Automatic segmentation of PPA in retinal images

Hanxiang Li; Jieliang Kang; Yunlong Feng; Jie Xu; Huiqi Li

doi:10.1109/ICIEA.2018.8397999

Automatic segmentation of PPA in retinal images

Hanxiang Li
, Jieliang Kang
, Yunlong Feng
, Jie Xu
, Huiqi Li^*

^*Corresponding author for this work

School of Information and Electronics

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Citations (Scopus)

Abstract

Parapapillary atrophy (PPA) is a crescent atrophic abnormality adjacent to optic disc (OD), which lies in retinal pigment epithelium, photoreceptor and laminae choriocapillaris. Clinically, PPA is an indicator for clinical or computer aided diagnosis of pathologies of eyes, such as myopia and glaucoma. In this paper, an algorithm is proposed in order to automatically segment PPA from retinal images. Firstly, evenly-oriented radial line segments were used to detect the candidate boundary points of OD and augmented-OD (A-OD, which indicates the region that combines PPA and OD). Then, to obtain smooth, non-discrete boundaries of A-OD and OD, those points are fitted to ellipses by the least square method. Finally, the boundary of PPA is obtained after finding the non-overlapping part of these two boundaries. The algorithm needs the coordinate of the center of OD and its approximate radius as inputs, with assurance that input retinal image contains PPA. Experimental results based on 100 retinal images tested show that the average F-score of this algorithm reaches 0.67.

Original language	English
Title of host publication	Proceedings of the 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1791-1796
Number of pages	6
ISBN (Electronic)	9781538637579
DOIs	https://doi.org/10.1109/ICIEA.2018.8397999
Publication status	Published - 26 Jun 2018
Event	13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018 - Wuhan, China Duration: 31 May 2018 → 2 Jun 2018

Publication series

Name	Proceedings of the 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018

Conference

Conference	13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018
Country/Territory	China
City	Wuhan
Period	31/05/18 → 2/06/18

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

parapapillary atrophy
segmentation

Access to Document

10.1109/ICIEA.2018.8397999

Cite this

Li, H., Kang, J., Feng, Y., Xu, J., & Li, H. (2018). Automatic segmentation of PPA in retinal images. In Proceedings of the 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018 (pp. 1791-1796). (Proceedings of the 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIEA.2018.8397999

Li, Hanxiang ; Kang, Jieliang ; Feng, Yunlong et al. / Automatic segmentation of PPA in retinal images. Proceedings of the 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1791-1796 (Proceedings of the 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018).

@inproceedings{0cd7578371bb42bbb5f0816cdf8639f8,

title = "Automatic segmentation of PPA in retinal images",

abstract = "Parapapillary atrophy (PPA) is a crescent atrophic abnormality adjacent to optic disc (OD), which lies in retinal pigment epithelium, photoreceptor and laminae choriocapillaris. Clinically, PPA is an indicator for clinical or computer aided diagnosis of pathologies of eyes, such as myopia and glaucoma. In this paper, an algorithm is proposed in order to automatically segment PPA from retinal images. Firstly, evenly-oriented radial line segments were used to detect the candidate boundary points of OD and augmented-OD (A-OD, which indicates the region that combines PPA and OD). Then, to obtain smooth, non-discrete boundaries of A-OD and OD, those points are fitted to ellipses by the least square method. Finally, the boundary of PPA is obtained after finding the non-overlapping part of these two boundaries. The algorithm needs the coordinate of the center of OD and its approximate radius as inputs, with assurance that input retinal image contains PPA. Experimental results based on 100 retinal images tested show that the average F-score of this algorithm reaches 0.67.",

keywords = "parapapillary atrophy, segmentation",

author = "Hanxiang Li and Jieliang Kang and Yunlong Feng and Jie Xu and Huiqi Li",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018 ; Conference date: 31-05-2018 Through 02-06-2018",

year = "2018",

month = jun,

day = "26",

doi = "10.1109/ICIEA.2018.8397999",

language = "English",

series = "Proceedings of the 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1791--1796",

booktitle = "Proceedings of the 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018",

address = "United States",

}

Li, H, Kang, J, Feng, Y, Xu, J & Li, H 2018, Automatic segmentation of PPA in retinal images. in Proceedings of the 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018. Proceedings of the 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018, Institute of Electrical and Electronics Engineers Inc., pp. 1791-1796, 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018, Wuhan, China, 31/05/18. https://doi.org/10.1109/ICIEA.2018.8397999

Automatic segmentation of PPA in retinal images. / Li, Hanxiang; Kang, Jieliang; Feng, Yunlong et al.
Proceedings of the 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1791-1796 (Proceedings of the 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Automatic segmentation of PPA in retinal images

AU - Li, Hanxiang

AU - Kang, Jieliang

AU - Feng, Yunlong

AU - Xu, Jie

AU - Li, Huiqi

PY - 2018/6/26

Y1 - 2018/6/26

N2 - Parapapillary atrophy (PPA) is a crescent atrophic abnormality adjacent to optic disc (OD), which lies in retinal pigment epithelium, photoreceptor and laminae choriocapillaris. Clinically, PPA is an indicator for clinical or computer aided diagnosis of pathologies of eyes, such as myopia and glaucoma. In this paper, an algorithm is proposed in order to automatically segment PPA from retinal images. Firstly, evenly-oriented radial line segments were used to detect the candidate boundary points of OD and augmented-OD (A-OD, which indicates the region that combines PPA and OD). Then, to obtain smooth, non-discrete boundaries of A-OD and OD, those points are fitted to ellipses by the least square method. Finally, the boundary of PPA is obtained after finding the non-overlapping part of these two boundaries. The algorithm needs the coordinate of the center of OD and its approximate radius as inputs, with assurance that input retinal image contains PPA. Experimental results based on 100 retinal images tested show that the average F-score of this algorithm reaches 0.67.

AB - Parapapillary atrophy (PPA) is a crescent atrophic abnormality adjacent to optic disc (OD), which lies in retinal pigment epithelium, photoreceptor and laminae choriocapillaris. Clinically, PPA is an indicator for clinical or computer aided diagnosis of pathologies of eyes, such as myopia and glaucoma. In this paper, an algorithm is proposed in order to automatically segment PPA from retinal images. Firstly, evenly-oriented radial line segments were used to detect the candidate boundary points of OD and augmented-OD (A-OD, which indicates the region that combines PPA and OD). Then, to obtain smooth, non-discrete boundaries of A-OD and OD, those points are fitted to ellipses by the least square method. Finally, the boundary of PPA is obtained after finding the non-overlapping part of these two boundaries. The algorithm needs the coordinate of the center of OD and its approximate radius as inputs, with assurance that input retinal image contains PPA. Experimental results based on 100 retinal images tested show that the average F-score of this algorithm reaches 0.67.

KW - parapapillary atrophy

KW - segmentation

UR - https://www.scopus.com/pages/publications/85050165032

U2 - 10.1109/ICIEA.2018.8397999

DO - 10.1109/ICIEA.2018.8397999

M3 - Conference contribution

AN - SCOPUS:85050165032

T3 - Proceedings of the 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018

SP - 1791

EP - 1796

BT - Proceedings of the 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018

Y2 - 31 May 2018 through 2 June 2018

ER -

Li H, Kang J, Feng Y, Xu J, Li H. Automatic segmentation of PPA in retinal images. In Proceedings of the 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1791-1796. (Proceedings of the 13th IEEE Conference on Industrial Electronics and Applications, ICIEA 2018). doi: 10.1109/ICIEA.2018.8397999

Automatic segmentation of PPA in retinal images

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this