Detection of Unseen Low-Contrast Signals Using Classic and Novel Model Observers

  • Yiling XuEmail author
  • Frank Schebesch
  • Nishant Ravikumar
  • Andreas Maier
Conference paper
Part of the Informatik aktuell book series (INFORMAT)


Automatic task-based image quality assessment has been of importance in various clinical and research applications. In this paper, we propose a neural network model observer, a novel concept which has recently been investigated. It is trained and tested on simulated images with different contrast levels, with the aim of trying to distinguish images based on their quality/contrast. Our model shows promising properties that its output is sensitive to image contrast, and generalizes well to unseen low-contrast signals. We also compare the results of the proposed approach with those of a channelized hotelling observer (CHO), on the same simulated dataset.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Barrett HH, Yao J, Rolland JP, et al. Model observers for assessment of image quality. PNAS. 1993;90:9758–9765.CrossRefGoogle Scholar
  2. 2.
    Damien R, Alexandre B, Julien O, et al. Objective assessment of low contrast detectability in computed tomography with channelized hotelling observer. Phys Med. 2016;32:76–83.Google Scholar
  3. 3.
    Kalayeh MM, Marin T, Brankov JG. Generalization evaluation of machine learning numerical observers for image quality assessment. IEEE Trans Nucl Sci. 2013;60(3):1609–1618.CrossRefGoogle Scholar
  4. 4.
    Alnowami MR, Mills G, Awis M, et al. A deep learning model observer for use in alterative forced choice virtual clinical trials. Proc SPIE. 2018;.Google Scholar
  5. 5.
    Maier A, Hofmann H, Berger M, et al. CONRAD: a software framework for conebeam imaging in radiology. Med Phys. 2013;40(11):111914–1–8.CrossRefGoogle Scholar
  6. 6.
    Wunderlich A. IQmodelo; 2016. [Online; accessed 28-October-2018].
  7. 7.
    He X, Park S. Model observers in medical imaging research. Theranostics. 2013;3(10):774–786.CrossRefGoogle Scholar
  8. 8.
    Gallas BD, Barrett HH. Validating the use of channels to estimate the ideal linear observer. JOSA A: Opt, Image Sci, Vis. 2003;20(9):1725–1738.CrossRefGoogle Scholar
  9. 9.
    Schebesch F, Maier A. Towards optimal channels for a detection channelized hotelling observer. 3rd Conf Proc Image-Guid Interv Fokus Neuroradiol. 2017; p. 12–13.Google Scholar

Copyright information

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

Authors and Affiliations

  • Yiling Xu
    • 1
    Email author
  • Frank Schebesch
    • 1
  • Nishant Ravikumar
    • 1
  • Andreas Maier
    • 1
  1. 1.Pattern Recognition LabFriedrich-Alexander-Universität Erlangen-NürnbergNürnbergDeutschland

Personalised recommendations