Reduction of false positives in the screening CAD tool for microcalcification detection


Breast cancer is one of the leading causes of cancer deaths among women worldwide. Early diagnosis of breast cancer can help in reducing the mortality rate. The major challenge in the early diagnosis of breast cancer is the fewer number of radiologists available per million population in developing countries. The total number of radiologists is less than 30 in many third world countries. Since majority of the screening mammograms are normal or do not show any cancer signs, there is need of a screening computer-aided diagnosis (CAD) tool that can detect normal mammograms correctly and thereby reduce the burden on radiologists. Thus, a screening CAD is developed that is able to detect microcalcification clusters in mammogram with 100% sensitivity on the subset of DDSM, INbreast and PGIMER-IITKGP databases at lower false positives as compared with state of the art methods. The synthetic minority over-sampling technique and the majority class under-sampling based on data distribution are used to improve the classifiers performance by reducing the false positives. An approach based on principal component analysis is proposed to further reduce the false positives by removing the vascular calcifications that are not of any clinical significance and may increase the false positives.

This is a preview of subscription content, access via your institution.

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6


  1. 1

    Bray F, Ferlay J, Soerjomataram I, Siegel R L, Torre L A and Jemal A 2018 Global cancer statistics 2018: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J. Clin. 68: 394–424

    Article  Google Scholar 

  2. 2

    Nalawade Y V 2009 Evaluation of breast calcifications. Indian J. Radiol. Imaging 19: 282–286

    Article  Google Scholar 

  3. 3

    Pace L E and Keating N L 2014 A systematic assessment of benefits and risks to guide breast cancer screening decisions. J. Am. Med. Assoc. 311: 1327–1335

    Article  Google Scholar 

  4. 4

    Oeffinger K C, Fontham E T H, Etzioni R, Herzig A, Michaelson J S, Shih Y T, Walter L C, Church T R, Flowers C R, LaMonte S J, Wolf A M D, DeSantis C, Lortet-Tieulent J, Andrews K, Manassaram-Baptiste D, Saslow D, Smith R A, Brawley O W and Wender R 2015 Breast cancer screening for women at average risk: 2015 guideline update from the American Cancer Society. J. Am. Med. Assoc. 314: 1599–1614

    Article  Google Scholar 

  5. 5

    Cox R F, Hernandez-Santana A, Ramdass S, McMahon G, Harmey J H and Morgan M P 2012 Microcalcifications in breast cancer: novel insights into the molecular mechanism and functional consequence of mammary mineralisation. Br. J. Cancer 106: 525–537

    Article  Google Scholar 

  6. 6

    Bulas D and Shah N 2014 International pediatric radiology education: who should be trained, and how? Pediatr. Radiol. 44: 639–641

    Article  Google Scholar 

  7. 7

    Papadopoulos A, Fotiadis D I and Costaridou L 2008 Improvement of microcalcification cluster detection in mammography utilizing image enhancement techniques. Comput. Biol. Med. 38: 1045–1055

    Article  Google Scholar 

  8. 8

    Kim J K and Park H W 1999 Statistical textural features for detection of microcalcifications in digitized mammograms. IEEE Trans. Med. Imaging 18: 231–238

    Article  Google Scholar 

  9. 9

    Soltanian-Zadeh H, Rafiee-Rad F and Pourabdollah-Nejad D S 2004 Comparison of multiwavelet, wavelet, Haralick, and shape features for microcalcification classification in mammograms. Pattern Recogn. 37: 1973–1986

    Article  Google Scholar 

  10. 10

    Yu S and Guan L 2000 A CAD system for the automatic detection of clustered microcalcifications in digitized mammogram films. IEEE Trans. Med. Imaging 19: 115–126

    Article  Google Scholar 

  11. 11

    El-Naqa I, Yang Y, Wernick M N, Galatsanos N P and Nishikawa R M 2002 A support vector machine approach for detection of microcalcifications. IEEE Trans. Med. Imaging 21: 1552–1563

