多尺度注意力细化视网膜分割算法

doi:10.3778/j.issn.1002-8331.2111-0514

摘要/Abstract

摘要： 针对现有算法存在因视网膜血管尺寸微小和对比度低等造成细小血管分割缺失以及因病理区域造成血管过分割等问题，提出一种基于U型网络多尺度注意力细化视网膜分割算法。在编码和解码阶段使用改进的密集卷积模块充分提取血管的特征信息，提升特征的利用率。将不同尺度的编码层特征提取的结果拼接后，通过跳跃连接经双向注意力机制将特征增强后传递到解码层。在解码处引入空间细化模块进一步提取微小血管的空间信息，减少背景伪影，细化血管形态。该算法在公开数据集DRIVE和STARE上进行验证，其在评估指标准确率分别为0.964 9和0.966 3，灵敏度分别为0.842 2和0.805 0，特异性分别为0.982 2和0.988 0，AUC分别为0.986 7和0.989 5。

关键词: 视网膜血管分割, 空间细化, 密集卷积, 双向注意力

Abstract: Aiming at the problems of unsegmented small blood vessels and over-segmented pathological areas due to the small size of retinal blood vessels and low contrast in existing algorithms, a multi-scale attention thinning retinal segmentation algorithm based on U-shaped network is proposed. First of all, the improved dense convolution module is used in the encoding and decoding stages to fully extract the feature information of the blood vessel, and improve the utilization of features. Secondly, the results of the four feature extractions of the coding layers of different scales are spliced, and then transferred to the decoding layer through skip connections. At the same time, a dual attention mechanism is introduced in the skipping connection and spatial refinement structure to spatially enhance the structure of the tiny blood vessels. Finally, the spatial refinement module is introduced in the decoding to further extract the spatial information of the tiny blood vessels and refine the distribution and shape of the blood vessels. The algorithm is verified on the public data sets DRIVE and STARE. The evaluation indicators ACC are 0.964 9 and 0.966 3, the sensitivity is 0.842 2 and 0.805 0, the specificity is 0.982 2 and 0.988 0, and the AUC is 0.986 7 and 0.989 5.

Key words: retinal vessel segmentation, spatial refinement, dense convolution, dual attention

梁礼明, 陈鑫, 余洁, 周珑颂. 多尺度注意力细化视网膜分割算法[J]. 计算机工程与应用, 2023, 59(6): 212-220.

LIANG Liming, CHEN Xin, YU Jie, ZHOU Longsong. Multi-Scale Attention Refinement Retinal Segmentation Algorithm[J]. Computer Engineering and Applications, 2023, 59(6): 212-220.

