Skip to main content
Springer Nature Link
Log in

Gabor Filter Based Classification of Mammography Images Using LS-SVM and Random Forest Classifier

  • Conference paper
  • First Online:
Recent Trends in Image Processing and Pattern Recognition (RTIP2R 2018)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1036))

  • 681 Accesses

Abstract

Breast cancer is formed in breast cells and it occurs primarily in women. Mammogram is x-ray of the breast that provides structural details. In the proposed work, attempt has been made to discriminate normal and abnormal mammograms belonging to fatty, fatty-glandular or dense-glandular breast tissue density. Breast x-ray images acquired in Medio-Lateral-Oblique (MLO) view (n = 197) chosen from mini-MIAS database are preprocessed using median filter to remove noise and adaptive histogram equalization has been applied to improve image contrast. The preprocessed images are subjected to Pectoral Muscle Removal (PMR) algorithm to obtain Region of Interest (RoI) comprising of only breast tissue region. For the obtained RoI, Gabor filtering has been employed at 5 various scales and 8 orientations leading to (5 \(\times \) 8) 40 filter responses. Magnitude, phase information and statistical features such as energy, entropy, variance, kurtosis and skewness are computed for the obtained filter responses. In the next step, reduced feature set is obtained by implementing two schemes. In scheme1, the dominant scale and orientations of Gabor filter responses are determined by employing Kernel Principal Component Analysis (KPCA) and features are considered for the obtained dominant scale and orientation coefficients. Further, absolute difference value of extracted features are computed and compared to choose the significant features. In scheme2, sequential forward selection algorithm is employed to obtain significant features that discriminates normal and abnormal subjects. The derived significant features belonging to each category of breast density are fed to Least Square-Support Vector Machine (LS-SVM) and Random Forest (RF) classifier to classify subjects as normal and abnormal. The results indicate that it is possible to discriminate normal and abnormal subjects using Gabor and statistical features. LS-SVM classifier performs better with an accuracy of 93.54%, sensitivity of 95.24% and specificity of 90% for fatty-glandular tissues.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Female Breast Cancer: Facts and figures. https://data.web.health.state.mn.us/cancer_breast

  2. Hoffman and Hoffmann Worldwide. http://www.hoffmanpr.com/press-release/global-cancer-rates-could-increase-50-by-2020

  3. Mina, L.M., Isa, N.A.M.: A review of computer-aided detection and diagnosis of breast cancer in digital mammography. J. Med. Sci. 15(3), 110–121 (2015). https://doi.org/10.3923/jms.2015.110.121

    Article  Google Scholar 

  4. The Susan G. Komen Breast Cancer Foundation, Inc. https://ww5.komen.org/BreastCancer/AccuracyofMammograms.html

  5. Saha, D., Bhowmik, M.K., De, B.K., Bhattacharjee, D.: A survey on imaging-based breast cancer detection. In: Das, K.N., Deep, K., Pant, M., Bansal, J.C., Nagar, A. (eds.) Proceedings of Fourth International Conference on Soft Computing for Problem Solving. AISC, vol. 335, pp. 255–266. Springer, New Delhi (2015). https://doi.org/10.1007/978-81-322-2217-0_22

    Chapter  Google Scholar 

  6. Lee, R.J., Vallow, L.A., McLaughlin, S.A., Tzou, K.S., Hines, S.L., Peterson, J.L.: Ductal carcinoma in situ of the breast. Int. J. Surg. Oncol. 1–12 (2012). https://doi.org/10.1155/2012/123549

    Article  Google Scholar 

  7. Pragathi, J., Patil, H.T.: Segmentation method for ROI detection in mammographic images using Wiener filter and Kittler’s method. In: IJCA Proceedings on International Conference on Recent Trends in Engineering and Technology 2013 ICRTET (4), pp. 27–33 (2013)

    Google Scholar 

  8. Sukassini, M.P., Velmurugan, T.: Noise removal using morphology and median filter methods in mammogram images. In: The 3rd International Conference on Small and Medium Business 2016, Hochiminh, Vietnam, pp. 413–419 (2016)

    Google Scholar 

  9. Alam, N., Islam, M.J.: Pectoral muscle elimination on mammogram using k-means clustering approach. Int. J. Comput. Vis. Signal Process. 4(1), 11–21 (2014)

    Google Scholar 

  10. Phadke, A.K., Rege, P.P.: Fusion of local and global features for classification of abnormality in mammograms. Sadhana 41(4), 385–395 (2016). https://doi.org/10.1007/s12046-016-0482-y

    Article  MathSciNet  MATH  Google Scholar 

  11. Vieira, M.A.C., Bakic, P.R., Maidment, A.D.A., Schiabel, H., Mascarenhas, N.D.A.: Filtering of poisson noise in digital mammography using local statistics and adaptive Wiener filter. In: Maidment, A.D.A., Bakic, P.R., Gavenonis, S. (eds.) IWDM 2012. LNCS, vol. 7361, pp. 268–275. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-31271-7_35

