Multimedia Tools and Applications

, Volume 77, Issue 8, pp 9249–9269 | Cite as

An efficient algorithm for mass detection and shape analysis of different masses present in digital mammograms

  • Kanchan Lata KashyapEmail author
  • Manish Kumar Bajpai
  • Pritee Khanna


The present study introduces an efficient algorithm for automatic segmentation and detection of mass present in the mammograms. The problem of over and under-segmentation of low-contrast mammographic images has been solved by applying preprocessing on original mammograms. Subtraction operation performed between enhanced and enhanced inverted mammogram significantly highlights the suspicious mass region in mammograms. The segmentation accuracy of suspicious region has been improved by combining wavelet transform and fast fuzzy c-means clustering algorithm. The accuracy of mass segmentation has been quantified by means of Jaccard coefficients. Better sensitivity, specificity, accuracy, and area under the curve (AUC) are observed with support vector machine using radial basis kernel function. The proposed algorithm is validated on Mini-Mammographic Image Analysis Society (MIAS) and Digital Database for Screening Mammography (DDSM) datasets. Highest 91.76% sensitivity, 96.26% specificity, 95.46% accuracy, and 96.29% AUC on DDSM dataset and 94.63% sensitivity, 92.74% specificity, 92.02% accuracy, and 95.33% AUC on MIAS dataset are observed. Also, shape analysis of mass is performed by using moment invariant and Radon transform based features. The best results are obtained with Radon based features and achieved accuracies for round, oval, lobulated, and irregular shape of mass are 100%, 70%, 64%, and 96%, respectively.


Mammography Increased efficiency Reduced computational time Unsharp masking Breast cancer Wavelet technique GLCM GLRLM FCM 


