Advertisement

Retinal Image Quality Classification Using Saliency Maps and CNNs

  • Dwarikanath MahapatraEmail author
  • Pallab K. Roy
  • Suman Sedai
  • Rahil Garnavi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10019)

Abstract

Retinal image quality assessment (IQA) algorithms use different hand crafted features without considering the important role of the human visual system (HVS). We solve the IQA problem using the principles behind the working of the HVS. Unsupervised information from local saliency maps and supervised information from trained convolutional neural networks (CNNs) are combined to make a final decision on image quality. A novel algorithm is proposed that calculates saliency values for every image pixel at multiple scales to capture global and local image information. This extracts generalized image information in an unsupervised manner while CNNs provide a principled approach to feature learning without the need to define hand-crafted features. The individual classification decisions are fused by weighting them according to their confidence scores. Experimental results on real datasets demonstrate the superior performance of our proposed algorithm over competing methods.

Keywords

Random Forest Human Visual System Convolutional Neural Network Salient Region Image Quality Assessment 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    The atherosclerosis risk in communities (ARIC) study: design and objectives. The ARIC investigators. Am J Epidemiol, 129(4), 687–702, April 1989Google Scholar
  2. 2.
    Goldstein, E.: Sensation and Perception. Thomson Wadsworth, Belmont (2007)Google Scholar
  3. 3.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    Dias, J., Oliveira, C., Cruz, L.: Retinal image quality assessment using generic image quality indicators. Inf. Fusion 19, 73–90 (2014)CrossRefGoogle Scholar
  5. 5.
    Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. In: Advances in Neural Information Processing Systems (NIPS), pp. 545–552 (2006)Google Scholar
  6. 6.
    Hou, X., Harel, J., Koch, C.: Image signature: highlighting sparse salient regions. IEEE Trans. Pattern Anal. Mach. Intell. 34(1), 194–201 (2012)CrossRefGoogle Scholar
  7. 7.
    Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254–1259 (1998)CrossRefGoogle Scholar
  8. 8.
    Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 1106–1114 (2012)Google Scholar
  9. 9.
    Lalonde, M., Gagnon, L., Boucher, M.: Automatic visual quality assessment in optical fundus images. In: Proceedings of Vision Interface, pp. 259–264 (2001)Google Scholar
  10. 10.
    Lee, S., Wang, Y.: Automatic retinal image quality assessment and enhancement. In: Proceedings of SPIE Medical Imaging, pp. 1581–1590 (1999)Google Scholar
  11. 11.
    Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: International Conference on Machine Learning, pp. 807–814 (2010)Google Scholar
  12. 12.
    Niemeijer, M., Abramoff, M., van Ginneken, B.: Image structure clustering for image quality verification of color retina images in diabetic retinopathy screening. Med. Imag. Anal. 10(6), 888–898 (2006)CrossRefGoogle Scholar
  13. 13.
    Palm, R.B.: Prediction as a Candidate for Learning Deep Hierarchical Models of Data. Masters Thesis, Technical University of Denmark (2012)Google Scholar
  14. 14.
    Paulus, J., Meier, J., Bock, R., Hornegger, J., Michelson, G.: Automated quality assessment of retinal fundus photos. Int. J. Comp. Assist. Radiol. Surg. 10(6), 888–898 (2006)Google Scholar
  15. 15.
    Usher, D., Himaga, M., Dumskyj, M.: Automated assessment of digital fundus image quality using detected vessel area. In: Proceedings of Medical Image Understanding and Analysis, pp. 81–84 (2003)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Dwarikanath Mahapatra
    • 1
    Email author
  • Pallab K. Roy
    • 1
  • Suman Sedai
    • 1
  • Rahil Garnavi
    • 1
  1. 1.IBM ResearchMelbourneAustralia

Personalised recommendations