Home > Research > Publications & Outputs > Dense Fully Convolutional Segmentation of the O...

Links

Text available via DOI:

View graph of relations

Dense Fully Convolutional Segmentation of the Optic Disc and Cup in Colour Fundus for Glaucoma Diagnosis

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Dense Fully Convolutional Segmentation of the Optic Disc and Cup in Colour Fundus for Glaucoma Diagnosis. / Al-Bander, Baidaa; Williams, Bryan; Al-Nuaimy, Waleed et al.
In: Symmetry, Vol. 10, No. 4, 87, 30.03.2018.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Al-Bander, B., Williams, B., Al-Nuaimy, W., Al-Taee, M., Pratt, H., & Zheng, Y. (2018). Dense Fully Convolutional Segmentation of the Optic Disc and Cup in Colour Fundus for Glaucoma Diagnosis. Symmetry, 10(4), Article 87. https://doi.org/10.3390/sym10040087

Vancouver

Al-Bander B, Williams B, Al-Nuaimy W, Al-Taee M, Pratt H, Zheng Y. Dense Fully Convolutional Segmentation of the Optic Disc and Cup in Colour Fundus for Glaucoma Diagnosis. Symmetry. 2018 Mar 30;10(4):87. doi: 10.3390/sym10040087

Author

Al-Bander, Baidaa ; Williams, Bryan ; Al-Nuaimy, Waleed et al. / Dense Fully Convolutional Segmentation of the Optic Disc and Cup in Colour Fundus for Glaucoma Diagnosis. In: Symmetry. 2018 ; Vol. 10, No. 4.

Bibtex

@article{61787e9993344d92b847be21af83a9f2,
title = "Dense Fully Convolutional Segmentation of the Optic Disc and Cup in Colour Fundus for Glaucoma Diagnosis",
abstract = "Glaucoma is a group of eye diseases which can cause vision loss by damaging the optic nerve. Early glaucoma detection is key to preventing vision loss yet there is a lack of noticeable early symptoms. Colour fundus photography allows the optic disc (OD) to be examined to diagnose glaucoma. Typically, this is done by measuring the vertical cup-to-disc ratio (CDR); however, glaucoma is characterised by thinning of the rim asymmetrically in the inferior-superior-temporal-nasal regions in increasing order. Automatic delineation of the OD features has potential to improve glaucoma management by allowing for this asymmetry to be considered in the measurements. Here, we propose a new deep-learning-based method to segment the OD and optic cup (OC). The core of the proposed method is DenseNet with a fully-convolutional network, whose symmetric U-shaped architecture allows pixel-wise classification. The predicted OD and OC boundaries are then used to estimate the CDR on two axes for glaucoma diagnosis. We assess the proposed method{\textquoteright}s performance using a large retinal colour fundus dataset, outperforming state-of-the-art segmentation methods. Furthermore, we generalise our method to segment four fundus datasets from different devices without further training, outperforming the state-of-the-art on two and achieving comparable results on the remaining two.",
author = "Baidaa Al-Bander and Bryan Williams and Waleed Al-Nuaimy and Majid Al-Taee and Harry Pratt and Yalin Zheng",
year = "2018",
month = mar,
day = "30",
doi = "10.3390/sym10040087",
language = "English",
volume = "10",
journal = "Symmetry",
issn = "2073-8994",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "4",

}

RIS

TY - JOUR

T1 - Dense Fully Convolutional Segmentation of the Optic Disc and Cup in Colour Fundus for Glaucoma Diagnosis

AU - Al-Bander, Baidaa

AU - Williams, Bryan

AU - Al-Nuaimy, Waleed

AU - Al-Taee, Majid

AU - Pratt, Harry

AU - Zheng, Yalin

PY - 2018/3/30

Y1 - 2018/3/30

N2 - Glaucoma is a group of eye diseases which can cause vision loss by damaging the optic nerve. Early glaucoma detection is key to preventing vision loss yet there is a lack of noticeable early symptoms. Colour fundus photography allows the optic disc (OD) to be examined to diagnose glaucoma. Typically, this is done by measuring the vertical cup-to-disc ratio (CDR); however, glaucoma is characterised by thinning of the rim asymmetrically in the inferior-superior-temporal-nasal regions in increasing order. Automatic delineation of the OD features has potential to improve glaucoma management by allowing for this asymmetry to be considered in the measurements. Here, we propose a new deep-learning-based method to segment the OD and optic cup (OC). The core of the proposed method is DenseNet with a fully-convolutional network, whose symmetric U-shaped architecture allows pixel-wise classification. The predicted OD and OC boundaries are then used to estimate the CDR on two axes for glaucoma diagnosis. We assess the proposed method’s performance using a large retinal colour fundus dataset, outperforming state-of-the-art segmentation methods. Furthermore, we generalise our method to segment four fundus datasets from different devices without further training, outperforming the state-of-the-art on two and achieving comparable results on the remaining two.

AB - Glaucoma is a group of eye diseases which can cause vision loss by damaging the optic nerve. Early glaucoma detection is key to preventing vision loss yet there is a lack of noticeable early symptoms. Colour fundus photography allows the optic disc (OD) to be examined to diagnose glaucoma. Typically, this is done by measuring the vertical cup-to-disc ratio (CDR); however, glaucoma is characterised by thinning of the rim asymmetrically in the inferior-superior-temporal-nasal regions in increasing order. Automatic delineation of the OD features has potential to improve glaucoma management by allowing for this asymmetry to be considered in the measurements. Here, we propose a new deep-learning-based method to segment the OD and optic cup (OC). The core of the proposed method is DenseNet with a fully-convolutional network, whose symmetric U-shaped architecture allows pixel-wise classification. The predicted OD and OC boundaries are then used to estimate the CDR on two axes for glaucoma diagnosis. We assess the proposed method’s performance using a large retinal colour fundus dataset, outperforming state-of-the-art segmentation methods. Furthermore, we generalise our method to segment four fundus datasets from different devices without further training, outperforming the state-of-the-art on two and achieving comparable results on the remaining two.

U2 - 10.3390/sym10040087

DO - 10.3390/sym10040087

M3 - Journal article

VL - 10

JO - Symmetry

JF - Symmetry

SN - 2073-8994

IS - 4

M1 - 87

ER -