Deep Generative Breast Cancer Screening and Diagnosis

  • Shayan Shams
  • Richard Platania
  • Jian Zhang
  • Joohyun Kim
  • Kisung Lee
  • Seung-Jong ParkEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11071)


Mammography is the primary modality for breast cancer screening, attempting to reduce breast cancer mortality risk with early detection. However, robust screening less hampered by misdiagnoses remains a challenge. Deep Learning methods have shown strong applicability to various medical image datasets, primarily thanks to their powerful feature learning capability. Such successful applications are, however, often overshadowed with limitations in real medical settings, dependency of lesion annotations, and discrepancy of data types between training and other datasets. To address such critical challenges, we developed DiaGRAM (Deep GeneRAtive Multi-task), which is built upon the combination of Convolutional Neural Networks (CNN) and Generative Adversarial Networks (GAN). The enhanced feature learning with GAN, and its incorporation with the hybrid training with the region of interest (ROI) and the whole images results in higher classification performance and an effective end-to-end scheme. DiaGRAM is capable of robust prediction, even for a small dataset, without lesion annotation, via transfer learning capacity. DiaGRAM achieves an AUC of 88.4% for DDSM and even 92.5% for the challenging INbreast with its small data size.



This work was partially funded by NIH grants (P20GM103458-10, P30GM110760-03, P20GM103424), NSF grants (MRI-1338051, IBSS-L-1620451, SCC-1737557, RAPID-1762600), LA Board of Regents grants (LEQSF(2016-19)-RD-A-08 and ITRS), and IBM faculty awards.


  1. 1.
    Ball, J.E., Bruce, L.M.: Digital mammographic computer aided diagnosis (CAD) using adaptive level set segmentation. In: 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2007, pp. 4973–4978. IEEE (2007)Google Scholar
  2. 2.
    Dhungel, N., Carneiro, G., Bradley, A.P.: The automated learning of deep features for breast mass classification from mammograms. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 106–114. Springer, Cham (2016). Scholar
  3. 3.
    Domingues, I., et al.: Inbreast-database masses characterization. XXIII CBEB (2012)Google Scholar
  4. 4.
    Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)Google Scholar
  5. 5.
    He, K., et al.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)Google Scholar
  6. 6.
    He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  7. 7.
    Litjens, G.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017)CrossRefGoogle Scholar
  8. 8.
    Ong, M.S., Mandl, K.D.: National expenditure for false-positive mammograms and breast cancer overdiagnoses estimated at \$4 billion a year. Health Aff. 34(4), 576–583 (2015)CrossRefGoogle Scholar
  9. 9.
    Orwat, J.: Comparing rural and urban cervical and breast cancer screening rates in a privately insured population. Soc. Work Publ. Health 32(5), 311–323 (2017)CrossRefGoogle Scholar
  10. 10.
    Platania, R., et al.: Automated breast cancer diagnosis using deep learning and region of interest detection (BC-DROID). In: Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, pp. 536–543. ACM (2017)Google Scholar
  11. 11.
    Siegel, R.: Cancer statistics, 2014. CA Cancer J. Clin. 64(1), 9–29 (2014)CrossRefGoogle Scholar
  12. 12.
    Teh, Y.C.: Opportunistic mammography screening provides effective detection rates in a limited resource healthcare system. BMC Cancer 15(1), 405 (2015)CrossRefGoogle Scholar
  13. 13.
    Varela, C.: Use of border information in the classification of mammographic masses. Physics Med. Biol. 51(2), 425 (2006)CrossRefGoogle Scholar
  14. 14.
    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). Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Shayan Shams
    • 1
  • Richard Platania
    • 1
  • Jian Zhang
    • 1
  • Joohyun Kim
    • 1
  • Kisung Lee
    • 1
  • Seung-Jong Park
    • 1
    Email author
  1. 1.Louisiana State UniversityBaton RougeUSA

Personalised recommendations