Multi-scale morphological analysis for retinal vessel detection in wide-field fluorescein angiography

Li Ding, Ajay Kuriyan, Rajeev Ramchandran, Gaurav Sharma

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

2 Citations (Scopus)

Abstract

We describe a new method for accurate retinal vessel detection in wide-field fluorescein angiography (FA), which is a challenging problem because of the variations in vasculature between different orientations and large and small vessels, and the changes in the vasculature appearance as the injection of the dye perfuses the retina. Decomposing the original FA image into multiple resolutions, the vessels at each scale are segmented independently by first correcting for inhomogeneous illumination, then applying morphological operations to extract rectilinear structure and finally applying adaptive binarization. Specifically, a modified top-hat filter is applied using linear structuring elements with 9 directions. The maximum value of the resulting response images at each pixel location is then used for adaptive binarization. Final vessel segments are identified by fusing vessel segments at each scale. Quantitative results on VAMPIRE dataset, which includes high resolution wide-field FA images and hand-labeled ground truth vessel segments, demonstrate that the proposed method provides a significant improvement on vessel detection (approximately 10% higher recall, with same precision) than the method originally published with VAMPIRE dataset.

Original languageEnglish (US)
Title of host publication2017 IEEE Western New York Image and Signal Processing Workshop, WNYISPW 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-5
Number of pages5
ISBN (Electronic)9781538664902
DOIs
StatePublished - May 8 2018
Externally publishedYes
Event2017 IEEE Western New York Image and Signal Processing Workshop, WNYISPW 2017 - Rochester, United States
Duration: Nov 17 2017 → …

Other

Other2017 IEEE Western New York Image and Signal Processing Workshop, WNYISPW 2017
CountryUnited States
CityRochester
Period11/17/17 → …

Fingerprint

Angiography
Dyes
Lighting
Pixels

Keywords

  • Blood vessel detection
  • opthalmological image analysis
  • wide-field fluorescein angiography

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Ding, L., Kuriyan, A., Ramchandran, R., & Sharma, G. (2018). Multi-scale morphological analysis for retinal vessel detection in wide-field fluorescein angiography. In 2017 IEEE Western New York Image and Signal Processing Workshop, WNYISPW 2017 (pp. 1-5). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WNYIPW.2017.8356256

Multi-scale morphological analysis for retinal vessel detection in wide-field fluorescein angiography. / Ding, Li; Kuriyan, Ajay; Ramchandran, Rajeev; Sharma, Gaurav.

2017 IEEE Western New York Image and Signal Processing Workshop, WNYISPW 2017. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-5.

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

Ding, L, Kuriyan, A, Ramchandran, R & Sharma, G 2018, Multi-scale morphological analysis for retinal vessel detection in wide-field fluorescein angiography. in 2017 IEEE Western New York Image and Signal Processing Workshop, WNYISPW 2017. Institute of Electrical and Electronics Engineers Inc., pp. 1-5, 2017 IEEE Western New York Image and Signal Processing Workshop, WNYISPW 2017, Rochester, United States, 11/17/17. https://doi.org/10.1109/WNYIPW.2017.8356256
Ding L, Kuriyan A, Ramchandran R, Sharma G. Multi-scale morphological analysis for retinal vessel detection in wide-field fluorescein angiography. In 2017 IEEE Western New York Image and Signal Processing Workshop, WNYISPW 2017. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-5 https://doi.org/10.1109/WNYIPW.2017.8356256
Ding, Li ; Kuriyan, Ajay ; Ramchandran, Rajeev ; Sharma, Gaurav. / Multi-scale morphological analysis for retinal vessel detection in wide-field fluorescein angiography. 2017 IEEE Western New York Image and Signal Processing Workshop, WNYISPW 2017. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-5
@inproceedings{4eec19c748fd4cff944733003374bbae,
title = "Multi-scale morphological analysis for retinal vessel detection in wide-field fluorescein angiography",
abstract = "We describe a new method for accurate retinal vessel detection in wide-field fluorescein angiography (FA), which is a challenging problem because of the variations in vasculature between different orientations and large and small vessels, and the changes in the vasculature appearance as the injection of the dye perfuses the retina. Decomposing the original FA image into multiple resolutions, the vessels at each scale are segmented independently by first correcting for inhomogeneous illumination, then applying morphological operations to extract rectilinear structure and finally applying adaptive binarization. Specifically, a modified top-hat filter is applied using linear structuring elements with 9 directions. The maximum value of the resulting response images at each pixel location is then used for adaptive binarization. Final vessel segments are identified by fusing vessel segments at each scale. Quantitative results on VAMPIRE dataset, which includes high resolution wide-field FA images and hand-labeled ground truth vessel segments, demonstrate that the proposed method provides a significant improvement on vessel detection (approximately 10{\%} higher recall, with same precision) than the method originally published with VAMPIRE dataset.",
keywords = "Blood vessel detection, opthalmological image analysis, wide-field fluorescein angiography",
author = "Li Ding and Ajay Kuriyan and Rajeev Ramchandran and Gaurav Sharma",
year = "2018",
month = "5",
day = "8",
doi = "10.1109/WNYIPW.2017.8356256",
language = "English (US)",
pages = "1--5",
booktitle = "2017 IEEE Western New York Image and Signal Processing Workshop, WNYISPW 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Multi-scale morphological analysis for retinal vessel detection in wide-field fluorescein angiography

