Transfer Learning-based One Versus Rest Classifier for Multiclass Multi-Label Ophthalmological Disease Prediction

The main objective of this paper is to propose transfer learning technique for multiclass multilabel opthalmological diseases prediction in fundus images by using the one versus rest strategy. The proposed transfer learning-based techniques to detect eight categories (seven diseases and one normal class) are Normal, Diabetic retinopathy, Cataract, Glaucoma, Age-related macular degeneration, Myopia, Hypertension and Other abnormalities in fundus images collected and augmented from Ocular Disease Intelligent Recognition (ODIR) dataset. To increase the data set, no differentiation between left and right eye images has been done and these images were used on VGG-16 CNN network to binary classify each disease separately and trained 8 separate models using one versus rest strategy to identify these 7 diseases plus normal eyes. In this paper, various results has been showcased such as accuracy of each organ and accuracy of the overall model compared to benchmark papers. Base line accuracy have increased from 89% to almost 91% and also proposed model has improved the performance of identifying disease drastically prediction of glaucoma has increased from 54% to 91%, normal images prediction has increased from 40% to 85.28% and other diseases prediction has increased from 44% to 88%. Out of 8 categories prediction, proposed model prediction rate has improved in 6 diseases by using proposed transfer learning technique vgg16 and eight different one versus classifier classification algorithms.