电子测量与仪器学报

何晓云,许江淳,陈文绪.基于改进 U-Net 网络的眼底血管图像分割研究[J].电子测量与仪器学报,2021,35(10):202-208

基于改进 U-Net 网络的眼底血管图像分割研究

Research on fundus blood vessel image segmentation basedon improved U-Net network

DOI：

英文关键词:blood vessel image segmentation U-Net network residual block attention mechanism hole convolution

基金项目:

作者	单位
何晓云	1.昆明理工大学信息工程与自动化学院
许江淳	1.昆明理工大学信息工程与自动化学院
陈文绪	1.昆明理工大学信息工程与自动化学院

Author	Institution
He Xiaoyun	1.Faculty of Information Engineering and Automation, Kunming University of Science and Technology
Xu Jiangchun	1.Faculty of Information Engineering and Automation, Kunming University of Science and Technology
Chen Wenxu	1.Faculty of Information Engineering and Automation, Kunming University of Science and Technology

摘要点击次数: 1339

全文下载次数: 2129

中文摘要:

针对眼底血管图像存在血管细小、视网膜病变而导致分割精度低的问题,提出了一种引入残差块、级联空洞卷积、嵌入注意力机制的 U-Net 视网膜血管图像分割模型。首先采用提高视网膜图像分辨率,以点噪声为中心、512 为边长裁剪来扩增数据集,然后在 U-Net 模型中引入残差块,增加像素特征的利用率和避免深层网络的退化;并将 U-Net 网络的底部替换为级联空洞卷积模块,扩大特征图的感受野,提取更丰富的像素特征;最后在解码器中嵌入注意力机制,加重目标特征的权重,减缓无用信息的干扰。基于 CHASE 数据集的实验结果表明,所提模型的准确率达到了 98. 2%,灵敏度达到了 81. 72%,特异值达到了 98. 90%,与其他多尺度神经网络方法相比体现了更好的分割效果,充分验证了提出改进的 U-Net 网络模型能有效提高血管分割精度、辅助确诊血管病变。

英文摘要:

Aiming at the problem of low segmentation accuracy due to small blood vessels and retinopathy in fundus blood vessel images, a U-Net retinal blood vessel image segmentation model that introduces residual blocks, cascaded cavity convolution, and embedded attention mechanism is proposed. First, increase the resolution of the retinal image, crop the data set with point noise as the center and 512 as the side length, and then introduce residual blocks in the U-Net model to increase the utilization of pixel features and avoid the degradation of deep networks; And replace the bottom of the U-Net network with a cascaded hole convolution module to expand the receptive field of the feature map and extract richer pixel features; finally, the attention mechanism is embedded in the decoder to increase the weight of the target feature and slow down useless information Interference. The experimental results based on the CHASE data set show that the accuracy of the proposed model reaches 98. 2%, the sensitivity reaches 81. 72%, and the singular value reaches 98. 90%. Compared with other multi-scale neural network methods, it embodies better segmentation results, and fully verifies that the improved U-Net network model can effectively improve the accuracy of blood vessel segmentation and assist in the diagnosis of vascular disease.

查看全文查看/发表评论下载PDF阅读器