Citation: | LIANG L M,YU J,CHEN X,et al. Cross-level fusion gated adaptive network for retinal vessel segmentation[J]. Journal of Beijing University of Aeronautics and Astronautics,2024,50(4):1097-1109 (in Chinese) doi: 10.13700/j.bh.1001-5965.2022.0410 |
To address the insufficient shallow feature extraction of most existing algorithms, which results in noise, blurred vascular boundary and capillary under segmentation, a cross-level fusion gated adaptive network is proposed. Firstly, shallow feature information is fully extracted by the dense gated channel transformation module in the network with promotion of competition or cooperation of channels to avoid the loss of shallow coarse-grained feature information. Secondly, cross-dimensional interaction information of each layer is captured by cross-level fusion module to effectively aggregate multi-scale context features. Thirdly, dual adaptive feature fusion method is used to guide the feature fusion of adjacent layers effectively and suppress noise. The validation was performed on public data sets DRIVE, CHASEDB1 and STARE, and the accuracy rates were 0.9652, 0.9668 and 0.9695 respectively; the
[1] |
贾洪, 郑楚君, 李灿标, 等. 基于局部线结构约束的FCM聚类视网膜血管分割[J]. 光学学报, 2020, 40(9): 0910001. doi: 10.3788/AOS202040.0910001
JIA H, ZHENG C J, LI C B, et al. Retinal blood vessel segmentation based on fuzzy C-means clustering according to the local line structural constraints[J]. Acta Optica Sinica, 2020, 40(9): 0910001 (in Chinese). doi: 10.3788/AOS202040.0910001
|
[2] |
周阳. 基于匹配滤波引导局部特征空间仿射传播聚类的视网膜血管分割[J]. 信息通信, 2019, 32(7): 35-39.
ZHOU Y. Retinal vascular segmentation based on affine propagation clustering in local feature space guided by matched filtering[J]. Information & Communications, 2019, 32(7): 35-39(in Chinese).
|
[3] |
DASH J, BHOI N. Retinal blood vessel extraction using morphological operators and Kirsch’s template[C]//Proceedings of the Soft Computing and Signal Processing. Berlin: Springer, 2019: 603-611.
|
[4] |
汪维华, 张景中, 吴文渊. 改进的形态学与Otsu相结合的视网膜血管分割[J]. 计算机应用研究, 2019, 36(7): 2228-2231.
WANG W H, ZHANG J Z, WU W Y. New approach to segment retinal vessel using morphology and Otsu[J]. Application Research of Computers, 2019, 36(7): 2228-2231(in Chinese).
|
[5] |
LI X, JIANG Y C, LI M L, et al. Lightweight attention convolutional neural network for retinal vessel image segmentation[J]. IEEE Transactions on Industrial Informatics, 2021, 17(3): 1958-1967.
|
[6] |
WANG C, ZHAO Z Y, REN Q Q, et al. Dense U-Net based on patch-based learning for retinal vessel segmentation[J]. Entropy, 2019, 21(2): 168. doi: 10.3390/e21020168
|
[7] |
YUE K J, ZOU B J, CHEN Z L, et al. Retinal vessel segmentation using dense U-Net with multiscale inputs[J]. Journal of Medical Imaging, 2019, 6(3): 034004.
|
[8] |
胡扬涛, 裴洋, 林川, 等. 空洞残差U型网络用于视网膜血管分割[J]. 计算机工程与应用, 2021, 57(7): 185-191. doi: 10.3778/j.issn.1002-8331.2009-0215
HU Y T, PEI Y, LIN C, et al. Atrous residual U-Net for retinal vessel segmentation[J]. Computer Engineering and Applications, 2021, 57(7): 185-191(in Chinese). doi: 10.3778/j.issn.1002-8331.2009-0215
|
[9] |
易三莉, 陈建亭, 贺建峰. 基于多路径输入和多尺度特征融合的视网膜血管分割[J]. 光电子·激光, 2021, 32(7): 735-741.
YI S L, CHEN J T, HE J F. Retinal vascular segmentation based on multi-scale input and multi-scale feature fusion[J]. Journal of Optoelectronics·Laser, 2021, 32(7): 735-741(in Chinese).
|
[10] |
HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2017: 2261-2269.
|
[11] |
WOO S, PARK J, LEE J Y, et al. CBAM: Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision. Berlin: Springer, 2018: 3-19.
|
[12] |
姜大光, 李明鸣, 陈羽中, 等. 骨架图引导的级联视网膜血管分割网络[J]. 工程科学学报, 2021, 43(9): 1244-1252.
JIANG D G, LI M M, CHEN Y Z, et al. Cascaded retinal vessel segmentation network guided by a skeleton map[J]. Chinese Journal of Engineering, 2021, 43(9): 1244-1252(in Chinese).
|
[13] |
RONNEBERGER O, FISCHER P, BROX T. U-Net: Convolutional networks for biomedical image segmentation[C]//Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin: Springer, 2015: 234-241.
|
[14] |
OKTAY O, SCHLEMPER J, LE FOLGOC L, et al. Attention U-Net: Learning where to look for the pancreas[EB/OL]. (2018-05-20)[2022-05-01]. http://arxiv.org/abs/1804.03999.
|
[15] |
易三莉, 陈建亭, 贺建峰. ASR-UNet: 一种基于注意力机制改进的视网膜血管分割算法[J]. 山东大学学报(理学版), 2021, 56(9): 13-20.
YI S L, CHEN J T, HE J F. ASR-UNet: An improved retinal vessels segmentation algorithm based on attention mechanism[J]. Journal of Shandong University (Natural Science), 2021, 56(9): 13-20 (in Chinese).
|
[16] |
YAN Z Q, YANG X, CHENG K T. 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. doi: 10.1109/TBME.2018.2828137
|
[17] |
LIN Y, ZHANG H G, HU G. Automatic retinal vessel segmentation via deeply supervised and smoothly regularized network[J]. IEEE Access, 2018, 7: 57717-57724.
|
[18] |
YAN Z Q, YANG X, CHENG K T. A three-stage deep learning model for accurate retinal vessel segmentation[J]. IEEE Journal of Biomedical and Health Informatics, 2019, 23(4): 1427-1436. doi: 10.1109/JBHI.2018.2872813
|
[19] |
SANTOS J C M D, CARRIJO G A, CARDOSO C D F D S, et al. Fundus image quality enhancement for blood vessel detection via a neural network using CLAHE and Wiener filter[J]. Research on Biomedical Engineering, 2020, 36(2): 107-119. doi: 10.1007/s42600-020-00046-y
|
[20] |
LV Y, MA H, LI J N, et al. Attention guided U-Net with atrous convolution for accurate retinal vessels segmentation[J]. IEEE Access, 2020, 8: 32826-32839. doi: 10.1109/ACCESS.2020.2974027
|
[21] |
ZHANG J W, ZHANG Y C, XU X W. Pyramid U-Net for retinal vessel segmentation[C]//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE Press, 2021: 1125-1129.
|
[22] |
TCHINDA B S, TCHIOTSOP D, NOUBOM M, et al. Retinal blood vessels segmentation using classical edge detection filters and the neural network[J]. Informatics in Medicine Unlocked, 2021, 23: 100521. doi: 10.1016/j.imu.2021.100521
|
[23] |
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. doi: 10.1016/j.neucom.2021.03.085
|
[24] |
KHAN T M, KHAN M A U, REHMAN N U, et al. Width-wise vessel bifurcation for improved retinal vessel segmentation[J]. Biomedical Signal Processing and Control, 2022, 71: 103169. doi: 10.1016/j.bspc.2021.103169
|