Skip to main content

2018 | OriginalPaper | Buchkapitel

Towards Safe Deep Learning: Accurately Quantifying Biomarker Uncertainty in Neural Network Predictions

verfasst von : Zach Eaton-Rosen, Felix Bragman, Sotirios Bisdas, Sébastien Ourselin, M. Jorge Cardoso

Erschienen in: Medical Image Computing and Computer Assisted Intervention – MICCAI 2018

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Automated medical image segmentation, specifically using deep learning, has shown outstanding performance in semantic segmentation tasks. However, these methods rarely quantify their uncertainty, which may lead to errors in downstream analysis. In this work we propose to use Bayesian neural networks to quantify uncertainty within the domain of semantic segmentation. We also propose a method to convert voxel-wise segmentation uncertainty into volumetric uncertainty, and calibrate the accuracy and reliability of confidence intervals of derived measurements. When applied to a tumour volume estimation application, we demonstrate that by using such modelling of uncertainty, deep learning systems can be made to report volume estimates with well-calibrated error-bars, making them safer for clinical use. We also show that the uncertainty estimates extrapolate to unseen data, and that the confidence intervals are robust in the presence of artificial noise. This could be used to provide a form of quality control and quality assurance, and may permit further adoption of deep learning tools in the clinic.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Iglesias, J.E., Sabuncu, M.R., Van Leemput, K.: Improved inference in bayesian segmentation using monte carlo sampling: application to hippocampal subfield volumetry. Med. Image Anal. 17(7), 766–778 (2013)CrossRef Iglesias, J.E., Sabuncu, M.R., Van Leemput, K.: Improved inference in bayesian segmentation using monte carlo sampling: application to hippocampal subfield volumetry. Med. Image Anal. 17(7), 766–778 (2013)CrossRef
2.
Zurück zum Zitat Srivastava, N.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetMATH Srivastava, N.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetMATH
3.
Zurück zum Zitat 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) 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)
4.
Zurück zum Zitat Menze, B.: The multimodal brain tumor image segmentation benchmark (brats). IEEE Trans. Med. Imaging 34(10), 1993–2024 (2015)CrossRef Menze, B.: The multimodal brain tumor image segmentation benchmark (brats). IEEE Trans. Med. Imaging 34(10), 1993–2024 (2015)CrossRef
5.
Zurück zum Zitat Bakas, S., et al.: Advancing the cancer genome atlas glioma mri collections with expert segmentation labels and radiomic features. Sci. Data 4, 170117 (2017)CrossRef Bakas, S., et al.: Advancing the cancer genome atlas glioma mri collections with expert segmentation labels and radiomic features. Sci. Data 4, 170117 (2017)CrossRef
6.
Zurück zum Zitat Li, W., Wang, G., Fidon, L., Ourselin, S., Cardoso, M.J., Vercauteren, T.: On the compactness, efficiency, and representation of 3D convolutional networks: brain parcellation as a pretext task. In: Niethammer, M. (ed.) IPMI 2017. LNCS, vol. 10265, pp. 348–360. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59050-9_28CrossRef Li, W., Wang, G., Fidon, L., Ourselin, S., Cardoso, M.J., Vercauteren, T.: On the compactness, efficiency, and representation of 3D convolutional networks: brain parcellation as a pretext task. In: Niethammer, M. (ed.) IPMI 2017. LNCS, vol. 10265, pp. 348–360. Springer, Cham (2017). https://​doi.​org/​10.​1007/​978-3-319-59050-9_​28CrossRef
7.
Zurück zum Zitat Gibson, E.: Niftynet: a deep-learning platform for medical imaging. Comput. Methods Programs Biomed. 158, 113–122 (2018)CrossRef Gibson, E.: Niftynet: a deep-learning platform for medical imaging. Comput. Methods Programs Biomed. 158, 113–122 (2018)CrossRef
8.
Zurück zum Zitat Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: Advances in Neural Information Processing Systems, pp. 5580–5590 (2017) Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: Advances in Neural Information Processing Systems, pp. 5580–5590 (2017)
9.
Zurück zum Zitat Kamnitsas, K., et al.: Ensembles of multiple models and architectures for robust brain tumour segmentation. arXiv preprint arXiv:1711.01468 (2017) Kamnitsas, K., et al.: Ensembles of multiple models and architectures for robust brain tumour segmentation. arXiv preprint arXiv:​1711.​01468 (2017)
Metadaten
Titel
Towards Safe Deep Learning: Accurately Quantifying Biomarker Uncertainty in Neural Network Predictions
verfasst von
Zach Eaton-Rosen
Felix Bragman
Sotirios Bisdas
Sébastien Ourselin
M. Jorge Cardoso
Copyright-Jahr
2018
DOI
https://doi.org/10.1007/978-3-030-00928-1_78