A Multi-scale CNN and Curriculum Learning Strategy for Mammogram Classification

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10553)

Abstract

Screening mammography is an important front-line tool for the early detection of breast cancer, and some 39 million exams are conducted each year in the United States alone. Here, we describe a multi-scale convolutional neural network (CNN) trained with a curriculum learning strategy that achieves high levels of accuracy in classifying mammograms. Specifically, we first train CNN-based patch classifiers on segmentation masks of lesions in mammograms, and then use the learned features to initialize a scanning-based model that renders a decision on the whole image, trained end-to-end on outcome data. We demonstrate that our approach effectively handles the “needle in a haystack” nature of full-image mammogram classification, achieving 0.92 AUROC on the DDSM dataset.

References

  1. 1.
    Arevalo, J., Gonzalez, F., Ramos-Pollan, R., et al.: Representation learning for mammography mass lesion classification with convolutional neural networks. Comput. Methods Programs Biomed. 127, 248–257 (2016)CrossRefGoogle Scholar
  2. 2.
    Bengio, Y., Louradour, J., Collobert, R., et al.: Curriculum learning. In: ICML (2009)Google Scholar
  3. 3.
    Berry, D.A., Cronin, K.A., Plevritis, S.K., et al.: Effect of screening and adjuvant therapy on mortality from breast cancer. In: NEJM (2005)Google Scholar
  4. 4.
    Brewer, N.T., Salz, T., Lillie, S.E.: Systematic review: the long-term effects of false-positive mammograms. Ann. Internal Med. 146(7), 502–510 (2007)CrossRefGoogle Scholar
  5. 5.
    Cancer Stat Facts: Female breast cancer. https://seer.cancer.gov/
  6. 6.
    Carneiro, G., Nascimento, J., Bradley, A.P.: Unregistered multiview mammogram analysis with pre-trained deep learning models. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 652–660. Springer, Cham (2015). doi: 10.1007/978-3-319-24574-4_78 CrossRefGoogle Scholar
  7. 7.
    Dhungel, N., Carneiro, G., Bradley, A.P.: Deep structured learning for mass segmentation from mammograms. arXiv:1410.7454 (2014)
  8. 8.
    Dhungel, N., Carneiro, G., Bradley, A.P.: Automated mass detection in mammograms using cascaded deep learning and random forests. In: DICTA (2015)Google Scholar
  9. 9.
    Elmore, J.G., Jackson, S.L., Abraham, L., et al.: Variability in interpretive performance at screening mammography and radiologists characteristics associated with accuracy. Radiology 253(3), 587–589 (2009)CrossRefGoogle Scholar
  10. 10.
    Geras, K.J., Wolfson, S., Kim, S.G., et al.: High-resolution breast cancer screening with multi-view deep convolutional neural networks. arXiv:1703.07047 (2017)
  11. 11.
    He, K., Zhang, X., Ren, X., Sun, J.: Deep residual learning for image recognition. arXiv:1512.03385 (2012)
  12. 12.
    Heath, M., Bowyer, K., Kopans, D., et al.: The digital database for screening mammography. In: Proceedings of the Fifth International Workshop on Digital Mammography (2001)Google Scholar
  13. 13.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167 (2015)
  14. 14.
    Kooi, T., Litjens, G., van Ginneken, B., et al.: Large scale deep learning for computer aided detection of mammographic lesions. Med. Image Anal. 35, 303–312 (2017)CrossRefGoogle Scholar
  15. 15.
    Lehman, C., Arao, R., Sprague, B., et al.: National performance benchmarks for modern screening digital mammography: update from the breast cancer surveillance consortium. Radiology 283(1), 49–58 (2017)CrossRefGoogle Scholar
  16. 16.
    Levy, D., Jain, A.: Breast mass classification from mammograms using deep convolutional neural networks. arXiv:1612.00542 (2016)
  17. 17.
    Mordang, J.-J., Janssen, T., Bria, A., Kooi, T., Gubern-Mérida, A., Karssemeijer, N.: Automatic microcalcification detection in multi-vendor mammography using convolutional neural networks. In: Tingberg, A., Lång, K., Timberg, P. (eds.) IWDM 2016. LNCS, vol. 9699, pp. 35–42. Springer, Cham (2016). doi: 10.1007/978-3-319-41546-8_5 Google Scholar
  18. 18.
    Moreira, I.C., Amaral, I., Domingues, I., et al.: INbreast: toward a full-field digital mammographic database. Acad. Radiol. 19(2), 236–248 (2012)CrossRefGoogle Scholar
  19. 19.
    Myers, E.R., Moorman, P., Gierisch, J.M., et al.: Benefits and harms of breast cancer screening: a systematic review. JAMA 314(15), 1615–1634 (2015)CrossRefGoogle Scholar
  20. 20.
    Nishikawa, R.M.: Current status and future directions of computer-aided diagnosis in mammography. Comput. Med. Imaging Graph. 31, 224–235 (2007)CrossRefGoogle Scholar
  21. 21.
    Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)CrossRefGoogle Scholar
  22. 22.
    Russakovsky, O., Deng, J., Su, H., et al.: ImageNet large scale visual recognition challenge. arXiv:1409.0575 (2014)
  23. 23.
    Szegedy, C., Liu, W., et al.: Going deeper with convolutions. In: CVPR (2015)Google Scholar
  24. 24.
    Szegedy, C., Vanhoucke, V., Ioffe, S., et al.: Rethinking the inception architecture for computer vision. arXiv:1512.00567 (2015)
  25. 25.
    Tieleman, T., Hinton, G.: Lecture 6.5 - rmsprop, coursera. Neural networks for machine learning (2012). http://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf
  26. 26.
    U.S. Breast Cancer Statistics. http://www.breastcancer.org/
  27. 27.
    Yi, D., Sawyer, R.L., Cohn III., D., et al.: Optimizing and visualizing deep learning for benign/malignant classification in breast tumors. arXiv:1705.06362 (2017)
  28. 28.
    Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv:1605.07146 (2016)
  29. 29.
    Zhu, W., Lou, Q., Vang, Y.S., Xie, X.: Deep multi-instance networks with sparse label assignment for whole mammogram classification. arXiv:1612.05968 (2016)
  30. 30.
    Zhu, W., Xie, X.: Adversarial deep structural networks for mammographic mass segmentation. arXiv:1612.05970 (2016)

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Harvard UniversityCambridgeUSA
  2. 2.DeepHealth Inc.CambridgeUSA

Personalised recommendations