The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
An Adaptive Algorithm for Detection of Exudates Based on Localized Properties of Fundus Images
|
Author(s): Katha Chanda (College of Computing, Georgia Institute of Technology, Atlanta, USA), Ashish Issac (Department of Electronics & Communication Engineering, Amity University, Noida, India)and Malay Kishore Dutta (Center for Advanced Studies, Dr. A.P.J Abdul Kalam Technical University, Lucknow, India)
Copyright: 2019
Volume: 10
Issue: 1
Pages: 20
Source title:
International Journal of E-Health and Medical Communications (IJEHMC)
Editor(s)-in-Chief: Joel J.P.C. Rodrigues (Senac Faculty of Ceará, Fortaleza-CE, Brazil; Instituto de Telecomunicações, Portugal)
DOI: 10.4018/IJEHMC.2019010102
Purchase
|
Abstract
This article presents an algorithm to detect exudates, which can be considered as one of the many abnormalities, to identify diabetic retinopathy from fundus images. The algorithm is invariant to illumination and works well on poor contrast images with high reflection noise. The artefacts are correctly rejected despite their colour, intensity and contrast being almost similar to that of exudates. Optic disc is localized and segmented using average filter of specially determined size which is an important step in the rejection of false positives. Exudates are located by generating candidate regions using variance and median filters followed by morphological reconstruction. The strategic selection of local properties to decide the threshold, makes this approach novel and adaptive, that is highly accurate for detection of exudates. The proposed method was tested on two publicly available labelled databases (DIARETDB1 and MESSIDOR) and a database from a local hospital and achieved a sensitivity of 96.765% and a positive predictive value of 93.514%.
Related Content
David Opeoluwa Oyewola, Emmanuel Gbenga Dada, Sanjay Misra.
© 2024.
21 pages.
|
Bin Hu, Gregory T. MacLennan.
© 2024.
11 pages.
|
Dantong Li, Guixin Li, Shuang Li, Ashley Bang.
© 2024.
12 pages.
|
Marlon Luca Machal.
© 2024.
16 pages.
|
Neetu Singh, Upkar Varshney.
© 2024.
17 pages.
|
Shihui Zhang, Jing Mi, Naidi Liu.
© 2024.
12 pages.
|
Lucy M. Lu, Richard S. Segall.
© 2024.
18 pages.
|
|
|