Screening for diabetic retinopathy using computer based image analysis and statistical classification

Diabetic retinopathy is one of the most common causes of blindness in Europe. However, efficient therapies do exist. An accurate and early diagnosis and correct application of treatment can prevent blindness in more than 50% of all cases. Digital imaging is becoming available as a means of screening...

Full description

Saved in:
Bibliographic Details
Published inComputer methods and programs in biomedicine Vol. 62; no. 3; pp. 165 - 175
Main Authors Ege, Bernhard M., Hejlesen, Ole K., Larsen, Ole V., Møller, Karina, Jennings, Barry, Kerr, David, Cavan, David A.
Format Journal Article
LanguageEnglish
Published Ireland Elsevier Ireland Ltd 01.07.2000
Subjects
Biometry
Blindness - prevention & control
Diabetic retinopathy
Diabetic Retinopathy - diagnosis
Diagnosis, Computer-Assisted
Evaluation Studies as Topic
Humans
Image analysis
Image Processing, Computer-Assisted
Mass Screening - methods
Medical imaging
Ophthalmology
Patient treatment
Retinal image analysis
Statistical classification
Statistical methods
Diabetic retinopathy
Retinal image analysis
Statistical classification
Online AccessGet full text

Cover

More Information
Summary:Diabetic retinopathy is one of the most common causes of blindness in Europe. However, efficient therapies do exist. An accurate and early diagnosis and correct application of treatment can prevent blindness in more than 50% of all cases. Digital imaging is becoming available as a means of screening for diabetic retinopathy. As well as providing a high quality permanent record of the retinal appearance, which can be used for monitoring of progression or response to treatment, and which can be reviewed by an ophthalmologist, digital images have the potential to be processed by automatic analysis systems. We have described the preliminary development of a tool to provide automatic analysis of digital images taken as part of routine monitoring of diabetic retinopathy in our clinic. Various statistical classifiers, a Bayesian, a Mahalanobis, and a KNN classifier were tested. The system was tested on 134 retinal images. The Mahalanobis classifier had the best results: microaneurysms, haemorrhages, exudates, and cotton wool spots were detected with a sensitivity of 69, 83, 99, and 80%, respectively.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
ISSN:0169-2607
1872-7565
DOI:10.1016/S0169-2607(00)00065-1