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

Self-Supervised Representation Distribution Learning for Reliable Data Augmentation in Histopathology WSI Classification

Tang, Kunming; Jiang, Zhiguo; Wu, Kun; Shi, Jun; Xie, Fengying; Wang, Wei; Wu, Haibo*; Zheng, Yushan*北京航空航天大学; 合肥工业大学
IEEE Transactions on Medical Imaging2025-1DOI: 10.1109/TMI.2024.3447672
13阅读
引用收藏
分享

摘要

Multiple instance learning (MIL) based whole slide image (WSI) classification is often carried out on the representations of patches extracted from WSI with a pre-trained patch encoder. The performance of classification relies on both patch-level representation learning and MIL classifier training. Most MIL methods utilize a frozen model pre-trained on ImageNet or a model trained with self-supervised learning on histopathology image dataset to extract patch image representations and then fix these representations in the training of the MIL classifiers for efficiency consideration. However, the invariance of representations cannot meet the diversity requirement for training a robust MIL classifier, which has significantly limited the performance of the WSI classification. In this paper, we propose a Self-Supervised Representation Distribution Learning framework (SSRDL) for patch-level representation learning with an online representation sampling strategy (ORS) for both patch feature extraction and WSI-level data augmentation. The proposed method was evaluated on three datasets under three MIL frameworks. The experimental results have demonstrated that the proposed method achieves the best performance in histopathology image representation learning and data augmentation and outperforms state-of-the-art methods under different WSI classification frameworks. The code is available at https://github.com/lazytkm/SSRDL.

学科与关键词

关键词
Data augmentationTrainingRepresentation learningData modelsHistopathologyFeature extractionSupervised learningSelf-supervised representation learningdata augmentationWSI classification
相关
加载中…
  • Position-Aware Masked Autoencoder for Histopathology WSI Representation Learning
    Wu, Kun; Zheng, Yushan*; Shi, Jun*; Xie, Fengying; Jiang, Zhiguo26th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Vancouver, CANADA, 2023-10-08 To 2023-10-12.
  • Lesion-Aware Contrastive Representation Learning for Histopathology Whole Slide Images Analysis
    Li, Jun; Zheng, Yushan*; Wu, Kun; Shi, Jun*; Xie, Fengying; Jiang, Zhiguo25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Singapore, SINGAPORE, 2022-09-18 To 2022-09-22.被引 3
  • Unsupervised mutual transformer learning for multi-gigapixel Whole Slide Image classification
    Javed, Sajid*; Mahmood, Arif; Qaiser, Talha; Werghi, Naoufel; Rajpoot, NasirMedical Image Analysis, 2024, 96: 103203.
查看全部 →

发表信息

论文状态
公开发表
期刊
IEEE Transactions on Medical Imaging
发表日期
2025-01
卷期
第 44 卷, 第 1 期
页码
462-474
DOI
10.1109/TMI.2024.3447672
语言
ENGLISH
成果收录
SCIE
资助标注
Beijing Natural Science Foundation [7242270]; National Natural Science Foundation of China [62171007, 61901018, 61906058]; Fundamental Research Funds for the Central Universities of China [YWF-23-Q-1075, JZ2022HGTB0285]; Emergency Key Program of Guangzhou Laboratory [EKPG21-32]; Joint Fund for Medical Artificial Intelligence [MAI2023C014]; National Key Research and Development Program of China [2021YFF1201004]

作者

  • T

    Tang, Kunming (第一作者)

    beihang univ

  • J

    Jiang, Zhiguo

    beihang univ

查看全部 8 位作者收起作者
  • W

    Wu, Kun

    beihang univ

  • S

    Shi, Jun

    hefei univ technol

  • X

    Xie, Fengying

    beihang univ

  • W

    Wang, Wei

    univ sci & technol china

  • W

    Wu, Haibo (通讯)

    univ sci & technol china

  • Z

    Zheng, Yushan (通讯)

    beihang univ

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