EMFN: Enhanced Multi-Feature Fusion Network for Hard Exudate Detection in Fundus Images

Hard exudates are the main symptom of diabetic retinopathy. Early detection of hard exudates can help reduce the risk of blinding. However, hard exudate detection is a challenging task due to their various sizes and intensities, which cause the misdetection. Aiming at the problem of low accuracy and low efficiency for most of existing hard exudate detection methods, we propose an Enhanced Multi-feature Fusion Network (EMFN) to lessen the burden of ophthalmologists and detect hard exudates more accurately and efficiently. Our network belongs to the category of Convolutional Neural Network (CNN), which adopts and fuses multiple input features with enhanced structures and detailed information as the input, that provide significant help in improving the performance of EMFN. Besides, we introduce attention mechanism and construct the Residual Attention Module (RAM), which is designed by integrating spatial and channel-wise attention modules after each residual block. With the RAM integrated in our network, the EMFN has the ability to suppress redundancy, enhance target-related information, and leverage the correlation between different channels and their locations. Compared with previous methods, EMFN can avoid many processing steps and reduce the impact of subjective factors. We evaluate our EMFN on the MESSIDOR, HEI-MED and E-Ophtha EX dataset, and the experiment results demonstrate that it can achieve better performance than most of the existing methods.