计算机科学 ›› 2020, Vol. 47 ›› Issue (5): 166-171.doi: 10.11896/jsjkx.190400062

所属专题: 医学图像

• 计算机图形学&多媒体 • 上一篇    下一篇

基于双注意力编码-解码器架构的视网膜血管分割

李天培, 陈黎   

  1. 武汉科技大学计算机科学与技术学院 武汉430065
    武汉科学大学湖北省智能信息处理与实时工业系统重点实验室 武汉430065
  • 收稿日期:2019-04-09 出版日期:2020-05-15 发布日期:2020-05-19
  • 通讯作者: 陈黎(52282375@qq.com)
  • 作者简介:2386586402@qq.com
  • 基金资助:
    国家自然科学基金(61773297);智能信息处理与实时工业系统湖北省重点实验室开放基金资助项目(2016znss01A)

Retinal Vessel Segmentation Based on Dual Attention and Encoder-decoder Structure

LI Tian-pei, CHEN Li   

  1. School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,China
    Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System,Wuhan University of Science and Technology,Wuhan 430065,China
  • Received:2019-04-09 Online:2020-05-15 Published:2020-05-19
  • About author:LI Tian-pei,born in 1995,postgraduate.His main research interests include ima-ge processing and deep learning.
    CHEN Li,born in 1977,Ph.D,professor,Ph.D supervisor.His main research interests include image processing,computer vision,intelligent media computing,and deep learning applications.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China(61773297) and Open Fund of Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System(2016znss01A)

摘要: 眼底视网膜血管的分割提取对于糖尿病、视网膜病、青光眼等眼科疾病的诊断具有重要的意义。针对视网膜血管图像中的血管难以提取、数据量较少等问题,文中提出了一种结合注意力模块和编码-解码器结构的视网膜血管分割方法。首先对编码-解码器卷积神经网络的每个卷积层添加空间和通道注意力模块,加强模型对图像特征的空间信息和通道信息(如血管的大小、形态和连通性等特点)的利用,从而改善视网膜血管的分割效果。其中,空间注意力模块关注于血管的拓扑结构特性,而通道注意力模块关注于血管像素点的正确分类。此外,在训练过程中采用Dice损失函数解决了视网膜血管图像正负样本不均衡的问题。在3个公开的眼底图像数据库DRIVE,STARE和CHASE_DB1上进行了实验,实验数据表明,所提算法的准确率、灵敏度、特异性和AUC值均优于已有的视网膜血管分割方法,其AUC值分别为0.9889,0.9812和0.9831。实验证明,所提算法能够有效提取健康视网膜图像和病变视网膜图像中的血管网络,能够较好地分割细小血管。

关键词: 编码-解码器结构, 空间注意力, 视网膜血管分割, 特征可视化, 通道注意力

Abstract: The segmentation of the retinal vessels in fundus image is important for the diagnosis of ophthalmic diseases such as diabetes,retinopathy and glaucoma.Aiming at the difficulties of extracting blood vessels from retinal blood vessel images and the lack of data samples,a retinal vessel segmentation method combining attention module with encoder-decoder structure is proposed.To improve the segmentation effect of retinal blood vessels,a spatial and channel attention module is added to each convolutional layer of the encoder-decoder convolutional neural network to enhance the utilization of the spatial and channel information of the image features (such as the size,shape,and connectivity of the blood vessels),where the spatial attention focuses on the topological characteristics of blood vessels,and the channel attention focuses on the correct classification of blood vessel pixels.Moreover,the Dice loss function is used to solve the imbalance of positive and negative samples in retinal blood vessel images.The proposed method has been applied on three public fundus image databases DRIVE,STARE and CHASE_DB1.The experimental data show that the accuracy,sensitivity,specificity and AUC values are superior to the existing retinal vessel segmentation me-thods,with AUC values of 0.9889,0.9812 and 0.9831,respectively.The experimental results show that the proposed method can effectively extract the vascular network in healthy retinal images and diseased retinal images,and can segment small blood vessels well.

Key words: Channel attention, Encoder decoder structure, Feature of proposed method visualization, Segmentation of retinal blood vessels, Spatial attention

中图分类号: 

