Convolutional neural network and texture descriptor-based automatic detection and diagnosis of glaucoma

作者：

Highlights：

• We propose an automatic method for the detection and diagnosis of glaucoma.

• Convolutional Neural Network is used for Optical Disc segmentation.

• Texture descriptors based on phylogenetic analysis are used to characterize the ROIs.

• Three image databases are used to train and test the proposed method.

• The results are promising, reaching 100% on all metrics in the red channel analysis.

摘要

•We propose an automatic method for the detection and diagnosis of glaucoma.•Convolutional Neural Network is used for Optical Disc segmentation.•Texture descriptors based on phylogenetic analysis are used to characterize the ROIs.•Three image databases are used to train and test the proposed method.•The results are promising, reaching 100% on all metrics in the red channel analysis.

论文关键词：Medical image,Glaucoma,Convolutional neural network,Phylogenetic diversity index

论文评审过程：Received 2 November 2017, Revised 30 April 2018, Accepted 3 June 2018, Available online 4 June 2018, Version of Record 18 June 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.06.010