A STRUCTURE-FUSION NETWORK FOR MEDICAL IMAGE CLASSIFICATION

被引:0
作者
Wu, Fuli [1 ]
Yuan, Wei [1 ]
Hao, Pengyi [1 ]
Tian, Shuyuan [2 ,3 ]
机构
[1] Zhejiang Univ Technol, Hangzhou, Peoples R China
[2] Zhejiang Acad Tradit Chinese Med, Hangzhou, Peoples R China
[3] Tongde Hosp Zhejiang Prov, Dept Ultrasound, Hangzhou, Peoples R China
来源
2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP | 2023年
关键词
Medical; Transformer; Classification;
D O I
10.1109/ICIP49359.2023.10222263
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The Convolutional Neural Networks and Transformer cannot provide satisfactory performance in medical image classification due to insufficient data, high resolution, and a lot of redundancy. To achieve better performance, this paper proposes a structure-fusion network that combines the architecture of convolution and transformer. To reduce the computational overhead incurred by the transformer structure, we optimize it by aggregating adjacent features. We further modify the Multilayer Perceptron using convolution to increase the network capacity. The network is verified on the grading of the Anterior Cruciate Ligament from knee MRI and the screening of pneumonia and COVID-19 from Chest X-ray. Compared with current advanced methods, the proposed network not only reduces FLOPs but also achieves improvement on AUC and F1score.
引用
收藏
页码:1540 / 1544
页数:5
相关论文
共 50 条
  • [41] An efficient Algorithm for medical image classification using Deep Convolutional Network: Case of Cancer Pathology
    Dahdouh, Yousra
    Anouar Boudhir, Abdelhakim
    Ben Ahmed, Mohamed
    3RD INTERNATIONAL CONFERENCE ON NETWORKING, INFORMATION SYSTEM & SECURITY (NISS'20), 2020,
  • [42] Network Pruning for OCT Image Classification
    Yang, Bing
    Zhang, Yi
    Cheng, Jun
    Zhang, Jin
    Mou, Lei
    Hao, Huaying
    Zhao, Yitian
    Liu, Jiang
    OPHTHALMIC MEDICAL IMAGE ANALYSIS, 2019, 11855 : 121 - 129
  • [44] Two-branch global spatial-spectral fusion transformer network for hyperspectral image classification
    Xie, Erxin
    Chen, Na
    Zhang, Genwei
    Peng, Jiangtao
    Sun, Weiwei
    PHOTOGRAMMETRIC RECORD, 2024, 39 (186) : 392 - 411
  • [45] Hyperspectral image classification based on a novel Lush multi-layer feature fusion bias network
    Shi, Cuiping
    Chen, Jiaxiang
    Wang, Liguo
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 247
  • [46] Evaluating the potential of pyramid-based fusion coupled with convolutional neural network for satellite image classification
    Achala Shakya
    Mantosh Biswas
    Mahesh Pal
    Arabian Journal of Geosciences, 2022, 15 (8)
  • [47] RITFusion: Reinforced Interactive Transformer Network for Infrared and Visible Image Fusion
    Li, Xiaoling
    Li, Yanfeng
    Chen, Houjin
    Peng, Yahui
    Chen, Luyifu
    Wang, Minjun
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2024, 73 : 1 - 16
  • [48] A Dual Cross Attention Transformer Network for Infrared and Visible Image Fusion
    Zhou, Zhuozhi
    Lan, Jinhui
    2024 7TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND BIG DATA, ICAIBD 2024, 2024, : 494 - 499
  • [49] iU-Net: a hybrid structured network with a novel feature fusion approach for medical image segmentation
    Yun Jiang
    Jinkun Dong
    Tongtong Cheng
    Yuan Zhang
    Xin Lin
    Jing Liang
    BioData Mining, 16
  • [50] iU-Net: a hybrid structured network with a novel feature fusion approach for medical image segmentation
    Jiang, Yun
    Dong, Jinkun
    Cheng, Tongtong
    Zhang, Yuan
    Lin, Xin
    Liang, Jing
    BIODATA MINING, 2023, 16 (01)