Automatic Recognition of Exudative Maculopathy using Fuzzy C-Means Clustering and Neural Networks

A Osareh; M Mirmehdi; B Thomas; R Markham

Automatic Recognition of Exudative Maculopathy using Fuzzy C-Means Clustering and Neural Networks

A Osareh, M Mirmehdi, B Thomas, R Markham

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

Abstract

Retinal exudates are typically manifested as spatially random yellow/white patches of varying sizes and shapes. They are a characteristic feature of retinal diseases such as diabetic maculopathy. An automatic method for the detection of exudate regions is introduced comprising image colour normalisation, enhancing the contrast between the objects and background, segmenting the colour retinal image into homogenous regions using Fuzzy C-Means clustering, and classifying the regions into exudates and non exudates patches using a neural network. Experimental results indicate that we are able to achieve 92\% sensitivity and 82\% specificity.

Translated title of the contribution	Automatic Recognition of Exudative Maculopathy using Fuzzy C-Means Clustering and Neural Networks
Original language	English
Title of host publication	Unknown
Editors	E Claridge, J Bamber
Publisher	BMVA Press
Pages	49 - 52
Number of pages	3
Publication status	Published - Jul 2001

Bibliographical note

Conference Proceedings/Title of Journal: Medical Image Understanding and Analysis

UN SDGs

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

Access to Document

http://www.cs.bris.ac.uk/Publications/pub_info.jsp?id=1000553

Handle.net

Persistent link

Cite this

@inproceedings{e879ef664865483380eb7496689b389c,

title = "Automatic Recognition of Exudative Maculopathy using Fuzzy C-Means Clustering and Neural Networks",

abstract = "Retinal exudates are typically manifested as spatially random yellow/white patches of varying sizes and shapes. They are a characteristic feature of retinal diseases such as diabetic maculopathy. An automatic method for the detection of exudate regions is introduced comprising image colour normalisation, enhancing the contrast between the objects and background, segmenting the colour retinal image into homogenous regions using Fuzzy C-Means clustering, and classifying the regions into exudates and non exudates patches using a neural network. Experimental results indicate that we are able to achieve 92\% sensitivity and 82\% specificity.",

author = "A Osareh and M Mirmehdi and B Thomas and R Markham",

note = "Conference Proceedings/Title of Journal: Medical Image Understanding and Analysis",

year = "2001",

month = jul,

language = "English",

pages = "49 -- 52",

editor = "E Claridge and J Bamber",

booktitle = "Unknown",

publisher = "BMVA Press",

}

TY - GEN

T1 - Automatic Recognition of Exudative Maculopathy using Fuzzy C-Means Clustering and Neural Networks

AU - Osareh, A

AU - Mirmehdi, M

AU - Thomas, B

AU - Markham, R

N1 - Conference Proceedings/Title of Journal: Medical Image Understanding and Analysis

PY - 2001/7

Y1 - 2001/7

N2 - Retinal exudates are typically manifested as spatially random yellow/white patches of varying sizes and shapes. They are a characteristic feature of retinal diseases such as diabetic maculopathy. An automatic method for the detection of exudate regions is introduced comprising image colour normalisation, enhancing the contrast between the objects and background, segmenting the colour retinal image into homogenous regions using Fuzzy C-Means clustering, and classifying the regions into exudates and non exudates patches using a neural network. Experimental results indicate that we are able to achieve 92\% sensitivity and 82\% specificity.

AB - Retinal exudates are typically manifested as spatially random yellow/white patches of varying sizes and shapes. They are a characteristic feature of retinal diseases such as diabetic maculopathy. An automatic method for the detection of exudate regions is introduced comprising image colour normalisation, enhancing the contrast between the objects and background, segmenting the colour retinal image into homogenous regions using Fuzzy C-Means clustering, and classifying the regions into exudates and non exudates patches using a neural network. Experimental results indicate that we are able to achieve 92\% sensitivity and 82\% specificity.

M3 - Conference Contribution (Conference Proceeding)

SP - 49

EP - 52

BT - Unknown

A2 - Claridge, E

A2 - Bamber, J

PB - BMVA Press

ER -

Automatic Recognition of Exudative Maculopathy using Fuzzy C-Means Clustering and Neural Networks

Abstract

Bibliographical note

UN SDGs

Access to Document

Handle.net

Fingerprint

Cite this