clustering algorithm is used to divide each database into 2 clusters. For content based retrieval of the mammograms based on the given query image, first the query image is classified into any of the three tissue class. Then the feature vector of the query image is compared with the two cluster centroids of the corresponding class, so as to confine the search within the closest cluster. Top 5 similar images are retrieved from its corresponding class database. Euclidean distance based k-NN is used for mammogram retrieval and this study obtained the highest precision rate ranging between 98 and 99%.

Keywords:

Breast tissue density, CBIR , mammography , statistical features , SVM,

References

1. Bozek, J., M. Mario, D. Kresimir and G. Mislav, 2009. A survey of image processing algorithms in digital mammography. In: Grgic, M. et al. (Eds.), Rec. Advan. in Mult. Sig. Process. and Commun., SCI 231, Springer-Verlag, Berlin, Heidlberg, pp: 631-657.
   CrossRef    
2. Chandy, D.A., J.S. Johnson and S.E. Selvan, 2014. Texture feature extraction using gray level statistical matrix for content-based mammogram retrieval. Multimed. Tools Appl., 72(2): 2011-2024.
   CrossRef    
3. Da Silva, S.F., M.X. Ribeiro, J.D.E.S. Batista Neto, C. Traina-Jr. and A.J.M. Traina, 2011. Improving the ranking quality of medical image retrieval using a genetic feature selection method. Decis. Support Syst., 51(4): 810-820.
   CrossRef    
4. Deserno, T.M., M. Soiron, J.E.E. de Oliveira and A. de A. Araújo, 2012. Towards computer-aided diagnostics of screening mammography using content-based image retrieval. Proceeding of 24th SIBGRAPI Conferences on Graphics, Patterns and Images (Sibgrapi), pp: 211-219.
   
5. El-Naqa, I., Y. Yang, N.P. Galatsanos, R.M. Nishikawa and M.N. Wernick, 2004. A similarity learning approach to content-based image retrieval: Application to digital mammography. IEEE T. Med. Imaging, 23(10): 1233-1244.
   CrossRef    PMid:15493691    
6. Jose, T.J. and P. Mythili, 2009. Neural network and genetic algorithm based hybrid model for content based mammogram image retrieval. J. Appl. Sci., 9(19): 3531-3538.
   CrossRef    
7. Kinoshita, S.K., P.M. de Azevedo-Marques, R.R. Pereira Jr, J.A.H. Rodrigues and R.M. Rangayyan, 2007. Content-based retrieval of mammograms using visual features related to breast density patterns. J. Digit. Imaging, 20(2): 172-190.
   CrossRef    PMid:17318705 PMCid:PMC3043906    
8. Kwok, S.M., R. Chandrasekhar and Y. Attikiouzel, 2000. Automatic pectoral muscle segmentation on mammograms by straight line estimation and cliff detection. Proceeding of Information Systems Conference. Perth, Australia, pp: 67-82.
   PMid:10653240    
9. Liasis, G., C. Pattichis and S. Petroudi, 2012. Combination of different texture features for mammographic breast density classification. Proceeding of IEEE 12th International Conference on Bioinformatics and Bioengineering (BIBE), pp: 732-737.
   CrossRef    
10. Muštra, M., M. Grgic and K. Delac, 2012. Breast density classification using multiple feature selection. Automatika, 53(4): 362-372.
    CrossRef    
11. Oliver, A., J. Freixenet, R. Marti, J. Pont, E. Perez, E.R.E. Denton and R. Zwiggelaar, 2008. A novel breast tissue density classification methodology. IEEE T. Inf. Technol. B., 12(1): 55-65.
    CrossRef    PMid:18270037    
12. Oliver, A., X. Lladó, E. Pérez, J. Pont, E. Denton, J. Freixenet and J. Martí, 2010. A statistical approach for breast density segmentation. J. Digit. Imaging, 23(5): 527-537.
    CrossRef    PMid:19506953 PMCid:PMC3046676    
13. Otsu, N., 1979. A threshold selection method from gray-level histograms. IEEE T. Sys. Man Cyb., 9(1): 62-66.
    CrossRef    
14. Rangayyan, R.M., F.J. Ayres and J.E. Leo Desautels, 2007. A review of computer-aided diagnosis of breast cancer: Toward the detection of subtle signs. J. Frankl. Inst., 344(3): 312-348.
    CrossRef    
15. Sheshadri, H.S. and A. Kandaswamy, 2007. Experimental investigation on breast tissue classification based on statistical feature extraction of mammograms. Comput. Med. Imag. Grap., 31: 46-48.
    CrossRef    PMid:17070012    
16. Srinivasan, G.N. and G. Shobha, 2008. Statistical texture analysis. Proceeding of World Academy of Science, Engineering and Technology, 36: 1264-1269, ISSN: 2070-3740.
    
