基于改进HRNet的眼底视网膜血管分割算法  

Improved HRNet Based Algorithm for Retinal Blood Vessel Segmentation

作　　者：梁礼明 曾嵩 冯骏 盛校棋 LIANG Li-Ming;ZENG Song;FENG Jun;SHENG Xiao-Qi(School of Electrical Engineering and Automation,Jiangxi University of Science and Technology,Ganzhou 341099,China;School of Computer Science and Engineering,South China University of Technology,Guangzhou 510006,China)

机构地区：[1]江西理工大学电气工程与自动化学院,赣州341099 [2]华南理工大学计算机科学与工程学院,广州510006

出　　处：《计算机系统应用》2021年第9期219-225,共7页Computer Systems & Applications

基　　金：国家自然科学基金(51365017,61463018);江西省自然科学基金面上项目(20192BAB205084);江西省教育厅科学技术研究重点项目(GJJ170491)。

摘　　要：针对现有眼底视网膜血管分割算法普遍存在的微小血管细节丢失和病灶信息误判等问题,提出一种基于改进HRNet的血管分割算法.在预处理阶段,利用限制对比度自适应直方图均衡化和自适应的Gamma矫正提高血管与背景对比度;在编码阶段,将HRNet原始卷积替换为可变形卷积,提升卷积对复杂血管形态结构的适应能力;在多尺度特征融合阶段,引入空间金字塔池化和多尺度卷积,扩大感受野同时增强对目标局部特征关注度,改善血管伪影和细微信息丢失的问题.该算法在DRIVE数据库上仿真实验,其准确率、灵敏度和特异性分别为95.79%、80.33%和98.12%.This study proposes an improved HRNet based algorithm to solve the common problems of microvascular detail loss and lesion information misjudgment in the existing retinal vascular segmentation algorithms.In the preprocessing stage,the contrast between the blood vessels and the background is improved by contrast-limited adaptive histogram equalization and adaptive Gamma correction.During coding,HRNet original convolution is replaced by deformable convolution to improve the adaptability of convolution to complex vascular morphological structures.Concerning multi-scale feature aggregation,spatial pyramid pooling and multi-scale convolution are introduced to expand the receptive field and enhance the attention to the local features of the target.Consequently,vascular artifacts and subtle information loss can be improved.Simulation on the DRIVE database shows that the accuracy,sensitivity,and specificity of the proposed algorithm are 95.79%,80.33%,and 98.12%,respectively.

关 键 词：视网膜血管分割 HRNet 可变形卷积 空间金字塔池化 多尺度 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] R774.1[自动化与计算机技术—计算机科学与技术]