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

UMRFormer-net: a three-dimensional U-shaped pancreas segmentation method based on a double-layer bridged transformer network

Fang, Kun; He, Baochun; Liu, Libo; Hu, Haoyu; Fang, Chihua; Huang, Xuguang*; Jia, Fucang*南方医科大学; 中国科学院; 1
QUANTITATIVE IMAGING IN MEDICINE AND SURGERY2023-3DOI: 10.21037/qims-22-544
6阅读
引用收藏
分享

摘要

Background: Methods based on the combination of transformer and convolutional neural networks (CNNs) have achieved impressive results in the field of medical image segmentation. However, most of the recently proposed combination segmentation approaches simply treat transformers as auxiliary modules which help to extract long-range information and encode global context into convolutional representations, and there is a lack of investigation on how to optimally combine self-attention with convolution. @@@ Methods: We designed a novel transformer block (MRFormer) that combines a multi-head self-attention layer and a residual depthwise convolutional block as the basic unit to deeply integrate both long-range and local spatial information. The MRFormer block was embedded between the encoder and decoder in U-Net at the last two layers. This framework (UMRFormer-Net) was applied to the segmentation of threedimensional (3D) pancreas, and its ability to effectively capture the characteristic contextual information of the pancreas and surrounding tissues was investigated. @@@ Results: Experimental results show that the proposed UMRFormer-Net achieved accuracy in pancreas segmentation that was comparable or superior to that of existing state-of-the-art 3D methods in both the Clinical Proteomic Tumor Analysis Consortium Pancreatic Ductal Adenocarcinoma (CPTAC-PDA) dataset and the public Medical Segmentation Decathlon dataset (self-division). UMRFormer-Net statistically significantly outperformed existing transformer-related methods and state-of-the-art 3D methods (P< 0.05, P<0.01, or P< 0.001), with a higher Dice coefficient ( 85.54% and 77.36%, respectively) or a lower 95% Hausdorff distance (4.05 and 8.34 mm, respectively). @@@ Conclusions: UMRFormer-Net can obtain more matched and accurate segmentation boundary and region information in pancreas segmentation, thus improving the accuracy of pancreas segmentation. The code is available at https://github.com/supersunshinefk/UMRFormer-Net.

学科与关键词

关键词
Pancreasimage segmentationtransformerdeep learningU-Net
相关
加载中…
  • MDHT-Net: Multi-scale Deformable U-Net with Cos-spatial and Channel Hybrid Transformer for pancreas segmentation
    Wang, HuiFang; Yang, DaWei; Zhu, Yu*; Liu, YaTong; Lin, JiaJunApplied Intelligence, 2024, 54(23): 12272-12292.
  • A 2.5D semantic segmentation of the pancreas using attention guided dual context embedded U-Net
    Li, Jingyuan; Liao, Guanqun*; Sun, Wenfang; Sun, Ji; Sheng, Tai; Zhu, Kaibin; von Deneen, Karen M.; Zhang, Yi*NEUROCOMPUTING, 2022, 480: 14-26.被引 10
  • MSAANet: Multi-scale Axial Attention Network for medical image segmentation
    Zeng, Hao; Shan, Xinxin; Feng, Yu; Wen, Ying*IEEE International Conference on Multimedia and Expo (ICME), Brisbane, AUSTRALIA, 2023-07-10 To 2023-07-14.
查看全部 →

发表信息

论文状态
公开发表
期刊
QUANTITATIVE IMAGING IN MEDICINE AND SURGERY
发表日期
2023-03
卷期
第 13 卷, 第 3 期
页码
1619-1630
DOI
10.21037/qims-22-544
成果收录
SCIE
资助标注
NSFC Grant Program [12026602, 62172401]; Key-Area Research and Development Program of Guangdong Province [2020B010165004]; National Key R&D Program, China [2019YFC0118100]; Natural Science Foundation of Guangdong Province [2022A1515010439]; Shenzhen Key Basic Science Program [JCYJ20180507182437217]; Shenzhen Key Laboratory Program [ZDSYS201707271637577]

作者

  • F

    Fang, Kun (第一作者)

    chinese acad sci

  • H

    He, Baochun

    chinese acad sci

查看全部 7 位作者收起作者
  • L

    Liu, Libo

    chinese acad sci

  • H

    Hu, Haoyu

    1 · southern med univ

  • F

    Fang, Chihua

    1 · southern med univ

  • H

    Huang, Xuguang (通讯)

  • J

    Jia, Fucang (通讯)

    chinese acad sci

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