Publication detail

Automatic no-reference quality assessment for retinal fundus images using vessel segmentation

KÖHLER, T. BUDAI, A. KRAUS, M. ODSTRČILÍK, J. MICHELSON, G. HORNEGGER, J.

Original Title

Automatic no-reference quality assessment for retinal fundus images using vessel segmentation

Type

conference paper

Language

English

Original Abstract

Fundus imaging is the most commonly used modality to collect information about the human eye background. Objective and quantitative assessment of quality for the acquired images is essential for manual, computer-aided and fully automatic diagnosis. In this paper, we present a noreference quality metric to quantify image noise and blur and its application to fundus image quality assessment. The proposed metric takes the vessel tree visible on the retina as guidance to determine an image quality score. In our experiments, the performance of this approach is demonstrated by correlation analysis with the established full-reference metrics peak-signal-to-noise ratio (PSNR) and structural similarity (SSIM). We found a Spearman rank correlation for PSNR and SSIM of 0.89 and 0.91. For real data, our metric correlates reasonable to a human observer, indicating high agreement to human visual perception.

Keywords

fundus images, image quality assesment, fundus camera, blood vessel segmentation

Authors

KÖHLER, T.; BUDAI, A.; KRAUS, M.; ODSTRČILÍK, J.; MICHELSON, G.; HORNEGGER, J.

RIV year

2013

Released

20. 6. 2013

Publisher

University of Porto

Location

Porto, Portugalsko

ISBN

978-1-4799-1053-3

Book

26th IEEE International Symposium on Computer-Based Medical Systems

Edition

26

Pages from

95

Pages to

100

Pages count

6

BibTex

@inproceedings{BUT99737,
  author="Thomas {Köhler} and Attila {Budai} and Martin {Kraus} and Jan {Odstrčilík} and Georg {Michelson} and Joachim {Hornegger}",
  title="Automatic no-reference quality assessment for retinal fundus images using vessel segmentation",
  booktitle="26th IEEE International Symposium on Computer-Based Medical Systems",
  year="2013",
  series="26",
  pages="95--100",
  publisher="University of Porto",
  address="Porto, Portugalsko",
  isbn="978-1-4799-1053-3"
}