姜大光等：骨架图引导的级联视网膜血管分割网络 1251 Proceedings of the 31st Conference on neural information 10-20)[2021-6-101.https://arxiv.org/abs/2004.03696 processing systems (NIPS 2017).Long Beach,2017:5998 [31]Mou L,Zhao Y T,Chen L,et al.CS-net:Channel and spatial [16]Hu J,Shen L,Sun G.Squeeze-and-excitation networks /2018 attention network for curvilinear structure segmentation /Medical IEEE/CVF Conference on Computer Vision and Pattern Image Computing and Computer Assisted Intervention -MICCAl Recognition.Salt Lake City,2018:7132 2019.Shenzhen,2019:721 [17]Yu F,Koltun V.Multi-scale context aggregation by dilated [32]Jiang Y,Tan N,Peng T T,et al.Retinal vessels segmentation convolutions //Proceedings of the 4th International Conference on based on dilated multi-scale convolutional neural network./EEE Learning Representations.San Juan,2016 4 ccess,,2019,7:76342 [1]Chen LC.Papandreou G.Kokkinos I,et al.DeepLab:semantic [33]Hatamizadeh A,Hosseini H,Liu Z Y,et al.Deep dilated image segmentation with deep convolutional nets,atrous convolutional nets for the automatic segmentation of retinal convolution,and fully connected CRFs.IEEE Trans Pattern Anal vessels[J/OL].arXiv preprint (2019-7-21)[2021-6-10]. Mach Intell,2018.40(4):834 https://arxiv.org/abs/1905.12120 [19]Chen L C,Szemenyei M,Schroff F,et al.Rethinking atrous [34]Gu Z,Cheng J,Fu H,et al.CE-net:Context encoder network for convolution for semantic image segmentation[J/OL].arYiv 2D medical image segmentation.IEEE Trans Med Imaging,2019, preprint(2017-12-5)[2021-6-10].https:://arxiv.org/abs/1706.05587 38(10):2281 [20]Chen L C.Papandreou G.Papandreou G,et al.Encoder-decoder [35]Mo J,Zhang L.Multi-level deep supervised networks for retinal with atrous separable convolution for semantic image vessel segmentation.Int J Comput Assist Radiol Surg,2017, segmentation /Computer Vision -ECCV 2018.Munich,2018: 12(12):2181 833 [36]Hu K,Zhang ZZ,Niu X R,et al.Retinal vessel segmentation of [21]Song H M,Wang W G,Zhao S Y,et al.Pyramid dilated deeper color fundus images using multiscale convolutional neural network ConvLSTM for video salient object detection /Computer Vision- with an improved cross-entropy loss function.Neurocomputing, ECCV 2018.Munich,2018:744 2018,309:179 [22]Xie S N,Tu Z W.Holistically-nested edge detection /2015 IEEE [37]Yan Z Q,Yang X,Cheng K T.Joint segment-level and pixel-wise International Conference on Computer Vision (ICCV).Santiago, losses for deep learning based retinal vessel segmentation.IEEE 2015:1395 Trans Biomed Eng,2018,65(9):1912 [23]Orlando JI,Blaschko M.Leamning fully-connected CRFs for blood [38]Zhang Z J,Fu HZ,Dai H,et al.ET-net:A generic edge-aTtention vessel segmentation in retinal images Interational Conference guidance network for medical image segmentation /Medical on Medical Image Computing and Computer-Assisted Imtervention Image Computing and Computer Assisted Intervention-MICCAl Boston,2014:634 2019.Shenzhen,.2019:442 [24]Ricci E,Perfetti R.Retinal blood vessel segmentation using line [39]Kang H,Gao Y Q,Guo S,et al.AVNet:A retinal artery/vein operators and support vector classification.IEEE Trans Med classification network with category-attention weighted fusion maging,2007,26(10):1357 Comput Methods Programs Biomed,020,195:105629 [25]Ganin Y,Lempitsky V.N'fields:Neural network nearest neighbor [40]Zhang S H,Fu H Z,Xu Y W,et al.Retinal image segmentation fields for image transforms /Asian Conference on Computer with a structure-texture demixing network /Medical Image Vision.Singapore,2015:536 Computing and Computer Assisted Intervention -MICCAl 2020. [26]Dollar P,Zitnick