ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

X-Net: a dual encoding-decoding method in medical image segmentation

Li, Yuanyuan; Wang, Ziyu; Yin, Li; Zhu, Zhiqin*; Qi, Guanqiu; Liu, Yu重庆大学
VISUAL COMPUTER2023-6DOI: 10.1007/s00371-021-02328-7
55被引25阅读
引用收藏
分享

摘要

Medical image segmentation has the priori guiding significance for clinical diagnosis and treatment. In the past ten years, a large number of experimental facts have proved the great success of deep convolutional neural networks in various medical image segmentation tasks. However, the convolutional networks seem to focus too much on the local image details, while ignoring the long-range dependence. The Transformer structure can encode long-range dependencies in image and learn high-dimensional image information through the self-attention mechanism. But this structure currently depends on the database scale to give full play to its excellent performance, which limits its application in medical images with limited database size. In this paper, the characteristics of CNNs and Transformer are integrated to propose a dual encoding-decoding structure of the X-shaped network (X-Net). It can serve as a good alternative to the traditional pure convolutional medical image segmentation network. In the encoding phase, the local and global features are simultaneously extracted by two types of encoders, convolutional downsampling, and Transformer and then merged through jump connection. In the decoding phase, a variational auto-encoder branch is added to reconstruct the input image itself in order to weaken the impact of insufficient data. Comparative experiments on three medical image datasets show that X-Net can realize the organic combination of Transformer and CNNs.

学科与关键词

关键词
Medical image segmentationTransformerVariational auto-encoderDual encoding-decoding
相关
加载中…

文献加载失败,请重试

重试

发表信息

论文状态
公开发表
期刊
VISUAL COMPUTER
发表日期
2023-06
卷期
第 39 卷, 第 6 期
页码
2223-2233
DOI
10.1007/s00371-021-02328-7
语言
ENGLISH
成果收录
ISTP · SCIE
资助标注
National Natural Science Foundation of China [61803061, 61906026, 6217021768]; Innovation research group of universities in Chongqing; Innovative project of shapingba district, Chongqing [Jcd202135]; Chongqing Kewei Joint Medical Research Project [2020GDRC019, 2021MSXM337]; Chongqing Natural Science Foundation [cstc2020jcyjmsxmX0577, cstc2020jcyj-msxmX0634]; "Chengdu-Chongqing Economic Circle" innovation funding of Chongqing Municipal Education Commission [KJCXZD2020028]; Special key project of Chongqing technology innovation and application development [cstc2019jscx-zdztzx0068]; China Postdoctoral Science Foundation [2020M670111ZX]; Special Fund for Young and Middle-aged Medical Top Talents of Chongqing [ZQNYXGDRCGZS2019005]

作者

  • L

    Li, Yuanyuan (第一作者)

  • W

    Wang, Ziyu

    chongqing univ posts & telecommun

查看全部 6 位作者收起作者
  • Y

    Yin, Li

  • Z

    Zhu, Zhiqin (通讯)

    chongqing univ posts & telecommun

  • Q

    Qi, Guanqiu

  • L

    Liu, Yu

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417