Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Serotype-specific neutralizing activity and clinical outcomes associated with intravenous immunoglobulin in pediatric HAdV-3 and HAdV-7 infections.

Scientific reports·2026
Same author

Efficacy and safety of remimazolam besylate plus propofol for sedation in endoscopic retrograde cholangiopancreatography: a randomized controlled study.

Frontiers in medicine·2026
Same author

Latent profiles of death coping competence among nursing interns and associations with death attitudes, death exposure, and death education; a cross-sectional survey.

International journal of nursing studies advances·2026
Same author

The Association Between Inclusive Leadership and Job Performance in Nurses: Exploring the Mediation Roles of Grit and Work Engagement Based on a Cross-Sectional Study.

Journal of nursing management·2026
Same author

Road networks facilitate invasive dominance by squeezing native mesopredators into niche margins.

Journal of environmental management·2026
Same author

Sedentary behavior type matters: compositional analysis of 24-hour movement behaviors and cognitive function in older adults.

Journal of activity, sedentary and sleep behaviors·2026

Related Experiment Video

Updated: Aug 6, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

Weakly supervised histopathology image segmentation with self-attention.

Kailu Li1, Ziniu Qian1, Yingnan Han1

  • 1School of Biological Science and Medical Engineering, State Key Laboratory of Software Development Environment, Key Laboratory of Biomechanics, Mechanobiology of Ministry of Education and Beijing Advanced Innovation Centre for Biomedical Engineering, Beihang University, Beijing 100191, China.

Medical Image Analysis
|March 18, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces SA-MIL, a novel weakly supervised method for pixel-level histopathology image segmentation. By incorporating self-attention and deep supervision into multiple instance learning (MIL), it improves segmentation accuracy and demonstrates strong generalization across datasets.

Keywords:
Histopathology imageMultiple instance learningSegmentationSelf-attentionWeakly supervised learning

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

471
Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
08:40

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

12.9K

Related Experiment Videos

Last Updated: Aug 6, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

471
Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
08:40

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

12.9K

Area of Science:

  • Digital Pathology
  • Computer Vision
  • Medical Image Analysis

Background:

  • Accurate pixel-level segmentation is crucial for digital pathology workflows.
  • Weakly supervised methods reduce manual annotation effort in histopathology.
  • Multiple Instance Learning (MIL) shows promise but lacks instance relationship modeling.

Purpose of the Study:

  • To develop a novel weakly supervised method for pixel-level histopathology image segmentation.
  • To address the limitation of independent instances in traditional MIL frameworks.
  • To enhance segmentation performance by capturing global instance correlations.

Main Methods:

  • Proposed SA-MIL method treating pixels as instances within a MIL framework.
  • Integrated a self-attention mechanism to capture global correlations among instances.
  • Utilized deep supervision to maximize information from limited annotations.

Main Results:

  • Achieved state-of-the-art results compared to existing weakly supervised methods.
  • Demonstrated strong generalization ability on both tissue and cell histopathology datasets.
  • Successfully aggregated global contextual information, overcoming MIL's instance independence limitation.

Conclusions:

  • SA-MIL effectively improves pixel-level segmentation in histopathology images.
  • The method shows significant potential for automated quantitative analysis in digital pathology.
  • SA-MIL offers a promising approach for various medical image analysis applications.