Detail publikace

Automatické hodnocení kvality snímků sítnice pomocí segmentace cévního řečiště

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

Originální název

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

Český název

Automatické hodnocení kvality snímků sítnice pomocí segmentace cévního řečiště

Anglický název

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

Typ

článek ve sborníku

Jazyk

en

Originální abstrakt

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.

Český abstrakt

Příspěvek popisuje možnost automatického hodnocení kvality snímků sítnice pořízených fundus kamerou. K hodnocení využívá segmentaci cévního řečiště.

Anglický abstrakt

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.

Klíčová slova

snímky sítnice, hodnocení kvality, fundus kamera, segmentace cévního řečiště

Rok RIV

2013

Vydáno

20.06.2013

Nakladatel

University of Porto

Místo

Porto, Portugalsko

ISBN

978-1-4799-1053-3

Kniha

26th IEEE International Symposium on Computer-Based Medical Systems

Edice

26

Strany od

95

Strany do

100

Strany počet

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",
  annote="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.",
  address="University of Porto",
  booktitle="26th IEEE International Symposium on Computer-Based Medical Systems",
  chapter="99737",
  edition="26",
  howpublished="electronic, physical medium",
  institution="University of Porto",
  year="2013",
  month="june",
  pages="95--100",
  publisher="University of Porto",
  type="conference paper"
}