Journal of Frontiers of Computer Science and Technology ›› 2021, Vol. 15 ›› Issue (12): 2401-2412.DOI: 10.3778/j.issn.1673-9418.2104111

• Graphics and Image • Previous Articles     Next Articles

Fundus Vessel Segmentation Algorithm Based on Multi-feature Fusion Neural Network

SONG Shujie, CUI Zhenchao, CHEN Liping, CHEN Xiangyang   

  1. 1. College of Cyber Security and Computer, Hebei University, Baoding, Hebei 071002, China
    2. Hebei Machine Vision Research Center (Hebei University), Baoding, Hebei 071002, China
  • Online:2021-12-01 Published:2021-12-10

多特征融合神经网络的眼底血管分割算法

宋姝洁,崔振超,陈丽萍,陈向阳   

  1. 1. 河北大学 网络空间安全与计算机学院,河北 保定 071002
    2. 河北省机器视觉研究中心(河北大学),河北 保定 071002

Abstract:

In the early screening of ophthalmic diseases, diabetes, heart disease and other diseases, automatic mon-itoring of fundus capillaries occupies an important position. To solve the deficiency of blood vessel segmentation caused by the imprecise expression of capillary features, this paper proposes a multi-block residual neural network model (MbResU-Net) which uses the encoding-decoding network structure. In order to reduce the information loss caused by the semantic gap between network encoder and decoder, the model uses a nonlinear network structure instead of shortcut connections to be embedded in the network. In order to obtain the detailed features of fundus blood vessels, MbResU-Net connects three U-shaped networks in a residual block, and  then extracts as much as possible low-level features of the fundus tube on the premise of avoiding information loss. To ensure the seg-mentation quality, with the proper pre-processing images to the network, it designs a cross-entropy loss function incorporating the cost matrix to train the network parameters. This paper compares MbResU-Net and the existing fundus blood vessel segmentation algorithms on the DRIVE and CHASE DB1 color fundus image datasets. Exper-iments show that MbResU-Net is superior to existing methods in Sen, ACC and AUC. The Sen is 0.7987 and 0.7972, ACC is 0.9648 and 0.9726 and AUC is 0.9791 and 0.9824. Experiments prove the effectiveness and robustness of the model in the segmentation of complex curvature and small blood vessels.

Key words: image processing, U-Net, residual neural network, multi-module, retinal vessels, image segmentation

摘要:

眼底毛细血管的自动监测对眼科疾病、糖尿病、心脏病等疾病的早期筛查具有重要意义。为了解决对毛细血管特征表达不精细带来的血管分割缺失问题,提出多模块融合的残差神经网络模型(MbResU-Net)。该模型利用了编码-解码网络结构。为了减少网络编码器与解码器之间的语义差距而带来的信息丢失,用非线性网络结构代替快捷连接嵌入到网络中。为了获得更多血管的细节特征,MbResU-Net提出将三块U型网络以残差方式连接,在避免丢失的前提下,最大地提取视网膜结构特征。为了保证分割质量,对图像执行预处理操作,并设计融合了代价矩阵的交叉熵损失函数来训练网络参数。对MbResU-Net与现有的眼底血管分割算法在DRIVE和CHASE DB1彩色眼底图像数据集上进行对比实验。实验表明MbResU-Net在[Sen]、[ACC]和[AUC]上优于现有方法。[Sen]为0.798 7和0.797 2,[ACC]为0.964 8和0.972 6,[AUC]为0.979 1和0.982 4。实验证明该模型在复杂曲率和小血管分割中具有有效性和鲁棒性。

关键词: 图像处理, U-Net, 残差神经网络, 多模块, 视网膜血管, 图像分割