参考文献

[1] 曹飞道，赵怀慈.基于三端注意力机制的视网膜血管分割算法[J].控制与决策，2022，37（10）：2505-2512.
CAO F D，ZHAO H C.Improved U-Net based on three-terminal attention mechanism for retinal vessel segmentation[J].Control and Decision，2022，37（10）：2505-2512.
[2] GHADERI R，HASSANPOUR H，SHAHIRI M.Retinal vessel segmentation using the 2-d morlet wavelet and neural network[C]//2007 International Conference on Intelligent and Advanced Systems，2007：1251-1255.
[3] YANG J Z，HUANG M X，FU J，et al.Frangi based multi-scale level sets for retinal vascular segmentation[J].Computer Methods and Programs in Biomedicine，2020，197.
[4] FAN Z，LU J，WEI C，et al.A hierarchical image matting model for blood vessel segmentation in fundus images[J].IEEE Transactions on Image Processing，2018，28（5）：2367-2377.
[5] WANG W，ZHANG J，WU W，et al.An automatic approach for retinal vessel segmentation by multi-scale morphology and seed point tracking[J].Journal of Medical Imaging and Health Informatics，2018，8（2）：262-274.
[6] JIN Q，MENG Z，PHAM T D，et al.Dunet：a deformable network for retinal vessel segmentation[J].Knowledge-Based Systems，2019，178：149-162.
[7] 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.
[8] ZHANG Y，CHUNG A C S.Deep supervision with additional labels for retinal vessel segmentation task[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention，2018：83-91.
[9] YAN Z，YANG X，CHENG K.A three-stage deep learning model for accurate retinal vessel segmentation[J].IEEE Journal of Biomedical and Health Informatics，2019，23（4）：1427-1436.
[10] YANG L，WANG H X，ZENG Q S，et al.A hybrid deep segmentation network for fundus vessels via deep-learning framework[J].Neurocomputing，2021，448：168-178.
[11] PARK K，CHOI S H，LEE J Y.M-gan：retinal blood vessel segmentation by balancing losses through stacked deep fully convolutional networks[J].IEEE Access，2020，8：146308-146322.
[12] HUANG G，LIU Z，VAN DER MAATEN L，et al.Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2017：2261-2269.
[13] GUAN S，KHAN A A，SIKDAR S，et al.Fully dense unet for 2-d sparse photoacoustic tomography artifact removal[J].IEEE Journal of Biomedical and Health Informatics，2019，24（2）：568-576.
[14] GUO C，SZEMENYEI M，PEI Y，et al.SD-Unet：a structured dropout u-net for retinal vessel segmentation[C]//2019 IEEE 19th International Conference on Bioinformatics and Bioengineering（BIBE），2019：439-444.
[15] YUAN Y，ZHANG L，WANG L，et al.Multi-level attention network for retinal vessel segmentation[J].IEEE Journal of Biomedical and Health Informatics，2022，26（1）：312-323.
[16] LI K，QI X，LUO Y，et al.Accurate retinal vessel segmentation in color fundus images via fully attention-based networks[J].IEEE Journal of Biomedical and Health Informatics，2021，25（6）：2071-2081.
[17] PAN H，ZHOU Q，LATECKI L J.Sgunet：semantic guided unet for thyroid nodule segmentation[C]//2021 IEEE 18th International Symposium on Biomedical Imaging（ISBI），2021：630-634.
[18] RONNEBERGER O，FISCHER P，BROX T.U-net：convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention，2015：234-241.
[19] OKTAY O，SCHLEMPER J，FOLGOC L L，et al.Attention U-net：learning where to look for the pancreas[J].arXiv：1804.03999v2，2018.
[20] GUO Y H，BUDAK ü，?ENGüR A.A novel retinal vessel detection approach based on multiple deep convolution neural networks[J].Computer Methods and Programs in Biomedicine，2018，167：43-48.
[21] GUO J，REN S，SHI Y，et al.Automatic retinal blood vessel segmentation based on multi-level convolutional neural network[C]//2018 11th International Congress on Image and Signal Processing，Biomedical Engineering and Informatics，2018：1-5.
[22] WU C，ZOU Y，YANG Z.U-gan：generative adversarial networks with u-net for retinal vessel segmentation[C]//2019 14th International Conference on Computer Science Education，2019：642-646.
[23] KHAN T M，ALHUSSEIN M，AURANGZEB K，et al.Residual connection-based encoder decoder network（RCED-net） for retinal vessel segmentation[J].IEEE Access，2020，8：131257-131272.
[24] YIN P，YUAN R，CHENG Y，et al.Deep guidance network for biomedical image segmentation[J].IEEE Access，2020，8：116106-116116.
[25] HE J，JIANG D.Fundus image segmentation based on improved generative adversarial network for retinal vessel analysis[C]//2020 3rd International Conference on Artificial Intelligence and Big Data，2020：231-236.
[26] ZHUANG J.LadderNet：multi-path networks based on U-net for medical image segmentation[J].arXiv：1810.07810，2018.
[27] ZHOU Z，SIDDIQUEE M M R，TAJBAKHSH N，et al.U-net++：redesigning skip connections to exploit multiscale features in image segmentation[J].IEEE Transactions on Medical Imaging，2019，39（6）：1856-1867.