基于双解码器结构的多尺度注意力特征融合网络的视网膜血管分割#br#

摘要/Abstract

摘要： 针对眼底视网膜图像中血管形态不规则、难以分割的问题，提出一种基于双解码器结构的多尺度注意力特征融合网络模型，可以实现视网膜血管精确分割。双解码器分支网络结构能减少信息丢失，编码器中设计多尺度注意力特征融合模块来提取丰富的多尺度特征，结合空间注意力模块加强空间上下文信息提取，提高血管识别能力。利用挤压与激励模块对融合特征进行优化，抑制不相关特征通道，提高模型综合分割能力。在DRIVE和CHASEDB1数据集上的实验结果显示，召回率分别达到0.841 1和0.855 1，相较目前一些先进网络取得了较大进步，最大提升分别达到6.6%和8.25%。

关键词: 医学图像分割, 视网膜血管分割, 双解码器结构, 多尺度特征提取, 空间注意力模块

Abstract: To solve the problem of irregular and difficult segmentation of blood vessels in fundus retinal images, a multi-scale attention feature fusion network model based on a dual-decoder structure is proposed to achieve accurate segmentation of retinal blood vessels. The dual decoder branch network structure can reduce information loss. In the encoder, the multi-scale attention feature fusion module is designed to extract rich multi-scale features and the spatial attention module is combined to enhance the extraction of spatial context information and improve vascular recognition ability. Squeeze-and-excitation module is used to optimize aggregated features, suppress irrelevant feature channels and improve the comprehensive segmentation ability of the model. The experimental results on the DRIVE and CHASEDB1 data sets show that the recall rate can reach 0.841 1 and 0.855 1 respectively, making great progress compared with some advanced networks at present, with the maximum increase of 6.6% and 8.25% respectively.

Key words: medical image segmentation, retinal vessel segmentation, dual-decoder structure, multi-scale feature extraction, spatial attention module

张文豪, 瞿绍军. 基于双解码器结构的多尺度注意力特征融合网络的视网膜血管分割#br#[J]. 计算机工程与科学, 2023, 45(12): 2175-2185.

ZHANG Wen-hao, QU Shao-jun. Retinal vessel segmentation based on multi-scale attention feature fusion network with dual-decoder structure[J]. Computer Engineering & Science, 2023, 45(12): 2175-2185.

