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

GDF11 Regulates Hypoxia-induced Pulmonary Endothelial Cell Pyroptosis Through SOX2/NLRP3 Axis.

European journal of pharmacology·2026
Same author

The safety and efficacy of human umbilical cord mesenchymal stem cell for acute respiratory distress syndrome: an open-label and multicenter phase 1 clinical trial.

Frontiers in immunology·2026
Same author

SMC4 is a hypoxia-responsive driver of pulmonary arterial hypertension through an HIF-1α-HDAC6-p21 regulatory axis.

Respiratory research·2026
Same author

A Dual-branch Network with Cross-scale Feature Interaction and Alignment for Weakly Supervised Whole Slide Image Analysis.

IEEE journal of biomedical and health informatics·2026
Same author

Inhibition of the QPCT-PDIA4 axis rescues ΔF508 and N1303K CFTR in cystic fibrosis.

Nature communications·2026
Same author

Anionic or Mixed-Charge Copolypeptides with Potent Antibiofilm Activities.

Biomacromolecules·2026

Related Experiment Video

Updated: Jun 29, 2025

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

6.9K

MSMTSeg: Multi-Stained Multi-Tissue Segmentation of Kidney Histology Images via Generative Self-Supervised

Xueyu Liu, Rui Wang, Yexin Lai

    IEEE Journal of Biomedical and Health Informatics
    |March 25, 2024
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces MSMTSeg, a new AI framework for segmenting kidney tissues in pathology images. It significantly improves accuracy with minimal data, aiding pathologists in diagnosing chronic kidney disease.

    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

    395
    Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
    12:06

    Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

    Published on: March 3, 2023

    4.0K

    Related Experiment Videos

    Last Updated: Jun 29, 2025

    Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
    09:16

    Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

    Published on: June 18, 2020

    6.9K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    395
    Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
    12:06

    Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

    Published on: March 3, 2023

    4.0K

    Area of Science:

    • Digital Pathology
    • Artificial Intelligence in Medicine
    • Computational Biology

    Background:

    • Chronic kidney disease diagnosis relies on manual assessment of multi-stained tissue structures, which is time-consuming.
    • Existing AI segmentation methods require extensive manual annotation and struggle with multi-stain variations.

    Purpose of the Study:

    • To develop an automated segmentation framework for multi-stained renal histology.
    • To address the limitations of manual annotation and single-stain domain focus in current AI methods.

    Main Methods:

    • Introduced MSMTSeg, a generative self-supervised meta-learning framework.
    • Incorporated multi-stain transform models for style translation.
    • Utilized self-supervision and meta-learning for domain-invariant feature representation.

    Main Results:

    • Achieved superior segmentation performance (mDSC 0.836, mIoU 0.718) for multi-stained tissues with minimal annotation (one sample per stain).
    • Demonstrated robustness across different stains and tissues.
    • Outperformed existing advanced segmentation, few-shot, and domain adaptation methods.

    Conclusions:

    • MSMTSeg offers a feasible and cost-effective solution for multi-stained renal histology segmentation.
    • The few-shot, cross-domain technology assists pathologists in clinical practice.
    • Reduces the burden of manual annotation in digital pathology workflows.