Abstract

Diabetic retinopathy (DR) is a common chronic fundus disease, which has four different kinds of microvessel structure and microvascular lesions: microaneurysms (MAs), hemorrhages (HEs), hard exudates, and soft exudates. Accurate detection and counting of them are a basic but important work. The manual annotation of these lesions is a labor-intensive task in clinical analysis. To solve the problem, we proposed a novel segmentation method for different lesions in DR. Our method is based on a convolutional neural network and can be divided into encoder module, attention module, and decoder module, so we refer it as EAD-Net. After normalization and augmentation, the fundus images were sent to the EAD-Net for automated feature extraction and pixel-wise label prediction. Given the evaluation metrics based on the matching degree between detected candidates and ground truth lesions, our method achieved sensitivity of 92.77%, specificity of 99.98%, and accuracy of 99.97% on the e_ophtha_EX dataset and comparable AUPR (Area under Precision-Recall curve) scores on IDRiD dataset. Moreover, the results on the local dataset also show that our EAD-Net has better performance than original U-net in most metrics, especially in the sensitivity and F1-score, with nearly ten percent improvement. The proposed EAD-Net is a novel method based on clinical DR diagnosis. It has satisfactory results on the segmentation of four different kinds of lesions. These effective segmentations have important clinical significance in the monitoring and diagnosis of DR.

Highlights

  • Diabetes is a common chronic disease that has a large number of patients over the world

  • Typical symptoms of Diabetic retinopathy (DR) mainly include microaneurysms (MAs), hemorrhages (HEs), hard exudates, and soft exudates, which are the major features of DR

  • Compared with the baseline U-net, the results shown in Table 3 indicate that the proposed method outperforms the original U-net in most metrics, especially in the sensitivity and F1-score

Read more

Summary

Introduction

Diabetes is a common chronic disease that has a large number of patients over the world. It is a global public health problem related to microcirculation disorders which seriously affects human health. Diabetic retinopathy (DR) is a common complication of diabetes, so it is a serious chronic disease. DR is caused by the insufficient blood supply and capillary occlusion due to excessive blood sugar content. It would lead to irreversible damage and even blindness. The timely monitoring and treatment are essential for DR patients. The analysis of microvascular lesion areas is one of the important ways of diagnosis. Typical symptoms of DR mainly include microaneurysms (MAs), hemorrhages (HEs), hard exudates, and soft exudates, which are the major features of DR

Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call