AU - Ding, Li

AU - Kuriyan, Ajay

AU - Ramchandran, Rajeev

AU - Sharma, Gaurav

PY - 2018/5/8

Y1 - 2018/5/8

N2 - We describe a new method for accurate retinal vessel detection in wide-field fluorescein angiography (FA), which is a challenging problem because of the variations in vasculature between different orientations and large and small vessels, and the changes in the vasculature appearance as the injection of the dye perfuses the retina. Decomposing the original FA image into multiple resolutions, the vessels at each scale are segmented independently by first correcting for inhomogeneous illumination, then applying morphological operations to extract rectilinear structure and finally applying adaptive binarization. Specifically, a modified top-hat filter is applied using linear structuring elements with 9 directions. The maximum value of the resulting response images at each pixel location is then used for adaptive binarization. Final vessel segments are identified by fusing vessel segments at each scale. Quantitative results on VAMPIRE dataset, which includes high resolution wide-field FA images and hand-labeled ground truth vessel segments, demonstrate that the proposed method provides a significant improvement on vessel detection (approximately 10% higher recall, with same precision) than the method originally published with VAMPIRE dataset.

AB - We describe a new method for accurate retinal vessel detection in wide-field fluorescein angiography (FA), which is a challenging problem because of the variations in vasculature between different orientations and large and small vessels, and the changes in the vasculature appearance as the injection of the dye perfuses the retina. Decomposing the original FA image into multiple resolutions, the vessels at each scale are segmented independently by first correcting for inhomogeneous illumination, then applying morphological operations to extract rectilinear structure and finally applying adaptive binarization. Specifically, a modified top-hat filter is applied using linear structuring elements with 9 directions. The maximum value of the resulting response images at each pixel location is then used for adaptive binarization. Final vessel segments are identified by fusing vessel segments at each scale. Quantitative results on VAMPIRE dataset, which includes high resolution wide-field FA images and hand-labeled ground truth vessel segments, demonstrate that the proposed method provides a significant improvement on vessel detection (approximately 10% higher recall, with same precision) than the method originally published with VAMPIRE dataset.

KW - Blood vessel detection

KW - opthalmological image analysis

KW - wide-field fluorescein angiography

UR - http://www.scopus.com/inward/record.url?scp=85048076267&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048076267&partnerID=8YFLogxK

U2 - 10.1109/WNYIPW.2017.8356256

DO - 10.1109/WNYIPW.2017.8356256

M3 - Conference contribution

SP - 1

EP - 5

BT - 2017 IEEE Western New York Image and Signal Processing Workshop, WNYISPW 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -