Attention Based Detection for Central Serious Chorioretinopathy in Fundus Image
- Resource Type
- Conference
- Authors
- Zhou, Chuan; Zhang, Tian; Chen, Leiting; Wen, Yang; Lei, Ting; Chen, Junjing
- Source
- 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) Bioinformatics and Biomedicine (BIBM), 2020 IEEE International Conference on. :1221-1225 Dec, 2020
- Subject
- Bioengineering
Computing and Processing
Signal Processing and Analysis
Feature extraction
Lesions
Iron
Training
Task analysis
Image resolution
Image coding
Central Serious Chorioretinopathy
Deep convolutional neural networks
Attention mechanism
Fundus images
- Language
The detection of Central Serious Chorioretinopathy (CSCR) which is one of the main causes of vision loss so far still relies on manual evaluation of fundus images which requires experienced clinicians and is time-consuming. In this paper, we aim to utilize deep learning to overcome the difficulty of the absence of automated diagnostic methods for CSCR. However, there still exists two issues in general neural networks when applied to CSCR detection: 1) The lesion area that contributes the most for the final result cannot get adequate attention in one-stream networks. 2)Lesion regions become blurred when high-resolution fundus images are resized into lower resolution. Attention mechanism has been proved to be effective in addressing the problem of insufficient attention to significant regions, so we propose a Crop Attention Network (CA-Net) to screen CSCR automatically. CA-Net is based on attention framework and tackles the issues mentioned above by cropping the whole image into patches and adding weights on each patch. Experiment results on in-house database show that the proposed method outperforms all baseline methods.