基于自适应补偿网络的视网膜血管分割  

Retinal Vessel Segmentation via Self-Adaptive Compensation Network

作　　者：张林 吴闯 范心宇 宫朝举 李甦雁 刘辉[1] Zhang Lin;Wu Chuang;Fan Xinyu;Gong Chaoju;Li Suyan;Liu Hui(School of Information and Control Engineering,China University of Mining and Technology,Xuzhou 221116,Jiangsu,China;Department of Ophthalmology,The First People′s Hospital of Xuzhou,Xuzhou 221116,Jiangsu,China)

机构地区：[1]中国矿业大学信息与控制工程学院,江苏徐州221116 [2]徐州市第一人民医院眼科,江苏徐州221116

出　　处：《光学学报》2023年第14期184-194,共11页Acta Optica Sinica

基　　金：国家自然科学基金(61971422);徐州市科技创新计划-社会发展重点专项(KC22112,KC21153)。

摘　　要：基于眼底图像的视网膜血管精确分割对眼科疾病诊断意义重大。但视网膜血管结构高度复杂,多尺度及前、背景比例失衡,自动分割困难。因此,本文提出自适应补偿网络(SACom)实现端到端的视网膜血管精确分割。SACom以U型网络为基本框架,首先在编码器端引入可变形卷积提高复杂血管结构信息学习能力;然后在U型网络底部设计自适应多尺度对齐上下文模块提取并聚合多尺度上下文信息,对齐上下文特征;最后在解码器端设计协同补偿分支,融合多级输出提升模型的映射能力,实现精细分割。实验结果表明,SACom可有效提高视网膜血管的分割精度,在DRIVE、CHASE_DB1和STARE三个公共数据集上的准确率分别达到0.9695、0.9763和0.9753,灵敏度分别达到0.8403、0.8748和0.8506,曲线下面积(AUC)分别达到0.9880、0.9917和0.9919。Objective Human eye is a crucial component of vision,but the number of patients suffering from ocular illnesses is growing every year.It has been discovered that the morphological characteristics of retinal blood vessels are strongly associated with several ocular conditions including diabetic retinopathy and glaucoma,and they are frequently employed in clinical diagnosis.Therefore,precise segmentation of retinal blood vessels based on color fundus images is crucial for the diagnosis of ocular illnesses.However,the fundus image itself displays noise,poor contrast,and an unbalanced distribution of blood vessels and background pixels.Additionally,morphological information gathering is challenging due to the delicate,highly curved,and multiscale properties of retinal blood vessels.The timeconsuming,difficult,and subjective nature of doctors′manual segmentation makes it ineffective for providing a large number of patients with a speedy diagnosis.To achieve precise automatic segmentation of retinal blood vessels from end to end,we propose the selfadaptive compensation network(SACom).Methods SACom employs the Ushaped network as its fundamental structure.First,deformable convolution is incorporated into the encoder to enhance the model′s capacity to learn information about morphological structures of retinal blood vessels.An adaptive multiscale aligned context(AMAC)module is then developed at the bottom of the Ushaped network to extract and aggregate multiscale context information and align the context features produced by pooling.It can adaptively extract context features according to the input image size and utilize the image context information correctly.Finally,a collaborative compensation branch(CCB)is proposed to fully leverage the feature layer in the decoder and highlevel semantic features at the bottom of the network.Its multilevel outputs are helpful for positioning the overall structure of the blood vessel to fine details.Then they are fused with the output feature layer of the decoder end through the fea

关 键 词：图像处理 视网膜血管 可变形卷积 上下文对齐 特征自适应融合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]