Feature extraction and selection for the automatic detection of hard exudates in retinal images
- PMID: 18003122
- DOI: 10.1109/IEMBS.2007.4353456
Feature extraction and selection for the automatic detection of hard exudates in retinal images
Abstract
Diabetic Retinopathy (DR) is a common cause of visual impairment among people of working age in industrialized countries. Automatic recognition of DR lesions, like hard exudates (HEs), in fundus images can contribute to the diagnosis and screening of this disease. In this study, we extracted a set of features from image regions and selected the subset which best discriminates between HEs and the retinal background. The selected features were then used as inputs to a multilayer perceptron (MLP) classifier to obtain a final segmentation of HEs in the image. Our database was composed of 100 images with variable color, brightness, and quality. 50 of them were used to train the MLP classifier and the remaining 50 to assess the performance of the method. Using a lesion-based criterion, we achieved a mean sensitivity of 84.4% and a mean positive predictive value of 62.7%. With an image-based criterion, our approach reached a 100% mean sensitivity, 84.0% mean specificity and 92.0% mean accuracy.
Similar articles
-
A review on exudates detection methods for diabetic retinopathy.Biomed Pharmacother. 2018 Jan;97:1454-1460. doi: 10.1016/j.biopha.2017.11.009. Epub 2017 Dec 14. Biomed Pharmacother. 2018. PMID: 29156536 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
-
Algorithms for the automated detection of diabetic retinopathy using digital fundus images: a review.J Med Syst. 2012 Feb;36(1):145-57. doi: 10.1007/s10916-010-9454-7. Epub 2010 Apr 6. J Med Syst. 2012. PMID: 20703740 Review.
-
Automatic detection of red lesions in retinal images using a multilayer perceptron neural network.Annu Int Conf IEEE Eng Med Biol Soc. 2008;2008:5425-8. doi: 10.1109/IEMBS.2008.4650441. Annu Int Conf IEEE Eng Med Biol Soc. 2008. PMID: 19163944
-
Neural network based detection of hard exudates in retinal images.Comput Methods Programs Biomed. 2009 Jan;93(1):9-19. doi: 10.1016/j.cmpb.2008.07.006. Epub 2008 Sep 7. Comput Methods Programs Biomed. 2009. PMID: 18778869
Cited by
-
Discriminative Learning Approach Based on Flexible Mixture Model for Medical Data Categorization and Recognition.Sensors (Basel). 2021 Apr 2;21(7):2450. doi: 10.3390/s21072450. Sensors (Basel). 2021. PMID: 33918120 Free PMC article.
-
Retinal Sensitivity over Hard Exudates in Diabetic Retinopathy.J Ophthalmic Vis Res. 2015 Apr-Jun;10(2):160-4. doi: 10.4103/2008-322X.163771. J Ophthalmic Vis Res. 2015. PMID: 26425319 Free PMC article.
Publication types
MeSH terms
LinkOut - more resources
Medical