An Automatic Computer-Aided Diagnosis System for Breast Cancer in Digital Mammograms via Deep Belief Network

  • Mugahed A. Al-antari
  • Mohammed A. Al-masni
  • Sung-Un Park
  • JunHyeok Park
  • Mohamed K. Metwally
  • Yasser M. Kadah
  • Seung-Moo Han
  • Tae-Seong KimEmail author
Original Article


Computer-aided diagnosis (CAD) offers assistance to radiologists in the interpretation of medical images. A CAD system learns the nature of different tissues and uses this information to diagnose abnormalities. In this paper, we propose a CAD system for breast cancer diagnosis via deep belief network (DBN) that automatically detects breast mass regions and recognizes them as normal, benign, or malignant. In this study, we utilize a standard digital database of mammography to evaluate our proposed DBN-based CAD system for breast cancer diagnosis. We utilize two techniques of ROI extraction: multiple mass regions of interest (ROIs) and whole mass ROIs. In the former technique, we randomly extract four ROIs with a size of 32 × 32 pixels from a detected mass. In the latter technique, the whole detected breast mass is utilized. A total of 347 statistical features are extracted for both techniques to train and test our proposed CAD system. For classification, we utilized linear discriminant analysis, quadratic discriminant analysis, and neural network classifiers as the conventional techniques. Finally, we employed DBN and compared the results. Our results demonstrate that the proposed DBN outperforms the conventional classifiers. The overall accuracies of a DBN are 92.86% and 90.84% for the two ROI techniques, respectively. The presented work shows the feasibility of a DBN-based CAD system for use as in the field of breast cancer diagnosis.


Breast cancer classification Digital mammography Computer-aided diagnosis (CAD) Automatic mass detection Deep learning Deep belief network (DBN) 



This work was supported by the Center for Integrated Smart Sensors funded by the Ministry of Science, ICT & Future Planning as Global Frontier Project (CISS- 2011-0031863). This work was supported by International Collaborative Research and Development Programme (funded by the Ministry of Trade, Industry and Energy (MOTIE, Korea) (N0002252)

Compliance with Ethical Standards

Conflict of interest

The authors declare that there is no conflict of interest regarding the publication of this paper.


