Automatic Image Processing Algorithm to Detect Hard Exudates based on Mixture Models
- 1 August 2006
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2006 (1557170X) , 4453-4456
- https://doi.org/10.1109/iembs.2006.260434
Abstract
Automatic detection of hard exudates from retinal images is clinically significant. Hard exudates are associated with diabetic retinopathy and have been found to be one of the most prevalent earliest clinical signs of retinopathy. In this study, an automatic method to detect hard exudates is proposed. The algorithm is based on mixture models to dynamically threshold the images in order to separate hard exudates from background. We prospectively assessed the algorithm performance using a database of 20 retinal images with variable color, brightness, and quality. The algorithm obtained a sensitivity of 90.23% and a predictive value of 82.5% using a lesion-based criterion. The image-based classification accuracy is also evaluated obtaining a sensitivity of 100% and a specificity of 90%Keywords
This publication has 12 references indexed in Scilit:
- Enhancing digital cephalic radiography with mixture models and local gamma correctionIEEE Transactions on Medical Imaging, 2005
- Mixture models with adaptive spatial regularization for segmentation with an application to FMRI dataIEEE Transactions on Medical Imaging, 2005
- Automated Feature Extraction in Color Retinal Images by a Model Based ApproachIEEE Transactions on Biomedical Engineering, 2004
- A contribution of image processing to the diagnosis of diabetic retinopathy-detection of exudates in color fundus images of the human retinaIEEE Transactions on Medical Imaging, 2002
- Finite Mixture ModelsPublished by Wiley ,2000
- The preprocessing of retinal images for the detection of fluorescein leakagePhysics in Medicine & Biology, 1999
- Snakes, shapes, and gradient vector flowIEEE Transactions on Image Processing, 1998
- Mapping the human retinaIEEE Transactions on Medical Imaging, 1998
- Automatic detection of diabetic retinopathy using an artificial neural network: a screening tool.British Journal of Ophthalmology, 1996
- Screening for Diabetic RetinopathyAnnals of Internal Medicine, 1992