Information Fusion from Mammogram and Ultrasound Images for Better Classification of Breast Mass

  • Minavathi
  • S. Murali
  • M. S. Dinesh
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 174)


Various medical modalities are used in all phases of cancer detection. Information extracted from these modalities reveals morphological, metabolic and functional information of tissues. Integrating this information in a meaningful way assists in clinical decision making. Sometimes using multimodal techniques supply complementary information for improved therapy planning. Proposed investigation is on classification of breast mass as benign or malignant for early detection of breast cancer using mammograms and Ultrasound modalities. The proposed approach is based on the fusion of information from two modalities at image feature level with different normalization techniques to improve the performance of breast mass classification. Gabor filters are used to retrieve texture features from mammograms, shape and structural features are retrieved from ultrasound images. Training of classifier is done using Support vector machine (SVM) classifiers to classify masses. Receiver operating characteristic curves (ROC) are used to evaluate the performance. Our method was validated on 20 set of images. Where each set consists of one mammogram and one ultrasound image of a same person out of which 9 sets were malignant and 11 were benign. SVM classifiers achieved 95.6% sensitivity in classifying the masses using the features retrieved from two modalities.


Mammogram Ultrasound Dual modality SVM Feature level fusion Z-score Normalization 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Krol, A., Coman, I.L., Mandel, J.A., Baum, K., Luo, M., Feiglin, D.H., Lipson, E.D., Beaumont, J.: Inter-Modality Non-Rigid Breast Image Registration Using Finite-Element Method (2004) 0-7803-8257-9/04/$20.00 © 2004 IEEEGoogle Scholar
  2. 2.
    Ravishankar Rao, A., Ramesh, C.: Computerized Flow Field Analysis: Oriented Texture Fields, 0162-8828. IEEE (1992)Google Scholar
  3. 3.
    Kopans, D.: Breast Imaging. Lippincott-Raven Publishers, New York (1998)Google Scholar
  4. 4.
    Sickles, E.A., Filly, R.A., Callen, P.W.: Breast detection with sonography and mammography. AJR 140, 843–845 (1983)CrossRefGoogle Scholar
  5. 5.
    Arena, F., DiCicco, T., Anand, A.: Multi-modality data fusion aids early detection of breast cancer Using conventional technology and advanced digital infrared Imaging. In: Proceedings of the 26th Annual International Conference of the IEEE EMBS, San Francisco, CA, USA, September 1-5 (2004) 0-7803-8439-3/04/$20.00© 2004 IEEEGoogle Scholar
  6. 6.
    Marcialis, G.L., Roli, F., Didaci, L.: Pattern Recognition 42(11), 2807–2817 (2009)MATHCrossRefGoogle Scholar
  7. 7.
    Zhang, H.-L., Yang, F.: Multimodality Medical Image Registration Using Hybrid Optimization Algorithm. In: 2008 International Conference on Bio Medical Engineering and Informatics (2008), 978-0-7695-3118-2/08 $25.00 © 2008 IEEE, doi:10.1109/BMEI.2008.108Google Scholar
  8. 8.
    Solimanv, H., Mohamed, A.S., Atwan, A.: Feature Level Fusion of Palm Veins and Signature Biometrics. International Journal of Video & Image Processing and Network Security IJVIPNS-IJENS 12(01), 28Google Scholar
  9. 9.
    Gholam Hosseini, H., Alizad, A., Fatemi, M.: Integration of Vibro-Acoustography Imaging Modality with the Traditional Mammography. International Journal of Biomedical Imaging 2007, Article ID 40980, 8 pages (2007), doi:10.1155/2007/40980Google Scholar
  10. 10.
    Kittler, J., Duin, R.P.W.: The combining classifier: to train or not to train. In: Proceedings of the International Conference on Pattern Recognition, vol. 16(2), pp. 765–770 (2002)Google Scholar
  11. 11.
    Jameson, M.: Ultrasound as a breast cancer test is becoming more accepted, Los Angeles Times, 000037057, June 14 (2004)Google Scholar
  12. 12.
    Sampat, M.P., Whitman, G.J., Bovik, A.C., Markey, M.K.: Comparison of Algorithms to Enhance Spicules of Spiculated Masses on Mammography. Journal of Digital Imaging, 1–8 (2007)Google Scholar
  13. 13.
    Minavathi, Murali, S., Dinesh, M.S.: Model based approach for Detection of Architectural Distortions and Spiculated Masses in Mammograms. International Journal on Computer Science and Engineering (IJCSE) 3(11), 3534 (2011) ISSN : 0975-3397 Google Scholar
  14. 14.
    Minavathi, Murali, S., Dinesh, M.S.: Detection of Architectural Distortions with Spiculations in Mammograms by analyzing the structure of mammary glands. In: Proceedings of Fifth Indian International Conference on Artificial Intelligence (IICAI), Tumkur, pp. 218–230 (December 2011)Google Scholar
  15. 15.
    Minavathi, Murali, S., Dinesh, M.S.: Curvature and shape analysis for the detection of spiculated masses in breast ultrasound images. IJMI International Journal of Machine Intelligence 3(4), 333–339 (2011) ISSN: 0975–2927 & E-ISSN: 0975–9166Google Scholar
  16. 16.
    Minavathi, Murali, S., Dinesh, M.S.: Classification of Mass in Breast Ultrasound Images using Image Processing Techniques. International Journal of Computer Applications(IJCA) 42(10), 5120/5731-7801 (March 2012)Google Scholar
  17. 17.
    Wirth, M.A.: Nonrigid Approach to Medical Image Registration Matching Images of the Breast, Ph.D. Thesis, RMIT University, Elbourne, Australia (2000)Google Scholar
  18. 18.
    Brunelli, R., Falavigna, D.: Person identification using multiple cues. IEEE Transactions on Pattern Analysis and Machine Intelligence (1995)Google Scholar
  19. 19.
    Gupta, R., Undrill, P.E.: The use of texture analysis to delineate suspicious masses in mammography. Phys. Med. Biol. 40, 835–855 (1995)CrossRefGoogle Scholar
  20. 20.
    Gunn, S.R.: Support Vector Machines for Classification and Regression, Technical Report, University of Southampton (1998)Google Scholar
  21. 21.
    Ikedoa, Y., Fukuokab, D., Haraa, T., Fujitaa, H., Takadac, E., Endod, T., Moritae, T.: Computerized mass detection in whole breast ultrasound images: Reduction of false positives using bilateral subtraction technique. In: Proc. of SPIE Medical Imaging 2007, vol. 6514, p. 65141T (2007)Google Scholar

Copyright information

© Springer India 2013

Authors and Affiliations

  1. 1.PES College of EngineeringMandyaIndia
  2. 2.MITMysoreIndia
  3. 3.PET Research CenterMandyaIndia

Personalised recommendations