参考文献［29］

［1］	Chen C,Chuah J H,Ali R,et al.Retinal vessel segmentation using deep learning:A review［J］.IEEE Access,2021,9:111985-112004.
［2］	Ronneberger O,Fischer P,Brox T.U-Net:Convolutional networks for biomedical image segmentation［C］∥Proc of International Conference on Medical Image Computing and Computer-Assisted Intervention,2015:234-241.
［3］	Xiao X, Lian S,Luo Z,et al.Weighted Res-UNet for high- quality retina vessel segmentation［C］∥Proc of 2018 9th International Conference on Information Technology in Medicine and Education,2018:327-331.
［4］	Francia G A,Pedraza C,Aceves M,et al.Chaining a U-Net with a residual U-Net for retinal blood vessels segmentation［J］.IEEE Access,2020,8:38493-38500.
［5］	Guo C, Szemenyei M,Pei Y,et al.SD-UNet:A structured dropout U-Net for retinal vessel segmentation［C］∥Proc of 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering,2019:439-444.
［6］	Sule O,Viriri S.Enhanced convolutional neural networks for segmentation of retinal blood vessel image［C］∥Proc of 2020 Conference on Information Communications Technology and Society,2020:1-6.
［7］	Zhou Z W, Rahman Siddiquee M M, Tajbakhsh N, et al. UNet++:A nested U-Net architecture for medical image segmentation［C］∥Proc of International Workshop on Deep Learning in Medical Image Analysis, and International Workshop on Multimodal Learning for Clinical Decision Support,2018:3-11.
［8］	Huang H M,Lin L F,Tong R F,et al.UNet 3+:A full-scale connected UNet for medical image segmentation［C］∥Proc of 2020 IEEE International Conference on Acoustics,Speech and Signal Processing,2020:1055-1059.
［9］	Milletari F,Navab N,Ahmadi S A.V-Net:Fully convolutional neural networks for volumetric medical image segmentation［C］∥Proc of 2016 4th International Conference on 3D Vision,2016:565-571.
［10］	Valanarasu J M J,Patel V M.UNeXt:MLP-based rapid medical image segmentation network［C］∥Proc of International Conference on Medical Image Computing and Computer-Assisted Intervention,2022: 23-33.
［11］	Chen L-C,Papandreou G,Kokkinos I,et al.DeepLab:Semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected crfs［J］.IEEE Tran- sactions on Pattern Analysis and Machine Intelligence,2018,40(4):834-848.
［12］	Meng Lin,Liu Jing,Cao Hui,et al.Retinal vessel segmentation based on Frangi filter and Otsu algorithm［J］.Laser & Optoelectronics Progress,2019,56(18):181004-1-181004-7.(in Chinese)
［13］	Xu Guang-zhu,Wang Ya-wen,Hu Song,et al.Retinal vascular segmentation combined with PCNN and morphological matching enhancement［J］.Opto-Electronic Engineering,2019,46(4):180466.(in Chinese)
［14］	Zhang Sai,Li Yan-ping.Retinal vascular image segmentation based on improved HED network［J］.Acta Optica Sinica,2020,40(6):0610002-1-0610002-10.(in Chinese)
［15］	Guo Y H,Budak ,Vespa L J,et al.A retinal vessel detection approach using convolution neural network with reinforcement sample learning strategy［J］.Measurement,2018,125:586-591.
［16］	Zhang B,Huang S,Hu S.Multi-scale neural networks for retinal blood vessels segmentation［J］.arXiv:1804.04206,2018.
［17］	Li W,Zhang M,Chen D.Fundus retinal blood vessel segmentation based on active learning［C］∥Proc of 2020 International Conference on Computer Information and Big Data Applications,2020:264-268.
［18］	Long J,Shelhamer E,Darrell T.Fully convolutional networks for semantic segmentation［C］∥Proc of 2015 IEEE Conference on Computer Vision and Pattern Recognition,2015:3431-3440.
［19］	Uysal E,Güraksin G E.Computer-aided retinal vessel segmentation in retinal images:Convolutional neural networks［J］.Multimedia Tools and Applications,2021,80(3):3505-3528.
［20］	Wu H,Wang W,Zhong J,et al.SCS-Net:A scale and context sensitive network for retinal vessel segmentation［J］.Medical Image Analysis,2021,70:102025.
［21］	Jiang Yun,Liu Wen-huan,Liang Jing.Retinal vessel segmentation network with joint attention and transformer［J］.Computer Engineering & Science,2022,44(11):2037-2047.(in Chinese)
［22］	Oktay O,Schlemper J,Folgoc L L,et al.Attention U-Net:Learning where to look for the pancreas［J］.arXiv:1804.03999,2018.
［23］	Trebing K,Stanczyk T,Mehrkanoon S.SmaAt-UNet:Precipitation nowcasting using a small attention-UNet architecture［J］.Pattern Recognition Letters,2021,145:178-186.
