您当前的位置:
首页 >
文章列表页 >
Multimodal medical image fusion method based on structural functional cross neural network
Information Sciences | 更新时间:2024-02-01
    • Multimodal medical image fusion method based on structural functional cross neural network

    • An innovative study has achieved significant results in addressing the issues of blurry texture details and low contrast in multimodal medical image fusion. The research team has proposed a multimodal medical image fusion method using a structural functional cross neural network, which has brought new breakthroughs to the field of medical image analysis. This method first designs a structural functional cross functional neural network model, which effectively extracts the structural and functional information of medical images, realizes the interaction between the two types of information, and can accurately capture the texture details of images. Secondly, the research team has developed a novel attention mechanism that significantly improves the contrast and contour clarity of fused images by dynamically adjusting the weights of structural and functional information. Finally, they also designed a decomposition process from the fused image to the source image, ensuring that the fused image contains richer detail information. Compared with the seven high-level methods proposed in recent years, this method has achieved an average improvement of 22.87%, 19.64%, 23.02%, 12.70%, 6.79%, and 30.35% in objective evaluation indicators such as AG, EN, SF, MI, QAB/F, and CC. This achievement not only demonstrates the advantages of this method in texture details and contrast, but also proves its superiority in subjective visual and objective indicators. The success of this research has brought new perspectives and solutions to the field of medical image analysis, which is expected to provide doctors with more accurate and comprehensive diagnostic basis, and help the medical field achieve more accurate diagnosis and treatment.
    • Optics and Precision Engineering   Vol. 32, Issue 2, Pages: 252-267(2024)
    • DOI:10.37188/OPE.20243202.0252    

      CLC: TP391
    • Received:05 May 2023

      Revised:13 July 2023

      Published:25 January 2024

    移动端阅览

  • DI Jing,GUO Wenqing,REN Li,et al.Multimodal medical image fusion method based on structural functional cross neural network[J].Optics and Precision Engineering,2024,32(02):252-267. DOI: 10.37188/OPE.20243202.0252.

  •  
  •  

0

Views

697

下载量

1

CSCD

Alert me when the article has been cited
提交
Tools
Download
Export Citation
Share
Add to favorites
Add to my album

Related Articles

Underwater image enhancement based on multi-branch residual attention network
End-to-end recognition of nighttime wildlife based on semi-supervised learning
Real-time deblurring of wideband small target based on attention mechanism
Integrating global information and dual-domain attention mechanism for optical remote sensing aircraft target detection
3D point cloud classification and segmentation based on dual attention and weighted dynamic graph convolution

Related Author

CHENG Zhuming
LI Jiaxuan
HUANG San'ao
HAN Lichao
WANG Peizhen
LU Han
CUI Bolun
WAN Huayang

Related Institution

School of Electrical and Information Engineering, Anhui University of Technology, Maanshan
School of Mechatronic Engineering and Automation,Shanghai University
Beijing Institute of Space Mechanics & Electricity
Key Laboratory of Space Optoelectronic Detection and Perception, Nanjing University of Aeronautics and Astronautics
College of Astronautics, Nanjing University of Aeronautics and Astronautics
0