Publication detail

Retinal Vessel Segmentation by Improved Matched Filtering: Evaluation on a New High–Resolution Fundus Image Database

ODSTRČILÍK, J. KOLÁŘ, R. BUDAI, A. HORNEGGER, J. JAN, J. GAZÁREK, J. KUBĚNA, T. ČERNOŠEK, P. SVOBODA, O. ANGELOPOULOU, E.

Original Title

Retinal Vessel Segmentation by Improved Matched Filtering: Evaluation on a New High–Resolution Fundus Image Database

Czech Title

Segmentace cévního řečiště ze snímků sítnice pomocí přizpůsobené filtrace: vyhodnocení na nové databází snímků sítnice s vysokým rozlišením

English Title

Retinal Vessel Segmentation by Improved Matched Filtering: Evaluation on a New High–Resolution Fundus Image Database

Type

journal article

Language

en

Original Abstract

Automatic assessment of retinal vessels plays an important role in the diagnosis of various eye, as well as systemic diseases. A public screening is highly desirable for prompt and effective treatment, since such diseases need to be diagnosed at an early stage. Automated and accurate segmentation of the retinal blood vessel tree is one of the challenging tasks in the computer-aided analysis of fundus images today. We improve the concept of matched filtering, and propose a novel and accurate method for segmenting retinal vessels. Our goal is to be able to segment blood vessels with varying vessel diameters in high-resolution colour fundus images. All recent authors compare their vessel segmentation results to each other using only low-resolution retinal image databases. Consequently, we provide a new publicly available high-resolution fundus image database of healthy and pathological retinas. Our performance evaluation shows that the proposed blood vessel segmentation approach is at least comparable with recent state-of-the-art methods. It outperforms most of them with an accuracy of 95% evaluated on the new database.

Czech abstract

Příspěvek se zabývá segmentací cévního řečiště ze snímků sítnice pomocí přizpůsobené filtrace. K vyhodnocení metody byla vytvořena nová veřejná databáze se zlatými standardy.

English abstract

Automatic assessment of retinal vessels plays an important role in the diagnosis of various eye, as well as systemic diseases. A public screening is highly desirable for prompt and effective treatment, since such diseases need to be diagnosed at an early stage. Automated and accurate segmentation of the retinal blood vessel tree is one of the challenging tasks in the computer-aided analysis of fundus images today. We improve the concept of matched filtering, and propose a novel and accurate method for segmenting retinal vessels. Our goal is to be able to segment blood vessels with varying vessel diameters in high-resolution colour fundus images. All recent authors compare their vessel segmentation results to each other using only low-resolution retinal image databases. Consequently, we provide a new publicly available high-resolution fundus image database of healthy and pathological retinas. Our performance evaluation shows that the proposed blood vessel segmentation approach is at least comparable with recent state-of-the-art methods. It outperforms most of them with an accuracy of 95% evaluated on the new database.

Keywords

image segmentation, matched filters, retinal blood vessel segmentation, fundus images

RIV year

2013

Released

16.07.2013

Publisher

The Institution of Engineering and Technology

Location

Stevenage, UK

Pages from

373

Pages to

383

Pages count

10

URL

BibTex


@article{BUT98394,
  author="Jan {Odstrčilík} and Radim {Kolář} and Attila {Budai} and Joachim {Hornegger} and Jiří {Jan} and Jiří {Gazárek} and Tomáš {Kuběna} and Pavel {Černošek} and Ondřej {Svoboda} and Elli {Angelopoulou}",
  title="Retinal Vessel Segmentation by Improved Matched Filtering: Evaluation on a New High–Resolution Fundus Image Database",
  annote="Automatic assessment of retinal vessels plays an important role in the diagnosis of various eye, as well as systemic diseases. A public screening is highly desirable for prompt and effective treatment, since such diseases need to be diagnosed at an early stage. Automated and accurate segmentation of the retinal blood vessel tree is one of the challenging tasks in the computer-aided analysis of fundus images today. We improve the concept of matched filtering, and propose a novel and accurate method for segmenting retinal vessels. Our goal is to be able to segment blood vessels with varying vessel diameters in high-resolution colour fundus images. All recent authors compare their vessel segmentation results to each other using only low-resolution retinal image databases. Consequently, we provide a new publicly available high-resolution fundus image database of healthy and pathological retinas. Our performance evaluation shows that the proposed blood vessel segmentation approach is at least comparable with recent state-of-the-art methods. It outperforms most of them with an accuracy of 95% evaluated on the new database.",
  address="The Institution of Engineering and Technology",
  chapter="98394",
  doi="10.1049/iet-ipr.2012.0455",
  institution="The Institution of Engineering and Technology",
  number="4",
  volume="7",
  year="2013",
  month="july",
  pages="373--383",
  publisher="The Institution of Engineering and Technology",
  type="journal article"
}