ARU-Net:基于残差注意力机制的胸腔积液图像分割模型
作者:
作者单位:

(1.河北医科大学第二医院数据中心 石家庄 050000;2.河北医科大学第二医院信息中心 石家庄 050000;3.河北医科大学第二医院神经外科 石家庄 050000;4.河北医科大学第二医院医学影像科 石家庄 050000;5.河北医科大学第二医院神经内科 石家庄050000)

作者简介:

杨靖祎,硕士,工程师;通信作者:底涛,刘晓云。

通讯作者:

中图分类号:

基金项目:

河北省医学重点科技研究计划(项目编号:20210030);河北医科大学临床医学创新研究团队项目(项目编号:2022LCTD-A7);河北省卫生健康委员会医学科学研究课题(项目编号:20221086)。


ARU-Net:A Pleural Effusion Imaging Segmentation Model Based on Residual Attention Mechanism
Author:
Affiliation:

(1.Data Center, The Second Hospital of Hebei Medical University, Shijiazhuang 050000, China;2.Information Center, The Second Hospital of Hebei Medical University, Shijiazhuang 050000, China;3.Department of Neurosurgery, The Second Hospital of Hebei Medical University, Shijiazhuang 050000, China;4.Department of Medical Imaging, The Second Hospital of Hebei Medical University, Shijiazhuang 050000, China;5.Department of Neurology, The Second Hospital of Hebei Medical University, Shijiazhuang 050000, China)

Fund Project:

  • 摘要
  • 图/表
  • 访问统计
  • 参考文献
  • 相似文献
  • 引证文献
  • 资源附件
  • 文章评论
    摘要:

    目的/意义 解决传统胸腔积液分割方法严重依赖先验知识、流程烦琐、耗时费力、性能不佳等问题,提高效率和准确率。方法/过程 根据胸部CT图像的积液特征,提出一种基于残差注意力机制的胸腔积液分割模型ARU-Net。以U-Net模型为主干网络,在编码和解码阶段引入残差注意力单元,有效获取图像上下文信息,提高对特征的利用率。结果/结论 在测试集上的DICE相似系数达到88.76%,与U-Net和ResU-Net相比在分割完整性和准确性方面具有显著优势,能够满足临床需求。

    Abstract:

    Purpose/Significance The traditional methods for segmenting pleural effusion heavily rely on prior knowledge, are cumbersome in process, time-consuming, and often exhibit poor performance. There is a need to enhance efficiency and accuracy in addressing these issues. Method/Process Based on the characteristics of pleural effusion in chest CT images, the paper proposes a pleural effusion segmentation model called ARU-Net, which is based on the residual attention mechanism. The ARU-Net model utilizes the U-Net architecture as its backbone network. It introduces residual attention units in both the encoding and decoding stages to effectively capture contextual information from the images, thereby improving the utilization of features. Result/Conclusion The DICE similarity coefficient on the test set reaches 88.76% for ARU-Net, and shows significant advantages in segmentation integrity and accuracy compared to U-Net and ResU-Net, which can meet clinical requirements.

    参考文献
    相似文献
    引证文献
引用本文

杨靖祎,陈隆鑫,杨建凯,等. ARU-Net:基于残差注意力机制的胸腔积液图像分割模型[J].医学信息学杂志,2024,45(4):85-90

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:2024-03-22
  • 录用日期:
  • 在线发布日期: 2024-05-11
  • 出版日期:

扫码关注

官方微信