带有注意力机制的OCTA视网膜血管分割方法

doi:10.3778/j.issn.1002-8331.2205-0134

摘要/Abstract

摘要： 视网膜血管分割是智能辅助诊断过程中的关键步骤。由于血管末端细小且易与背景混淆，导致很难精确分割。针对此类问题，提出一种基于深度可分离卷积与块注意力机制的高效视网膜血管分割算法。使用步长为2的卷积层代替最大池化层进行特征筛选；为了降低网络的参数量，用深度可分离卷积代替常规的卷积；引入注意力机制学习重要特征，对OCTA视网膜血管图像的像素进行精确分类。将该方法在2020版的公开数据集OCTA-500上进行充分实验。结果表明，该方法在分割性能指标F1、mIoU、Se、Sp、Acc和Pre上分别达到了80.01%、81.18%、84.39%、96.41%、95.32%和76.24%；和基准方法U-net相比，该方法的参数量和FLOPs也显著降低，分别只有U-net的19.2%和16.5%。

关键词: 深度学习, 医学图像处理, 视网膜血管分割, 深度可分离卷积, 块注意力机制

Abstract: Retinal vascular segmentation is a key step in the process of intelligent aided diagnosis. Because the ends of the vessels are small and easy to be confused with the background, it is difficult to segment accurately. To solve this problem, an efficient retinal vessel segmentation algorithm based on deep separable convolution and block attention mechanism is proposed in this paper. Firstly, the convolution layer with step size of 2 is used to replace the maximum pooling layer for feature screening. Then, in order to reduce the complexity of the network, the general convolution operation is replaced by the depth separable convolution operation. Finally, the attention mechanism is introduced to learn important features to accurately classify the pixels of the OCTA image. The proposed method is tested on the 2020 public dataset OCTA-500. The results show that the F1, mIoU, Se, Sp, Acc and Pre are 80.01%, 81.18%, 84.39%, 96.41%, 95.32% and 76.24% respectively. Compared with the U-net, the parameters and FLOPs of this method are also significantly reduced, only 19.2% and 16.5% of the U-net.

Key words: deep learning, medical image processing, retinal vascular segmentation, depth separable convolution, block attention mechanism

崔少国, 文浩, 张宇楠, 唐艺菠, 杜兴. 带有注意力机制的OCTA视网膜血管分割方法[J]. 计算机工程与应用, 2023, 59(18): 163-171.

CUI Shaoguo, WEN Hao, ZHANG Yunan, TANG Yibo, DU Xing. Segmentation Method of Retinal Vessels in OCTA with Attention Mechanism[J]. Computer Engineering and Applications, 2023, 59(18): 163-171.

