Publication detail

Automatic Rigid Registration and Analysis of Colour Fundus Image in Patients with Diabetic Retinopathy

KOLÁŘ, R. HARABIŠ, V.

Original Title

Automatic Rigid Registration and Analysis of Colour Fundus Image in Patients with Diabetic Retinopathy

English Title

Automatic Rigid Registration and Analysis of Colour Fundus Image in Patients with Diabetic Retinopathy

Type

conference proceedings

Language

en

Original Abstract

This paper describes a new method for detection biffurcation points of retinal vascular tree. This approach uses Hessian matrix for blood vessel segmentation, followed by morphological thinning and binary matched filtering. Thesebifurcation points are consequently used as landmarks for rigid image registration based on the iterative closest point method. Registered images were used for simple analysis with the aim to enhance the new pathologies in analyzed image sequence.

English abstract

This paper describes a new method for detection biffurcation points of retinal vascular tree. This approach uses Hessian matrix for blood vessel segmentation, followed by morphological thinning and binary matched filtering. Thesebifurcation points are consequently used as landmarks for rigid image registration based on the iterative closest point method. Registered images were used for simple analysis with the aim to enhance the new pathologies in analyzed image sequence.

Keywords

Diabetic retinopathy, landmark registration, feature detection, blood vessel segmentation

Released

07.09.2009

Publisher

Springer

ISBN

978-3-642-03881-5

Book

World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany

Edition number

25/IV

Pages from

251

Pages to

254

Pages count

4

BibTex


@proceedings{BUT65676,
  author="Radim {Kolář} and Vratislav {Harabiš}",
  title="Automatic Rigid Registration and Analysis of Colour Fundus Image in Patients with Diabetic Retinopathy",
  annote="This paper describes a new method for detection biffurcation points of retinal vascular tree. This approach uses Hessian matrix for blood vessel segmentation, followed by morphological thinning and binary matched filtering. Thesebifurcation points are consequently used as landmarks for
rigid image registration based on the iterative closest point  method. Registered images were used for simple analysis with the aim to enhance the new pathologies in analyzed image sequence.",
  address="Springer",
  booktitle="World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany",
  chapter="65676",
  institution="Springer",
  year="2009",
  month="september",
  pages="251--254",
  publisher="Springer",
  type="conference proceedings"
}