Multi-space clustering for segmentation of exudates in retinal color photographs

Author

Ram, Keerthi ; Sivaswamy, Jayanthi

Author_Institution

Centre for Visual Inf. Technol., Int. Inst. of Inf. Technol., Hyderabad, India

fYear

2009

fDate

3-6 Sept. 2009

Firstpage

1437

Lastpage

1440

Abstract

Exudates are a class of lipid retinal lesions visible through optical fundus imaging, and indicative of diabetic retinopathy. We propose a clustering-based method to segment exudates, using multi-space clustering, and colorspace features. The method was evaluated on a set of 89 images from a publicly available dataset, and achieves an accuracy of 89.7% and positive predictive value of 87%.

Keywords

biomedical optical imaging; diseases; eye; image colour analysis; image segmentation; lipid bilayers; medical image processing; colorspace features; diabetic retinopathy; exudates; image segmentation; lipid retinal lesions; multispace clustering; optical fundus imaging; retinal color photographs; Algorithms; Biomedical Engineering; Cluster Analysis; Databases, Factual; Diabetic Retinopathy; Diagnostic Techniques, Ophthalmological; Exudates and Transudates; Humans; Image Processing, Computer-Assisted; Photography; Retina;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE

Conference_Location

Minneapolis, MN

ISSN

1557-170X

Print_ISBN

978-1-4244-3296-7

Electronic_ISBN

1557-170X

Type

conf

DOI

10.1109/IEMBS.2009.5332911

Filename

5332911