Optic disc boundary and vessel origin segmentation of fundus images

Sohini Roychowdhury, Dara Koozekanani, Sam N. Kuchinka, Keshab K Parhi

Research output: Contribution to journalArticle

34 Citations (Scopus)

Abstract

This paper presents a novel classification-based optic disc (OD) segmentation algorithm that detects the OD boundary and the location of vessel origin (VO) pixel. First, the green plane of each fundus image is resized and morphologically reconstructed using a circular structuring element. Bright regions are then extracted from the morphologically reconstructed image that lie in close vicinity of the major blood vessels. Next, the bright regions are classified as bright probable OD regions and non-OD regions using six region-based features and a Gaussian mixture model classifier. The classified bright probable OD region with maximum Vessel-Sum and Solidity is detected as the best candidate region for the OD. Other bright probable OD regions within 1-disc diameter from the centroid of the best candidate OD region are then detected as remaining candidate regions for the OD. A convex hull containing all the candidate OD regions is then estimated, and a best-fit ellipse across the convex hull becomes the segmented OD boundary. Finally, the centroid of major blood vessels within the segmented OD boundary is detected as the VO pixel location. The proposed algorithm has low computation time complexity and it is robust to variations in image illumination, imaging angles, and retinal abnormalities. This algorithm achieves 98.8%-100% OD segmentation success and OD segmentation overlap score in the range of 72%-84% on images from the six public datasets of DRIVE, DIARETDB1, DIARETDB0, CHASE-DB1,MESSIDOR, and STARE in less than 2.14 s per image. Thus, the proposed algorithm can be used for automated detection of retinal pathologies, such as glaucoma, diabetic retinopathy, and maculopathy.

Original languageEnglish (US)
Pages (from-to)1562-1574
Number of pages13
JournalIEEE Journal of Biomedical and Health Informatics
Volume20
Issue number6
DOIs
StatePublished - Nov 1 2016

Fingerprint

Optic Disk
Optics
Blood vessels
Blood Vessels
Pixels
Diabetic Retinopathy
Lighting
Glaucoma
Pathology

Keywords

  • Centroid
  • Major vessels
  • Optic disc (OD)
  • Overlap score
  • Solidity
  • Vessel origin (VO)

Cite this

Optic disc boundary and vessel origin segmentation of fundus images. / Roychowdhury, Sohini; Koozekanani, Dara; Kuchinka, Sam N.; Parhi, Keshab K.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 20, No. 6, 01.11.2016, p. 1562-1574.

Research output: Contribution to journalArticle

@article{62cf81e70b2547b4b98b60a6646c1a29,
title = "Optic disc boundary and vessel origin segmentation of fundus images",
abstract = "This paper presents a novel classification-based optic disc (OD) segmentation algorithm that detects the OD boundary and the location of vessel origin (VO) pixel. First, the green plane of each fundus image is resized and morphologically reconstructed using a circular structuring element. Bright regions are then extracted from the morphologically reconstructed image that lie in close vicinity of the major blood vessels. Next, the bright regions are classified as bright probable OD regions and non-OD regions using six region-based features and a Gaussian mixture model classifier. The classified bright probable OD region with maximum Vessel-Sum and Solidity is detected as the best candidate region for the OD. Other bright probable OD regions within 1-disc diameter from the centroid of the best candidate OD region are then detected as remaining candidate regions for the OD. A convex hull containing all the candidate OD regions is then estimated, and a best-fit ellipse across the convex hull becomes the segmented OD boundary. Finally, the centroid of major blood vessels within the segmented OD boundary is detected as the VO pixel location. The proposed algorithm has low computation time complexity and it is robust to variations in image illumination, imaging angles, and retinal abnormalities. This algorithm achieves 98.8{\%}-100{\%} OD segmentation success and OD segmentation overlap score in the range of 72{\%}-84{\%} on images from the six public datasets of DRIVE, DIARETDB1, DIARETDB0, CHASE-DB1,MESSIDOR, and STARE in less than 2.14 s per image. Thus, the proposed algorithm can be used for automated detection of retinal pathologies, such as glaucoma, diabetic retinopathy, and maculopathy.",
keywords = "Centroid, Major vessels, Optic disc (OD), Overlap score, Solidity, Vessel origin (VO)",
author = "Sohini Roychowdhury and Dara Koozekanani and Kuchinka, {Sam N.} and Parhi, {Keshab K}",
year = "2016",
month = "11",
day = "1",
doi = "10.1109/JBHI.2015.2473159",
language = "English (US)",
volume = "20",
pages = "1562--1574",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - Optic disc boundary and vessel origin segmentation of fundus images

