Detection of glaucoma from fundus image using pre-trained Densenet201 model
In recent years, the performance of deep learning algorithms for image recognition has improved tremendously. Theinherent ability of a convolutional neural network has made the task of classifying glaucoma and normal fundus imagesmore appropriately. Transferring the weights from the pre-trained model resulted in faster and easier training than trainingthe network from scratch. In this paper, a dense convolutional neural network (Densenet201) has been utilized to extract therelevant features for classification. Training with 80% of the images and testing with 20% of the images has beenperformed. The performance metrics obtained by various classifiers such as softmax, support vector machine (SVM), knearestneighbor (KNN), and Naive Bayes (NB) have been compared. Experimental results have shown that the softmaxclassifier outperformed the other classifiers with 96.48% accuracy, 98.88% sensitivity, 92.1% specificity, 95.82% precision,and 97.28% F1-score, with DRISHTI-GS1 database. An increase in the classification accuracy of about 1% has beenachieved with enhanced fundus images.
Deep learning, Fine-tuning, Ocular disease, Transfer learning
Full Text: PDF (downloaded 239 times)
- There are currently no refbacks.