Discriminative Localization in CNNs for Weakly-Supervised Segmentation of Pulmonary Nodules

  • Xinyang Feng
  • Jie Yang
  • Andrew F. Laine
  • Elsa D. AngeliniEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10435)


Automated detection and segmentation of pulmonary nodules on lung computed tomography (CT) scans can facilitate early lung cancer diagnosis. Existing supervised approaches for automated nodule segmentation on CT scans require voxel-based annotations for training, which are labor- and time-consuming to obtain. In this work, we propose a weakly-supervised method that generates accurate voxel-level nodule segmentation trained with image-level labels only. By adapting a convolutional neural network (CNN) trained for image classification, our proposed method learns discriminative regions from the activation maps of convolution units at different scales, and identifies the true nodule location with a novel candidate-screening framework. Experimental results on the public LIDC-IDRI dataset demonstrate that, our weakly-supervised nodule segmentation framework achieves competitive performance compared to a fully-supervised CNN-based segmentation method.



Thanks NIH R01-HL121270 for funding.


  1. 1.
    MacMahon, H., Austin, J.H., et al.: Guidelines for management of small pulmonary nodules detected on CT scans: a statement from the Fleischner society 1. Radiology 237(2), 395–400 (2005)CrossRefGoogle Scholar
  2. 2.
    Henschke, C.I., McCauley, D.I., et al.: Early lung cancer action project: overall design and findings from baseline screening. Lancet 354(9173), 99–105 (1999)CrossRefGoogle Scholar
  3. 3.
    Messay, T., Hardie, R.C., et al.: Segmentation of pulmonary nodules in computed tomography using a regression neural network approach and its application to the Lung Image Database Consortium and Image Database Resource Initiative dataset. Med. Image Anal. 22(1), 48–62 (2015)CrossRefGoogle Scholar
  4. 4.
    Anirudh, R., Thiagarajan, J.J., et al.: Lung nodule detection using 3D convolutional neural networks trained on weakly labeled data. In: SPIE Medical Imaging, p. 978532 (2016)Google Scholar
  5. 5.
    Zhou, B., Khosla, A., et al.: Learning deep features for discriminative localization. In: IEEE CVPR (2016)Google Scholar
  6. 6.
    Armato, S.G., McLennan, G., et al.: The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans. Med. Phys. 38(2), 915–931 (2011)CrossRefGoogle Scholar
  7. 7.
    Clark, K., et al.: The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J. Digit. Imaging 26(6), 1045–1057 (2013)CrossRefGoogle Scholar
  8. 8.
    Shelhamer, E., Long, J., et al.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. PP(99), 1 (2016)Google Scholar
  9. 9.
    Israel-Jost, V., Breton, E., et al.: Vectorial multi-phase mouse brain tumor segmentation in T1–T2 MRI. In: IEEE ISBI, pp. 5–8 (2008)Google Scholar
  10. 10.
    Setio, A.A.A., Traverso, A., et al.: Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge. arXiv preprint arXiv:1612.08012 (2016)
  11. 11.
    Warfield, S.K., Zou, K.H., et al.: Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. IEEE Trans. Med. Imaging 23(7), 903–921 (2004)CrossRefGoogle Scholar
  12. 12.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  13. 13.
    Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). doi: 10.1007/978-3-319-24574-4_28 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Xinyang Feng
    • 1
  • Jie Yang
    • 1
  • Andrew F. Laine
    • 1
  • Elsa D. Angelini
    • 1
    • 2
    Email author
  1. 1.Department of Biomedical EngineeringColumbia UniversityNew YorkUSA
  2. 2.ITMAT Data Science Group, NIHR Imperial BRCImperial CollegeLondonUK

Personalised recommendations