    Chapter  Google Scholar 

  12. Singh, V.P., Srivastava, A., Kulshreshtha, D., Chaudhary, A., Srivastava, R.: Mammogram classification using selected GLCM features and random forest classifier. Int. J. Comput. Sci. Inf. Secur. 14(6), 82–87 (2016)

    Google Scholar 

  13. Babu, J.S., Sukumar, L.B., Anandan, K.: Quantitative analysis of digitized mammograms using nonsubsampled contourlets and evolutionary extreme learning machine. J. Med. Imaging Health Inform. 3(2), 206–213 (2013). https://doi.org/10.1166/jmihi.2013.1146

    Article  Google Scholar 

  14. Langarizadeh, M., et al.: Improvement of digital mammogram images using histogram equalization, histogram stretching and median filter. J. Med. Eng. Technol. 35(2), 103–108 (2011). https://doi.org/10.3109/03091902.2010.542271

    Article  Google Scholar 

  15. Rajkumar, K.K., Raju, G.: Enhancement of mammograms using top hat filtering and wavelet decomposition. J. Comp. Math. Sci. 2(6), 812–818 (2011)

    Google Scholar 

  16. Kamra, A., Jain, V.K., Singh, S.: Extraction of orientation field using Gabor filter and gradient based approach for the detection of subtle signs in mammogram. J. Med. Imaging Health Inform. 4(3), 374–381 (2014). https://doi.org/10.1166/jmihi.2014.1266

    Article  Google Scholar 

  17. Alquodl, A., Jaffar, M.A.: Hybrid Gabor based local binary patterns texture features for classification of breast mammograms. Int. J. Comput. Sci. Netw. Secur. 16(2), 16–21 (2016)

    Google Scholar 

  18. Kinoshita, S.K., Azevedo-Marques, P.M., Pereira, R.R., Rodrigues, J.A.H., Rangayyan, R.M.: Radon-domain detection of nipple and pectoral muscle in mammograms. J. Digit. Imaging 21(1), 37–49 (2007). https://doi.org/10.1007/s10278-007-9035-6

    Article  Google Scholar 

  19. Sreedevi, S., Sherly, E.: A novel approach for removal of pectoral muscles in digital mammograms. Procedia Comput. Sci. 46, 1724–1731 (2015). https://doi.org/10.1016/j.procs.2015.02.117

    Article  Google Scholar 

  20. Santosh, K.C., Alam, N., Roy, P.P., Wendling, L., Antani, S., Thoma, G.R.: A simple and efficient arrowhead detection technique in biomedical images. Int. J. Pattern Recogn. Artif. Intell. 30(5), 1657002-1–1657002-16 (2016). https://doi.org/10.1142/S0218001416570020

    Article  Google Scholar 

  21. Santosh, K.C., Vajda, S., Antani, S., Thoma, G.R.: Edge map analysis in chest x-rays for automatic pulmonary abnormality screening. Int. J. Comput. Assist. Radiol. Surg. 11(9), 1637–1646 (2016). https://doi.org/10.1007/s11548-016-1359-6

    Article  Google Scholar 

  22. Bailur, A., Pandey, A.K., Sharma, A.K., Saseendran, S.: Modified Gabor filter with control chart and image plots for identifying architectural distortion of mammogram images. Int. J. Comput. Sci. Telecommun. 5(4), 12–19 (2014)

    Google Scholar 

  23. Rangayyan, R.M., Ayres, F.J.: Gabor filters and phase portraits for the detection of architectural distortion in mammograms. Med. Bio. Eng. Comput. 44, 883–894 (2006). https://doi.org/10.1007/s11517-006-0088-3

    Article  Google Scholar 

  24. Hussain, M., Khan, S., Muhammad, G., Berbar, M., Bebis, G.: Mass detection in digital mammograms using Gabor filter bank. In: IET Conference on Image Processing, London, pp. 1–5 (2012). https://doi.org/10.1049/cp.2012.0465

  25. Khan, S., Khan, A., Maqsood, M., Aadil, F., Ghazanfar, M.A.: Optimized Gabor feature extraction for mass classification using cuckoo search for big data e-health care. J. Grid Comput. (2018). https://doi.org/10.1007/s10723-018-9459-x

    Article  Google Scholar 

  26. Zheng, Y.: Breast cancer detection with Gabor features from digital mammograms. Algorithms 3, 44–62 (2010). https://doi.org/10.3390/a3010044

    Article  MATH  Google Scholar 

  27. Abdel-Naseer, M., Moreno, A., Puig, D.: Towards cost reduction of breast cancer diagnosis using mammography texture analysis. J. Exp. Theor. Artif. Intell. (2015). https://doi.org/10.1080/0952813X.2015.1024496

    Article  Google Scholar 

  28. Prasad, R.K., Basha, M.S.: Effective texture feature model for classification of mammogram images. ARPN J. Eng. Appl. Sci. 13(3), 961–967 (2018)

    Google Scholar 

  29. Torrents-Barrena, J., Puig, D., Melendez, J., Vallas, A.: Computer-aided diagnosis of breast cancer via Gabor wavelet bank and binary class SVM in mammographic images. J. Exp. Theor. Artif. Intell. (2015). https://doi.org/10.1080/0952813X.2015.1024491

