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

Nicotinamide N-Methyltransferase Epigenetically Activates Fibronectin 1 Through H3K9me3 Remodeling in Clear Cell Renal Cell Carcinoma.

MedComm·2026
Same author

High-fat diet promotes colorectal cancer via carnitine/acetylcarnitine-driven CPT1A metabolic reprogramming and the intervention of β-hydroxybutyrate.

Oncogene·2026
Same author

Effect comparison between a new hypofractionated radiotherapy regimen and conventional moderately hypofractionated regimen for localized prostate cancer.

Radiation oncology (London, England)·2026
Same author

DB-2B, a Novel and Selective STAT3 Inhibitor Inhibits Colorectal Cancer Progression In Vitro and In Vivo.

Biomolecules·2026
Same author

SDPT: Synchronous Dual Prompt Tuning for Visual-Language Pre-trained Models.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

UniPET: A universal network for high-quality PET image denoising across varied dose reduction factors.

Medical image analysis·2026

Related Experiment Video

Updated: Jul 30, 2025

Exploiting Live Imaging to Track Nuclei During Myoblast Differentiation and Fusion
09:03

Exploiting Live Imaging to Track Nuclei During Myoblast Differentiation and Fusion

Published on: April 13, 2019

8.2K

Cyclic Learning: Bridging Image-Level Labels and Nuclei Instance Segmentation.

Yang Zhou, Yongjian Wu, Zihua Wang

    IEEE Transactions on Medical Imaging
    |May 12, 2023
    PubMed
    Summary

    This study introduces cyclic learning, a novel image-level weakly supervised method for nuclei instance segmentation in histopathology images. It significantly reduces annotation burden, outperforming existing methods and nearing fully-supervised performance.

    More Related Videos

    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
    Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy
    08:49

    Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy

    Published on: August 1, 2022

    3.6K

    Related Experiment Videos

    Last Updated: Jul 30, 2025

    Exploiting Live Imaging to Track Nuclei During Myoblast Differentiation and Fusion
    09:03

    Exploiting Live Imaging to Track Nuclei During Myoblast Differentiation and Fusion

    Published on: April 13, 2019

    8.2K
    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
    Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy
    08:49

    Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy

    Published on: August 1, 2022

    3.6K

    Area of Science:

    • Digital Pathology
    • Computational Biology
    • Medical Image Analysis

    Background:

    • Nuclei instance segmentation in histopathology is crucial for disease analysis but requires laborious pixel-wise annotations.
    • Existing weakly supervised methods often need more detailed annotations than image-level labels, limiting their applicability.
    • Image-level labels lack precise location information, posing challenges for accurate nuclei segmentation, leading to omissions or overlaps.

    Purpose of the Study:

    • To develop a labor-saving, image-level weakly supervised method for nuclei instance segmentation.
    • To overcome the limitations of inadequate location information in image-level labels for this task.
    • To improve the efficiency and accuracy of nuclei instance segmentation in histopathology images.

    Main Methods:

    • Propose a novel 'cyclic learning' method utilizing multi-task learning (MTL).
    • Employ a front-end interpretable deep learning classifier to generate high-confidence pseudo masks from image-level labels.
    • Utilize a back-end semi-supervised instance segmentation architecture supervised by these pseudo masks.
    • Implement knowledge sharing between the front-end and back-end components for enhanced information extraction.

    Main Results:

    • The proposed cyclic learning method effectively extracts information from image-level labels.
    • Demonstrated good generality across three different datasets.
    • Outperformed other image-level weakly supervised methods for nuclei instance segmentation.
    • Achieved performance comparable to fully-supervised methods.

    Conclusions:

    • Cyclic learning offers a highly efficient and effective solution for nuclei instance segmentation using only image-level labels.
    • The method significantly alleviates the annotation burden in digital pathology.
    • It represents a promising advancement for automated disease analysis through histopathology image interpretation.