  1. 1.
    Cheng, H., & Cui, M. (2004). Mass lesion detection with a fuzzy neural network. Pattern Recognition, 37(6), 1189–1200.CrossRefGoogle Scholar
  2. 2.
    Jalalian, A., Mashohor, S., Mahmud, H., Saripan, M., Rahman, A., Ramli, B., et al. (2013). Computer-aided detection/diagnosis of breast cancer in mammography and ultrasound: A review. Clinical Imaging, 37(3), 420–426.CrossRefGoogle Scholar
  3. 3.
    Verma, B. (2008). Novel network architecture and learning algorithm for the classification of mass abnormalities in digitized mammograms. Artificial Intelligence in Medicine, 42(1), 67–79.MathSciNetCrossRefGoogle Scholar
  4. 4.
    Grau, A., Vives, J., Font, A., & Ochoa, C. (2016). Positive psychological functioning in breast cancer: An integrative review. The Breast, 27, 136–168.CrossRefGoogle Scholar
  5. 5.
    Peng, Y., Yao, B., & Jiang, J. (2006). Knowledge-discovery incorporated evolutionary search for microcalcification detection in breast cancer diagnosis. Artificial Intelligence in Medicine, 37(1), 43–53.CrossRefGoogle Scholar
  6. 6.
    Junior, B., Rocha, D., Gattass, M., Silva, C., & Paiva, A. D. (2013). A mass classification using spatial diversity approaches in mammography images for false positive reduction. Expert Systems with Applications, 40(18), 7534–7543.CrossRefGoogle Scholar
  7. 7.
    Oliveira, F., Filho, A., Silva, A., Paiva, A., & Gattass, M. (2015). Classification of breast regions as mass and non-mass based on digital mammograms using taxonomic indexes and SVM. Computers in Biology and Medicine, 57, 42–53.CrossRefGoogle Scholar
  8. 8.
    Al-antari, M., AL-masni, M., & Kadah, Y. (2017). Hybrid model of computer-aided breast cancer diagnosis from digital mammograms. Journal of Scientific and Engineering Research, 4(2), 114–126.Google Scholar
  9. 9.
    Balanica, V., Dumitrache, I., & Preziosi, L. (2013). Breast cancer diagnosis based on spiculation feature and neural network techniques. International Journal of Computers Communications & Control, 8(3), 354–365.CrossRefGoogle Scholar
  10. 10.
    Al-Olfe, M., Al-Akwaa, F., Mohamed, W., & Kadah, Y. (2010). Computer-aided diagnosis of digital mammography images using unsupervised clustering and biclustering techniques. Proceedings SPIE conference on Medical Imaging, 7624, 1–6.Google Scholar
  11. 11.
    Kang, Y., Ke, L., & Mu, N. (2010). Mass computer-aided diagnosis method in mammogram based on texture features. In Proceedings of IEEE BMEI Conference on biomedical engineering and informatics (BMEI) (vol. 1, pp. 354–357).Google Scholar
  12. 12.
    Sharma, S., & Khanna, P. (2015). Computer-aided diagnosis of malignant mammograms using Zernike moments and SVM. Journal of Digital Imaging, 28(1), 77–90.CrossRefGoogle Scholar
  13. 13.
    Arevalo, J., González, F., Ramos-Pollan, R., Oliveira, J., & Lopez, M. (2016). Representation learning for mammography mass lesion classification with convolutional neural networks. Computer Methods and Programs in Biomedicine, 127, 248–257.CrossRefGoogle Scholar
  14. 14.
    Jiao, Z., Gao, X., Wang, Y., & Li, J. (2016). A deep feature based framework for breast masses classification. Neurocomputing, 167, 221–231.CrossRefGoogle Scholar
  15. 15.
    Kooi, T., Gubern A., Mordang J., Mann R., Pijnappel R., Schuur K, Heeten, A., & Karssemeijer N. (2016). A comparison between a deep convolutional neural network and radiologists for classifying regions of interest in mammography. In A. Tingberg et al. (Eds.), IWDM 2016, LNCS 9699 (pp. 51–56). Switzerland: Springer.Google Scholar
  16. 16.
    Hinton, G., Osindero, S., & The, Y. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18(7), 1527–1554.MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Heath, M., Bowyer, K., Kopans, D., Moore, R., & Kegelmeyer, W. (2001). The digital database for screening mammography. In Proceedings of the 5th international workshop on digital mammography (pp. 212–218).Google Scholar
  18. 18.
    Tortajada, M., Oliver, A., Marti, R., Ganau, S., Tortajada, L., Sentis, M., et al. (2014). Breast peripheral area correction in digital mammograms. Computers in Biology and Medicine, 50, 32–40.CrossRefGoogle Scholar
  19. 19.
    Wu, T., Moore, R., & Kopans, D. (2010). Multi-threshold peripheral equalization method and apparatus for digital mammography and breast Tomosynthesis. Google patents, US Patent 7, 764, 823.Google Scholar
  20. 20.
    Gonzalez, R., & Woods, R. (2008). Digital image processing (3rd ed.). USA: Prentice Hall. ISBN 013168728.Google Scholar
  21. 21.
    Tommasi, T., Orabona, F., & Caputo, B. (2008). Discriminative cue integration for medical image annotation. Pattern Recognition Letters, 29, 1996–2002.CrossRefGoogle Scholar
  22. 22.
    Kadah, Y., Farag, A., Zurada, J., Badawi, A., & Yousef, A. (1996). Classification algorithms for quantitative tissue characterization of diffuse liver disease from ultrasound images. IEEE Transactions on Medical Imaging, 15(4), 466–478.CrossRefGoogle Scholar
  23. 23.