  1. 1.
    American College Radiology (1998) BI-RADS Committee. Breast imaging reporting and data system. American College of Radiology, RestonGoogle Scholar
  2. 2.
    Bellotti R, De Carlo F, Tangaro S, Gargano G, Maggipinto G, Castellano M, Massafra R, Cascio D, Fauci F, Magro R, Raso G (2006) A completely automated CAD system for mass detection in a large mammographic database. Med phy 33:3066–3075. doi: 10.1118/1.2214177 CrossRefGoogle Scholar
  3. 3.
    Bocchi L, Nori J (2007) Shape analysis of micro-calcifications using radon transform. Med Eng Phy 29:691–698. doi: 10.1016/j.medengphy.2006.07.012 CrossRefGoogle Scholar
  4. 4.
    Cao A, Song Q, Yang X, Wang L (2004) Breast mass segmentation based on information theory. In: Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th IEEE International Conference vol. 3, pp 758–761. Doi: 10.1016/j.cviu.2007.07.004
  5. 5.
    Cascio D, Fauci F, Magro R, Raso G, Bellotti R, De Carlo F, Tangaro S, De Nunzio G, Quarta M, Forni G et al (2006) Mammogram segmentation by contour searching and mass lesions classification with neural network. IEEE Trans Nucl Sci 53:2827–2833. doi: 10.1109/TNS.2006.878003 CrossRefGoogle Scholar
  6. 6.
    Che FN, Fairhust MC, Wells CP, Hanson M (1996) Evaluation of a two-stage model for detection of abnormalities in digital mammograms. In: IEEE Colloquium Digest Mammography, pp 13–1. Doi:  10.1049/ic:19960496
  7. 7.
    Cheetham AH, Hazel JE (1969) Binary (presence-absence) similarity coefficients. J Paleontol 43(5):1130–1136Google Scholar
  8. 8.
    Christoyianni I, Dermatas E, Kokkinakis G (2000) Fast detection of masses in computer-aided mammography. Sig Proc Mag 17:54–64. doi: 10.1109/79.814646 CrossRefGoogle Scholar
  9. 9.
    Constantinidis AS, Fairhust MC, Deravi F, Hanson M, Wells CP, Chapman-Jones C (1999) Evaluating classification strategies for detection of circumscribed masses in digital mammograms. In: International Conference on Image Processing and its Application. pp 435–439. Doi: 10.1049/cp:19990359
  10. 10.
    Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297zbMATHGoogle Scholar
  11. 11.
    Deans SR (2007) The Radon transform and some of its applications. Courier Corporation, North ChelmsfordGoogle Scholar
  12. 12.
    Do Nascimento MZ, Martins AS, Neves LA, Ramos RP, Flores EL, Carrijo GA (2013) Classification of masses in mammographic image using wavelet domain features and polynomial classifier. Expert Sys Appl 40:6213–6221. doi: 10.1016/j.eswa.2013.04.036 CrossRefGoogle Scholar
  13. 13.
    Dominguez AR, Nandi AK (2009) Toward breast cancer diagnosis based on automated segmentation of masses in mammograms. Pattern Recog 42:1138–1148. doi: 10.1016/j.patcog.2008.08.006 CrossRefGoogle Scholar
  14. 14.
    Ganesan K, Acharya UR, Chua CK, Min LC, Abraham KT, Ng KH (2013) Computer-aided breast cancer detection using mammograms: a review. IEEE Rev Biomed Eng 6:77–98. doi: 10.1109/ICoCS.2014.7060995 CrossRefGoogle Scholar
  15. 15.
    Gonzalez RC, Woods RE (2008) Digital Image Processing, 3rd edn. Pearson Prentice Hall, Upper Saddle RiverGoogle Scholar
  16. 16.
    Haralick RM, Shanmugam K, Dinstein IH (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 6:610–621. doi: 10.1109/TSMC.1973.4309314 CrossRefGoogle Scholar
  17. 17.
    Hu MK (1962) Visual pattern recognition by moment invariants. IRE Trans Inf Theory 8:179–187zbMATHGoogle Scholar
  18. 18.
    Hu K, Gao X, Li F (2011) Detection of suspicious lesions by adaptive thresholding based on multi-resolution analysis in mammograms. IEEE Trans Instrum Meas 60:462–472. doi: 10.1109/TIM.2010.2051060 CrossRefGoogle Scholar
  19. 19.
    Huo Z, Giger ML, Vyborny CJ, Bick U, Lu P, Wolverton DE, Schmidt RA (1995) Analysis of spiculation in the computerized classification of mammographic masses. Med Phys 22:1569–1579. doi: 10.1118/1.597626 CrossRefGoogle Scholar
  20. 20.
    Jen CC, Yu SS (2015) Automatic detection of abnormal mammograms in mammographic images. Expert Syst Appl 42:3048–3055. doi: 10.1016/j.eswa.2014.11.061 CrossRefGoogle Scholar
  21. 21.
    Jolliffe I (2002) Principal component analysis. John Wiley & Sons, Ltd., New YorkzbMATHGoogle Scholar
  22. 22.
    Kom G, Tiedeu A, Kom M (2007) Automated detection of masses in mammograms by local adaptive thresholding. Comput Biol Med 37:37–48. doi: 10.1016/j.compbiomed.2005.12.004 CrossRefGoogle Scholar
  23. 23.
    Kupinski MA, Giger ML (1998) Automated seeded lesion segmentation on digital mammograms. IEEE Trans Med Imag 17:510–517. doi: 10.1109/42.730396 CrossRefGoogle Scholar
  24. 24.
    Kurt B, Nabiyev VV, Turhan K (2014) A novel automatic suspicious mass regions identification using Havrda & Charvat entropy and Otsu's N thresholding. Comput Methods Prog Biomed 114:349–360. doi: 10.1016/j.cmpb.2014.02.014 CrossRefGoogle Scholar
  25. 25.
    Llado X, Oliver A, Freixenet J, Mart R, Mart J (2009) A textural approach for mass false positive reduction in mammography. Comput Med Imaging Graph 33:415–422. doi: 10.1016/j.compmedimag.2009.03.007 CrossRefGoogle Scholar
