Automatic detection of red lesions in retinal images using a multilayer perceptron neural network
- PMID: 19163944
- DOI: 10.1109/IEMBS.2008.4650441
Automatic detection of red lesions in retinal images using a multilayer perceptron neural network
Abstract
Diabetic Retinopathy (DR) is an important cause of visual impairment among people of working age in industrialized countries. Automatic detection of DR clinical signs in retinal images would be an important contribution to the diagnosis and screening of the disease. The aim of the present study is to automatically detect some of these clinical signs: red lesions (RLs), like hemorrhages (HEs) and microaneurysms (MAs). Based on their properties, we extracted a set of features from image regions and selected the subset which best discriminated between these RLs and the retinal background. A multilayer perceptron (MLP) classifier was subsequently used to obtain the final segmentation of RLs. Our database was composed of 100 images with variable color, brightness, and quality. 50 of them were used to obtain the examples to train the MLP classifier. The remaining 50 images were used to test the performance of the method. Using a lesion based criterion, we reached a mean sensitivity of 86.1% and a mean positive predictive value of 71.4%. With an image-based criterion, we achieved a 100% mean sensitivity, 60.0% mean specificity and 80.0% mean accuracy.
Similar articles
-
Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: a review.Comput Med Imaging Graph. 2013 Oct-Dec;37(7-8):581-96. doi: 10.1016/j.compmedimag.2013.09.005. Epub 2013 Sep 27. Comput Med Imaging Graph. 2013. PMID: 24139134 Review.
-
Comparison of logistic regression and neural network classifiers in the detection of hard exudates in retinal images.Annu Int Conf IEEE Eng Med Biol Soc. 2013;2013:5891-4. doi: 10.1109/EMBC.2013.6610892. Annu Int Conf IEEE Eng Med Biol Soc. 2013. PMID: 24111079
-
Assessment of four neural network based classifiers to automatically detect red lesions in retinal images.Med Eng Phys. 2010 Dec;32(10):1085-93. doi: 10.1016/j.medengphy.2010.07.014. Epub 2010 Aug 23. Med Eng Phys. 2010. PMID: 20739211
-
Algorithms for digital image processing in diabetic retinopathy.Comput Med Imaging Graph. 2009 Dec;33(8):608-22. doi: 10.1016/j.compmedimag.2009.06.003. Epub 2009 Jul 18. Comput Med Imaging Graph. 2009. PMID: 19616920 Review.
-
Detection of hard exudates in retinal images using a radial basis function classifier.Ann Biomed Eng. 2009 Jul;37(7):1448-63. doi: 10.1007/s10439-009-9707-0. Epub 2009 May 9. Ann Biomed Eng. 2009. PMID: 19430906
Cited by
-
Red-lesion extraction in retinal fundus images by directional intensity changes' analysis.Sci Rep. 2021 Sep 14;11(1):18223. doi: 10.1038/s41598-021-97649-x. Sci Rep. 2021. PMID: 34521886 Free PMC article.
-
Entropy Rate Superpixel Classification for Automatic Red Lesion Detection in Fundus Images.Entropy (Basel). 2019 Apr 19;21(4):417. doi: 10.3390/e21040417. Entropy (Basel). 2019. PMID: 33267131 Free PMC article.
-
Effective Fundus Image Decomposition for the Detection of Red Lesions and Hard Exudates to Aid in the Diagnosis of Diabetic Retinopathy.Sensors (Basel). 2020 Nov 16;20(22):6549. doi: 10.3390/s20226549. Sensors (Basel). 2020. PMID: 33207825 Free PMC article.
-
Automatic non-proliferative diabetic retinopathy screening system based on color fundus image.Biomed Eng Online. 2017 Oct 26;16(1):122. doi: 10.1186/s12938-017-0414-z. Biomed Eng Online. 2017. PMID: 29073912 Free PMC article.
-
Automated detection of diabetic retinopathy in retinal images.Indian J Ophthalmol. 2016 Jan;64(1):26-32. doi: 10.4103/0301-4738.178140. Indian J Ophthalmol. 2016. PMID: 26953020 Free PMC article. Review.
Publication types
MeSH terms
LinkOut - more resources
Medical