    Verma, B., McLeod, P., & Klevansky, A. (2010). Classification of benign and malignant patterns in digital mammograms for the diagnosis of breast cancer. Expert Systems with Applications, 37(4), 3344–3541.CrossRefGoogle Scholar
  24. 24.
    Nanni, L., Brahnam, S., & Lumini, A. (2012). A very high performance system to discriminate tissues in mammograms as benign and malignant. Expert Systems with Applications, 39(2), 1968–1971.CrossRefGoogle Scholar
  25. 25.
    Bueno, G., Vallez, N., Deniz, O., Esteve, P., Rienda, M., Arias, M., et al. (2011). Automatic breast parenchymal density classification integrated into a CADe system. International Journal of Computer Assisted Radiology and Surgery, 6(3), 309–318.CrossRefGoogle Scholar
  26. 26.
    Ramos, R., Nascimento, M., & Pereira, D. (2012). Texture extraction: An evaluation of ridgelet, wavelet and co-occurrence based methods applied to mammograms. Expert Systems with Applications, 39, 11036–11047.CrossRefGoogle Scholar
  27. 27.
    Vallez, N., Bueno, G., Deniz, O., Dorado, J., Seoane, J., Pazos, A., et al. (2014). Breast density classification to reduce false positives in CADe systems. Computer Methods and Programs in Biomedicine, 113, 569–584.CrossRefGoogle Scholar
  28. 28.
    Kumar, I., Virmani, J., & Bhadauria, H. (2015). A Review of Breast Density Classification Methods. In Proceedings of IEEE international conference on computing for sustainable global development (INDIACom) (pp. 1960–1967).Google Scholar
  29. 29.
    Zhang, P., Verma, B., & Kumar, K. (2005). Neural vs. statistical classifier in conjunction with genetic algorithm based feature selection. Pattern Recognition Letters, 26(7), 909–919.CrossRefGoogle Scholar
  30. 30.
    Dheeba, J., Singh, N., & Selvi, S. (2014). Computer-aided detection of breast cancer on mammograms: A swarm intelligence optimized wavelet neural network approach. Journal of Biomedical Informatics, 49, 45–52.CrossRefGoogle Scholar
  31. 31.
    Haralick, R., Shanmugam, K., & Dinstein, I. (1973). Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, 3(6), 610–662.CrossRefGoogle Scholar
  32. 32.
    Ou, X., Pan, W., & Xiao, P. (2014). In vivo skin capacitive imaging analysis by using grey level co-occurrence matrix (GLCM). International Journal of Pharmaceutics, 460, 28–32.CrossRefGoogle Scholar
  33. 33.
    Duin, R., Juszczak, P., Paclik, P., Pekalska, E., Ridder, D., Tax, D., & Verzakov, S. (2007). PRTools4.1: A Matlab toolbox for pattern recognition. Delft: Delft University of Technology.Google Scholar
  34. 34.
    Rao, C. R. (1948). The utilization of multiple measurements in problems of biological classification. Journal of the Royal Statistical Society, 10(2), 159–203.MathSciNetzbMATHGoogle Scholar
  35. 35.
    Thomas, M. C. (1965). Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition. IEEE Transactions on Electronic Computers, 14(3), 326–334.Google Scholar
  36. 36.
    Fischer, A., & Igel, C. (2014). Training restricted Boltzmann machines: An introduction. Pattern Recognition, 47(1), 25–39.CrossRefzbMATHGoogle Scholar
  37. 37.
    Nam, S., Park, S., Park, J., & Kim, T-S. (2015). A single depth sensor based human activity recognition via deep belief network. In Proceedings of WCSET of the 4th world conference on applied sciences, engineering & technology (pp. 15–19).Google Scholar
  38. 38.
    Sampat, M., Patel, A., Wang, Y., Gupta, S., Kan, C., Bovik, A., et al. (2009). Indexes for three-class classification performance assessment—An empirical comparison. IEEE Transactions on Information Technology in Biomedicine, 13(3), 300–312.CrossRefGoogle Scholar
  39. 39.
    Litjens, G., Sanchez, C., Timofeeva, N., Hermsen, M., Nagtegaal, I., Kovacs, I., et al. (2016). Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis. Scientific Reports, 6, 1–11.CrossRefGoogle Scholar
  40. 40.
    Mavroforakis, M., Georgiou, H., Dimitropoulos, N., Cavouras, D., & Theodoridis, S. (2006). Mammographic masses characterization based on localized texture and dataset fractal analysis using linear, neural and support vector machine classifiers. Artificial Intelligence in Medicine, 37(2), 145–162.CrossRefGoogle Scholar
  41. 41.
    Rojas-Domínguez, A., & Nandi, A. (2009). Development of tolerant features for characterization of masses in mammograms. Computers in Biology and Medicine, 39(8), 678–688.CrossRefGoogle Scholar
  42. 42.
    Tome, D., Monti, F., Baroffio, L., Bondi, L., Tagliasacchi, M., & Tubaro, S. (2016). Deep convolutional neural networks for pedestrian detection. Signal Processing: Image Communication. doi: 10.1016/j.image.2016.05.007.
  43. 43.
    Wang, Y., Zhou, S., Gong, Y., & Zheng, N. (2016). Incorporating image priors with deep convolutional neural networks for image super-resolution. Neurocomputing, 194, 340–347.CrossRefGoogle Scholar

Copyright information

© Taiwanese Society of Biomedical Engineering 2017

Authors and Affiliations

  1. 1.Department of Biomedical Engineering, College of Electronics and InformationKyung Hee UniversityYonginRepublic of Korea
  2. 2.Department of Electrical and Computer EngineeringKing Abdulaziz UniversityJeddahKingdom of Saudi Arabia

Personalised recommendations