Advertisement

Conditional Infilling GANs for Data Augmentation in Mammogram Classification

  • Eric WuEmail author
  • Kevin Wu
  • David Cox
  • William Lotter
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11040)

Abstract

Deep learning approaches to breast cancer detection in mammograms have recently shown promising results. However, such models are constrained by the limited size of publicly available mammography datasets, in large part due to privacy concerns and the high cost of generating expert annotations. Limited dataset size is further exacerbated by substantial class imbalance since “normal” images dramatically outnumber those with findings. Given the rapid progress of generative models in synthesizing realistic images, and the known effectiveness of simple data augmentation techniques (e.g. horizontal flipping), we ask if it is possible to synthetically augment mammogram datasets using generative adversarial networks (GANs). We train a class-conditional GAN to perform contextual in-filling, which we then use to synthesize lesions onto healthy screening mammograms. First, we show that GANs are capable of generating high-resolution synthetic mammogram patches. Next, we experimentally evaluate using the augmented dataset to improve breast cancer classification performance. We observe that a ResNet-50 classifier trained with GAN-augmented training data produces a higher AUROC compared to the same model trained only on traditionally augmented data, demonstrating the potential of our approach.

Notes

Acknowledgements

This work was supported by the National Science Foundation (NSF IIS 1409097).

References

  1. 1.
    Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. IJCV 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Goodfellow, I.J., et al.: Generative adversarial netsGoogle Scholar
  3. 3.
    Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: NIPS, pp. 5769–5779 (2017)Google Scholar
  4. 4.
    Berthelot, D., Schumm, T., Metz, L.: Began: boundary equilibrium generative adversarial networks. arXiv preprint arXiv:1703.10717 (2017)
  5. 5.
    Peng, X., Tang, Z., Yang, F., Feris, R.S., Metaxas, D.: Jointly optimize data augmentation and network training: adversarial data augmentation in human pose estimation. In: CVPR (2018)Google Scholar
  6. 6.
    Yu, A., Grauman, K.: Semantic jitter: dense supervision for visual comparisons via synthetic images. Technical report (2017)Google Scholar
  7. 7.
    Wang, X., Shrivastava, A., Gupta, A.: A-fast-RCNN: hard positive generation via adversary for object detection. arXiv, vol. 2 (2017)Google Scholar
  8. 8.
    Wang, Y.-X., Girshick, R., Hebert, M., Hariharan, B.: Low-shot learning from imaginary data. arXiv preprint arXiv:1801.05401 (2018)
  9. 9.
    Antoniou, A., Storkey, A., Edwards, H.: Data augmentation generative adversarial networks. arXiv preprint arXiv:1711.04340 (2017)
  10. 10.
    Wolterink, J.M., Dinkla, A.M., Savenije, M.H.F., Seevinck, P.R., van den Berg, C.A.T., Išgum, I.: Deep MR to CT synthesis using unpaired data. In: Tsaftaris, S.A., Gooya, A., Frangi, A.F., Prince, J.L. (eds.) SASHIMI 2017. LNCS, vol. 10557, pp. 14–23. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-68127-6_2CrossRefGoogle Scholar
  11. 11.
    Nie, D., et al.: Medical image synthesis with context-aware generative adversarial networks. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 417–425. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66179-7_48CrossRefGoogle Scholar
  12. 12.
    Frid-Adar, M., Klang, E., Amitai, M., Goldberger, J., Greenspan, H.: Synthetic data augmentation using GAN for improved liver lesion classification. arXiv preprint arXiv:1801.02385 (2018)
  13. 13.
    Guibas, J.T., Virdi, T.S., Li, P.S.: Synthetic medical images from dual generative adversarial networks. arXiv preprint arXiv:1709.01872 (2017)
  14. 14.
    Hou, L., Agarwal, A., Samaras, D., Kurc, T.M., Gupta, R.R., Saltz, J.H.: Unsupervised histopathology image synthesis. arXiv (2017)Google Scholar
  15. 15.
    Salehinejad, H., Valaee, S., Dowdell, T., Colak, E., Barfett, J.: Generalization of deep neural networks for chest pathology classification in x-rays using generative adversarial networks. arXiv preprint arXiv:1712.01636 (2017)
  16. 16.
    Cancer.gov: Cancer facts and figures, 2015–2016 (2016)Google Scholar
  17. 17.
    Ribli, D., Horváth, A., Unger, Z., Pollner, P., Csabai, I.: Detecting and classifying lesions in mammograms with deep learning. Sci. Rep. 8(1), 4165 (2018)CrossRefGoogle Scholar
  18. 18.
    Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: NIPS, pp. 2234–2242 (2016)Google Scholar
  19. 19.
    Kodali, N., Abernethy, J., Hays, J., Kira, Z.: How to train your dragan. arXiv preprint arXiv:1705.07215 (2017)
  20. 20.
    Chen, Q., Koltun, V.: Photographic image synthesis with cascaded refinement networks. In: ICCV 2017, pp. 1520–1529. IEEE (2017)Google Scholar
  21. 21.
    Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)
  22. 22.
    Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network. arXiv (2015)Google Scholar
  23. 23.
    Lotter, W., Sorensen, G., Cox, D.: A multi-scale CNN and curriculum learning strategy for mammogram classification. In: Cardoso, M.J., et al. (eds.) DLMIA/ML-CDS -2017. LNCS, vol. 10553, pp. 169–177. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-67558-9_20CrossRefGoogle Scholar
  24. 24.
    Nikulin, Y.: DM challenge yaroslav nikulin (therapixel) (2017). Synapse.org
  25. 25.
    Shen, L.: End-to-end training for whole image breast cancer diagnosis using an all convolutional design. arXiv preprint arXiv:1708.09427 (2017)
  26. 26.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  27. 27.
    Goodfellow, I., et al.: Generative adversarial nets. In: NIPSGoogle Scholar
  28. 28.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  29. 29.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)Google Scholar
  30. 30.
    DeLong, E.R., DeLong, D.M., Clarke-Pearson, D.L.: Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44(3), 837–845 (1988)CrossRefGoogle Scholar
  31. 31.
    Zhu, W., Lou, Q., Vang, Y.S., Xie, X.: Deep multi-instance networks with sparse label assignment for whole mammogram classification. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 603–611. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66179-7_69CrossRefGoogle Scholar
  32. 32.
    Lévy, D., Jain, A.: Breast mass classification from mammograms using deep convolutional neural networks. arXiv (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Eric Wu
    • 1
    • 2
    Email author
  • Kevin Wu
    • 1
    • 2
  • David Cox
    • 1
  • William Lotter
    • 1
    • 2
  1. 1.Harvard UniversityCambridgeUSA
  2. 2.DeepHealth, Inc.BostonUSA

Personalised recommendations