College of Information Science and Engineering,Shandong University of Science and Technology, Shandong, Qingdao 266590, China.
Shandong Province Key Laboratory of Wisdom Mining Information Technology, Shandong University of Science and Technology, Shandong, Qingdao 266590, China.
BMC Med Imaging. 2020 Feb 18;20(1):20. doi: 10.1186/s12880-020-0412-7.
Retinal blood vessel segmentation has an important guiding significance for the analysis and diagnosis of cardiovascular diseases such as hypertension and diabetes. But the traditional manual method of retinal blood vessel segmentation is not only time-consuming and laborious but also cannot guarantee the accuracy and efficiency of diagnosis. Therefore, it is especially significant to create a computer-aided method of automatic and accurate retinal vessel segmentation.
In order to extract the blood vessels' contours of different diameters to realize fine segmentation of retinal vessels, we propose a Bidirectional Symmetric Cascade Network (BSCN) where each layer is supervised by vessel contour labels of specific diameter scale instead of using one general ground truth to train different network layers. In addition, to increase the multi-scale feature representation of retinal blood vessels, we propose the Dense Dilated Convolution Module (DDCM), which extracts retinal vessel features of different diameters by adjusting the dilation rate in the dilated convolution branches and generates two blood vessel contour prediction results by two directions respectively. All dense dilated convolution module outputs are fused to obtain the final vessel segmentation results.
We experimented the three datasets of DRIVE, STARE, HRF and CHASE_DB1, and the proposed method reaches accuracy of 0.9846/0.9872/0.9856/0.9889 and AUC of 0.9874/0.9941/0.9882/0.9874 on DRIVE, STARE, HRF and CHASE_DB1.
The experimental results show that compared with the state-of-art methods, the proposed method has strong robustness, it not only avoids the adverse interference of the lesion background but also detects the tiny blood vessels at the intersection accurately.
视网膜血管分割对高血压、糖尿病等心血管疾病的分析和诊断具有重要的指导意义。但是传统的视网膜血管手动分割方法不仅耗时费力，而且不能保证诊断的准确性和效率。因此，创建一种自动、准确的视网膜血管分割的计算机辅助方法尤为重要。
为了提取不同直径的血管轮廓，实现视网膜血管的精细分割，我们提出了一种双向对称级联网络（BSCN），其中每一层都由特定直径尺度的血管轮廓标签进行监督，而不是使用一个通用的真实标签来训练不同的网络层。此外，为了增加视网膜血管的多尺度特征表示，我们提出了密集扩张卷积模块（DDCM），通过调整扩张卷积分支中的扩张率来提取不同直径的视网膜血管特征，并分别从两个方向生成两个血管轮廓预测结果。所有密集扩张卷积模块的输出都融合在一起，得到最终的血管分割结果。
我们在 DRIVE、STARE、HRF 和 CHASE_DB1 三个数据集上进行了实验，所提出的方法在 DRIVE、STARE、HRF 和 CHASE_DB1 上的准确率分别达到了 0.9846/0.9872/0.9856/0.9889，AUC 分别达到了 0.9874/0.9941/0.9882/0.9874。
实验结果表明，与最先进的方法相比，所提出的方法具有较强的鲁棒性，不仅能避免病变背景的不利干扰，还能准确检测到交叉处的微小血管。
