Fig 1.
Illustration of the proposed procedure in this study.
Fig 2.
Performance of deep learning methods with 5-fold cross validation according to the number of categories.
(A) the performance plot of accuracy (B) the performance plot of relative classifier information (C) the performance plot of Kappa. AMD, age-related macular degeneration; BDR, background diabetic retinopathy; PDR, proliferative diabetic retinopathy; RVO, retinal vein occlusion; RAO, retinal artery occlusion; VGG19-TL-RF, transfer learning with random forest based on VGG-19 structure; VGG19-TL-SVM, transfer learning with one-vs-one support vector machine based on VGG-19 structure.
Fig 3.
Binary discriminative accuracy between retinal diseases using transfer learning with random forest based on VGG-19 structure.
The number of each pair shows the accuracy of binary classifiers.
Fig 4.
Receiver operating characteristic (ROC) curves of transfer learning with random forest based on VGG-19 structure (VGG19-TL-RF), transfer learning with random forest based on VGG-19 structure (VGG19-TL-SVM), and VGG-19, and AlexNet in predicting normal retina or retinal disease status using fundus photographs.
We divided all data set (10,000 images) into training dataset (70%) and test dataset (30%). Retinal disease status includes diabetic retinopathy, age-related macular degeneration, retinal vein occlusion, retinal artery occlusion, hypertensive retinopathy, Coat’s disease, and retinitis.
Table 1.
Results from multi-categorical deep learning models for different approaches combining fundus images of normal, diabetic retinopathy and age-related macular degeneration.
Fig 5.
Comparison of different feature selection methods for 10 multi-categorical retinal image classification problem.
KW, Kruskal-Walis one-way ANOVA; BW, ratio of features between-categories to within-category sum of squares; MRMD, Max-Relevance-Max-Distance.
Table 2.
Performance results by using classic machine learning and ensemble classification for multi-categorical 10 retinal diseases classification problem in the VGG-19 transfer learning setting.