Abstract: Adversarial Examples as Benchmark for Medical Imaging Neural Networks

  • Magdalini PaschaliEmail author
  • Sailesh Conjeti
  • Fernando Navarro
  • Nassir Navab
Conference paper
Part of the Informatik aktuell book series (INFORMAT)


Deep learning has been widely adopted as the solution of choice for a plethora of medical imaging applications, due to its state-of-the-art performance and fast deployment. Traditionally, the performance of a deep learning model is evaluated on a test dataset, originating from the same distribution as the training set. This evaluation method provides insight regarding the generalization ability of a model.


  1. 1.
    Paschali M, Conjeti S, Navarro F, et al. Generalizability vs. robustness: investigating medical imaging networks using adversarial examples. Proc MICCAI. 2018; p. 493–501.Google Scholar
  2. 2.
    Szegedy C, Zaremba W, Sutskever I, et al. Intriguing properties of neural networks. Int Conf Learn Representations. 2014;Available from:

Copyright information

© Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2019

Authors and Affiliations

  • Magdalini Paschali
    • 1
    Email author
  • Sailesh Conjeti
    • 2
  • Fernando Navarro
    • 1
  • Nassir Navab
    • 1
    • 3
  1. 1.Computer Aided Medical ProceduresTechnische Universität MünchenMünchenDeutschland
  2. 2.Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)BonnDeutschland
  3. 3.Computer Aided Medical ProceduresJohns Hopkins UniversityBaltimoreUSA

Personalised recommendations