Advertisement

Abstract: Self-Supervised 3D Context Feature Learning on Unlabeled Volume Data

  • Maximilian BlendowskiEmail author
  • Mattias P. Heinrich
Conference paper
  • 58 Downloads
Part of the Informatik aktuell book series (INFORMAT)

Zusammenfassung

Deep learning with convolutional networks (DCNN) has established itself as a powerful tool for a variety of medical imaging tasks. However, DCNNs in particular require strong monitoring by expert annotations, which cannot be generated cost-effectively by laymen. In contrast to manual annotations, the mere availability of medical volume data is not a problem.

Literatur

  1. 1.
    Blendowski M, Nickisch H, Heinrich MP. How to learn from unlabeled volume data: self-supervised 3d context feature learning. In: MICCAI. Springer; 2019. p. 649–657.Google Scholar
  2. 2.
    Doersch C, Gupta A, Efros AA. Unsupervised visual representation learning by context prediction. In: Proc IEEE Int Conf Comput Vis; 2015. .Google Scholar
  3. 3.
    Heinrich MP, Blendowski M. Multi-organ segmentation using vantage point forests and binary context features. In: MICCAI. Springer; 2016. p. 598–606.Google Scholar

Copyright information

© Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2020

Authors and Affiliations

  1. 1.Institut für Medizinische InformatikUniversität zu LübeckLübeckDeutschland

Personalised recommendations