Optic Nerve Head Segmentation in HRT Images

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

Accurate segmentation of the optic nerve head (or optic disk) is very useful during the analysis and assessment of glaucoma in the eye. The Heidelberg retinal tomograph (HRT) can acquire high quality images of the optic disk and also allows three dimensional topographic measurements to be made. However, there are significant problems in optic disk segmentation due to having to deal with issues such as distractors along blood vessel edges; the extent of pallor in the optic disk or the very variable appearance of the optic nerve head itself. We propose a multi-scale region and boundary hybrid snake method to extract the optic disk. This model takes account of the vessel edge gradient direction and tries to avoid its force influence when evolving the snake. Experimental results are assessed using an overlap ratio
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages65-68
Number of pages4
DOIs
Publication statusPublished - Oct 2006
EventIEEE International Conference on Image Processing, 2006 (ICIP 2006) -
Duration: 1 Oct 2006 → …

Conference

ConferenceIEEE International Conference on Image Processing, 2006 (ICIP 2006)
Period1/10/06 → …

Fingerprint

Optics
Blood vessels
Image quality

Cite this

Yang, Xiaoyun ; Morrow, Philip ; Scotney, Bryan. / Optic Nerve Head Segmentation in HRT Images. Unknown Host Publication. 2006. pp. 65-68
@inproceedings{47d8679bc4cd40d28a4984f7a455afcd,
title = "Optic Nerve Head Segmentation in HRT Images",
abstract = "Accurate segmentation of the optic nerve head (or optic disk) is very useful during the analysis and assessment of glaucoma in the eye. The Heidelberg retinal tomograph (HRT) can acquire high quality images of the optic disk and also allows three dimensional topographic measurements to be made. However, there are significant problems in optic disk segmentation due to having to deal with issues such as distractors along blood vessel edges; the extent of pallor in the optic disk or the very variable appearance of the optic nerve head itself. We propose a multi-scale region and boundary hybrid snake method to extract the optic disk. This model takes account of the vessel edge gradient direction and tries to avoid its force influence when evolving the snake. Experimental results are assessed using an overlap ratio",
author = "Xiaoyun Yang and Philip Morrow and Bryan Scotney",
year = "2006",
month = "10",
doi = "10.1109/ICIP.2006.312358",
language = "English",
pages = "65--68",
booktitle = "Unknown Host Publication",

}

Yang, X, Morrow, P & Scotney, B 2006, Optic Nerve Head Segmentation in HRT Images. in Unknown Host Publication. pp. 65-68, IEEE International Conference on Image Processing, 2006 (ICIP 2006), 1/10/06. https://doi.org/10.1109/ICIP.2006.312358

Optic Nerve Head Segmentation in HRT Images. / Yang, Xiaoyun; Morrow, Philip; Scotney, Bryan.

Unknown Host Publication. 2006. p. 65-68.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Optic Nerve Head Segmentation in HRT Images

AU - Yang, Xiaoyun

AU - Morrow, Philip

AU - Scotney, Bryan

PY - 2006/10

Y1 - 2006/10

N2 - Accurate segmentation of the optic nerve head (or optic disk) is very useful during the analysis and assessment of glaucoma in the eye. The Heidelberg retinal tomograph (HRT) can acquire high quality images of the optic disk and also allows three dimensional topographic measurements to be made. However, there are significant problems in optic disk segmentation due to having to deal with issues such as distractors along blood vessel edges; the extent of pallor in the optic disk or the very variable appearance of the optic nerve head itself. We propose a multi-scale region and boundary hybrid snake method to extract the optic disk. This model takes account of the vessel edge gradient direction and tries to avoid its force influence when evolving the snake. Experimental results are assessed using an overlap ratio

AB - Accurate segmentation of the optic nerve head (or optic disk) is very useful during the analysis and assessment of glaucoma in the eye. The Heidelberg retinal tomograph (HRT) can acquire high quality images of the optic disk and also allows three dimensional topographic measurements to be made. However, there are significant problems in optic disk segmentation due to having to deal with issues such as distractors along blood vessel edges; the extent of pallor in the optic disk or the very variable appearance of the optic nerve head itself. We propose a multi-scale region and boundary hybrid snake method to extract the optic disk. This model takes account of the vessel edge gradient direction and tries to avoid its force influence when evolving the snake. Experimental results are assessed using an overlap ratio

U2 - 10.1109/ICIP.2006.312358

DO - 10.1109/ICIP.2006.312358

M3 - Conference contribution

SP - 65

EP - 68

BT - Unknown Host Publication

ER -