Optic Disc Segmentation from Retinal Fundus Images via Deep Object Detection Networks

Xu Sun; Yanwu Xu; Wei Zhao; Tianyuan You; Jiang Liu

doi:10.1109/EMBC.2018.8513592

Optic Disc Segmentation from Retinal Fundus Images via Deep Object Detection Networks

Xu Sun, Yanwu Xu, Wei Zhao, Tianyuan You, Jiang Liu

Research output: Journal Publication › Article › peer-review

27 Citations (Scopus)

Abstract

Accurate optic disc (OD) segmentation is a fundamental step in computer-aided ocular disease diagnosis. In this paper, we propose a new pipeline to segment OD from retinal fundus images based on deep object detection networks. The fundus image segmentation problem is redefined as a relatively more straightforward object detection task. This then allows us to determine the OD boundary simply by transforming the predicted bounding box into a vertical and non-rotated ellipse. Using Faster R-CNN as the object detector, our method achieves state-of-the-art OD segmentation results on ORIGA dataset, outperforming existing methods in this field.

Original language	English
Pages (from-to)	5954-5957
Number of pages	4
Journal	Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
Volume	2018
DOIs	https://doi.org/10.1109/EMBC.2018.8513592
Publication status	Published - 1 Jul 2018
Externally published	Yes

ASJC Scopus subject areas

Signal Processing
Biomedical Engineering
Computer Vision and Pattern Recognition
Health Informatics

UN SDGs

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

Access to Document

10.1109/EMBC.2018.8513592

Cite this

@article{bb6226c949944e2f890fff905be6e876,

title = "Optic Disc Segmentation from Retinal Fundus Images via Deep Object Detection Networks",

abstract = "Accurate optic disc (OD) segmentation is a fundamental step in computer-aided ocular disease diagnosis. In this paper, we propose a new pipeline to segment OD from retinal fundus images based on deep object detection networks. The fundus image segmentation problem is redefined as a relatively more straightforward object detection task. This then allows us to determine the OD boundary simply by transforming the predicted bounding box into a vertical and non-rotated ellipse. Using Faster R-CNN as the object detector, our method achieves state-of-the-art OD segmentation results on ORIGA dataset, outperforming existing methods in this field.",

author = "Xu Sun and Yanwu Xu and Wei Zhao and Tianyuan You and Jiang Liu",

year = "2018",

month = jul,

day = "1",

doi = "10.1109/EMBC.2018.8513592",

language = "English",

volume = "2018",

pages = "5954--5957",

journal = "Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings",

issn = "1557-170X",

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

}

TY - JOUR

T1 - Optic Disc Segmentation from Retinal Fundus Images via Deep Object Detection Networks

AU - Sun, Xu

AU - Xu, Yanwu

AU - Zhao, Wei

AU - You, Tianyuan

AU - Liu, Jiang

PY - 2018/7/1

Y1 - 2018/7/1

N2 - Accurate optic disc (OD) segmentation is a fundamental step in computer-aided ocular disease diagnosis. In this paper, we propose a new pipeline to segment OD from retinal fundus images based on deep object detection networks. The fundus image segmentation problem is redefined as a relatively more straightforward object detection task. This then allows us to determine the OD boundary simply by transforming the predicted bounding box into a vertical and non-rotated ellipse. Using Faster R-CNN as the object detector, our method achieves state-of-the-art OD segmentation results on ORIGA dataset, outperforming existing methods in this field.

AB - Accurate optic disc (OD) segmentation is a fundamental step in computer-aided ocular disease diagnosis. In this paper, we propose a new pipeline to segment OD from retinal fundus images based on deep object detection networks. The fundus image segmentation problem is redefined as a relatively more straightforward object detection task. This then allows us to determine the OD boundary simply by transforming the predicted bounding box into a vertical and non-rotated ellipse. Using Faster R-CNN as the object detector, our method achieves state-of-the-art OD segmentation results on ORIGA dataset, outperforming existing methods in this field.

UR - http://www.scopus.com/inward/record.url?scp=85056647484&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2018.8513592

DO - 10.1109/EMBC.2018.8513592

M3 - Article

C2 - 30441692

AN - SCOPUS:85056647484

SN - 1557-170X

VL - 2018

SP - 5954

EP - 5957

JO - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

JF - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

ER -

Optic Disc Segmentation from Retinal Fundus Images via Deep Object Detection Networks

Abstract

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this