Multi-frame Super-resolution with Quality Self-assessment for Retinal Fundus Videos

  • Thomas Köhler
  • Alexander Brost
  • Katja Mogalle
  • Qianyi Zhang
  • Christiane Köhler
  • Georg Michelson
  • Joachim Hornegger
  • Ralf P. Tornow
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8673)

Abstract

This paper proposes a novel super-resolution framework to reconstruct high-resolution fundus images from multiple low-resolution video frames in retinal fundus imaging. Natural eye movements during an examination are used as a cue for super-resolution in a robust maximum a-posteriori scheme. In order to compensate heterogeneous illumination on the fundus, we integrate retrospective illumination correction for photometric registration to the underlying imaging model. Our method utilizes quality self-assessment to provide objective quality scores for reconstructed images as well as to select regularization parameters automatically. In our evaluation on real data acquired from six human subjects with a low-cost video camera, the proposed method achieved considerable enhancements of low-resolution frames and improved noise and sharpness characteristics by 74%. In terms of image analysis, we demonstrate the importance of our method for the improvement of automatic blood vessel segmentation as an example application, where the sensitivity was increased by 13% using super-resolution reconstruction.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Tornow, R., Kopp, O., Schultheiss, B.: Time course of fundus reflection changes according to the cardiac cycle. Invest. Ophthalmol. Vis. Sci. 44, 1296 (2003)Google Scholar
  2. 2.
    Köhler, T., Hornegger, J., Mayer, M., Michelson, G.: Quality-guided denoising for low-cost fundus imaging. In: Proceedings BVM 2012, pp. 292–297 (2012)Google Scholar
  3. 3.
    Marrugo, A.G., Sorel, M., Sroubek, F., Millán, M.S.: Retinal image restoration by means of blind deconvolution. J. Biomed. Opt. 16(11), 116016 (2011)Google Scholar
  4. 4.
    Milanfar, P.: Super-resolution imaging. CRC Press (2010)Google Scholar
  5. 5.
    Pickup, L.C., Capel, D.P., Roberts, S.J., Zisserman, A.: Overcoming Registration Uncertainty in Image Super-Resolution: Maximize or Marginalize? EURASIP J. Adv. Signal Process., 1–15 (2007)Google Scholar
  6. 6.
    Farsiu, S., Robinson, M.D., Elad, M., Milanfar, P.: Fast and robust multiframe super resolution. IEEE Trans. Image. Process. 13(10), 1327–1344 (2004)CrossRefGoogle Scholar
  7. 7.
    Greenspan, H.: Super-Resolution in Medical Imaging. Comput. J. 52(1), 43–63 (2008)CrossRefMathSciNetGoogle Scholar
  8. 8.
    Murillo, S., Echegaray, S., Zamora, G., Soliz, P., Bauman, W.: Quantitative and qualitative image quality analysis of super resolution images from a low cost scanning laser ophthalmoscope. In: Proc. SPIE Medical Imaging, pp. 79624T (2011)Google Scholar
  9. 9.
    Kolar, R., Odstrcilik, J., Jan, J., Harabis, V.: Illumination Correction and Contrast Equalization in Colour Fundus Images. In: Proc. EUSIPCO 2011, pp. 298–302 (2011)Google Scholar
  10. 10.
    Evangelidis, G.D., Psarakis, E.Z.: Parametric image alignment using enhanced correlation coefficient maximization. IEEE Trans. Pattern. Anal. Mach. Intell. 30(10), 1858–1865 (2008)CrossRefGoogle Scholar
  11. 11.
    Köhler, T., Budai, A., Kraus, M.F., Odstrcilik, J., Michelson, G., Hornegger, J.: Automatic no-reference quality assessment for retinal fundus images using vessel segmentation. In: Proceedings CBMS 2013, pp. 95–100 (2013)Google Scholar
  12. 12.
    Staal, J., Abràmoff, M.D., Niemeijer, M., Viergever, M.A., van Ginneken, B.: Ridge-based vessel segmentation in color images of the retina. IEEE Trans. Med. Imaging 23(4), 501–509 (2004)CrossRefGoogle Scholar
  13. 13.
    Budai, A., Bock, R., Maier, A., Hornegger, J., Michelson, G.: Robust vessel segmentation in fundus images. Int. J. Biomed. Imaging, 154860 (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Thomas Köhler
    • 1
    • 2
  • Alexander Brost
    • 1
  • Katja Mogalle
    • 1
  • Qianyi Zhang
    • 1
  • Christiane Köhler
    • 3
  • Georg Michelson
    • 2
    • 3
  • Joachim Hornegger
    • 1
    • 2
  • Ralf P. Tornow
    • 3
  1. 1.Pattern Recognition LabFriedrich-Alexander-Universität Erlangen-NürnbergErlangenGermany
  2. 2.Erlangen Graduate School in Advanced Optical Technologies (SAOT)ErlangenGermany
  3. 3.Department of OphthalmologyFriedrich-Alexander-Universität Erlangen-NürnbergErlangenGermany

Personalised recommendations