Red lesion detection in retinal fundus images using Frangi-based filters

Ruchir Srivastava; Damon W.K. Wong; Lixin Duan; Jiang Liu; Tien Yin Wong

doi:10.1109/EMBC.2015.7319677

Red lesion detection in retinal fundus images using Frangi-based filters

Ruchir Srivastava
, Damon W.K. Wong
, Lixin Duan
, Jiang Liu
, Tien Yin Wong

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

44 Citations (Scopus)

Abstract

This paper presents a method to detect red lesions related to Diabetic Retinopathy (DR), namely Microaneurysms and Hemorrhages from retinal fundus images with robustness to the presence of blood vessels. Filters based on Frangi filters are used for the first time for this task. Green channel of the input image was decomposed into smaller sub images and proposed filters were applied to each sub image after initial preprocessing. Features were extracted from the filter response and used to train a Support Vector Machine classifier to predict whether a test image had lesions or not. Experiments were performed on a dataset of 143 retinal fundus and the proposed method achieved areas under the ROC curve equal to 0.97 and 0.87 for Microaneurysms and Hemorrhages respectively. Results show the effectiveness of the proposed method for detecting red lesions. This method can help significantly in automated detection of DR with fewer false positives.

Original language	English
Title of host publication	2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	5663-5666
Number of pages	4
ISBN (Electronic)	9781424492718
DOIs	https://doi.org/10.1109/EMBC.2015.7319677
Publication status	Published - 4 Nov 2015
Externally published	Yes
Event	37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015 - Milan, Italy Duration: 25 Aug 2015 → 29 Aug 2015

Publication series

Name	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Volume	2015-November
ISSN (Print)	1557-170X

Conference

Conference	37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015
Country/Territory	Italy
City	Milan
Period	25/08/15 → 29/08/15

UN SDGs

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

SDG 3 Good Health and Well-being

ASJC Scopus subject areas

Signal Processing
Biomedical Engineering
Computer Vision and Pattern Recognition
Health Informatics

Access to Document

10.1109/EMBC.2015.7319677

Cite this

Srivastava, R., Wong, D. W. K., Duan, L., Liu, J., & Wong, T. Y. (2015). Red lesion detection in retinal fundus images using Frangi-based filters. In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015 (pp. 5663-5666). Article 7319677 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Vol. 2015-November). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2015.7319677

Srivastava, Ruchir ; Wong, Damon W.K. ; Duan, Lixin et al. / Red lesion detection in retinal fundus images using Frangi-based filters. 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 5663-5666 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

@inproceedings{35ac85f99cfd438b88838430bf5b4ef9,

title = "Red lesion detection in retinal fundus images using Frangi-based filters",

abstract = "This paper presents a method to detect red lesions related to Diabetic Retinopathy (DR), namely Microaneurysms and Hemorrhages from retinal fundus images with robustness to the presence of blood vessels. Filters based on Frangi filters are used for the first time for this task. Green channel of the input image was decomposed into smaller sub images and proposed filters were applied to each sub image after initial preprocessing. Features were extracted from the filter response and used to train a Support Vector Machine classifier to predict whether a test image had lesions or not. Experiments were performed on a dataset of 143 retinal fundus and the proposed method achieved areas under the ROC curve equal to 0.97 and 0.87 for Microaneurysms and Hemorrhages respectively. Results show the effectiveness of the proposed method for detecting red lesions. This method can help significantly in automated detection of DR with fewer false positives.",

author = "Ruchir Srivastava and Wong, \{Damon W.K.\} and Lixin Duan and Jiang Liu and Wong, \{Tien Yin\}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015 ; Conference date: 25-08-2015 Through 29-08-2015",

year = "2015",

month = nov,

day = "4",

doi = "10.1109/EMBC.2015.7319677",

language = "English",

series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

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

pages = "5663--5666",

booktitle = "2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015",

address = "United States",

}

Srivastava, R, Wong, DWK, Duan, L, Liu, J & Wong, TY 2015, Red lesion detection in retinal fundus images using Frangi-based filters. in 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015., 7319677, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, vol. 2015-November, Institute of Electrical and Electronics Engineers Inc., pp. 5663-5666, 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015, Milan, Italy, 25/08/15. https://doi.org/10.1109/EMBC.2015.7319677

Red lesion detection in retinal fundus images using Frangi-based filters. / Srivastava, Ruchir; Wong, Damon W.K.; Duan, Lixin et al.
2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 5663-5666 7319677 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Vol. 2015-November).

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

TY - GEN

T1 - Red lesion detection in retinal fundus images using Frangi-based filters

AU - Srivastava, Ruchir

AU - Wong, Damon W.K.

AU - Duan, Lixin

AU - Liu, Jiang

AU - Wong, Tien Yin

PY - 2015/11/4

Y1 - 2015/11/4

N2 - This paper presents a method to detect red lesions related to Diabetic Retinopathy (DR), namely Microaneurysms and Hemorrhages from retinal fundus images with robustness to the presence of blood vessels. Filters based on Frangi filters are used for the first time for this task. Green channel of the input image was decomposed into smaller sub images and proposed filters were applied to each sub image after initial preprocessing. Features were extracted from the filter response and used to train a Support Vector Machine classifier to predict whether a test image had lesions or not. Experiments were performed on a dataset of 143 retinal fundus and the proposed method achieved areas under the ROC curve equal to 0.97 and 0.87 for Microaneurysms and Hemorrhages respectively. Results show the effectiveness of the proposed method for detecting red lesions. This method can help significantly in automated detection of DR with fewer false positives.

AB - This paper presents a method to detect red lesions related to Diabetic Retinopathy (DR), namely Microaneurysms and Hemorrhages from retinal fundus images with robustness to the presence of blood vessels. Filters based on Frangi filters are used for the first time for this task. Green channel of the input image was decomposed into smaller sub images and proposed filters were applied to each sub image after initial preprocessing. Features were extracted from the filter response and used to train a Support Vector Machine classifier to predict whether a test image had lesions or not. Experiments were performed on a dataset of 143 retinal fundus and the proposed method achieved areas under the ROC curve equal to 0.97 and 0.87 for Microaneurysms and Hemorrhages respectively. Results show the effectiveness of the proposed method for detecting red lesions. This method can help significantly in automated detection of DR with fewer false positives.

UR - https://www.scopus.com/pages/publications/84953268198

U2 - 10.1109/EMBC.2015.7319677

DO - 10.1109/EMBC.2015.7319677

M3 - Conference contribution

C2 - 26737577

AN - SCOPUS:84953268198

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 5663

EP - 5666

BT - 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015

Y2 - 25 August 2015 through 29 August 2015

ER -

Srivastava R, Wong DWK, Duan L, Liu J, Wong TY. Red lesion detection in retinal fundus images using Frangi-based filters. In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 5663-5666. 7319677. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). doi: 10.1109/EMBC.2015.7319677

Red lesion detection in retinal fundus images using Frangi-based filters

Abstract

Publication series

Conference

UN SDGs

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this