Advertisement

Bayesian Neural Networks for Uncertainty Estimation of Imaging Biomarkers

  • Jyotirmay Senapati
  • Abhijit Guha Roy
  • Sebastian Pölsterl
  • Daniel Gutmann
  • Sergios Gatidis
  • Christopher Schlett
  • Anette Peters
  • Fabian Bamberg
  • Christian WachingerEmail author
Conference paper
  • 762 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12436)

Abstract

Image segmentation enables to extract quantitative measures from scans that can serve as imaging biomarkers for diseases. However, segmentation quality can vary substantially across scans, and therefore yield unfaithful estimates in the follow-up statistical analysis of biomarkers. The core problem is that segmentation and biomarker analysis are performed independently. We propose to propagate segmentation uncertainty to the statistical analysis to account for variations in segmentation confidence. To this end, we evaluate four Bayesian neural networks to sample from the posterior distribution and estimate the uncertainty. We then assign confidence measures to the biomarker and propose statistical models for its integration in group analysis and disease classification. Our results for segmenting the liver in patients with diabetes mellitus clearly demonstrate the improvement of integrating biomarker uncertainty in the statistical inference.

Notes

Acknowledgement

This research was supported by DFG, BMBF (project DeepMentia), and the Bavarian State Ministry of Science and the Arts and coordinated by the Bavarian Research Institute for Digital Transformation (bidt).

