Automatic Classification of Bright Retinal Lesions via Deep Network Features
This work addresses the need for automated diagnosis of diabetic retinopathy to assist ophthalmologists, but it is incremental as it applies existing deep learning methods to a specific medical imaging task.
The paper tackled the problem of classifying diabetic retinopathy from retinal images by using deep features from pre-trained CNNs and a non-linear classifier, achieving an average accuracy of 91.23% to 92.00% with over 13% improvement over traditional methods.
The diabetic retinopathy is timely diagonalized through color eye fundus images by experienced ophthalmologists, in order to recognize potential retinal features and identify early-blindness cases. In this paper, it is proposed to extract deep features from the last fully-connected layer of, four different, pre-trained convolutional neural networks. These features are then feeded into a non-linear classifier to discriminate three-class diabetic cases, i.e., normal, exudates, and drusen. Averaged across 1113 color retinal images collected from six publicly available annotated datasets, the deep features approach perform better than the classical bag-of-words approach. The proposed approaches have an average accuracy between 91.23% and 92.00% with more than 13% improvement over the traditional state of art methods.