Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Root cause analysis of the challenges to sustain effectiveness of clinical pharmacist-driven antimicrobial stewardship in a Chinese Tertiary Hospital.

Frontiers in public health·2026

Same author

TriPDCL: A Tri-Pathway Prototype-Driven Contrastive Learning Framework for Cross-Modality Single-Cell Integration.

Journal of chemical information and modeling·2026

Same author

Bridging the Semantic Gap: Synergistic Feature Fusion and Multi-Scale Adaptation for Medical Image Segmentation.

IEEE journal of biomedical and health informatics·2026

Same author

Resistant Starch-Capric Acid Effectively Improves Lipopolysaccharide-Induced Depressive Behavior by Protecting the Intestinal Microbiota Barrier and Inhibiting Inflammatory Responses.

Journal of food science·2026

Same author

MFS-Unet: A Multi-Path Vision Mamba Network for Precise Thyroid Nodule Segmentation.

IET systems biology·2026

Same author

MFR-UNet: A Medical Image Segmentation Network With Fused Multi-Scale Feature Refinement.

IET systems biology·2025

Search research articles

相关实验视频

Updated: May 1, 2026

Analysis of Tubular Membrane Networks in Cardiac Myocytes from Atria and Ventricles

Analysis of Tubular Membrane Networks in Cardiac Myocytes from Atria and Ventricles

Published on: October 15, 2014

TSSP-UNet:一个双阶段的弱监督的病态图像细分与点注释.

Shaoqiang Wang¹, Guiling Shi¹, Yuchen Wang¹

¹Qingdao University of Technology, Qingdao, China.

IET systems biology

|March 3, 2026

概括

此摘要是机器生成的。

本研究介绍了TSSP-UNet,这是一种新的两阶段弱监督细分方法. 它有效地提高了使用伪标签和精细学习的细胞核细分精度,优于基线方法.

关键词:

图像分割图像细分图像细分机器学习是机器学习.神经网络的神经网络的神经网络

更多相关视频

Evaporation-reducing Culture Condition Increases the Reproducibility of Multicellular Spheroid Formation in Microtiter Plates

Evaporation-reducing Culture Condition Increases the Reproducibility of Multicellular Spheroid Formation in Microtiter Plates

Published on: March 7, 2017

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

相关实验视频

Last Updated: May 1, 2026

Analysis of Tubular Membrane Networks in Cardiac Myocytes from Atria and Ventricles

Analysis of Tubular Membrane Networks in Cardiac Myocytes from Atria and Ventricles

Published on: October 15, 2014

Evaporation-reducing Culture Condition Increases the Reproducibility of Multicellular Spheroid Formation in Microtiter Plates

Evaporation-reducing Culture Condition Increases the Reproducibility of Multicellular Spheroid Formation in Microtiter Plates

Published on: March 7, 2017

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

科学领域:

医疗图像分析医学图像分析
计算机视觉计算机视觉计算机视觉
机器学习是机器学习.

背景情况:

深度卷积神经网络擅长图像细分,但难以处理复杂的实例和注释成本.
弱监督学习通过使用不太精确的注释或算法衍生的监督提供了一个解决方案.

研究的目的:

为复杂的图像细分任务开发一种有效的两阶段弱监督细分方法.
为了应对医学成像中高精度数据注释的挑战.

主要方法:

提出了TSSP-UNet,这是一个两阶段的细分网络,包含伪标签上的约束和注意力机制.
利用边界和超像素信息,以及通过伪标签和二进制面具的轮增强.
采用特征聚合网络进行前景细分以及用于伪标签改进的自信学习算法.

主要成果:

TSSP-UNet在弱监督的细胞核细分方面表现出强的表现.
与基线方法相比,该方法在MoNuSeg和TNBC数据集上显示出显著的改进.

结论:

拟议的TSSP-UNet有效地处理复杂的实例,并减少对图像分割的注释依赖.
这种方法为在具有挑战性的数据集中准确的细胞核细分提供了有希望的解决方案.