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

作者：

Highlights：

• We propose a novel multi-view DCNN-based approach which can take advantage of not only multi-view images but also the relationships between them.

• The proposed networks learn the integrated features of multi-view fundus images for DR detection.

• We introduce the attention mechanisms for mining the relationship between different views.

• In order to boost the ability to capture the tiny lesion features in the retinal images, we combine the idea of attention mechanisms with the channel dimension.

摘要

•We propose a novel multi-view DCNN-based approach which can take advantage of not only multi-view images but also the relationships between them.•The proposed networks learn the integrated features of multi-view fundus images for DR detection.•We introduce the attention mechanisms for mining the relationship between different views.•In order to boost the ability to capture the tiny lesion features in the retinal images, we combine the idea of attention mechanisms with the channel dimension.

论文关键词：Diabetic retinopathy (DR),Deep convolutional neural networks (DCNNs),Multi-view,Attention mechanisms,Classification

论文评审过程：Received 3 June 2020, Revised 29 April 2021, Accepted 4 June 2021, Available online 2 July 2021, Version of Record 14 July 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108104