C L.Structured forests for fast edge detection / Lima,2020:765 2013 IEEE International Conference on Computer Vision.Sydney, [41]Zheng S M,Zhang T Y,Zhuang J W,et al.A two-stream 2013:1841 meticulous processing network for retinal vessel [27]Maninis KK,Pont-Tuset J,Arbelaez P,et al.Deep retinal image segmentation[J/OL].arXiy preprint (2020-1-15)[2021-6-10]. understanding /Medical Image Computing and Computer- https://arxiv.org/abs/2001.05829 Assisted Intervention-MICCAl 2016.Athens,2016:140 [42]Zou B J,Dai YL,He Q.et al.Multi-label classification scheme [28]Simonyan K,Zisserman A.Very deep convolutional networks for based on local regression for retinal vessel segmentation. large-scale image recognition I/Proceedings of the 3th IEEE/ACM Trans Comput Biol Bioinform,2020,PP(99):1 International Conference on Learning Representations.San Diego, [43]Zhang T Y,Suen C Y.A fast parallel algorithm for thinning digital 2015 patterns.Commun ACM,1984,27(3):236 [29]Zhang S H,Fu HZ,Yan Y G,et al.Attention guided network for [44]Hakim L,Yudistira N,Kavitha M,et al.U-net with graph based retinal image segmentation II Medical Image Computing and smoothing regularizer for small vessel segmentation on fundus Computer Assisted Intervention MICCAl 2019.Shenzhen,2019: image l/Proceedings of the 26th International Conference on 797 Neural Information Processing.Sydney,2019:515 [30]Guo C L,Szemenyei M,Yi Y G,et al.SA-UNet:spatial attention [45]Oktay O,Schlemper J,Folgoc LL,et al.Attention U-net:Learning U-net for retinal vessel segmentation [J/OL].arYiv preprint (2020- where to look for the pancreas.2018[J/OL].arXi preprint (2018-Proceedings of the 31st Conference on neural information processing systems (NIPS 2017). Long Beach, 2017: 5998 Hu  J,  Shen  L,  Sun  G.  Squeeze-and-excitation  networks  //  2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 7132 [16] Yu  F,  Koltun  V.  Multi-scale  context  aggregation  by  dilated convolutions //Proceedings of the 4th International Conference on Learning Representations. San Juan, 2016 [17] Chen  L  C,  Papandreou  G,  Kokkinos  I,  et  al.  DeepLab:  semantic image  segmentation  with  deep  convolutional  nets,  atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell, 2018, 40（4）: 834 [18] Chen  L  C,  Szemenyei  M,  Schroff  F,  et  al.  Rethinking  atrous convolution  for  semantic  image  segmentation[J/OL]. arXiv preprint (2017-12-5) [2021-6-10].https://arxiv.org/abs/1706.05587 [19] Chen  L  C,  Papandreou  G,  Papandreou  G,  et  al.  Encoder-decoder with  atrous  separable  convolution  for  semantic  image segmentation  // Computer Vision – ECCV 2018.  Munich,  2018: 833 [20] Song H M, Wang W G, Zhao S Y, et al. Pyramid dilated deeper ConvLSTM for video salient object detection // Computer Vision – ECCV 2018. Munich, 2018: 744 [21] Xie S N, Tu Z W. Holistically-nested edge detection // 2015 IEEE International Conference on Computer Vision (ICCV).  Santiago, 2015: 1395 [22] Orlando J I, Blaschko M. Learning fully-connected CRFs for blood vessel segmentation in retinal images // International Conference on Medical Image Computing and Computer-Assisted Intervention. Boston, 2014: 634 [23] Ricci  E,  Perfetti  R.  