AU - Roychowdhury, Sohini

AU - Koozekanani, Dara

AU - Kuchinka, Sam N.

AU - Parhi, Keshab K

PY - 2016/11/1

Y1 - 2016/11/1

N2 - This paper presents a novel classification-based optic disc (OD) segmentation algorithm that detects the OD boundary and the location of vessel origin (VO) pixel. First, the green plane of each fundus image is resized and morphologically reconstructed using a circular structuring element. Bright regions are then extracted from the morphologically reconstructed image that lie in close vicinity of the major blood vessels. Next, the bright regions are classified as bright probable OD regions and non-OD regions using six region-based features and a Gaussian mixture model classifier. The classified bright probable OD region with maximum Vessel-Sum and Solidity is detected as the best candidate region for the OD. Other bright probable OD regions within 1-disc diameter from the centroid of the best candidate OD region are then detected as remaining candidate regions for the OD. A convex hull containing all the candidate OD regions is then estimated, and a best-fit ellipse across the convex hull becomes the segmented OD boundary. Finally, the centroid of major blood vessels within the segmented OD boundary is detected as the VO pixel location. The proposed algorithm has low computation time complexity and it is robust to variations in image illumination, imaging angles, and retinal abnormalities. This algorithm achieves 98.8%-100% OD segmentation success and OD segmentation overlap score in the range of 72%-84% on images from the six public datasets of DRIVE, DIARETDB1, DIARETDB0, CHASE-DB1,MESSIDOR, and STARE in less than 2.14 s per image. Thus, the proposed algorithm can be used for automated detection of retinal pathologies, such as glaucoma, diabetic retinopathy, and maculopathy.

AB - This paper presents a novel classification-based optic disc (OD) segmentation algorithm that detects the OD boundary and the location of vessel origin (VO) pixel. First, the green plane of each fundus image is resized and morphologically reconstructed using a circular structuring element. Bright regions are then extracted from the morphologically reconstructed image that lie in close vicinity of the major blood vessels. Next, the bright regions are classified as bright probable OD regions and non-OD regions using six region-based features and a Gaussian mixture model classifier. The classified bright probable OD region with maximum Vessel-Sum and Solidity is detected as the best candidate region for the OD. Other bright probable OD regions within 1-disc diameter from the centroid of the best candidate OD region are then detected as remaining candidate regions for the OD. A convex hull containing all the candidate OD regions is then estimated, and a best-fit ellipse across the convex hull becomes the segmented OD boundary. Finally, the centroid of major blood vessels within the segmented OD boundary is detected as the VO pixel location. The proposed algorithm has low computation time complexity and it is robust to variations in image illumination, imaging angles, and retinal abnormalities. This algorithm achieves 98.8%-100% OD segmentation success and OD segmentation overlap score in the range of 72%-84% on images from the six public datasets of DRIVE, DIARETDB1, DIARETDB0, CHASE-DB1,MESSIDOR, and STARE in less than 2.14 s per image. Thus, the proposed algorithm can be used for automated detection of retinal pathologies, such as glaucoma, diabetic retinopathy, and maculopathy.

KW - Centroid

KW - Major vessels

KW - Optic disc (OD)

KW - Overlap score

KW - Solidity

KW - Vessel origin (VO)

UR - http://www.scopus.com/inward/record.url?scp=85027067344&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027067344&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2015.2473159

DO - 10.1109/JBHI.2015.2473159

M3 - Article

C2 - 26316237

AN - SCOPUS:85027067344

VL - 20

SP - 1562

EP - 1574

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 6

ER -