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

A smartphone-based centrifugal mHealth platform implementing hollow daisy-shaped quick response chip for hematocrit measurement.

Talanta·2023
Same author

An accurate prediction of the origin for bone metastatic cancer using deep learning on digital pathological images.

EBioMedicine·2022
Same author

Unsupervised domain adaptive tumor region recognition for Ki67 automated assisted quantification.

International journal of computer assisted radiology and surgery·2022
Same author

Using Sparse Patch Annotation for Tumor Segmentation in Histopathological Images.

Sensors (Basel, Switzerland)·2022
Same author

[Portable Pulse Detection System Based on IoT].

Zhongguo yi liao qi xie za zhi = Chinese journal of medical instrumentation·2021
Same author

Wnt5a promotes renal tubular inflammation in diabetic nephropathy by binding to CD146 through noncanonical Wnt signaling.

Cell death & disease·2021

Related Experiment Video

Updated: Aug 17, 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

2.9K

Expression site agnostic histopathology image segmentation framework by self supervised domain adaption.

Qiming He1, Ling He1, Hufei Duan1

  • 1Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School, Shenzhen 518055, China.

Computers in Biology and Medicine
|December 14, 2022
PubMed
Summary

This study introduces ESASeg, a novel framework for segmenting immunohistochemical (IHC) histopathology images across different antigen expression sites. ESASeg achieves high performance by leveraging H&E images and domain adaptation techniques.

Keywords:
Domain adaptionHistopathology imagesImmunohistochemicalSelf supervisionSemantic segmentationTumor

More Related Videos

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.5K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.6K

Related Experiment Videos

Last Updated: Aug 17, 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

2.9K
Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.5K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.6K

Area of Science:

  • Computational pathology
  • Digital histopathology
  • Medical image analysis

Background:

  • Immunohistochemical (IHC) image segmentation is challenging due to varying antigen expression sites and visual differences.
  • Hematoxylin and eosin (H&E) images offer broad tissue structure information that can aid IHC segmentation.

Purpose of the Study:

  • To develop an expression site agnostic domain adaptive histopathology image semantic segmentation framework (ESASeg).
  • To improve segmentation performance on IHC images regardless of antigen location.

Main Methods:

  • Proposed ESASeg framework utilizing multi-level feature alignment for expression site invariance.
  • Incorporated self-supervision with pseudo-labeling to enhance domain adaptation and semantic perception.
  • Constructed a dataset with three IHC types (Her2, Ki67, GPC3) across breast and liver cancers.

Main Results:

  • ESASeg demonstrated superior performance in tumor region segmentation across all evaluated metrics.
  • Each module within ESASeg contributed significantly to the overall performance improvements.
  • Experiments confirmed the framework's effectiveness on IHC images with diverse staining patterns.

Conclusions:

  • ESASeg offers an efficient and novel solution for expression site agnostic IHC image segmentation tasks.
  • The domain adaptation and self-supervision modules enhance feature extraction and adaptation without requiring labeled data.
  • The framework facilitates joint analysis of IHC images from different expression sites.