Calculating Texture Features from Mammograms and Evaluating Their Performance in Classifying Clusters of Microcalcifications

  • Marcelo A. Duarte
  • Wagner C. A. Pereira
  • André Victor AlvarengaEmail author
Conference paper
Part of the IFMBE Proceedings book series (IFMBE, volume 76)


In this work, 2432 texture features were calculated from microcalcification clusters presented on 190 images from the Digital Database for Screening Mammography. Mutual information technique was used to rank texture features. Then, an incremental procedure adds top ranked features to the Fisher discriminant analysis to determine the best set of texture features in classifying benign or malignant microcalcification clusters. The result was achieved using 13 texture features (AUC.632+ = 0.945 ± 0.019). However, to assure a consistent statistical analysis, at least 30 sample images for each feature added was assumed. The best performance was achieved by a set with 5 texture features (AUC.632+ = 0.884 ± 0.025), which is comparable to the ones presented in literature.


Microcalcifications Texture features Feature selection Breast cancer Mammograms 



Thanks to the financial support of the Brazilian National Council for Scientific and Technological Development (CNPq) (Grants: 434.858/2016-1, 309717/2014-0, and 308.627/2013-0), and CAPES/PROEX.


  1. 1.
    Brasil, Ministério da Saúde, Instituto Nacional de Câncer (INCA), Tipos de Câncer, Câncer de Mama.
  2. 2.
    Brasil, Ministério da Saúde, Instituto Nacional de Câncer (INCA), Câncer de Mama, Detecção Precoce.
  3. 3.
    Jalalian, A., Mashoror, S.B.T., Mahmudb, H.R., Saripan, M.I.B., Ramli, A.R.B., Karasfi, B.: Computer-aided detection/diagnosis of breast cancer in mammography and ultrasound: a review. Clin. Imaging 37(3), 420–426 (2013)CrossRefGoogle Scholar
  4. 4.
    Calas, M.J.G., Gutfilen, B., Pereira, W.C.A.: CAD and mammography: why use this tool? Braz. J. Biomed. Eng. 45(1), 46–52 (2012)Google Scholar
  5. 5.
    Wei, L., Yanga, Y., Nishikawa, R.M.: Microcalcification classification assisted by content-based image retrieval for breast cancer diagnosis. Pattern Recogn. 42(6), 1126–1132 (2009)CrossRefGoogle Scholar
  6. 6.
    Halkiots, S., Botsis, T., Rangoussi, M.: Automatic detection of clustered microcalcifications in digital mammograms using mathematical morphology and neural networks. Sig. Process. 87(7), 1559–1568 (2007)zbMATHCrossRefGoogle Scholar
  7. 7.
    Nishikawa, R.M.: Current status and future directions of computer-aided diagnosis in mammography. Comput. Med. Imaging Graph. 31(4–5), 224–235 (2007)CrossRefGoogle Scholar
  8. 8.
    Elter, M., Horsch, A.: CADx of mammographic masses and clustered microcalcifications: a review. Med. Phys. 36(6), 2052–2068 (2009)CrossRefGoogle Scholar
  9. 9.
    Chen, C.H., Lee, G.G.: On digital mammogram segmentation and microcalcification detection using multiresolution wavelet analysis. Graph. Models Image Process. 59(5), 349–364 (1997)CrossRefGoogle Scholar
  10. 10.
    Cheng, H.D., Cai, X., Chen, X., Hu, L., Lou, X.: Computer-aided detection and classification of microcalcifications in mammograms: a survey. Pattern Recogn. 36(12), 2967–2991 (2003)zbMATHCrossRefGoogle Scholar
  11. 11.
