EAR-NET: Error Attention Refining Network For Retinal Vessel Segmentation

Abstract

The precise detection of blood vessels in retinal images is crucial to the early diagnosis of the retinal vascular diseases, e.g., diabetic, hypertensive and solar retinopathies. Existing works often fail in predicting the abnormal areas, e.g, sudden brighter and darker areas and are inclined to predict a pixel to background due to the significant class imbalance, leading to high accuracy and specificity while low sensitivity. To that end, we propose a novel error attention refining network (ERA-Net) that is capable of learning and predicting the potential false predictions in a two-stage manner for effective retinal vessel segmentation. The proposed ERA-Net in the refine stage drives the model to focus on and refine the segmentation errors produced in the initial training stage. To achieve this, unlike most previous attention approaches that run in an unsupervised manner, we introduce a novel error attention mechanism which considers the differences between the ground truth and the initial segmentation masks as the ground truth to supervise the attention map learning. Experimental results demonstrate that our method achieves state-of-the-art performance on two common retinal blood vessel datasets.

A Survey on Attention Mechanisms for Medical Applications: are we Moving Toward Better Algorithms?

“…Regarding this task, several other approaches were proposed. Wang et al [159] introduced a network that focuses on refining segmentation errors by using an attention mechanism that considers the differences between the ground truth and the predicted masks as the (source of) supervision for learning the attention maps. Guo et al [160] proposed a network that builds upon residual blocks and spatial attention to promoting the extraction of complex vascular features while alleviating overfitting.…”

An effective and comprehensible method to detect and evaluate retinal damage due to diabetes complications

“…According to statistics, diabetic retinopathy accounts for 12% of all new blindness cases, each year in the United States. Diabetic retinopathy is also the leading cause of blindness for patients from 20 to 64 years old, especially the elderly ( Li et al, 2020 ; Wang et al, 2021 ; Lakshminarayanan et al, 2021 ). If not detected and treated promptly, it will cause severe damage to the fundus such as macular edema, vitreous hemorrhage, retinal hemorrhage, etc .…”