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

Semi-supervised medical image segmentation via uncertainty rectified pyramid consistency

Luo, Xiangde; Wang, Guotai*; Liao, Wenjun; Chen, Jieneng; Song, Tao; Chen, Yinan; Zhang, Shichuan; Metaxas, Dimitris N.; Zhang, Shaoting电子科技大学; 南方医科大学; 四川大学; 同济大学
Medical Image Analysis2022-8DOI: 10.1016/j.media.2022.102517
59被引22阅读
引用收藏
分享

摘要

Despite that Convolutional Neural Networks (CNNs) have achieved promising performance in many medical image segmentation tasks, they rely on a large set of labeled images for training, which is expensive and time-consuming to acquire. Semi-supervised learning has shown the potential to alleviate this challenge by learning from a large set of unlabeled images and limited labeled samples. In this work, we present a simple yet efficient consistency regularization approach for semi-supervised medical image segmentation, called Uncertainty Rectified Pyramid Consistency (URPC). Inspired by the pyramid feature network, we chose a pyramid-prediction network that obtains a set of segmentation predictions at different scales. For semi-supervised learning, URPC learns from unlabeled data by minimizing the discrepancy between each of the pyramid predictions and their average. We further present multi-scale uncertainty rectification to boost the pyramid consistency regularization, where the rectification seeks to temper the consistency loss at outlier pixels that may have substantially different predictions than the average, potentially due to upsampling errors or lack of enough labeled data. Experiments on two public datasets and an in-house clinical dataset showed that: 1) URPC can achieve large performance improvement by utilizing unlabeled data and 2) Compared with five existing semi-supervised methods, URPC achieved better or comparable results with a simpler pipeline. Furthermore, we build a semi-supervised medical image segmentation codebase to boost research on this topic: https://github.com/HiLab- git/SSL4MIS.

学科与关键词

关键词
Semi-supervised learningUncertainty rectifyingPyramid consistencyImage segmentation
相关
加载中…
  • Prototype Consistency Learning for Medical Image Segmentation by Cross Pseudo Supervision
    Xie, Lu; Li, Weigang*; Wang, Yongqiang; Zhao, YuntaoCognitive Computation, 2024, 16(1): 215-228.
  • Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation
    Bai, Yunhao; Chen, Duowen; Li, Qingli; Shen, Wei; Wang, Yan*IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, CANADA, 2023-06-17 To 2023-06-24.被引 6
  • Deep Mutual Distillation for Semi-supervised Medical Image Segmentation
    Xie, Yushan; Yin, Yuejia; Li, Qingli; Wang, Yan*26th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Vancouver, CANADA, 2023-10-08 To 2023-10-12.被引 1
查看全部 →

发表信息

论文状态
公开发表
期刊
Medical Image Analysis
发表日期
2022-08
卷期
第 80 卷
页码
102517
DOI
10.1016/j.media.2022.102517
语言
ENGLISH
期刊等级
1区
成果收录
SCIE
资助标注
National Natural Science Foundations of China [81771921, 61901084]; key research and development project of Sichuan province, China [2020YFG0084]

作者

  • L

    Luo, Xiangde (第一作者)

    univ elect sci & technol china

  • W

    Wang, Guotai (通讯)

    univ elect sci & technol china

查看全部 9 位作者收起作者
  • L

    Liao, Wenjun

    southern med univ

  • C

    Chen, Jieneng

    tongji univ

  • S

    Song, Tao

  • C

    Chen, Yinan

    sichuan univ

  • Z

    Zhang, Shichuan

    sichuan canc hosp & inst · univ elect sci & technol china

  • M

    Metaxas, Dimitris N.

    rutgers

  • Z

    Zhang, Shaoting

    univ elect sci & technol china

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