    Article  Google Scholar 

  12. 12

    Wei L, Yang Y, Nishikawa R M, Vernick M N and Edwards A 2005 Relevance vector machine for automatic detection of clustered microcalcifications. IEEE Trans. Med. Imaging 24: 1278–1285

    Article  Google Scholar 

  13. 13

    Peng R, Chen H and Varshney P K 2009 Noise-enhanced detection of micro-calcifications in digital mammograms. IEEE J. Sel. Topics Signal Process. 3: 62–73

    Article  Google Scholar 

  14. 14

    Nakayama R, Uchiyama Y, Yamamoto K, Watanabe R and Namba K 2006 Computer-aided diagnosis scheme using a filter bank for detection of microcalcification clusters in mammograms. IEEE Trans. Biomed. Eng. 53: 273–283

    Article  Google Scholar 

  15. 15

    Oliver A, Torrent A, Lladó X, Tortajada M, Tortajada L, Sentís M, Freixenet J and Zwiggelaar R 2012 Automatic microcalcification and cluster detection for digital and digitised mammograms. Knowl. Based Syst. 28: 68–75

    Article  Google Scholar 

  16. 16

    Zhang X, Homma N, Goto S, Kawasumi Y, Ishibashi T, Abe M, Sugita N and Yoshizawa M 2013 A hybrid image filtering method for computer-aided detection of microcalcification clusters in mammograms. J. Med. Eng.

    Article  Google Scholar 

  17. 17

    Shin S, Lee S and Yun I D 2014 Classification based micro-calcification detection using discriminative restricted boltzmann machine in digitized mammograms. In: Proceedings of Medical Imaging, SPIE, p. 90351L

  18. 18

    Liu X, Mei M, Liu J and Hu W 2015 Microcalcification detection in full-field digital mammograms with pfcm clustering and weighted SVM-based method. EURASIP J. Adv. Signal Process. 2015: 1

    Article  Google Scholar 

  19. 19

    Guo Y, Dong M, Yang Z, Gao X, Wang K, Luo C, Ma Y and Zhang J 2016 A new method of detecting micro-calcification clusters in mammograms using contourlet transform and non-linking simplified PCNN. Comput. Methods Prog. Biomed. 130: 31–45

    Article  Google Scholar 

  20. 20

    Mordang J, Janssen T, Bria A, Kooi T, Gubern-Mérida A and Karssemeijer N 2016 Automatic microcalcification detection in multi-vendor mammography using convolutional neural networks. In: Proceedings of IWDM, pp. 35–42

  21. 21

    Karale V A, Mukhopadhyay S, Singh T, Khandelwal N and Sadhu A 2017 Automated detection of microcalcification clusters in mammograms. In: Proceedings of Medical Imaging, SPIE, vol. 10134, p. 101342R

  22. 22

    Wang J, Nishikawa R M and Yang Y 2017 Global detection approach for clustered microcalcifications in mammograms using a deep learning network. J. Med. Imaging 4: 024501

    Article  Google Scholar 

  23. 23

    Wang J and Yang Y 2018 A context-sensitive deep learning approach for microcalcification detection in mammograms. Pattern Recogn. 78: 12–22

    Article  Google Scholar 

  24. 24

    Karale V A, Ebenezer J P, Chakraborty J, Singh T, Sadhu A, Khandelwal N and Mukhopadhyay S 2019 A screening CAD tool for the detection of microcalcification clusters in mammograms J. Digit. Imaging 32: 728–745

    Article  Google Scholar 

  25. 25

    Rose C, Turi D, Williams A, Wolstencroft K and Taylor C 2006 Web services for the DDSM and digital mammography research. In: Proceedings of the 8th International Conference on Digital Mammography, IWDM’06. Berlin–Heidelberg: Springer, pp. 376–383