References

  1. 1.
    Baumgartner, C.F., et al.: PHiSeg: capturing uncertainty in medical image segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 119–127. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-32245-8_14CrossRefGoogle Scholar
  2. 2.
    Eaton-Rosen, Z., Bragman, F., Bisdas, S., Ourselin, S., Cardoso, M.J.: Towards safe deep learning: accurately quantifying biomarker uncertainty in neural network predictions. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 691–699. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00928-1_78CrossRefGoogle Scholar
  3. 3.
    Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning, pp. 1050–1059 (2016)Google Scholar
  4. 4.
    Ghesu, F.C., et al.: Quantifying and leveraging classification uncertainty for chest radiograph assessment. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 676–684. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-32226-7_75CrossRefGoogle Scholar
  5. 5.
    Gutiérrez-Becker, B., Klein, T., Wachinger, C.: Gaussian process uncertainty in age estimation as a measure of brain abnormality. NeuroImage 175, 246–258 (2018)CrossRefGoogle Scholar
  6. 6.
    Gutiérrez-Becker, B., Wachinger, C.: Deep multi-structural shape analysis: application to neuroanatomy. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11072, pp. 523–531. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00931-1_60CrossRefGoogle Scholar
  7. 7.
    Gutiérrez-Becker, B., Wachinger, C.: Learning a conditional generative model for anatomical shape analysis. In: IPMI 2019, pp. 505–516. Springer, Heidelberg (2019).  https://doi.org/10.1007/978-3-030-20351-1_39
  8. 8.
    Hu, S., Worrall, D., Knegt, S., Veeling, B., Huisman, H., Welling, M.: Supervised uncertainty quantification for segmentation with multiple annotations. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 137–145. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-32245-8_16CrossRefGoogle Scholar
  9. 9.
    Jungo, A., Reyes, M.: Assessing reliability and challenges of uncertainty estimations for medical image segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 48–56. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-32245-8_6CrossRefGoogle Scholar
  10. 10.
    Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: Advances in Neural Information Processing Systems, pp. 5574–5584 (2017)Google Scholar
  11. 11.
    Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)
  12. 12.
    Kingma, D.P., Salimans, T., Welling, M.: Variational dropout and the local reparameterization trick. In: Advances in Neural Information Processing Systems, pp. 2575–2583 (2015)Google Scholar
  13. 13.
    Kohl, S., et al.: A probabilistic u-net for segmentation of ambiguous images. In: Advances in Neural Information Processing Systems, pp. 6965–6975 (2018)Google Scholar
  14. 14.
    Kohl, S.A., et al.: A hierarchical probabilistic u-net for modeling multi-scale ambiguities. arXiv preprint arXiv:1905.13077 (2019)
  15. 15.
    Minaee, S., Boykov, Y., Porikli, F., Plaza, A., Kehtarnavaz, N., Terzopoulos, D.: Image segmentation using deep learning: A survey. arXiv preprint arXiv:2001.05566 (2020)
  16. 16.
    Nair, T., Precup, D., Arnold, D.L., Arbel, T.: Exploring uncertainty measures in deep networks for multiple sclerosis lesion detection and segmentation. Med. Image Anal. 59, 101557 (2020)CrossRefGoogle Scholar
  17. 17.
    Roy, A.G., Conjeti, S., Navab, N., Wachinger, C.: Inherent brain segmentation quality control from fully ConvNet Monte Carlo sampling. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 664–672. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00928-1_75CrossRefGoogle Scholar
  18. 18.
    Roy, A.G., Conjeti, S., Navab, N., Wachinger, C.: Bayesian quicknat: model uncertainty in deep whole-brain segmentation for structure-wise quality control. NeuroImage 195, 11–22 (2019)CrossRefGoogle Scholar
  19. 19.
    Roy, A.G., Conjeti, S., Navab, N., Wachinger, C.: Quicknat: a fully convolutional network for quick and accurate segmentation of neuroanatomy. NeuroImage 186, 713–727 (2019)CrossRefGoogle Scholar
  20. 20.
    Roy, A.G., Conjeti, S., Sheet, D., Katouzian, A., Navab, N., Wachinger, C.: Error corrective boosting for learning fully convolutional networks with limited data. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 231–239. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66179-7_27CrossRefGoogle Scholar
  21. 21.
    Sedai, S., Antony, B., Rai, R., Jones, K., Ishikawa, H., Schuman, J., Gadi, W., Garnavi, R.: Uncertainty guided semi-supervised segmentation of retinal layers in OCT images. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11764, pp. 282–290. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-32239-7_32CrossRefGoogle Scholar
  22. 22.
    Wachinger, C., Golland, P., Kremen, W., Fischl, B., Reuter, M.: Brainprint: a discriminative characterization of brain morphology. NeuroImage 109, 232–248 (2015)CrossRefGoogle Scholar
  23. 23.
    Wachinger, C., Reuter, M.: Domain adaptation for Alzheimer’s disease diagnostics. Neuroimage 139, 470–479 (2016)CrossRefGoogle Scholar
  24. 24.
    Wachinger, C., Salat, D.H., Weiner, M., Reuter, M.: Whole-brain analysis reveals increased neuroanatomical asymmetries in dementia for hippocampus and amygdala. Brain 139(12), 3253–3266 (2016)CrossRefGoogle Scholar
  25. 25.
    Yu, L., Wang, S., Li, X., Fu, C.-W., Heng, P.-A.: Uncertainty-aware self-ensembling model for semi-supervised 3D left atrium segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 605–613. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-32245-8_67CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Jyotirmay Senapati
    • 1
  • Abhijit Guha Roy
    • 1
  • Sebastian Pölsterl
    • 1
  • Daniel Gutmann
    • 2
  • Sergios Gatidis
    • 2
  • Christopher Schlett
    • 3
  • Anette Peters
    • 4
  • Fabian Bamberg
    • 3
  • Christian Wachinger
    • 1
    Email author
  1. 1.Artificial Intelligence in Medical Imaging (AI-Med), KJP, LMU MünchenMunichGermany
  2. 2.Department of Diagnostic and Interventional RadiologyUniversity of TübingenTübingenGermany
  3. 3.Department of Diagnostic and Interventional RadiologyUniversity FreiburgFreiburg im BreisgauGermany
  4. 4.Institute of EpidemiologyHelmholtz Zentrum MünchenMunichGermany

Personalised recommendations