Retinal  blood  vessel  segmentation  using  line operators  and  support  vector  classification. IEEE Trans Med Imaging, 2007, 26（10）: 1357 [24] Ganin Y, Lempitsky V. N4 -fields: Neural network nearest neighbor fields  for  image  transforms  // Asian Conference on Computer Vision. Singapore, 2015: 536 [25] Dollár P, Zitnick C L. Structured forests for fast edge detection // 2013 IEEE International Conference on Computer Vision. Sydney, 2013: 1841 [26] Maninis K K, Pont-Tuset J, Arbeláez P, et al. Deep retinal image understanding  // Medical Image Computing and Computer￾Assisted Intervention – MICCAI 2016. Athens, 2016: 140 [27] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale  image  recognition  //Proceedings of the 3th International Conference on Learning Representations. San Diego, 2015 [28] Zhang S H, Fu H Z, Yan Y G, et al. Attention guided network for retinal  image  segmentation  // Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. Shenzhen, 2019: 797 [29] Guo C L, Szemenyei M, Yi Y G, et al. SA-UNet: spatial attention U-net for retinal vessel segmentation [J/OL]. arXiv preprint (2020- [30] 10-20) [2021-6-10]. https://arxiv.org/abs/2004.03696 Mou  L,  Zhao  Y  T,  Chen  L,  et  al.  CS-net:  Channel  and  spatial attention network for curvilinear structure segmentation // Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. Shenzhen, 2019: 721 [31] Jiang  Y,  Tan  N,  Peng  T  T,  et  al.  Retinal  vessels  segmentation based  on  dilated  multi-scale  convolutional  neural  network. IEEE Access, 2019, 7: 76342 [32] Hatamizadeh  A,  Hosseini  H,  Liu  Z  Y,  et  al.  Deep  dilated convolutional  nets  for  the  automatic  segmentation  of  retinal vessels[J/OL]. arXiv preprint (2019-7-21)  [2021-6-10]. https://arxiv.org/abs/1905.12120 [33] Gu Z, Cheng J, Fu H, et al. CE-net: Context encoder network for 2D medical image segmentation. IEEE Trans Med Imaging, 2019, 38（10）: 2281 [34] Mo  J,  Zhang  L.  Multi-level  deep  supervised  networks  for  retinal vessel  segmentation. Int J Comput Assist Radiol Surg,  2017, 12（12）: 2181 [35] Hu K, Zhang Z Z, Niu X R, et al. Retinal vessel segmentation of color fundus images using multiscale convolutional neural network with  an  improved  cross-entropy  loss  function. Neurocomputing, 2018, 309: 179 [36] Yan Z Q, Yang X, Cheng K T. Joint segment-level and pixel-wise losses  for  deep  learning  based  retinal  vessel  segmentation. IEEE Trans Biomed Eng, 2018, 65（9）: 1912 [37] Zhang Z J, Fu H Z, Dai H, et al. ET-net: A generic edge-aTtention guidance  network  for  medical  image  segmentation  // Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. Shenzhen, 2019: 442 [38] Kang  H,  Gao  Y  Q,  Guo  S,  et  al.  AVNet:  A  retinal  artery/vein classification  network  with  category-attention  weighted  fusion. Comput Methods Programs Biomed, 2020, 195: 105629 [39] Zhang S H, Fu H Z, Xu Y W, et al. Retinal image segmentation with  a  structure-texture  demixing  network  // Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. Lima, 2020: 765 [40] Zheng  S  M,  Zhang  T  Y,  Zhuang  J  W,  et  al.  A  two-stream meticulous  processing  network  for  retinal  vessel segmentation[J/OL]. arXiv preprint (2020-1-15)  [2021-6-10]. https://arxiv.org/abs/2001.05829 [41] Zou B J, Dai Y L, He Q, et al. Multi-label classification scheme based  on  local  regression  for  retinal  vessel  segmentation. IEEE/ACM Trans Comput Biol Bioinform, 2020, PP（99）: 1 [42] Zhang T Y, Suen C Y. A fast parallel algorithm for thinning digital patterns. Commun ACM, 1984, 27（3）: 236 [43] Hakim L, Yudistira N, Kavitha M, et al. U-net with graph based smoothing  regularizer  for  small  vessel  segmentation  on  fundus image  // Proceedings of the 26th International Conference on Neural Information Processing. Sydney, 2019: 515 [44] Oktay O, Schlemper J, Folgoc L L, et al. Attention U-net: Learning where to look for the pancreas. 2018[J/OL]. arXiv preprint (2018- [45] 姜大光等： 骨架图引导的级联视网膜血管分割网络 · 1251 ·