    Arikidis, N.S., Karajaliou, A., Skiadopoulos, S., Korfiatis, P., Likaki, E., Panayiotakis, G., et al.: Size-adapted microcalcification segmentation in mammography utilizing scale-space signatures. Comput. Med. Imaging Graph. 34(6), 487–493 (2010)CrossRefGoogle Scholar
  12. 12.
    Paquerault, S., Yarusso, L.M., Papaioannou, J., Jiang, Y.: Radial gradient-based segmentation of mammographic microcalcifications: observer evaluation and effect on CAD performance. Med. Phys. 31(9), 2648–2657 (2004)CrossRefGoogle Scholar
  13. 13.
    De Santo, M., Molinara, M., Tortorella, F., Vento, M.: Automated classification of clustered microcalcifications by a multiple expert system. Pattern Recogn. 36(7), 1467–1477 (2003)CrossRefGoogle Scholar
  14. 14.
    Veldkamp, W.J., Karssemeijer, N., Otten, J.D.M., Hendriks, J.H.C.L.: Automated classification of clusters microcalcifications into malignant and benign types. Med. Phys. 27(11), 2600–2608 (2000)CrossRefGoogle Scholar
  15. 15.
    Chan, H.P., Sahiner, B.: Computerized analysis of mammographic microcalcifications in morphological and texture feature spaces. Med. Phys. 25(10), 2007–2019 (1998)CrossRefGoogle Scholar
  16. 16.
    Karahaliou, A.N., Boniatis, I.S., Skiadopoulos, S.G., Sakellaropoulos, F.N., Likaki, E., Panayiotakis, G.S., Costaridou, L.I.: A texture analysis approach for characterizing microcalcifications on mammograms. In: Proceeding of IEEE International Special Topic Conference on Information Technology in Biomedicine (ITAB 2006), pp. 251–257, October 2006Google Scholar
  17. 17.
    Karahaliou, A.N., Boniatis, I.S., Skiadopoulos, S.G., Sakellaropoulos, F.N., Arikidis, N.S., Likaki, E.A., Panayiotakis, G.S., Costaridou, L.I.: Breast cancer diagnosis: analyzing texture of tissue surrounding microcalcifications. IEEE Trans. Inf Technol. Biomed. 12(6), 731–738 (2008)CrossRefGoogle Scholar
  18. 18.
    Flores, W.G., Pereira, W.C.A., Infantosi, A.F.C.: Improving classification performance of breast lesions on ultrasonography. Pattern Recogn. 48(4), 1125–1136 (2015)CrossRefGoogle Scholar
  19. 19.
    University of South Florida, DOD Breast Cancer Research Program, US Army Research and Material Command, Digital Database for Screening Mammography (DDSM). Accessed 03 Jan 2014
  20. 20.
    Zhang, P., Verma, B., Kumar, K.: Neural vs. statistical classifier in conjunction with genetic algorithm based feature selection. Pattern Recogn. Lett. 26(7), 909–919 (2005)CrossRefGoogle Scholar
  21. 21.
    Alvarenga, A.V., Pereira, W.C.A., Infantosi, A.F.C., Azevedo, C.M.: Complexity curve and grey level co-occurrence matrix in the texture evaluation of breast tumor on ultrasound images. Med. Phys. 34(2), 379–387 (2007)CrossRefGoogle Scholar
  22. 22.
    Gomez, W., Pereira, W., Infantosi, A.F.C.: Analysis of co-occurrence texture statistics as a function of gray-level quantization for classifying breast ultrasound. IEEE Trans. Med. Imaging 31(10), 1889–1899 (2012)CrossRefGoogle Scholar
  23. 23.
    Kriti, J.V., Dey, N., Kumar, V.: PCA-PNN and PCA-SVM based CAD systems for breast density classification. In: Applications of Intelligent Optimization in Biology and Medicine: Current Trends and Open Problems, pp. 159–180 (2016)Google Scholar
  24. 24.
    Chang, R.-F., Wu, W.-J., Moon, W.K., Chen, D.-R.: Improvement in breast tumor discrimination by support vector machines and speckle-emphasis texture analysis. Ultrasound Med. Biol. 29(5), 679–686 (2003)CrossRefGoogle Scholar