    Article  Google Scholar 

  30. Jaffar, M.A.: Hybrid texture based classification of breast mammograms using AdaBoost classifier. Int. J. Adv. Comput. Sci. Appl. 8(5), 321–327 (2017). https://doi.org/10.14569/IJACSA.2017.080540

    Article  Google Scholar 

  31. Sheba, K.U., Raj, S.G.: An approach for automatic lesion detection in mammograms. Cogent Eng. 5, 1–16 (2018). https://doi.org/10.1080/23311916.2018.1444320

    Article  Google Scholar 

  32. Gardezi, S.J.S., Faye, I., Adjed, F., Kamel, N., Hussain, M.: Mammogram classification using chi-square distribution on local binary pattern features. J. Med. Imaging Health Inform. 7(1), 1–5 (2017). https://doi.org/10.1166/jmihi.2017.1982

    Article  Google Scholar 

  33. Ergin, S., Kilinc, O.: A new feature extraction framework based on wavelets for breast cancer diagnosis. Comput. Biol. Med. 51C, 171–182 (2014). https://doi.org/10.1016/j.compbiomed.2014.05.008

    Article  Google Scholar 

  34. Mini-MIAS database for mammograms. http://peipa.essex.ac.uk/info/mias.html

  35. Kamarainen, J.K., Kyrki, V., Kalviainen, H.: Invariance properties of Gabor filter-based features - overview and applications. IEEE Trans. Image Proc. 15(5), 1088–1099 (2006). https://doi.org/10.1109/TIP.2005.864174

    Article  Google Scholar 

  36. Schölkopf, B., Smola, A., Müller, K.-R.: Kernel principal component analysis. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, J.-D. (eds.) ICANN 1997. LNCS, vol. 1327, pp. 583–588. Springer, Heidelberg (1997). https://doi.org/10.1007/BFb0020217

    Chapter  Google Scholar 

  37. Vajda, S., et al.: Feature selection for automatic tuberculosis screening in frontal chest radiographs. J. Med. Syst. 42, 146 (2018)

    Article  Google Scholar 

  38. Suykens, J.A.K., Vandewalle, J.: Least square support vector machine classifiers. Neural Process. Lett. 9(3), 293–300 (1999). https://doi.org/10.1023/A:1018628609742

    Article  Google Scholar 

  39. Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001). https://doi.org/10.1023/A:1010933404324

    Article  MATH  Google Scholar 

  40. Institute of Medicine and National Research Council: Saving Women’s Lives: Strategies for Improving Breast Cancer Detection and Diagnosis (Consensus Study Report). The National Academies Press, Washington, DC (2005). https://doi.org/10.17226/11016

  41. Ruikar, D.D., Hegadi, R.S., Santosh, K.C.: A systematic review on orthopedic simulators for psycho-motor skill and surgical procedure training. J. Med. Syst. 42(9), 168 (2018)

    Article  Google Scholar 

  42. Ruikar, D.D., Santosh, K.C., Hegadi, R.S.: Automated fractured bone segmentation and labeling from CT images. J. Med. Syst. 43(3), 60 (2019). https://doi.org/10.1007/s10916-019-1176-x

    Article  Google Scholar 

  43. Ruikar, D.D., Santosh, K.C., Hegadi, R.S.: Segmentation and analysis of CT images for bone fracture detection and labeling. In: Medical Imaging: Artificial Intelligence, Image Recognition, and Machine Learning Techniques, chap. 7. CRC Press, Boca Raton (2019). ISBN 9780367139612

    Google Scholar 

  44. Hegadi, R.S., Navale, D.I., Pawar, T.D., Ruikar, D.D.: Multi feature-based classification of osteoarthritis in knee joint X-ray images. In: Medical Imaging: Artificial Intelligence, Image Recognition, and Machine Learning Techniques, chap. 5. CRC Press, Boca Raton (2019). ISBN 9780367139612

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. East Point College of Engineering and Technology, Bengaluru, Karnataka, India

    Mantragar Vijaya Madhavi

  2. M. S. Ramaiah University of Applied Sciences, Bengaluru, Karnataka, India

    T. Christy Bobby

Authors
  1. Mantragar Vijaya Madhavi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. T. Christy Bobby
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mantragar Vijaya Madhavi .

Editor information

Editors and Affiliations

  1. Department of Computer Science, University of South Dakota, Vermillion, SD, USA

    K. C. Santosh

  2. Solapur University, Solapur, India

    Ravindra S. Hegadi

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Vijaya Madhavi, M., Christy Bobby, T. (2019). Gabor Filter Based Classification of Mammography Images Using LS-SVM and Random Forest Classifier. In: Santosh, K., Hegadi, R. (eds) Recent Trends in Image Processing and Pattern Recognition. RTIP2R 2018. Communications in Computer and Information Science, vol 1036. Springer, Singapore. https://doi.org/10.1007/978-981-13-9184-2_6

Download citation

  • DOI: https://doi.org/10.1007/978-981-13-9184-2_6

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-13-9183-5

  • Online ISBN: 978-981-13-9184-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics