Advertisement

Detection and Delineation of Acute Cerebral Infarct on DWI Using Weakly Supervised Machine Learning

  • Stefano PedemonteEmail author
  • Bernardo Bizzo
  • Stuart Pomerantz
  • Neil Tenenholtz
  • Bradley Wright
  • Mark Walters
  • Sean Doyle
  • Adam McCarthy
  • Renata Rocha De Almeida
  • Katherine Andriole
  • Mark Michalski
  • R. Gilberto Gonzalez
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11072)

Abstract

Improved outcome in patients with ischemic stroke is achieved through acute diagnosis and early restoration of cerebral flow in appropriate patients. Diffusion-weighted MR imaging (DWI) plays a central role in these efforts by enabling rapid early localization and quantification of ischemic lesions. Automated detection and quantification can potentially accelerate diagnosis, improve treatment safety and efficacy and reduce costs. However, the manual quantification of acute ischemic stroke volumes for algorithm training is time consuming and imprecise. We present YNet as a novel fully-automated deep learning algorithm for detection and volumetric segmentation and quantification of acute cerebral ischemic lesions from DWI. The algorithm is a semi-supervised multi-tasking deep neural network architecture we developed that enables the combination of both weak labels derived from radiology report classification and manually delineated pixel level training data. The model is trained on a very large dataset of 10000 studies, achieves detection sensitivity 0.981, detection specificity 0.980 and segmentation Dice score 0.623 on a heterogeneous test set.

Keywords

Weakly supervised deep learning Stroke detection Segmentation Diffusion-weighted MRI 

References

  1. 1.
    Berkhemer, O., et al.: A randomized trial of intraarterial treatment for acute ischemic stroke. N. Engl. J. Med. 372(1), 11–20 (2015)CrossRefGoogle Scholar
  2. 2.
    Chen, L., Bentley, P., Rueckert, D.: Fully automated acute ischemic lesion segmentation in DWI using convolutional neural networks. Neuroimage 15, 633–643 (2017)CrossRefGoogle Scholar
  3. 3.
    Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 424–432. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46723-8_49CrossRefGoogle Scholar
  4. 4.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: PMLR, vol. 9, pp. 249–256 (2010)Google Scholar
  5. 5.
    Goyal, M., Menon, B., van Zwam, W.: Endovascular thrombectomy after large-vessel ischaemic stroke: a meta-analysis of individual patient data from five randomised trials. Lancet 387, 1723–1731 (2016)CrossRefGoogle Scholar
  6. 6.
    Hacke, W.: A new DAWN for imaging-based selection in the treatment of acute stroke. N. Engl. J. Med. 378, 81–83 (2018)CrossRefGoogle Scholar
  7. 7.
    Klambauer, G., Unterthiner, T., Mayr, A.: Self-normalizing neural networks. In: NIPS, pp. 971–980 (2017)Google Scholar
  8. 8.
    Martel, A.L., Allder, S.J., Delay, G.S., Morgan, P.S., Moody, A.R.: Measurement of infarct volume in stroke patients using adaptive segmentation of diffusion weighted MR images. In: Taylor, C., Colchester, A. (eds.) MICCAI 1999. LNCS, vol. 1679, pp. 22–31. Springer, Heidelberg (1999).  https://doi.org/10.1007/10704282_3CrossRefGoogle Scholar
  9. 9.
    Milletari, F., Navab, N., Ahmadi, S.: V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: 3DV, pp. 565–571 (2016)Google Scholar
  10. 10.
    Papandreou, G., Chen, L., Murphy, K., Yuille, A.: Weakly- and semi-supervised learning of a DCNN for semantic image segmentation. CoRR 1502.02734 (2015)Google Scholar
  11. 11.
    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).  https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
  12. 12.
    Subudhi, A., Jena, S., Sabut, S.: Delineation of the ischemic stroke lesion based on watershed and relative fuzzy connectedness in brain MRI. Med. Biol. Eng. Comput. 56, 1–13 (2017)Google Scholar
  13. 13.
    Tsai, J., et al.: Automated detection and quantification of acute cerebral infarct by fuzzy clustering and histographic characterization on diffusion weighted MR imaging and apparent diffusion coefficient. BioMed. Res. Int. (2014). Article no. 963032Google Scholar
  14. 14.
    Tustison, N.: N4ITK: improved N3 bias correction. IEEE Trans. Med. Imaging 29(6), 1310–1320 (2010)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Stefano Pedemonte
    • 1
    • 2
    • 3
    Email author
  • Bernardo Bizzo
    • 1
    • 2
    • 3
  • Stuart Pomerantz
    • 1
    • 2
    • 3
  • Neil Tenenholtz
    • 1
  • Bradley Wright
    • 1
  • Mark Walters
    • 1
  • Sean Doyle
    • 1
  • Adam McCarthy
    • 1
    • 4
  • Renata Rocha De Almeida
    • 1
    • 2
    • 3
  • Katherine Andriole
    • 1
    • 2
    • 3
  • Mark Michalski
    • 1
    • 2
    • 3
  • R. Gilberto Gonzalez
    • 2
    • 3
  1. 1.Center for Clinical Data ScienceBostonUSA
  2. 2.Harvard Medical SchoolBostonUSA
  3. 3.Massachusetts General HospitalBostonUSA
  4. 4.Department of Computer ScienceUniversity of OxfordOxfordUK

Personalised recommendations