A novel method for automatic hard exudates detection in color retinal images

Xiang Chen; Wei Bu; Xiangqian Wu; Baisheng Dai; Yan Teng

doi:10.1109/ICMLC.2012.6359522

A novel method for automatic hard exudates detection in color retinal images

Xiang Chen
, Wei Bu^*
, Xiangqian Wu
, Baisheng Dai
, Yan Teng

^*Corresponding author for this work

School of Computer Science and Technology, Harbin Institute of Technology
Harbin Institute of Technology
Harbin Medical University

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

18 Scopus citations

Abstract

Diabetic Retinopathy (DR) is one of the major causes of blindness, and Hard Exudates (HEs) which are common and early clinical signs of DR. This paper presented a novel method to automatically detect HEs in color retinal images. We first extract HEs candidate regions by combining histogram segmentation with morphological reconstruction. Next, we define 44 significant features for each candidate region. A supervised support vector machine (SVM) is finally trained based on these features to classify the candidate regions for HEs. We evaluate the proposed method on the public DIARETDB1 database and achieve an sensitivity of 94.7% and an positive predictive value of 90.0%. Experimental results show that our method can produce reliable detection of HEs.

Original language	English
Title of host publication	Proceedings of 2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012
Publisher	IEEE Computer Society
Pages	1175-1181
Number of pages	7
ISBN (Print)	9781467314855
DOIs	https://doi.org/10.1109/ICMLC.2012.6359522
State	Published - 2012
Externally published	Yes
Event	2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012 - Xian, Shaanxi, China Duration: 15 Jul 2012 → 17 Jul 2012

Publication series

Name	Proceedings - International Conference on Machine Learning and Cybernetics
Volume	3
ISSN (Print)	2160-133X
ISSN (Electronic)	2160-1348

Conference

Conference	2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012
Country/Territory	China
City	Xian, Shaanxi
Period	15/07/12 → 17/07/12

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Diabetic retinopathy
Hard Exudates
Histogram segmentation
Morphological reconstruction
SVM

Access to Document

10.1109/ICMLC.2012.6359522

Cite this

Chen, X., Bu, W., Wu, X., Dai, B., & Teng, Y. (2012). A novel method for automatic hard exudates detection in color retinal images. In Proceedings of 2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012 (pp. 1175-1181). Article 6359522 (Proceedings - International Conference on Machine Learning and Cybernetics; Vol. 3). IEEE Computer Society. https://doi.org/10.1109/ICMLC.2012.6359522

@inproceedings{09c1c056221c40a78932aa1ab9c42c48,

title = "A novel method for automatic hard exudates detection in color retinal images",

abstract = "Diabetic Retinopathy (DR) is one of the major causes of blindness, and Hard Exudates (HEs) which are common and early clinical signs of DR. This paper presented a novel method to automatically detect HEs in color retinal images. We first extract HEs candidate regions by combining histogram segmentation with morphological reconstruction. Next, we define 44 significant features for each candidate region. A supervised support vector machine (SVM) is finally trained based on these features to classify the candidate regions for HEs. We evaluate the proposed method on the public DIARETDB1 database and achieve an sensitivity of 94.7\% and an positive predictive value of 90.0\%. Experimental results show that our method can produce reliable detection of HEs.",

keywords = "Diabetic retinopathy, Hard Exudates, Histogram segmentation, Morphological reconstruction, SVM",

author = "Xiang Chen and Wei Bu and Xiangqian Wu and Baisheng Dai and Yan Teng",

year = "2012",

doi = "10.1109/ICMLC.2012.6359522",

language = "英语",

isbn = "9781467314855",

series = "Proceedings - International Conference on Machine Learning and Cybernetics",

publisher = "IEEE Computer Society",

pages = "1175--1181",

booktitle = "Proceedings of 2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012",

address = "美国",

note = "2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012 ; Conference date: 15-07-2012 Through 17-07-2012",

}

Chen, X, Bu, W, Wu, X, Dai, B & Teng, Y 2012, A novel method for automatic hard exudates detection in color retinal images. in Proceedings of 2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012., 6359522, Proceedings - International Conference on Machine Learning and Cybernetics, vol. 3, IEEE Computer Society, pp. 1175-1181, 2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012, Xian, Shaanxi, China, 15/07/12. https://doi.org/10.1109/ICMLC.2012.6359522

A novel method for automatic hard exudates detection in color retinal images. / Chen, Xiang; Bu, Wei; Wu, Xiangqian et al.
Proceedings of 2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012. IEEE Computer Society, 2012. p. 1175-1181 6359522 (Proceedings - International Conference on Machine Learning and Cybernetics; Vol. 3).

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

TY - GEN

T1 - A novel method for automatic hard exudates detection in color retinal images

AU - Chen, Xiang

AU - Bu, Wei

AU - Wu, Xiangqian

AU - Dai, Baisheng

AU - Teng, Yan

PY - 2012

Y1 - 2012

N2 - Diabetic Retinopathy (DR) is one of the major causes of blindness, and Hard Exudates (HEs) which are common and early clinical signs of DR. This paper presented a novel method to automatically detect HEs in color retinal images. We first extract HEs candidate regions by combining histogram segmentation with morphological reconstruction. Next, we define 44 significant features for each candidate region. A supervised support vector machine (SVM) is finally trained based on these features to classify the candidate regions for HEs. We evaluate the proposed method on the public DIARETDB1 database and achieve an sensitivity of 94.7% and an positive predictive value of 90.0%. Experimental results show that our method can produce reliable detection of HEs.

AB - Diabetic Retinopathy (DR) is one of the major causes of blindness, and Hard Exudates (HEs) which are common and early clinical signs of DR. This paper presented a novel method to automatically detect HEs in color retinal images. We first extract HEs candidate regions by combining histogram segmentation with morphological reconstruction. Next, we define 44 significant features for each candidate region. A supervised support vector machine (SVM) is finally trained based on these features to classify the candidate regions for HEs. We evaluate the proposed method on the public DIARETDB1 database and achieve an sensitivity of 94.7% and an positive predictive value of 90.0%. Experimental results show that our method can produce reliable detection of HEs.

KW - Diabetic retinopathy

KW - Hard Exudates

KW - Histogram segmentation

KW - Morphological reconstruction

KW - SVM

UR - https://www.scopus.com/pages/publications/84871551247

U2 - 10.1109/ICMLC.2012.6359522

DO - 10.1109/ICMLC.2012.6359522

M3 - 会议稿件

AN - SCOPUS:84871551247

SN - 9781467314855

T3 - Proceedings - International Conference on Machine Learning and Cybernetics

SP - 1175

EP - 1181

BT - Proceedings of 2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012

PB - IEEE Computer Society

T2 - 2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012

Y2 - 15 July 2012 through 17 July 2012

ER -

Chen X, Bu W, Wu X, Dai B, Teng Y. A novel method for automatic hard exudates detection in color retinal images. In Proceedings of 2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012. IEEE Computer Society. 2012. p. 1175-1181. 6359522. (Proceedings - International Conference on Machine Learning and Cybernetics). doi: 10.1109/ICMLC.2012.6359522

A novel method for automatic hard exudates detection in color retinal images

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this