Multiscale retinal vessel segmentation with precise width estimation

Qin Li, Xuejin Li, Changjiang Song, Jia You

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

1 Citation (Scopus)


Automated segmentation of blood vessels in retinal images can tell us about retinal, ophthalmic and even systemic diseases so that it can help ophthalmologists screen larger populations for vessel abnormalities. For example, the vessel width shows the abnormality of arterial narrowing, a serious damage caused by hypertension. Because the width of retinal vessels can vary from very large to very small, and the local contrast of vessels is unstable especially in unhealthy ocular fundus, the automated vessel segmentation with precise width estimation is a very difficult task. In this paper, we propose an efficient multiscale vessel segmentation scheme. Our scheme includes 1) Image resampling using Lanczos interpolation, 2) Scale production to enhance vessels, and 3) Multiscale morphological reconstruction to segment vessels in each scale. The experimental results demonstrate that the proposed scheme works well for accurately segmenting vessels with good width estimation.
Original languageEnglish
Title of host publicationICCH 2012 Proceedings - International Conference on Computerized Healthcare
PublisherIEEE Computer Society
Number of pages4
ISBN (Print)9781467351294
Publication statusPublished - 1 Jan 2012
Event2012 International Conference on Computerized Healthcare, ICCH 2012 - Hong Kong, Hong Kong
Duration: 17 Dec 201218 Dec 2012


Conference2012 International Conference on Computerized Healthcare, ICCH 2012
Country/TerritoryHong Kong
CityHong Kong

ASJC Scopus subject areas

  • Health Informatics

Cite this