  • TP391
[1]CHENG E,DU L,WU Y,et al.Discriminative vessel segmentation in retinal images by fusing context-aware hybrid features[J].Machine Vision and Applications,2014,25(7):1779-1792.
[2]KANG W,WU Q.Contactless palm vein recognition using amutual foreground-based local binary pattern[J].IEEE Tran-sactions on Information Forensics and Security,2014,9(11):1974-1985.
[3]WANG X H,XUE Q S.Optical design of portable non-mydriatic fundus camera with large field of view[J].Acta Optica Sinica,2017,37(9):0922001.
[4]RAMESH N,YOO J H,SETHI I K.Thresholding based on histogram approximation[J].IEE Proceedings-Vision,Image and Signal Processing,1995,142(5):271-279.
[5]BOYKOV Y Y,JOLLY M P.Interactive graph cuts for optimal boundary & region segmentation of objects in ND images[C]//Proceedings Eighth IEEE International Conference on Computer vision(ICCV 2001).IEEE,2001:105-112.
[6]SOARES J V B,LEANDRO J J G,CESAR R M,et al.Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification[J].IEEE Transactions on Medical Imaging,2006,25(9):1214-1222.
[7]WANG S,YIN Y,CAO G,et al.Hierarchical retinal blood vessel segmentation based on feature and ensemble learning[J].Neurocomputing,2015,149:708-717.
[8]MAJI D,SANTARA A,GHOSH S,et al.Deep neural network and random forest hybrid architecture for learning to detect retinal vessels in fundus images[C]//2015 37th Nnnual International Conference of the IEEE Engineering in Medicine and Bio-logy Society (EMBC).IEEE,2015:3029-3032.
[9]FU H,XU Y,WONG D W K,et al.Retinal vessel segmentation via deep learning network and fully-connected conditional random fields[C]//2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).IEEE,2016:698-701.
[10]XIAO X,LIAN S,LUO Z,et al.Weighted Res-UNet for High-Quality Retina Vessel Segmentation[C]//2018 9th International Conference on Information Technology in Medicine and Education (ITME).IEEE,2018:327-331.
[11]RONNEBERGER O,FISCHER P,BROX T.U-net:Convolu-tional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-assisted Intervention.Cham:Springer,2015:234-241.
[12]BADRINARAYANAN V,KENDALL A,CIPOLLA R.Segnet:A deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[13]LAROCHELLE H,HINTON G E.Learning to combine foveal glimpses with a third-order Boltzmann machine[C]//Advances in Neural Information Processing Systems.2010:1243-1251.
[14]WANG F,JIANG M,QIAN C,et al.Residual attention network for image classification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:3156-3164.
[15]HU J,SHEN L,SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:7132-7141.
[16]ZHAO H,SHI J,QI X,et al.Pyramid scene parsing network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:2881-2890.
[17]PENG C,ZHANG X,YU G,et al.Large Kernel Matters--Improve Semantic Segmentation by Global Convolutional Network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:4353-4361.
[18]MILLETARI F,NAVAB N,AHMADI S A.V-net:Fully convolutional neural networks for volumetric medical image segmentation[C]//2016 Fourth International Conference on 3D Vision (3DV).IEEE,2016:565-571.
[19]STAAL J,ABRÁMOFF M D,NIEMEIJER M,et al.Ridge-based vessel segmentation in color images of the retina[J].IEEE Transactions on Medical Imaging,2004,23(4):501-509.
[20]HOOVER A,KOUZNETSOVA V,GOLDBAUM M.Locating blood vessels in retinal images by piece-wise threshold probing of a matched filter response[C]//Proceedings of the AMIA Symposium.American Medical Informatics Association,1998:931.
[21]FRAZ M M,REMAGNINO P,HOPPE A,et al.An ensemble classification-based approach applied to retinal blood vessel segmentation[J].IEEE Transactions on Biomedical Engineering,2012,59(9):2538-2548.
[22]GLOROT X,BENGIO Y.Understanding the difficulty of training deep feedforward neural networks[C]//Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics.2010:249-256.
[23]AZZOPARDI G,STRISCIUGLIO N,VENTO M,et al.Trainable COSFIRE filters for vessel delineation with application to retinal images[J].Medical Image Analysis,2015,19(1):46-57.
[24]ROYCHOWDHURY S,KOOZEKANANI D D,PARHI K K.Iterative vessel segmentation of fundus images[J].IEEE Transactions on Biomedical Engineering,2015,62(7):1738-1749.
[25]ZHAO Y,RADA L,CHEN K,et al.Automated vessel segmentation using infinite perimeter active contour model with hybrid region information with application to retinal images[J].IEEE Transactions on Medical Imaging,2015,34(9):1797-1807.
[26]FU H,XU Y,LIN S,et al.Deepvessel:Retinal vessel segmentation via deep learning and conditional random field[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.Cham:Springer,2016:132-139.
[1] 杨玥, 冯涛, 梁虹, 杨扬.
融合交叉注意力机制的图像任意风格迁移
Image Arbitrary Style Transfer via Criss-cross Attention
计算机科学, 2022, 49(6A): 345-352. https://doi.org/10.11896/jsjkx.210700236
[2] 沈超, 何希平.
基于纹理特征增强和轻量级网络的人脸防伪算法
Face Anti-spoofing Algorithm Based on Texture Feature Enhancement and Light Neural Network
计算机科学, 2022, 49(6A): 390-396. https://doi.org/10.11896/jsjkx.210600217
[3] 晏旭, 马帅, 曾凤娇, 郭正华, 伍俊龙, 杨平, 许冰.
基于编码-解码器架构的光场深度估计方法
Light Field Depth Estimation Method Based on Encoder-decoder Architecture
计算机科学, 2021, 48(10): 212-219. https://doi.org/10.11896/jsjkx.200900005
[4] 吕泽宇李纪旋陈如剑陈东明.
电商平台用户再购物行为的预测研究
Research on Prediction of Re-shopping Behavior of E-commerce Customers
计算机科学, 2020, 47(6A): 424-428. https://doi.org/10.11896/JsJkx.190900018
[5] 尚骏远, 杨乐涵, 何琨.
基于特征可视化分析深度神经网络的内部表征
Analyzing Latent Representation of Deep Neural Networks Based on Feature Visualization
计算机科学, 2020, 47(5): 190-197. https://doi.org/10.11896/jsjkx.190700128
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!