  25. 25.
    Shen, W.-C., Chang, R.-F., Moon, W.K., Chou, Y.-H., Huang, C.-S.: Breast ultrasound computer-aided diagnosis using bi-rads features. Acad. Radiol. 14(8), 928–939 (2007)CrossRefGoogle Scholar
  26. 26.
    Huang, Y.-L., Wang, K.-L., Chen, D.-R.: Diagnosis of breast tumors with ultrasonic texture analysis using support vector machines. Neural Comput. Appl. 15(2), 164–169 (2006)CrossRefGoogle Scholar
  27. 27.
    Fernandez, A., Alvarez, M.X., Bianconi, F.: Image classification with binary gradient contours. Opt. Lasers Eng. 49, 1177–1184 (2011)CrossRefGoogle Scholar
  28. 28.
    Horsch, K., Giger, M.L., Venta, L.A., Vyborny, C.J.: Computerized diagnosis of breast lesions on ultrasound. Med. Phys. 29(2), 157–164 (2002)CrossRefGoogle Scholar
  29. 29.
    Duarte, M.A., Alvarenga, A.V., Azevedo, C.M., Calas, M.J.G., Infantosi, A.F.C., Pereira, W.C.A.: Segmenting mammographic microcalcifications using a semi-automatic procedure based on Otsu’s method morphological filters. Braz. J. Biomed. Eng. 29(4), 377–388 (2013)Google Scholar
  30. 30.
    Duarte, M.A., Alvarenga, A.V., Azevedo, C.M., Calas, M.J.G., Infantosi, A.F.C., Pereira, W.C.A.: Evaluating geodesic active contours in microcalcifications segmentation on mammograms. Comput. Methods Prog. Biomed. 122(3), 304–315 (2015)CrossRefGoogle Scholar
  31. 31.
    Peng, H., Long, F., Ding, C.: Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans. Pattern Anal. Mach. Intell. 27(8), 1226–1238 (2005)CrossRefGoogle Scholar
  32. 32.
    Pereira, W.C., Alvarenga, A.V., Infantosi, A.F.C., Macrini, L., Pedreira, C.E.: A non-linear morphometric feature selection approach for breast tumor contour from ultrasonic images. Comput. Biol. Med. 11(12), 912–918 (2010)CrossRefGoogle Scholar
  33. 33.
    Sahiner, B., Chan, H.P., Hadjiiski, L.: Classifier performance prediction for computer-aided diagnosis using a limited dataset. Med. Phys. 35(4), 1559–1570 (2008)CrossRefGoogle Scholar
  34. 34.
    Sugiyama, M.: Dimensionality reduction of multimodal labeled data by local Fisher discriminant analysis. J. Mach. Learn. Res. 8, 1027–1061 (2007)zbMATHGoogle Scholar
  35. 35.
    Stoline, M.R.: The status of multiple comparisons: simultaneous estimation of all pairwise comparisons in one-way ANOVA designs. Am. Stat. 35(3), 134–141 (1981)zbMATHGoogle Scholar
  36. 36.
    Dheeba, J., Tamil Selvi, S.: Classification of malignant and benign microcalcification using SVM classifier. In: Proceedings of the 2011 International Conference on Emerging Trends in Electrical and Computer Technology (ICETECT 2011), India, pp. 686–690, March 2011Google Scholar
  37. 37.
    Tiedeu, A., Daul, C., Kentsop, A., Graebling, P., Wolf, D.: Texture-based analysis of clustered microcalcifications detected on mammograms. Digital Sig. Process. 22(1), 124–132 (2012)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Electronic Engineering DepartmentUniCarioca University CentreRio de JaneiroBrazil
  2. 2.Biomedical Engineering Program/COPPEFederal University of Rio de JaneiroRio de JaneiroBrazil
  3. 3.Laboratory of UltrasoundNational Institute of Metrology, Quality and TechnologyRio de JaneiroBrazil

Personalised recommendations