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: Jun 12, 2026

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

Class Sensitive Calibration and Discrepancy-Aware Synthesis for Semi-Supervised Medical Image Segmentation.

Tingwei Liu, Ning Ma, Yongri Piao

    IEEE Journal of Biomedical and Health Informatics
    |June 10, 2026
    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

    Programmable RNA editing by recruiting endogenous ADAR using engineered RNAs.

    Nature biotechnology·2019
    Same author

    Retrospective analysis of seven cases of pancreatic mixed adenoneuroendocrine carcinoma from a high-volume center and review of the literature.

    BMC surgery·2019
    Same author

    Multiscale Visualization of Colloidal Particle Lens Array Mediated Plasma Dynamics for Dielectric Nanoparticle Enhanced Femtosecond Laser-Induced Breakdown Spectroscopy.

    Analytical chemistry·2019
    Same author

    Evolutionary Metabolomics Identifies Substantial Metabolic Divergence between Maize and Its Wild Ancestor, Teosinte.

    The Plant cell·2019
    Same author

    Protective effect of <i>Danhong</i> injection in patients with acute myocardial infarction at a high risk of no-reflow during primary percutaneous coronary intervention.

    Journal of geriatric cardiology : JGC·2019
    Same author

    Exosome-derived uterine microRNAs isolated from cows with endometritis impede blastocyst development.

    Reproductive biology·2019
    Same journal

    AD-DAE: Alzheimer's Disease Progression Modeling with Unpaired Longitudinal MRI using Diffusion Auto-Encoders.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    EEG Connectivity Signatures in Active vs. Passive Mental Fatigue Settings.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    Privacy-Enhanced Vertical Federated Learning for Healthcare via Directional Noise and Subset Representations.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    Multimodal Bidirectional Direct Preference Optimization and Instruction Fine-Tuning for Medical Image Understanding and Generation.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    CT: A Controllable Transformer for Multi-Task TCM Facial Inspection.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    Marfan Syndrome Prediction Via Graph Neural Networks on 3D Facial Cues.

    IEEE journal of biomedical and health informatics·2026
    See all related articles

    This study introduces a new semi-supervised framework for medical image segmentation, improving accuracy for critical targets by addressing data distribution shifts and class imbalance. The novel approach enhances segmentation performance, especially for underrepresented classes.

    Area of Science:

    • Medical Image Analysis
    • Computer Vision
    • Machine Learning

    Background:

    • Accurate organ segmentation is crucial for medical image analysis.
    • Semi-supervised methods balance annotation cost and precision but face challenges.
    • Distribution shift and class imbalance degrade segmentation quality, particularly for critical targets.

    Purpose of the Study:

    • To develop a novel semi-supervised framework to overcome distribution shift and class imbalance in medical image segmentation.
    • To enhance pseudo-label quality and improve segmentation of critical and minority classes.

    Main Methods:

    • Proposed a Class-Sensitive Temperature Scaling (CSTS) strategy for robust per-class adaptation to distribution shift.
    • Introduced a Discrepancy-Aware Sampling Strategy (DSS) to guide diffusion models for high-quality sample generation.

    Related Experiment Videos

    Last Updated: Jun 12, 2026

    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

  • Utilized a dual-head decoupled architecture for dynamic logit adjustment and class-wise consistency modeling.

    • Main Results:

    • The proposed framework significantly outperforms state-of-the-art methods on abdominal multi-organ segmentation tasks.
    • Achieved comprehensive improvements in overall segmentation accuracy.
    • Demonstrated particularly significant gains in segmenting minority classes.

    Conclusions:

    • The novel semi-supervised framework effectively addresses distribution shift and class imbalance in medical image segmentation.
    • The CSTS and DSS strategies enhance segmentation precision, especially for underrepresented targets.
    • The method offers a promising solution for improving medical image analysis accuracy and efficiency.