Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Lagged crop responses to drought across China: contrasting multivariate environmental pathways in rainfed and irrigated systems.

Journal of environmental management·2026
Same author

Deep Cleaning Device as a Treatment Is Effective for Blepharitis and Significantly Reduces Bacterial Load.

Journal of ophthalmology·2026
Same author

Positive serial dependences of social characteristics perception in group context are similar but different.

Perception·2026
Same author

Correction: GALNT5 uaRNA promotes gastric cancer progression through its interaction with HSP90.

Oncogene·2025
Same author

A foundation model for rock thin-section images analysis.

Communications engineering·2025
Same author

The role of substance P in Th17/Treg imbalance and ocular surface damage in chronic allergic conjunctivitis.

Journal of translational medicine·2025

相关实验视频

Updated: May 1, 2026

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.2K

DIPathMamba:一个域增量弱监督状态空间模型用于病理图像细分的病理图像.

Jiansong Fan1, Qi Sun2, Yicheng Di1

  • 1School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, 214122, China.

Medical image analysis
|April 10, 2025
PubMed
概括

这项研究引入了一种新的域增量弱监督状态空间模型 (DIPathMamba) 用于病理图像细分. 它有效地使用仅图像级标签对图像进行细分,同时学习新领域并保留先前的知识.

关键词:
领域-增量学习.病理学图像细分 病理学图像细分国家空间模型监管能力较弱的监管机构

更多相关视频

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.8K
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

2.9K

相关实验视频

Last Updated: May 1, 2026

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.2K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.8K
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

2.9K

科学领域:

  • 数字病理学数字病理学
  • 医学图像分析 医学图像分析
  • 机器学习 机器学习

背景情况:

  • 准确的病理图像细分对于数字病理学至关重要.
  • 当前的方法在密集的注释和处理跨多个领域的多样化,大规模数据集方面扎.
  • 现有的模型往往无法在不降低性能的情况下适应新的数据领域.

研究的目的:

  • 为病理图像细分开发一种新的域增量弱监督状态空间模型 (DIPathMamba).
  • 仅使用图像级标签来实现细分,克服了对密集的像素级注释的需求.
  • 为了促进新的数据领域的动态学习,同时保持以前学习的领域的性能.

主要方法:

  • 设计了一个基于硬件意识状态空间模型的共享功能提取器.
  • 多实例多标签学习提取像素级特征,集成到一个对比的Mamba块 (CMB).
  • 一个域参数约束模型 (DPCM) 和协作增量深度监督损失 (CIDSL) 解决增量学习挑战并优化参数学习.

主要成果:

  • DIPathMamba模型将精细细节与全球背景集成在一起,以改善细分.
  • 与现有方法相比,它产生了更为区域一致的细分结果.
  • 在三个公共数据集上的实验结果表明,比最先进的方法更优越的性能.

结论:

  • 拟议的DIPathMamba有效地执行弱监督的病理图像细分.
  • 它解决了密集注释的局限性以及数字病理学中特定领域的数据挑战.
  • 该方法显示了在数字病理学工作流程中推进自动化分析的巨大潜力.