MVDRNet: Multi-view diabetic retinopathy detection by combining DCNNs and attention mechanisms

Diabetic retinopathy (DR) detection has attracted much attention recently, and the deep learning algorithms have gained traction in this area. At present, DR screening by deep learning algorithms is often based on single-view fundus images, which usually leads to an unsatisfactory accuracy of DR grading due to the incomplete lesion features. In this paper, we proposed a novel diabetic retinopathy detection convolutional network for automatic DR detection by integrating multi-view fundus images. Compared to existing single-view DCNN-based DR detection methods, the proposed method has the following advantages. First, our method fully utilizes the lesion features from the retina with a field-of-view around 120 degrees - 150 degrees. Second, by introducing the attention mechanisms, more attention will be paid on the influential view and the performance can be improved. Besides, we also assign large weights to important channels in the network for effective feature extraction. Experiments are conducted on our collected multi-view DR dataset contained 15,468 images, in which each eye sample provides four-view images. The experimental results indicate that using multi-view images is suitable for automatic DR detection and our proposed method is superior to other benchmarking methods. (C) 2021 Elsevier Ltd. All rights reserved.

Automated summary

The novel diabetic retinopathy detection convolutional network integrates multi-view fundus images to improve the accuracy of DR grading. By utilizing lesions features from the retina within a field-of-view of 120 to 150 degrees, introducing attention mechanisms, and assigning large weights to important channels, the proposed method outperforms other benchmarking methods. The experimental results on a multi-view DR dataset show the effectiveness and superiority of the proposed method for automatic DR detection.