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

Authors: Ege, B.M., Hejlesen, O.K., Larsen, O.V., Møller, K., Jennings, B., Kerr, D. and Cavan, D.A.

Journal: Computer Methods and Programs in Biomedicine

Volume: 62

Issue: 3

Pages: 165-175

ISSN: 0169-2607

DOI: 10.1016/S0169-2607(00)00065-1

Abstract:

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. (C) 2000 Elsevier Science Ireland Ltd.

Source: Scopus

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

Authors: Ege, B.M., Hejlesen, O.K., Larsen, O.V., Møller, K., Jennings, B., Kerr, D. and Cavan, D.A.

Journal: Comput Methods Programs Biomed

Volume: 62

Issue: 3

Pages: 165-175

ISSN: 0169-2607

DOI: 10.1016/s0169-2607(00)00065-1

Abstract:

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.

Source: PubMed

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

Authors: Ege, B.M., Hejlesen, O.K., Larsen, O.V., Moller, K., Jennings, B., Kerr, D. and Cavan, D.A.

Journal: COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE

Volume: 62

Issue: 3

Pages: 165-175

ISSN: 0169-2607

DOI: 10.1016/S0169-2607(00)00065-1

Source: Web of Science (Lite)

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

Authors: Ege, B.M., Hejlesen, O.K., Larsen, O.V., Moller, K., Jennings, B., Kerr, D. and Cavan, D.A.

Journal: Computer Methods and Programs in Biomedicine

Volume: 62

Pages: 165-175

ISSN: 0169-2607

DOI: 10.1016/S0169-2607(00)00065-1

Abstract:

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.

http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6T5J-40CRNCM-3&_user=1682380&_rdoc=1&_fmt=&_orig=search&_sort=d&view=c&_acct=C000011378&_version=1&_urlVersion=0&_userid=1682380&md5=6fd87685b7744bdf77f5f1168b9bdd6e

Source: Manual

Preferred by: David Kerr

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

Authors: Ege, B.M., Hejlesen, O.K., Larsen, O.V., Møller, K., Jennings, B., Kerr, D. and Cavan, D.A.

Journal: Comput. Methods Programs Biomed.

Volume: 62

Pages: 165-175

DOI: 10.1016/S0169-2607(00)00065-1

Source: DBLP

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

Authors: Ege, B.M., Hejlesen, O.K., Larsen, O.V., Møller, K., Jennings, B., Kerr, D. and Cavan, D.A.

Journal: Computer methods and programs in biomedicine

Volume: 62

Issue: 3

Pages: 165-175

eISSN: 1872-7565

ISSN: 0169-2607

DOI: 10.1016/s0169-2607(00)00065-1

Abstract:

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.

Source: Europe PubMed Central