  26. 26

    Moreira I C, Amaral I, Domingues I, Cardoso A, Cardoso M J and Cardoso J S 2012 INbreast: toward a full-field digital mammographic database. Acad. Radiol. 19: 236–248

    Article  Google Scholar 

  27. 27

    Guan P P and Yan H 2012 A hierarchical multilevel thresholding method for edge information extraction using fuzzy entropy. Int. J. Mach. Learn. Cyb. 3: 297–305

    Article  Google Scholar 

  28. 28

    Seth S and Mukhopadhyay S 2010 Multi-level thresholding-based breast segmentation in mammograms. In: Proceedings of the International Conference on Communication, Computers, and Devices (ICCCD-2010), India

  29. 29

    Ciecholewski M 2017 Microcalcification segmentation from mammograms: a morphological approach. J. Digit. Imaging 30: 172–184

    Article  Google Scholar 

  30. 30

    Shen L, Rangayyan R M and Desautels J L 1992 Shape analysis of mammographic calcifications. In: Proceedings of the Fifth Annual IEEE Symposium on Computer-Based Medical Systems, IEEE, pp. 123–128

  31. 31

    Gonzalez R C and Woods R E 2002 Digital image processing, 2nd ed. Upper Saddle River, NJ: Prentice-Hall

    Google Scholar 

  32. 32

    Haralick R M, Shanmugam K and Dinstein I 1973 Textural features for image classification. IEEE Trans. Syst. Man Cyb. 3: 610–622

    Article  Google Scholar 

  33. 33

    Dalal N and Triggs B 2005 Histograms of oriented gradients for human detection. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), IEEE, vol. 1, pp. 886–893

  34. 34

    Ding C and Peng H 2005 Minimum redundancy feature selection from microarray gene expression data. J. Bioinf. Comput. Biol. 3: 185–205

    Article  Google Scholar 

  35. 35

    Velez D R, White B C, Motsinger A A, Bush W S, Ritchie M D, Williams S M and Moore J H 2007 A balanced accuracy function for epistasis modeling in imbalanced datasets using multifactor dimensionality reduction. Genet. Epidemiol. 31: 306–315

    Article  Google Scholar 

  36. 36

    Chawla N V, Bowyer K W, Hall L O, and Kegelmeyer W P 2002 SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16: 321–357

    Article  Google Scholar 

  37. 37

    Cristianini N and Shawe-Taylor J 2000 An introduction to support vector machines and other kernel-based learning methods. Cambridge: Cambridge University Press

    Google Scholar 

  38. 38

    Woods K S, Solka J L, Priebe C E, Doss C C, Bowyer K W and Clarke L P 1993 Comparative evaluation of pattern recognition techniques for detection of microcalcifications. Int. J. Pattern Recogn. Artif. Intell. 7(6): 841–852

    Article  Google Scholar 

  39. 39

    Lai K C, Slanetz P J and Eisenberg R L 2012 Linear breast calcifications. Am. J. Roentgenol. 199: W151–W157

    Article  Google Scholar 

  40. 40

    Marrocco C, Molinara M, D’Elia C and Tortorella F 2010 A computer-aided detection system for clustered microcalcifications. Artif. Intell. Med. 50: 23–32

    Article  Google Scholar 

  41. 41

    Gallardo-Caballero R, García-Orellana C J, García-Manso A, González-Velasco H M and Macías-Macías M 2012 Independent component analysis to detect clustered microcalcification breast cancers. Sci. World J. 2012: 540457

    Article  Google Scholar 

Download references

Author information



Corresponding author

Correspondence to Sudipta Mukhopadhyay.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Karale, V.A., Singh, T., Sadhu, A. et al. Reduction of false positives in the screening CAD tool for microcalcification detection. Sādhanā 45, 44 (2020).

Download citation


  • 2D-NEO
  • nonlinear energy operator
  • HOG
  • CAD
  • breast cancer
  • microcalcifications