融合Resnet50和U-Net的眼底彩色血管图像分割  

Fundus Blood Vessel Image Segmentation Combining Resnet50 and U-Net

作　　者：司明明 陈玮[1] 胡春燕[1] 尹钟[1] SI Mingming;CHEN Wei;HU Chunyan;YIN Zhong(School of Optical Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093, China)

机构地区：[1]上海理工大学光电信息与计算机工程学院,上海200093

出　　处：《电子科技》2021年第8期19-24,共6页Electronic Science and Technology

基　　金：国家自然科学基金(61703277)。

摘　　要：眼底血管图像特征信息复杂度较高且现有算法对视网膜微血管分割不足,对病灶区域会产生误分割。针对以上问题,文中提出了一种融合Resnet50和U-Net的眼底彩色血管图像分割模型。通过数据增强提高数据集的数量以增加算法的鲁棒性。融合高斯双边滤波和限制对比度直方图均衡化来增强视网膜微细管的特征信息。利用自适应Gamma矫正提升图像亮度信息并降低图像伪影的干扰。在编码部分使用残差网路对彩色图像进行深层次的特征提取,将得到的特征图进行4次上采样和跳跃连接,实现像素级的分割。在每个卷积层使用ReLU激活函数和批量归一化来提高模型的性能。最后,利用公开数据集DRIVE进行实验,结果显示文中算法的特异性为0.9892,准确率为0.9676,灵敏度为0.8120。The characteristic information of the fundus blood vessel image has high complexity,and the existing algorithms have the problems of insufficient retinal microvascular segmentation and wrong segmentation of the focus area.In view of these problems,a fundus color blood vessel image segmentation model combined RESNET 50 and U-Net is proposed.Through data enhancement,the number of datasets is increased,so as to improve the robustness of the algorithm.The adaptive Gamma correction is used to improve the brightness information and reduce the interference of the image artifacts.In the coding part,the residual network is used to extract the deep-seated features of the color image.After four times up-sampling and skip-connection of the feature map,pixel level segmentation is achieved.In each convolution layer,the ReLU activation function and batch normalization are used to improve the performance of the model.A large number of experiments in the open dataset DRIVE show that the specificity of the proposed algorithm is 0.9892,the accuracy is 0.9676,and the sensitivity is 0.8120.

关 键 词：眼底血管 神经网络 数据增强 图像预处理 双边滤波 特征提取 图像分割 残差网络 U-net 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]