Automatic feature learning for glaucoma detection based on deep learning

Published

Conference Paper

© Springer International Publishing Switzerland 2015. Glaucoma is a chronic and irreversible eye disease in which the optic nerve is progressively damaged, leading to deterioration in vision and quality of life. In this paper, we present an Automatic feature Learning for glAucomaDetection based onDeep LearnINg (ALADDIN),with deep convolutional neural network (CNN) for feature learning. Different from the traditional convolutional layer that uses linear filters followed by a nonlinear activation function to scan the input, the adopted network embeds micro neural networks (multilayer perceptron) with more complex structures to abstract the data within the receptive field. Moreover, a contextualizing deep learning structure is proposed in order to obtain a hierarchical representation of fundus images to discriminate between glaucoma and non-glaucoma pattern,where the network takes the outputs fromother CNN as the context information to boost the performance. Extensive experiments are performed on the ORIGA and SCES datasets. The results showarea under curve (AUC) of the receiver operating characteristic curve in glaucoma detection at 0.838 and 0.898 in the two databases,much better than state-of-the-art algorithms. The method could be used for glaucoma diagnosis.

Full Text

Duke Authors

Cited Authors

  • Chen, X; Xu, Y; Yan, S; Wong, DWK; Wong, TY; Liu, J

Published Date

  • January 1, 2015

Published In

Volume / Issue

  • 9351 /

Start / End Page

  • 669 - 677

Electronic International Standard Serial Number (EISSN)

  • 1611-3349

International Standard Serial Number (ISSN)

  • 0302-9743

International Standard Book Number 13 (ISBN-13)

  • 9783319245737

Digital Object Identifier (DOI)

  • 10.1007/978-3-319-24574-4_80

Citation Source

  • Scopus