17. Subashini, T.S., V. Ramaingam and S. Palanivel, 2010. Automated assessment of breast tissue density in digital mammograms. Comput. Vis. Image Und., 114: 33-43.
    CrossRef    
18. Suckling, J., J. Parker, D. Dance, S. Astley, I. Hutt, C. Boggis, I. Ricketts, E. Stamatakis, N. Cerneaz, S. Kok, P. Taylor, D. Betal and J. Savage, 1994. The mammographic images analysis society digital mammogram database. Exerp. Med. Int. Congress Series, 1069: 375-378.
    
19. Tagliafico, A., G. Tagliafico, S. Tosto, F. Chiesa, C. Marinoli, L.E. Derchi and M. Calabrese, 2009. Mammographic density estimation: Comparison among BI-RADS categories, a semi-automated software and a fully automated one. Breast, 18(1): 35-40.
    CrossRef    PMid:19010678    
20. Tzikopoulos, S.D., M.E. Mavroforakis, H.V. Georgiou, N. Dimitropoulos and S. Theodoridies, 2011. A fully automated scheme for mammographic segmentation and classification based on breast density and asymmetry. Comput. Meth. Prog. Bio., 102: 47-63.
    CrossRef    PMid:21306782    
21. Vaidehi, K. and T.S. Subashini, 2013. Automatic Identification and elimination of pectoral muscle in digital mammograms. Int. J. Comput. Appl., 75(14): 15-18.
    CrossRef    
22. Vállez, N., G. Bueno, O. Déniz-Suárez, J.A. Seone, J. Dorado and A. Pazos, 2011. A tree classifier for automatic breast tissue classification based on BIRADS categories. In: Vitria, J., J.M. Sanches and M. Hernandez (Eds.), IbPRIA 2011. LNCS 6669, Springer-Verlag, Berlin, Heidelberg, pp: 580-587.
    CrossRef    
23. Vapnik, V., 1998. Statistical Learning Theory. Wiley, New York.
    
24. Wang, X.H., W.F. Good, B.E. Chapman, Y.H. Chang, W.R. Poller, T.S. Chang and L.A. Hardesty, 2003. Automated assessment of the composition of breast tissue revealed on tissue-thickness-corrected mammography. Am. J. Roentgenol., 180: 227-262.
    CrossRef    PMid:12490516    
25. Wei, C.H., S.Y. Chen and X. Liu, 2012. Mammogram retrieval on similar mass lesions. Comput. Meth. Prog. Bio., 106(3): 234-248.
    CrossRef    PMid:20933295    
26. Wei, L., Y. Yang and R.M. Nishikawa, 2009a. Microcalcification classification assisted by content-based image retrieval for breast cancer diagnosis. Pattern Recogn., 42(6): 1126-1132.
    CrossRef    PMid:20161326 PMCid:PMC2678744    
27. Wei, L., Y. Yang, M.N. Wernick and R.M. Nishikawa, 2009b. Learning of perceptual similarity from expert readers for mammogram retrieval. IEEE J. Sel. Top. Signa., 3(1): 53-61.
    CrossRef    
28. Winsberg, F., M. Elkin and J. Macy, 1967. Detection of radiographic abnormalities in mammograms by means of optical scanning and computer analysis. Radiology, 89: 211-215.
    CrossRef    
29. Zheng, B., 2009. Computer-aided diagnosis in mammographic using content based image retrieval approaches: Current status and future perspectives. Algorithms, 2(2): 828-849.
    CrossRef    PMid:20305801 PMCid:PMC2841362    

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.