  26. 26.
    Materka A, Strzelecki M et al (1998) Texture analysis methods–a review. Technical University of Lodz, Institute of Electronics, COST B11 Report, Brussels, pp 9–11Google Scholar
  27. 27.
    Muramatsu C, Hara T, Endo T, Fujita H (2016) Breast mass classification on mammograms using radial local ternary patterns. Comput Biol Med 72:43–53. doi: 10.1016/j.compbiomed.2016.03.007 CrossRefGoogle Scholar
  28. 28.
    Ng SL, Bischof WF (1992) Automated detection and classification of breast tumors. Comput Biomed Res 25:218–237. doi: 10.1016/0010-4809(92)90040-H CrossRefGoogle Scholar
  29. 29.
    Nguyen TM, Rangayyan RM (2006) Shape analysis of breast masses in mammograms via the fractal dimension. In: Engineering in Medicine and Biology Society, 2005. IEEE-EMBS 2005. 27th Annual International Conference pp 3210–3213. doi: 10.1109/IEMBS.2005.1617159
  30. 30.
    Nunes AP, Silva AC, de Paiva AC (2010) Detection of masses in mammographic images using geometry, Simpson’s diversity index and SVM. Int J Signal Imaging Syst Eng 3:43–51. doi: 10.1504/IJSISE.2010.034631 Google Scholar
  31. 31.
    Ojala T, Pietikainen M, Maenpaa T (2002) Multi-resolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24:971–987. doi: 10.1109/TPAMI.2002.1017623 CrossRefzbMATHGoogle Scholar
  32. 32.
    Oliveira Martins L, Silva AC, De Paiva AC, Gattass M (2009) Detection of breast masses in mammogram images using growing neural gas algorithm and Ripley’s K function. J Signal Process Syst 55:77–90. doi: 10.1007/s11265-008-0209-3 CrossRefGoogle Scholar
  33. 33.
    Oliver A, Freixenet J, Martí J, Pérez E, Pont J, Denton ERE, Zwiggelaar R (2010) A review of automatic mass detection and segmentation in mammographic images. Med Image Anal 14:87–110. doi: 10.1016/ CrossRefGoogle Scholar
  34. 34.
    Pal NR, Bezdek JC (1995) On cluster validity for the fuzzy c-means model. IEEE Trans Fuzzy Syst 3:370–379. doi: 10.1109/91.413225 CrossRefGoogle Scholar
  35. 35.
    Pereira DC, Ramos RP, Do Nascimento MZ (2014) Segmentation and detection of breast cancer in mammograms combining wavelet analysis and genetic algorithm. Comput Methods Prog Biomed 114:88–10. doi: 10.1016/j.cmpb.2014.01.014 CrossRefGoogle Scholar
  36. 36.
    Petrick N, Chan HP, Sahiner B, Wei D (1996a) An adaptive density-weighted contrast enhancement filter for mammographic breast mass detection. IEEE Trans Med Imaging 15:59–67. doi: 10.1109/42.481441 CrossRefGoogle Scholar
  37. 37.
    Petrick N, Chan HP, Wei D, Sahiner B, Helvie MA, Adler DD (1996b) Automated detection of breast masses on mammograms using adaptive contrast enhancement and texture classification. Med Phys 23:1685–1696. doi: 10.1118/1.597756 CrossRefGoogle Scholar
  38. 38.
    Rose C, Turi D, Williams A, Wolstencroft K, Taylor C (2006) Web services for the ddsm and digital mammography research. In: Digital Mammography pp 376–383Google Scholar
  39. 39.
    Sampaio WB et al (2011) Detection of masses in mammogram images using CNN, geostatistic functions and SVM. Comput Biol Med 41:653–664. doi: 10.1016/j.compbiomed.2005.12.004 CrossRefGoogle Scholar
  40. 40.
    de Sampaio WB, Silva AC, de Paiva AC, Gattass M (2015) Detection of masses in mammograms with adaption to breast density using genetic algorithm, phylogenetic trees, LBP and SVM. Expert Syst Appl 42:8911–8928. doi: 10.1016/j.eswa.2015.07.046 CrossRefGoogle Scholar
  41. 41.
    Sharma S, Khanna P (2015) Computer-aided diagnosis of malignant mammograms using Zernike moments and SVM. J Digit Imaging 28:77–90. doi: 10.1007/s10278-014-9719-7 CrossRefGoogle Scholar
  42. 42.
    Suckling J, Parker J, Dance D, Astley S, Hutt I, Boggis C, Ricketts I, Stamatakis E, Cerneaz N, Kok S, Taylor P (1994) The mammographic image analysis society digital mammogram database. Excerpta Med Int Congr Ser 1069:375–378Google Scholar
  43. 43.
    Surendiran B, Vadivel A (2012) Mammogram mass classification using various geometric shape and margin features for early detection of breast cancer. Int J Med Eng Inf 4:36–54. doi: 10.1504/IJMEI.2012.045302 Google Scholar
  44. 44.
    Tai SC, Chen ZS, Tsai WT (2014) An automatic mass detection system in mammograms based on complex texture features. IEEE J Biomed Health Inform 18:618–627. doi: 10.1109/JBHI.2013.2279097 CrossRefGoogle Scholar
  45. 45.
    Tang X (1998) Texture information in run length matrices. IEEE Trans Image Process 7:1602–1609. doi: 10.1109/83.725367 CrossRefGoogle Scholar
  46. 46.
    Wang D, Shi L, Heng PA (2009) Automatic detection of breast cancers in mammograms using structured support vector machines. Neurocomputing 72:3296–3302. doi: 10.1016/j.neucom.2009.02.015 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  • Kanchan Lata Kashyap
    • 1
    Email author
  • Manish Kumar Bajpai
    • 1
  • Pritee Khanna
    • 1
  1. 1.Computer Science and EngineeringIndian Institute of Information Technology, Design & ManufacturingJabalpurIndia

Personalised recommendations