Raghavendra, U and Fujita, Hamido and Bhandary, Sulatha V and Gudigar, Anjan and Tan, Jen Hong and Acharya, Rajendra U (2018) Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images. Information Sciences, 441 (1). pp. 41-49. ISSN 0020-0255

PDF 4131.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Glaucoma progressively affects the optic nerve and may cause partial or complete vision loss. Raised intravascular pressure is the only factor which can be modified to prevent blindness from this condition. Accurate early detection and continuous screening may pre- vent the vision loss. Computer aided diagnosis (CAD) is a non-invasive technique which can detect the glaucoma in its early stage using digital fundus images. Developing such a system require diverse huge database in order to reach optimum performance. This pa- per proposes a novel CAD tool for the accurate detection of glaucoma using deep learning technique. An eighteen layer convolutional neural networks (CNN) is effectively trained in order to extract robust features from the digital fundus images. Finally these features are classified into normal and glaucoma classes during testing. We have achieved the high- est accuracy of 98.13% using 1426 (589: normal and 837: glaucoma) fundus images. Our experimental results demonstrates the robustness of the system, which can be used as a supplementary tool for the clinicians to validate their decisions

Actions (login required)

View Item