Volumetric Adversarial Training for Ischemic Stroke Lesion Segmentation

  • Hao-Yu YangEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11383)


Ischemic stroke is one of the most common and yet deadly cerebrovascular diseases. Identifying lesion area is an essential step for stroke management and outcome assessment. Currently, manual delineation is the gold standard for clinical diagnosis. However, inter-annotator variances and labor-intensive nature of manual labeling can lead to observer bias or potential disagreement of between annotators. While incorporating a computer-aided diagnosis system may alleviate these issues, other challenges such as highly varying shapes and difficult boundaries in the lesion area make the designing of such system non-trivial. To address these issues, we propose a novel adversarial training paradigm for segmenting ischemic stroke lesion. The training procedure involves the main segmentation network and an auxiliary critique network. The segmentation network is a 3D residual U-net that produces a segmentation mask in each training iteration while critique network enforces high-level constraints on the segmentation network to produce predictions that mimic the ground truth distribution. We applied the proposed model on the 2018 ISLES stroke lesion segmentation challenge dataset and achieved competitive results on the training dataset.


3D convolution neural networks Adversarial training Ischemic Stroke Lesion Segmentation 


  1. 1.
    Feigin, V.L., Lawes, C.M., Bennett, D.A., Anderson, C.S.: Stroke epidemiology: a review of population-based studies of incidence, prevalence, and case-fatality in the late 20th century. Lancet Neurol. 2(1), 43–53 (2003). Scholar
  2. 2.
    Gillebert, C.R., Humphreys, G.W., Mantini, D.: Automated delineation of stroke lesions using brain ct images. NeuroImage: Clin. 4, 540–548 (2014). Scholar
  3. 3.
    Goodfellow, I.J., et al.: Generative Adversarial Networks. arXiv e-prints, June 2014Google Scholar
  4. 4.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778, June 2016.
  5. 5.
    Keys, R.: Cubic convolution interpolation for digital image processing. IEEE Trans. Acoust. Speech Signal Process. 29(6), 1153–1160 (1981). Scholar
  6. 6.
    Luc, P., Couprie, C., Chintala, S., Verbeek, J.: Semantic segmentation using adversarial networks. CoRR abs/1611.08408 (2016).
  7. 7.
    Maier, O., et al.: ISLES 2015 - a public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI. Med. Image Anal. 35, 250–269 (2017). Scholar
  8. 8.
    Moseley, M.E., et al.: Early detection of regional cerebral ischemia in cats: comparison of diffusion- and T2-weighted MRI and spectroscopy. Magn. Reson. Med. 14(2), 330–346 (1990)CrossRefGoogle Scholar
  9. 9.
    Praveen, G., Agrawal, A., Sundaram, P., Sardesai, S.: Ischemic stroke lesion segmentation using stacked sparse autoencoder. Comput. Biol. Med. 99, 38–52 (2018). Scholar
  10. 10.
    Quan, T.M., Hildebrand, D.G.C., Jeong, W.: FusionNet: a deep fully residual convolutional neural network for image segmentation in connectomics. CoRR abs/1612.05360 (2016).
  11. 11.
    Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. CoRR abs/1505.04597 (2015). Scholar
  12. 12.
    Yushkevich, P.A., et al.: User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage 31(3), 1116–1128 (2006)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Cura Cloud CooperationSeattleUSA
  2. 2.Yale UniversityNew HavenUSA

Personalised recommendations