Abstract：The ratio of retinal artery to vein diameter is a prerequisite for quantitative analysis of chronic diseases, such as diabetes and hypertension, and is an important risk indicator for many cardiovascular diseases. With the development of deep learning technology, many methods based on convolution neural network have made great progress in the classification of fundus images based on their ability to capture high-level semantics. However, most of the methods are based on superimposed local convolution and pooling operation, which is difficult to be well applied to striped retinal blood vessel segmentation. In this paper, in order to extract the features of retinal blood vessels in the shape of stripes more effectively, we introduced stripe pooling to capture the long-distance dependence of spatial pixels. Taking into account the complex characteristics of arteriovenous interleaving and further combining with spatial pyramid pooling, a new mixed pooling technology was proposed to expand the receptive field and learning context information of the neural network. On the other hand, considering that the proportion of blood vessel and non-blood vessel distribution in the fundus image is extremely unbalanced, this paper introduced a blood vessel enhancement module, which used the information of blood vessel distribution and the information of blood vessel edge constrained by Gaussian kernel function as weights to correct the arteriovenous features and suppress the background features, thus solving the problem of the imbalance between blood vessel and background distribution. Experiments on three internationally available datasets, DRIVE, LES, and HRF, containing 40, 22, and 45 color fundus images respectively, showed that the proposed algorithm achieved results of 0.955, 0.946, and 0.967 in term of BACC scores, which verified that the method combining strip pooling and vascular enhancement effectively solved the problems of complex arteriovenous interlacing and category imbalance in fundus images, achieving accurate classification of retinal arteriovenous malformations, holding a high application value.
[1] 于舒扬, 袁鑫, 郑秀娟.融合感受野模块的卷积神经网络视杯视盘联合分割[J]. 中国生物医学工程学. 2022,41(2):167-176. [2] Hemelings R, Elen B, Stalmans I, et al. Artery-vein segmentation in fundus images using a fully convolutional network[J]. Computerized Medical Imaging and Graphics, 2019, 76:101636. [3] Gegundez AME, Marin SD, Perez BI, et al. A new deep learning method for blood vessel segmentation in retinal images based on convolutional kernels and modified U-Net model[J]. Computer Methods and Programs in Biomedicine, 2021, 205: 106081. [4] Ma Wenao, Yu Shuang, Ma Kai, et al. Multi-task neural networks with spatial activation for retinal vessel segmentation and artery/vein classification[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2019: 769-778. [5] Li, Liangzhi, Verma, M, Nakashima, Y, et al. Joint learning of vessel segmentation and artery/vein classification with post-processing[C]// Medical Imaging with Deep Learning. Montreal: PMLR, 2020: 440-453. [6] Hu Jingfei, Wang Hua, Cao Zhaohui, et al. Automatic artery/vein classification using a vessel-constraint network for multicenter fundus images[J]. Frontiers in Cell and Developmental Biology, 2021,9: 659941. [7] Ronneberger O, Fischer P, Bro 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. [8] Gao Shanghua, Cheng Mingming, Zhao Kai, et al. Res2Net: a new multi-scale backbone architecture[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 43(2): 652-662. [9] Duta IC, Liu L, Zhu F, et al. Pyramidal convolution: rethinking convolutional neural networks for visual recognition[EB/OL]// arXiv.2006.11538, 2020-06-20/2022-4-21. [10] Hu J, Wang H, Wu G, et al. Multi-scale interactive network with artery/vein discriminator for retinal vessel classification[J]. IEEE Journal of Biomedical and Health Informatics, 2022, 26(8): 3896-3905. [11] Khandouzi A, Ariafar A, Mashayekhpour Z, et al. Retinal vessel segmentation, a review of classic and deep methods[J]. Annals of Biomedical Engineering, 2022, 50(10): 1292-1314. [12] Karlsson RA, Hardarson SH. Artery vein classification in fundus images using serially connected U-Nets[J]. Computer Methods and Programs in Biomedicine, 2022, 216: 106650. [13] Dashtbozorg B, Mendonca AM, Campilho A. An automatic graph-based approach for artery/vein classification in retinal images[J]. IEEE Transactions on Image Processing, 2014, 23(3): 1073-1083. [14] Estrada R, Allingham M, Mettu P, et al. Retinal artery-vein classification via topology estimation[J]. IEEE Transactions on Medical Imaging, 2015, 34(12): 2518-2534. [15] Mou Lei, Zhao Yitian, Chen Li, et al. CS-Net: channel and spatial attention network for curvilinear structure segmentation[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2019: 721-730. [16] Gu Zaiwang, Cheng Jun, Huazhu Fu, et al. CE-Net: context encoder network for 2D medical image segmentation[J]. IEEE Transactions on Medical Imaging[J]. 2019, 38(10): 2281-2292. [17] Xu Xiayu, Ding Wenxiang, Abramoff M D, et al. An improved arteriovenous classification method for the early diagnostics of various diseases in retinal image[J]. Computer Methods & Programs in Biomedicine, 2017, 141: 3-9. [18] Guo Song, Wang Kai, Kang Hong, et al. BTS-DSN: deeply supervised neural network with short connections for retinal vessel segmentation[J]. International Journal of Medical Informatics, 2019, 126: 105-113. [19] Zhao Yitian, Xie Jiangyang, Su Pan, et al. Retinal artery and vein classification via dominant sets clustering-based vascular topology estimation[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2018: 56-64. [20] Wang Bo, Qiu Shuang, He Huiguang. Dual encoding U-Net for retinal vessel segmentation[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2019: 84-92. [21] Galdra NA, Meyer M, Costa P, et al. Uncertainty-aware artery/vein classification on retinal images[C]// International Symposium on Biomedical Imaging. Washington: IEEE, 2019: 556-560. [22] Orlando JI, Prokofyeva E, Blaschko MB. A discriminatively trained fully connected conditional random field model for blood vessel segmentation in fundus images[J]. IEEE Transactions on Biomedical Engineering, 2016, 64(1): 16-27. [23] Yan Zengqiang, Yang Xin, Cheng KT. Joint segment-level and pixel-wise losses for deep learning based retinal vessel segmentation[J]. IEEE Transactions on Biomedical Engineering, 2018, 65(9): 1912-1923. [24] Chen Wenting, Yu Shuang, Wu Junde, et al. TR-GAN: topology ranking GAN with triplet loss for retinal artery/vein classification[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2020: 616-625. [25] Chen Wenting, Yu Shuang, Ma Kai, et al. TW-GAN: topology and width aware GAN for retinal artery/vein classification[J]. Medical Image Analysis, 2022, 77: 102340. [26] Raj PK, Manjunath A, Kumar JRH, et al. Automatic classification of artery/cein from single wavelength fundus images[C]// International Symposium on Biomedical Imaging. Washington: IEEE, 2020: 1262-1265. [27] Dipak M,Aditi S. An automatic approach to segment retinal blood vessels and its separation into arteries/veins[C]//Proceedings of the International Conference on Data Engineering and Communication Technology. Singapore: Springer, 2017: 191-199.
