IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 1
Segmentation of Virus-Infected areas in Retinal Angiograms Using a Learning-by-Sample Approach
Como, Italy
July 24-July 27
ISBN: 0-7695-0619-4
An operational system devoted to the segmentation of virus-infected areas in the retina is described. It means of a 3-stage approach, which involves image sampling, unsupervised coding and supervised classification. Principal Component Analysis provides unsupervised coding whereas supervised classification is performed by a multilayer perceptron. Segmentation as realized by ophthalmologists is considered the gold standard. It is shown that, despite the high variability of images, automatic segmentation is accurate and helps to spot problematic areas.
Citation:
Djamel Brahmi, Camille Serruys, Alain Giron, Bernard Fertil, Nathalie Cassoux, Phuc Lehoang, "Segmentation of Virus-Infected areas in Retinal Angiograms Using a Learning-by-Sample Approach," ijcnn, vol. 1, pp.1158, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 1, 2000