Deep Learning for Automatic Detection of Abnormal Findings in Breast Mammography

  • Ayelet Akselrod-Ballin
  • Leonid. Karlinsky
  • Alon Hazan
  • Ran Bakalo
  • Ami Ben Horesh
  • Yoel Shoshan
  • Ella Barkan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10553)

Abstract

Automatic identification of abnormalities is a key problem in medical imaging. While the majority of previous work in mammography has focused on classification of abnormalities rather than detection and localization, here we introduce a novel deep learning method for detection of masses and calcifications. The power of this approach comes from generating an ensemble of individual Faster-RCNN models each trained for a specific set of abnormal clinical categories, together with extending a modified two stage Faster-RCNN scheme to a three stage cascade. The third stage being an additional classifier working directly on the image pixels with the handful of sub-windows generated by the first two stages. The performance of the algorithm is evaluated on the INBreast benchmark and on a large internal multi-center dataset. Quantitative results compete well with state of the art in terms of accuracy. Computationally the methods runs significantly faster than current state-of-the art techniques.

References

  1. 1.
    American Cancer Society: 2015 Cancer Facts and Figures. American Cancer Society, Atlanta (2015)Google Scholar
  2. 2.
    Saranya, R., Bharathi, M., Showbana, R.: Automatic detection and classification of microcalcification on mammographic images. IOSR J. Electron. Commun. Eng. (IOSR-JECE) 9(3), 65–71 (2014)Google Scholar
  3. 3.
    Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: NIPS, vol. 25, pp. 1097–1105 (2012)Google Scholar
  4. 4.
    Simonyan K., Zisserman A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:1409.1556 (2014)
  5. 5.
    Girshick R., Donahue J., Darrell T., Malik J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580–587 (2014)Google Scholar
  6. 6.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS. arXiv:1506.01497 (2015)
  7. 7.
    Uijlings, J.R., Van de Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vis. 104(2), 154–171 (2013)CrossRefGoogle Scholar
  8. 8.
    Girshick R.: Fast R-CNN. In: ICCV, pp. 1440–1448 (2015)Google Scholar
  9. 9.
    Erhan, D., Szegedy, C., Toshev, A., Anguelov, D.: Scalable object detection using deep neural networks. In: CVPR, pp. 2155–2162 (2014)Google Scholar
  10. 10.
    Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)Google Scholar
  11. 11.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, Boston, MA, pp. 3431–3440 (2015)Google Scholar
  12. 12.
    Gulshan, V., Peng, L., Coram, M., et al.: Development and validation of a DL algorithm for detection of diabetic retinopathy in retinal fundus photos. JAMA 316, 2402–2410 (2016)CrossRefGoogle Scholar
  13. 13.
    Esteva, A., Kuprel, B., Novoa, R.A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017(542), 115–118 (2017)CrossRefGoogle Scholar
  14. 14.
    Giger, M.L., Karssemeijer, N., Schnabel, J.A.: Breast image analysis for risk assessment, detection, diagnosis, and treatment of cancer. Annu. Rev. Biomed. Eng. 15, 327–357 (2013)CrossRefGoogle Scholar
  15. 15.
    Oliver, A., Freixenet, J., Marti, J., Perez, E., Pont, J., Denton, E., Zwiggelaar, R.: A review of automatic mass detection and segmentation in MG images. MIA 14, 87–110 (2010)Google Scholar
  16. 16.
    Dhungel, N., Carneiro, G., Bradley, A.P.: Automated mass detection in mammograms using cascaded deep learning and random forests. In: DICTA, pp. 1–8 (2015) Google Scholar
  17. 17.
    Lu, Z., Carneiro, G., Dhungel, N., Bradley, A.P.: Automated detection of individual microcalcifications from MG using a multistage cascade approach. arXiv:1610.02251v (2016)
  18. 18.
    Dhungelz, N., Carneiroy, G., Bradley, A.P.: Fully automated classification of mammograms using deep residual neural networks. In: ISBI 2017 (2017)Google Scholar
  19. 19.
    Moreira, I.C., Amaral, I., Domingues, I., Cardoso, A., Cardoso, M.J., Cardoso, J.S.: INBreast: toward a full-field digital MG database. Acad. Radiology. 19(2), 236–248 (2012)CrossRefGoogle Scholar
  20. 20.
    Akselrod-Ballin, A., Karlinsky, L., Alpert, S., Hasoul, S., Ben-Ari, R., Brakan, E.: A region based convolutional network for tumor detection and classification in breast mammography. In: DLMIA (2016)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Ayelet Akselrod-Ballin
    • 1
  • Leonid. Karlinsky
    • 1
  • Alon Hazan
    • 1
  • Ran Bakalo
    • 1
  • Ami Ben Horesh
    • 1
  • Yoel Shoshan
    • 1
  • Ella Barkan
    • 1
  1. 1.IBM ResearchHaifaIsrael

Personalised recommendations