THALIA - An automatic hierarchical analysis system to detect drusen lesion images for amd assessment

Damon W.K. Wong; Jiang Liu; Xiangang Cheng; Jielin Zhang; Fengshou Yin; Mayuri Bhargava; Gemmy C.M. Cheung; Tien Yin Wong

doi:10.1109/ISBI.2013.6556617

THALIA - An automatic hierarchical analysis system to detect drusen lesion images for amd assessment

Damon W.K. Wong, Jiang Liu, Xiangang Cheng, Jielin Zhang, Fengshou Yin, Mayuri Bhargava, Gemmy C.M. Cheung, Tien Yin Wong

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

17 Citations (Scopus)

Abstract

Age-related macular degeneration (AMD) is a leading cause of permanent blindness. In its early stage AMD is characterized by drusen which are extracellelur deposits in the retina. In this paper, we present THALIA, an automatic system for the detection of drusen images for AMD assessment. First, the macular region of interest is detected using a seeded mode tracking approach. The macular region of interest is then mapped into a new representation using a hierarchicial word transform (HWI). In HWI, dense sampling is first carried out to generate structured pixels which embed local context. These structured pixels are then clustered using hierarchical k-means. The HWI image is subsequently classified using a SVM-based classifier. We have tested THALIA on a dataset of 350 images and obtained an accuracy of 95.46%. Results are promising for further validation of the THALIA system.

Original language	English
Title of host publication	ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging
Subtitle of host publication	From Nano to Macro
Pages	884-887
Number of pages	4
DOIs	https://doi.org/10.1109/ISBI.2013.6556617
Publication status	Published - 2013
Externally published	Yes
Event	2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013 - San Francisco, CA, United States Duration: 7 Apr 2013 → 11 Apr 2013

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013
Country/Territory	United States
City	San Francisco, CA
Period	7/04/13 → 11/04/13

Keywords

AMD
drusen
retinal image

ASJC Scopus subject areas

Biomedical Engineering
Radiology Nuclear Medicine and imaging

Access to Document

10.1109/ISBI.2013.6556617

Cite this

Wong, D. W. K., Liu, J., Cheng, X., Zhang, J., Yin, F., Bhargava, M., Cheung, G. C. M., & Wong, T. Y. (2013). THALIA - An automatic hierarchical analysis system to detect drusen lesion images for amd assessment. In ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro (pp. 884-887). Article 6556617 (Proceedings - International Symposium on Biomedical Imaging). https://doi.org/10.1109/ISBI.2013.6556617

@inproceedings{668ff6df009840e7a0ba441bfa28b376,

title = "THALIA - An automatic hierarchical analysis system to detect drusen lesion images for amd assessment",

abstract = "Age-related macular degeneration (AMD) is a leading cause of permanent blindness. In its early stage AMD is characterized by drusen which are extracellelur deposits in the retina. In this paper, we present THALIA, an automatic system for the detection of drusen images for AMD assessment. First, the macular region of interest is detected using a seeded mode tracking approach. The macular region of interest is then mapped into a new representation using a hierarchicial word transform (HWI). In HWI, dense sampling is first carried out to generate structured pixels which embed local context. These structured pixels are then clustered using hierarchical k-means. The HWI image is subsequently classified using a SVM-based classifier. We have tested THALIA on a dataset of 350 images and obtained an accuracy of 95.46%. Results are promising for further validation of the THALIA system.",

keywords = "AMD, drusen, retinal image",

author = "Wong, {Damon W.K.} and Jiang Liu and Xiangang Cheng and Jielin Zhang and Fengshou Yin and Mayuri Bhargava and Cheung, {Gemmy C.M.} and Wong, {Tien Yin}",

note = "Copyright: Copyright 2013 Elsevier B.V., All rights reserved.; 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013 ; Conference date: 07-04-2013 Through 11-04-2013",

year = "2013",

doi = "10.1109/ISBI.2013.6556617",

language = "English",

isbn = "9781467364546",

series = "Proceedings - International Symposium on Biomedical Imaging",

pages = "884--887",

booktitle = "ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging",

}

Wong, DWK, Liu, J, Cheng, X, Zhang, J, Yin, F, Bhargava, M, Cheung, GCM & Wong, TY 2013, THALIA - An automatic hierarchical analysis system to detect drusen lesion images for amd assessment. in ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro., 6556617, Proceedings - International Symposium on Biomedical Imaging, pp. 884-887, 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013, San Francisco, CA, United States, 7/04/13. https://doi.org/10.1109/ISBI.2013.6556617

THALIA - An automatic hierarchical analysis system to detect drusen lesion images for amd assessment. / Wong, Damon W.K.; Liu, Jiang; Cheng, Xiangang et al.
ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro. 2013. p. 884-887 6556617 (Proceedings - International Symposium on Biomedical Imaging).

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

TY - GEN

T1 - THALIA - An automatic hierarchical analysis system to detect drusen lesion images for amd assessment

AU - Wong, Damon W.K.

AU - Liu, Jiang

AU - Cheng, Xiangang

AU - Zhang, Jielin

AU - Yin, Fengshou

AU - Bhargava, Mayuri

AU - Cheung, Gemmy C.M.

AU - Wong, Tien Yin

PY - 2013

Y1 - 2013

N2 - Age-related macular degeneration (AMD) is a leading cause of permanent blindness. In its early stage AMD is characterized by drusen which are extracellelur deposits in the retina. In this paper, we present THALIA, an automatic system for the detection of drusen images for AMD assessment. First, the macular region of interest is detected using a seeded mode tracking approach. The macular region of interest is then mapped into a new representation using a hierarchicial word transform (HWI). In HWI, dense sampling is first carried out to generate structured pixels which embed local context. These structured pixels are then clustered using hierarchical k-means. The HWI image is subsequently classified using a SVM-based classifier. We have tested THALIA on a dataset of 350 images and obtained an accuracy of 95.46%. Results are promising for further validation of the THALIA system.

AB - Age-related macular degeneration (AMD) is a leading cause of permanent blindness. In its early stage AMD is characterized by drusen which are extracellelur deposits in the retina. In this paper, we present THALIA, an automatic system for the detection of drusen images for AMD assessment. First, the macular region of interest is detected using a seeded mode tracking approach. The macular region of interest is then mapped into a new representation using a hierarchicial word transform (HWI). In HWI, dense sampling is first carried out to generate structured pixels which embed local context. These structured pixels are then clustered using hierarchical k-means. The HWI image is subsequently classified using a SVM-based classifier. We have tested THALIA on a dataset of 350 images and obtained an accuracy of 95.46%. Results are promising for further validation of the THALIA system.

KW - AMD

KW - drusen

KW - retinal image

UR - http://www.scopus.com/inward/record.url?scp=84881623283&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2013.6556617

DO - 10.1109/ISBI.2013.6556617

M3 - Conference contribution

AN - SCOPUS:84881623283

SN - 9781467364546

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 884

EP - 887

BT - ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging

T2 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013

Y2 - 7 April 2013 through 11 April 2013

ER -

Wong DWK, Liu J, Cheng X, Zhang J, Yin F, Bhargava M et al. THALIA - An automatic hierarchical analysis system to detect drusen lesion images for amd assessment. In ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro. 2013. p. 884-887. 6556617. (Proceedings - International Symposium on Biomedical Imaging). doi: 10.1109/ISBI.2013.6556617

THALIA - An automatic hierarchical analysis system to detect drusen lesion images for amd assessment

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this