Coarse-to-fine classification for diabetic retinopathy grading using convolutional neural network
作者：
Highlights：
• For the first time, a hierarchically Coarse-to-fine diabetic retinopathy (DR) network (CF-DRNet) is proposed and this network can enables a hierarchically five-stage grading using convolutional neural networks.
• The proposed CF-DRNet consists of the pre-trained Coarse Network and the pre-trained Fine Network. The Coarse Network performs two-class classification and the Fine Network further performs four- class classification DR severity grades.
• The self-gated soft-attention mechanism modules are introduced in the pre-trained Coarse Network for two-class classification to effectively highlight the lesion features and suppress irrelevant information.
摘要
•For the first time, a hierarchically Coarse-to-fine diabetic retinopathy (DR) network (CF-DRNet) is proposed and this network can enables a hierarchically five-stage grading using convolutional neural networks.•The proposed CF-DRNet consists of the pre-trained Coarse Network and the pre-trained Fine Network. The Coarse Network performs two-class classification and the Fine Network further performs four- class classification DR severity grades.•The self-gated soft-attention mechanism modules are introduced in the pre-trained Coarse Network for two-class classification to effectively highlight the lesion features and suppress irrelevant information.
论文关键词：Diabetic retinopathy grading,Coarse-to-fine classification,Convolutional neural networks,Fundus images
论文评审过程：Received 31 January 2020, Revised 28 June 2020, Accepted 20 July 2020, Available online 24 July 2020, Version of Record 4 August 2020.
论文官网地址：https://doi.org/10.1016/j.artmed.2020.101936