参考文献

[1] KIRBAS C，QUEK F.A review of vessel extraction techniques and algorithms[J].ACM Computing Surveys（CSUR），2004，36（2）：81-121.
[2] 李兰兰，张孝辉，牛得草，等.深度学习在视网膜血管分割上的研究进展[J].计算机科学与探索，2021，15（11）：2063-2076.
LI L L，ZHANG X H，NIU D C，et al.Research progress of deep learning in retinal vessel segmentation[J].Journal of Frontiers of Computer Science and Technology，2021，15（11）：2063-2076.
[3] 张宸嘉，朱磊，俞璐.卷积神经网络中的注意力机制综述[J].计算机工程与应用，2021，57（20）：64-72.
ZHANG C J，ZHU L，YU L.Review of attention mechanism in convolutional neural networks[J].Computer Engineering and Applications，2021，57（20）：64-72.
[4] SIMONYAN K，ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv：1409.
1556，2014.
[5] LECUN Y，BENGIO Y，HINTON G.Deep learning[J].Nature，2015，521（7553）：436-444.
[6] LONG J，SHELHAMER E，DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2015：3431-3440.
[7] 殷晓航，王永才，李德英.基于U-Net结构改进的医学影像分割技术综述[J].软件学报，2021，32（2）：519-550.
YIN X H，WANG Y C，LI D Y.Suvery of medical image segmentation technology based on U-Net structure improvement[J].Journal of Software，2021，32（2）：519-550.
[8] 张欢，仇大伟，冯毅博，等.U-Net模型改进及其在医学图像分割上的研究综述[J].激光与光电子学进展，2022，59（2）：55-71.
ZHANG H，QIU D W，FENG Y B，et al.Improved U-Net models and its applications in medical image segmentation：a review[J].Laser & Optoelectronics Progress，2022，59（2）：55-71.
[9] 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 Transactions on Pattern Analysis and Machine Intelligence，2017，40（4）：834-848.
[10] KHAN S，NASEER M，HAYAT M，et al.Transformers in vision：a survey[J].arXiv：2101.01169，2021.
[11] ZHENG S，LU J，ZHAO H，et al.Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：6881-6890.
[12] XIAO X，LIAN S，LUO Z，et al.Weighted resunet for high-quality retina vessel segmentation[C]//2018 9th International Conference on Information Technology in Medicine and Education（ITME），2018：327-331.
[13] ZHOU Z，SIDDIQUEE M M R，TAJBAKHSH N，et al.Unet++：redesigning skip connections to exploit multiscale features in image segmentation[J].IEEE Transactions on Medical Imaging，2019，39（6）：1856-1867.
[14] VALANARASU J M J，OZA P，HACIHALILOGLU I，et al.Medical transformer：gated axial-attention for medical image segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.Cham：Springer，2021：36-46.
[15] 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.
[16] ELADAWI N，ELMOGY M，HELMY O，et al.Automatic blood vessels segmentation based on different retinal maps from OCTA scans[J].Computers in Biology and Medicine，2017，89：150-161.
[17] GU Z，CHENG J，FU H，et al.Ce-net：context encoder network for 2d medical image segmentation[J].IEEE Transactions on Medical Imaging，2019，38（10）：2281-2292.
[18] LI M，CHEN Y，JI Z，et al.Image projection network：3D to 2D image segmentation in OCTA images[J].IEEE Transactions on Medical Imaging，2020，39（11）：3343-3354.
[19] WU S，WU S W，FENG H，et al.An optimized segmentation and quantification approach in microvascular imaging for OCTA-based neovascular regression monitoring[J].BMC Medical Imaging，2021，21（1）：1-9.
[20] 蒋芸，谭宁.基于条件深度卷积生成对抗网络的视网膜血管分割[J].自动化学报，2021，47（1）：136-147.
JIANG Y，TAN N.Retinal vessel segmentation based on conditional deep convolutional generative adversarial neworks[J].Acta Automatica Sinica，2021，47（1）：136-147.
[21] MA Y，HAO H，XIE J，et al.ROSE：a retinal OCT-angiography vessel segmentation dataset and new model[J].IEEE Transactions on Medical Imaging，2020，40（3）：928-939.
[22] BOUDEGGA H，ELLOUMI Y，AKIL M，et al.Fast and efficient retinal blood vessel segmentation method based on deep learning network[J].Computerized Medical Imaging and Graphics，2021，90：101902.
[23] 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.Cham：Springer，2015：234-241.
[24] CHOLLET F.Xception：deep learning with depthwise separable convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：1251-1258.
[25] HOWARD A G，ZHU M，CHEN B，et al.Mobilenets：efficient convolutional neural networks for mobile vision applications[J].arXiv：1704.04861，2017.
[26] 耿磊，邱玲，吴骏，等.结合深度可分离卷积与通道加权的全卷积神经网络视网膜图像血管分割[J].生物医学工程学杂志，2019，36（1）：107-115.
GENG L，QIU L，WU J，et al.Segmentation of retinal image vessels based on fully convolutional network with depthwise separable convolution and channel weighting[J].Journal of Biomedical Engineering，2019，36（1）：107-115.
[27] LI X，JIANG Y，LI M，et al.Lightweight attention convolutional neural network for retinal vessel image segmentation[J].IEEE Transactions on Industrial Informatics，2020，17（3）：1958-1967.
[28] WOO S，PARK J，LEE J Y，et al.Cbam：convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：3-19.
[29] 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.
[30] WANG C，HE Y，LIU Y，et al.Sclerasegnet：an improved u-net model with attention for accurate sclera segmentation[C]//2019 International Conference on Biometrics（ICB），2019：1-8.
[31] LI M，ZHANG Y，JI Z，et al.IPN-V2 and OCTA-500：methodology and dataset for retinal image segmentation[J].arXiv：2012.07261，2020.
[32] 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.