FSOU-Net: Feature supplement and optimization U-Net for 2D medical image segmentation

被引:2
|
作者
Wang, Yongtao [1 ,2 ]
Tian, Shengwei [1 ,2 ]
Yu, Long [3 ]
Wu, Weidong [4 ,5 ]
Zhang, Dezhi [4 ]
Wang, Junwen [1 ,2 ]
Cheng, Junlong [6 ]
机构
[1] Xinjiang Univ, Coll Software Engn, Urumqi, Xinjiang, Peoples R China
[2] Xinjiang Univ, Key Lab Software Engn Technol, Urumqi, Xinjiang, Peoples R China
[3] Xinjiang Univ, Coll Informat Sci & Engn, Urumqi, Xinjiang, Peoples R China
[4] Peoples Hosp Xinjiang Uygur Autonomous Reg, Urumqi, Xinjiang, Peoples R China
[5] China Xinjiang Key Lab Dermatol Res XJYS1707, Urumqi, Xinjiang, Peoples R China
[6] Sichuan Univ, Coll Comp Sci, Chengdu, Sichuan, Peoples R China
关键词
Deep learning algorithm; medical image analysis; semantic segmentation; multi-scale; convolutional neural networks; OPTIC DISC;
D O I
10.3233/THC-220174
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
BACKGROUND: The results of medical image segmentation can provide reliable evidence for clinical diagnosis and treatment. The U-Net proposed previously has been widely used in the field of medical image segmentation. Its encoder extracts semantic features of different scales at different stages, but does not carry out special processing for semantic features of each scale. OBJECTIVE: To improve the feature expression ability and segmentation performance of U-Net, we proposed a feature supplement and optimization U-Net (FSOU-Net). METHODS: First, we put forward the view that semantic features of different scales should be treated differently. Based on this view, we classify the semantic features automatically extracted by encoders into two categories: shallow semantic features and deep semantic features. Then, we propose the shallow feature supplement module (SFSM), which obtains fine-grained semantic features through up-sampling to supplement the shallow semantic information. Finally, we propose the deep feature optimization module (DFOM), which uses the expansive convolution of different receptive fields to obtain multi-scale features and then performs multi-scale feature fusion to optimize the deep semantic information. RESULTS: The proposed model is experimented on three medical image segmentation public datasets, and the experimental results prove the correctness of the proposed idea. The segmentation performance of the model is higher than the advanced models for medical image segmentation. Compared with baseline network U-NET, the main index of Dice index is 0.75% higher on the RITE dataset, 2.3% higher on the Kvasir-SEG dataset, and 0.24% higher on the GlaS dataset. CONCLUSIONS: The proposed method can greatly improve the feature representation ability and segmentation performance of the model.
引用
收藏
页码:181 / 195
页数:15
相关论文
共 50 条
  • [21] ELU-Net: An Efficient and Lightweight U-Net for Medical Image Segmentation
    Deng, Yunjiao
    Hou, Yulei
    Yan, Jiangtao
    Zeng, Daxing
    IEEE ACCESS, 2022, 10 : 35932 - 35941
  • [22] DRLSU-Net: Level set with U-Net for medical image segmentation
    Wang, Xiaofeng
    Liu, Jiashan
    Yang, Rentao
    Wu, Zhize
    Sun, Lingma
    Zou, Le
    DIGITAL SIGNAL PROCESSING, 2025, 157
  • [23] BCU-Net: Bridging ConvNeXt and U-Net for medical image segmentation
    Zhang, Hongbin
    Zhong, Xiang
    Li, Guangli
    Liu, Wei
    Liu, Jiawei
    Ji, Donghong
    Li, Xiong
    Wu, Jianguo
    COMPUTERS IN BIOLOGY AND MEDICINE, 2023, 159
  • [24] Multiscale feature U-Net for remote sensing image segmentation
    Wei, Youhua
    Liu, Xuzhi
    Lei, Jingxiong
    Yue, Ruihan
    Feng, Jun
    JOURNAL OF APPLIED REMOTE SENSING, 2022, 16 (01)
  • [25] MAEF-Net: MLP Attention for Feature Enhancement in U-Net based Medical Image Segmentation Networks
    Zhang, Yunchu
    Dong, Jianfei
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2024, 28 (02) : 846 - 857
  • [26] An Attention-oriented U-Net Model and Global Feature for Medical Image Segmentation
    Han, Yandong
    Li, Jiangjiang
    JOURNAL OF APPLIED SCIENCE AND ENGINEERING, 2020, 23 (04): : 731 - 738
  • [27] DEU-Net: Dual Encoder U-Net for 3D Medical Image Segmentation
    Zhou, Yuxiang
    Kang, Xin
    Ren, Fuji
    Nakagawa, Satoshi
    Shan, Xiao
    2023 IEEE 22ND INTERNATIONAL CONFERENCE ON TRUST, SECURITY AND PRIVACY IN COMPUTING AND COMMUNICATIONS, TRUSTCOM, BIGDATASE, CSE, EUC, ISCI 2023, 2024, : 2735 - 2741
  • [28] Rethinking the unpretentious U-net for medical ultrasound image segmentation
    Chen, Gongping
    Li, Lei
    Zhang, Jianxun
    Dai, Yu
    PATTERN RECOGNITION, 2023, 142
  • [29] Design of Superpiexl U-Net Network for Medical Image Segmentation
    Wang H.
    Liu H.
    Guo Q.
    Deng K.
    Zhang C.
    Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2019, 31 (06): : 1007 - 1017
  • [30] Medical Ultrasound Image Segmentation Using U-Net Architecture
    Shereena, V. B.
    Raju, G.
    ADVANCES IN COMPUTING AND DATA SCIENCES (ICACDS 2022), PT I, 2022, 1613 : 361 - 372