［24］	Guo C L,Szemenyei M,Yi Y G,et al.SA-UNet:Spatial attention U-Net for retinal vessel segmentation［C］∥Proc of 2020 25th International Conference on Pattern Recognition,2020:1236-1242.
［25］	Wang B,Wang S,Qiu S,et al.CSU-Net:A context spatial U-Net for accurate blood vessel segmentation in fundus images［J］.IEEE Journal of Biomedical and Health Informatics,2020,25(4):1128-1138.
［26］	Tang X,Zhong B,Peng J,et al.Multi-scale channel importance sorting and spatial attention mechanism for retinal vessels segmentation［J］.Applied Soft Computing,2020,93:106353.
［27］	Ouyang Liu,He Xi,Qu Shao-jun.Fully convolutional neural network with attention module for semantic segmentation［J］.Journal of Frontiers of Computer Science and Technology,2022,16(5):1136-1145.(in Chinese)
［28］	Wu Cong-zhong,Dong Hao,Fang Jing.An adaptive filtering remote sensing image segmentation network based on attention mechanism［J］.Computer Engineering & Science,2022,44(11):2010-2018.(in Chinese)
［29］	Bi Xiu-li, Lu Meng,Xiao Bin,et al.Pancreas segmentation based on dual-decoding U-Net［J］.Journal of Software,2022,33(5):1947-1958.(in Chinese)
［30］	Woo S,Park J,Lee J Y,et al.CBAM:Convolutional block attention module［C］∥Proc of the 15th European Conference on Computer Vision,2018:3-19.
［31］	Hu J,Shen L,Sun G.Squeeze-and-excitation networks［C］∥Proc of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition,2018:7132-7141.
［32］	Staal J,Abràmoff 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.
［33］	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.
［34］	Alom M Z,Yakopcic C,Hasan M,et al.Recurrent residual U-Net for medical image segmentation［J］.Journal of Medical Imaging,2019,6(1):014006.
［35］	Wang B,Qiu S,He H G.Dual encoding U-Net for retinal vessel segmentation［C］∥Proc of the 22nd International Conference on Medical Image Computing and Computer- Assisted Intervention,2019:84-92.
［36］	Lü Y,Ma H,Li J,et al.Attention guided U-Net with atrous convolution for accurate retinal vessels segmentation［J］.IEEE Access,2020,8:32826-32839.
［37］	Zou B,Dai Y,He Q,et al.Multi-label classification scheme based on local regression for retinal vessel segmentation［J］.IEEE/ACM Transactions on Computational Biology and Bioinformatics,2020,18(6):2586-2597.
［38］	Oliveira A,Pereira S,Silva C A.Retinal vessel segmentation based on fully convolutional neural networks［J］.Expert Systems with Applications,2018,112:229-242.
［39］	Atli I, Gedik O S. Sine-Net:A fully convolutional deep learning architecture for retinal blood vessel segmentation［J］.Engineering Science and Technology,an International Journal,2021,24(2):271-283.
［40］	Wu Y,Xia Y,Song Y,et al.Vessel-Net:Retinal vessel segmentation under multi-path supervision［C］∥Proc of the 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention,2019:264-272.
［41］	Wu C,Zou Y,Yang Z.U-GAN:Generative adversarial networks with U-Net for retinal vessel segmentation［C］∥Proc of 2019 14th International Conference on Computer Science & Education,2019:642-646.
［42］	Liu Y,Shen J,Yang L,et al.ResDO-UNet:A deep residual network for accurate retinal vessel segmentation from fundus images［J］.Biomedical Signal Processing and Control,2023,79:104087.
［43］	Cao J M, Li Y Y, Sun M C,et al.DO-Conv:Depth wise over-parameterized convolutional layer［J］.IEEE Transactions on Image Processing, 2022,31:3726-3736.
［44］	Yang L,Wang H,Zeng Q,et al.A hybrid deep segmentation network for fundus vessels via deep-learning framework［J］.Neurocomputing,2021,448:168-178.
［45］	Hu H G,Zheng Y X,Zhou Q W,et al.MC-Unet:Multi-scale convolution unet for bladder cancer cell segmentation in phase-contrast microscopy images［C］∥Proc of 2019 IEEE International Conference on Bioinformatics and Biomedicine,2019:1197-1199.
	附中文参考文献：
［12］	孟琳,刘静,曹慧,等.基于Frangi滤波器和Otsu视网膜血管分割［J］.激光与光电子学进展,2019,56(18):181004-1-101004-7.
［13］	徐光柱,王亚文,胡松,等.PCNN与形态匹配增强相结合的视网膜血管分割［J］.光电工程，2019，46(4):180466.
［14］	张赛,李艳萍.基于改进 HED 网络的视网膜血管图像分割［J］.光学学报,2020,40(6):0610002-1-0610002-10.
［21］	蒋芸,刘文欢,梁菁.联合注意力和Transformer的视网膜血管分割网络［J］.计算机工程与科学,2022,44(11):2037-2047.
［27］	欧阳柳,贺禧,瞿绍军.全卷积注意力机制神经网络的图像语义分割［J］.计算机科学与探索,2022,16(5):1136-1145.
［28］	吴从中,董浩,方静.基于注意力机制的自适应滤波遥感图像分割网络［J］.计算机工程与科学,2022,44(11):2010-2018.
［29］	毕秀丽,陆猛,肖斌,等.基于双解码U型卷积神经网络的胰腺分割［J］.软件学报,2022,33(5):1947-1958.