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 Experiment Video

Updated: Jul 12, 2026

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Segment Together: A Versatile Paradigm for Semi-Supervised Medical Image Segmentation.

Qingjie Zeng, Yutong Xie, Zilin Lu

    IEEE Transactions on Medical Imaging
    |April 1, 2025
    PubMed
    Summary
    This summary is machine-generated.

    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

    When Octahedra Learn to Be Prisms: Unlocking a Record Deep‑UV NLO Crystal.

    Angewandte Chemie (International ed. in English)·2026
    Same author

    Ultrafast damage dynamics and ablation mechanism of a BaGa<sub>4</sub>Se<sub>7</sub> crystal induced by femtosecond laser irradiation.

    Optics express·2026
    Same author

    LiMn(IO<sub>3</sub>)<sub>3</sub>: A Noncentrosymmetric Iodate Synthesized by Polyhedral Volume Ratio Modulation.

    Inorganic chemistry·2026
    Same author

    SegRap2025: A benchmark of gross tumor volume and lymph node clinical target volume Segmentation for Radiotherapy Planning of nasopharyngeal carcinoma.

    Medical image analysis·2026
    Same author

    Effect of the cation-to-silicon ratio on structural transformation and optical performance in [NaSr<sub>3</sub>Cl<sub>3</sub>][SiS<sub>4</sub>] and [NaSr<sub>4</sub>SCl][Si<sub>3</sub>S<sub>9</sub>].

    Chemical communications (Cambridge, England)·2026
    Same author

    Genome-Wide InDel Marker Development and Genetic Diversity Analysis of 52 Tomato Germplasm Accessions.

    Plants (Basel, Switzerland)·2026

    This study introduces VerSemi, a versatile semi-supervised learning framework for medical image segmentation. VerSemi effectively utilizes unlabeled data across diverse tasks, significantly improving segmentation accuracy and setting a new state-of-the-art.

    Area of Science:

    • Medical image analysis
    • Deep learning
    • Computer vision

    Background:

    • Limited annotated medical data hinders deep learning model training for segmentation.
    • Existing semi-supervised learning (SSL) methods often focus on specific tasks, underutilizing cross-dataset potential.
    • Leveraging abundant unlabeled data is crucial for advancing medical image segmentation.

    Purpose of the Study:

    • To propose a Versatile Semi-supervised (VerSemi) framework for enhanced medical image segmentation.
    • To integrate diverse SSL tasks into a unified model with an extensive label space.
    • To exploit unlabeled data more effectively for improved segmentation performance.

    Main Methods:

    • Developed a dynamic task-prompted design for segmenting various targets across different datasets.

    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

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    Related Experiment Videos

    Last Updated: Jul 12, 2026

    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
    06:48

    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

    Published on: January 7, 2019

    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

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

  • Created a synthetic task using CutMix augmentation to expand the label space and capture cross-dataset semantics.
  • Implemented a consistency constraint aligning task predictions with a synthetic task for accurate foreground segmentation.

    • Main Results:

    • VerSemi demonstrated superior performance compared to seven established SSL methods on four public datasets.
    • Achieved a 2.69% average Dice gain over the second-best method.
    • Established a new state-of-the-art in semi-supervised medical image segmentation.

    Conclusions:

    • The VerSemi framework effectively addresses the challenge of limited annotations in medical image segmentation.
    • Integrating diverse SSL tasks and leveraging unlabeled data significantly boosts segmentation accuracy.
    • VerSemi represents a significant advancement in semi-supervised medical image segmentation, offering broader clinical applicability.