A feature aggregation and feature fusion network for retinal vessel segmentation

被引:19
作者
Ni, Jiajia [1 ]
Sun, Haizhou [1 ]
Xu, Jinxin [2 ]
Liu, Jinhui [1 ]
Chen, Zhengming [1 ]
机构
[1] HoHai Univ, Coll Internet Things Engn, Changzhou, Peoples R China
[2] Nanjing Marine Radar Inst, Nanjing, Peoples R China
关键词
Neural networks; Vessel segmentation; Feature fusion; Multi -scale feature; Attention mechanisms; BLOOD-VESSELS; U-NET; IMAGES; PLUS;
D O I
10.1016/j.bspc.2023.104829
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Neural networks have achieved outstanding performance in retinal vessel segmentation. However, since its continuous upsampling and convolution operation in the decoding stage, the semantic information and class information of the high-level features are destroyed. To address these problems, we proposed a new feature aggregation and feature fusion network (FAF-Net). Firstly, we introduced a multi-scale feature aggregation (MFA) block, which adjusts the receptive fields to learn more multi-scale features information. Furthermore, a feature reuse and distribution (FRD) block is intended to preserve the multi-scale feature information of the image and reduce the background noises in the feature map. Finally, the attention feature fusion (AFF) block is employed to effectively reduce the information loss of high-level features and connect the encoding and decoding stages. This multi-path combination helps to learn better representations and more accurate vessel feature maps. We evaluate the network on three retinal image databases (DRIVE, CHASEDB1, STARE). The proposed network outperforms existing current state-of-the-art vessel segmentation methods. Comprehensive experiments prove that FAF-Net is suited to processing medical image segmentation with limited samples and complicated features.
引用
收藏
页数:9
相关论文
共 52 条
  • [1] Genetic algorithm matched filter optimization for automated detection of blood vessels from digital retinal images
    Al-rawi, Mohammed
    Karajeh, Huda
    [J]. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2007, 87 (03) : 248 - 253
  • [2] MSAL-Net: improve accurate segmentation of nuclei in histopathology images by multiscale attention learning network
    Ali, Haider
    ul Haq, Imran
    Cui, Lei
    Feng, Jun
    [J]. BMC MEDICAL INFORMATICS AND DECISION MAKING, 2022, 22 (01)
  • [3] Recurrent residual U-Net for medical image segmentation
    Alom, Md Zahangir
    Yakopcic, Chris
    Hasan, Mahmudul
    Taha, Tarek M.
    Asari, Vijayan K.
    [J]. JOURNAL OF MEDICAL IMAGING, 2019, 6 (01)
  • [4] Amrehn M., 2017, arXiv
  • [5] [Anonymous], 2015, P 2015 IEEE C COMPUT
  • [6] Badrinarayanan V, 2016, Arxiv, DOI [arXiv:1511.00561, DOI 10.1109/TPAMI.2016.2644615]
  • [7] Chen LC, 2018, Arxiv, DOI [arXiv:1802.02611, DOI 10.48550/ARXIV.1802.02611, DOI 10.1007/978-3-030-01234-249]
  • [8] DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
    Chen, Liang-Chieh
    Papandreou, George
    Kokkinos, Iasonas
    Murphy, Kevin
    Yuille, Alan L.
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (04) : 834 - 848
  • [9] Dual Attention Network for Scene Segmentation
    Fu, Jun
    Liu, Jing
    Tian, Haijie
    Li, Yong
    Bao, Yongjun
    Fang, Zhiwei
    Lu, Hanqing
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 3141 - 3149
  • [10] CE-Net: Context Encoder Network for 2D Medical Image Segmentation
    Gu, Zaiwang
    Cheng, Jun
    Fu, Huazhu
    Zhou, Kang
    Hao, Huaying
    Zhao, Yitian
    Zhang, Tianyang
    Gao, Shenghua
    Liu, Jiang
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2019, 38 (10) : 2281 - 2292