Advertisement

Simulation of Realistic Low Dose Fluoroscopic Images from their High Dose Counterparts

  • Sai Gokul Hariharan
  • Norbert Strobel
  • Markus Kowarschik
  • Rebecca Fahrig
  • Nassir Navab
Conference paper
Part of the Informatik aktuell book series (INFORMAT)

Zusammenfassung

Learning based denoising methods have attracted increasing interest in the recent past. These methods rely on data pairs. In the case of denoising, the data pairs are usually noise corrupted images and their noise-free counterparts, if available. Otherwise an associated high-dose X-ray image can be used instead as a practical alternative. As the current image processing techniques are not yet able to provide the necessary image quality at very low dose levels, it is usually not possible to acquire clinical sequences. As variation in the data is extremely important for learning based methods, phantom data alone cannot be used to train a network and achieve optimal performance. A possibility to overcome this issue is to simulate low dose images from the related high dose images. However, to make sure that the simulated low dose images are realistic (replicate the properties of real low dose images), image noise attributes associated with low dose image acquisition need to be taken into account. In their paper we introduce a novel method to simulate low dose images from high dose images based on modelling the X-ray image formation process. This way, we can better account for imaging parameters such as system gain and electronic noise. We have evaluated our method by comparing several corresponding regions of the simulated lower dose images with that of real lower dose images using a two sample Kolmogorov-Smirnov Test at 5% significance. Out of 40 pairs, in 85% of the cases the hypothesis that the corresponding regions (from the low and simulated low dose images) belong to the same distribution has been accepted.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Literatur

  1. 1.
    Zhang K, Zuo W, Chen Y, et al. Beyond a gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans Image Process. 2017.Google Scholar
  2. 2.
    Wolterink JM, Leiner T, Viergever MA, et al. Generative adversarial networks for noise reduction in low-dose CT. IEEE Trans Med Imaging. 2017.Google Scholar
  3. 3.
    Matviychuk Y, Mailhé B, Chen X, et al.; IEEE. Learning a multiscale patch-based representation for image denoising in x-ray fluoroscopy. Proc Int Conf Image Proc. 2016; p. 2330–2334.Google Scholar
  4. 4.
    Yang K, Huang SY, Packard NJ, et al. Noise variance analysis using a flat panel x-ray detector: a method for additive noise assessment with application to breast CT applications. Med Phys. 2010;37(7):3527–3537.Google Scholar
  5. 5.
    Makitalo M, Foi A. Optimal inversion of the generalized Anscombe transformation for poisson-gaussian noise. IEEE Trans Image Process. 2013;22(1):91–103.Google Scholar
  6. 6.
    Massey Jr FJ. The kolmogorov-smirnov test for goodness of fit. J Am Stat Assoc. 1951;46(253):68–78.Google Scholar

Copyright information

© Springer-Verlag GmbH Deutschland 2018

Authors and Affiliations

  • Sai Gokul Hariharan
    • 1
    • 2
  • Norbert Strobel
    • 2
    • 4
  • Markus Kowarschik
    • 1
    • 2
  • Rebecca Fahrig
    • 2
    • 5
  • Nassir Navab
    • 1
    • 3
  1. 1.Computer Aided Medical Procedures (CAMP)Technische Universität MünchenMunichDeutschland
  2. 2.Siemens Healthineers, Advanced TherapiesForchheimDeutschland
  3. 3.Whiting School of EngineeringJohns Hopkins UniversityBaltimoreUSA
  4. 4.Fakultät für ElektrotechnikHochschule für angewandte Wissenschaften Würzburg-SchweinfurtSchweinfurtDeutschland
  5. 5.Pattern Recognition LabFriedrich-Alexander-Universität Erlangen-Nürnberg (FAU)ErlangenDeutschland

Personalised recommendations