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

SUDA: Simultaneous unsupervised knowledge distillation and adaptation of foundation models for efficient pathological image analysis.

Medical image analysis·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

Saikosaponin B1 alleviates hepatic fibrosis by targeting the LDHA-MCT1/4 axis to inhibit lactate-driven profibrogenic signaling.

Naunyn-Schmiedeberg's archives of pharmacology·2026
Same author

Is Deep Learning Ready for Abdominal Organ-at-Risk Segmentation in the Foundation Model Era: A Comprehensive Study of Challenging Clinical Cases.

International journal of radiation oncology, biology, physics·2026
Same author

Response-Adapted Benefit of Postoperative Adjuvant Therapy Following Neoadjuvant Treatment in Resectable NSCLC: A Single-Center Retrospective Cohort Study.

Cancers·2026
Same author

Resveratrol inhibits pancreatic cancer progression via the ING5 signaling pathway.

Scientific reports·2026

Related Experiment Video

Updated: Aug 4, 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

2.8K

PA-Seg: Learning From Point Annotations for 3D Medical Image Segmentation Using Contextual Regularization and Cross

Shuwei Zhai, Guotai Wang, Xiangde Luo

    IEEE Transactions on Medical Imaging
    |April 6, 2023
    PubMed
    Summary

    This study introduces PA-Seg, a novel framework for 3D medical image segmentation using only seven points for annotation. The method significantly reduces annotation effort while achieving high accuracy, approaching fully supervised performance.

    More Related Videos

    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
    12:08

    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

    Published on: August 13, 2014

    24.6K
    Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
    10:23

    Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

    Published on: September 8, 2023

    2.8K

    Related Experiment Videos

    Last Updated: Aug 4, 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

    2.8K
    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
    12:08

    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

    Published on: August 13, 2014

    24.6K
    Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
    10:23

    Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

    Published on: September 8, 2023

    2.8K

    Area of Science:

    • Medical Imaging
    • Computer Vision
    • Machine Learning

    Background:

    • 3D medical image segmentation is crucial for diagnosis and treatment planning.
    • Fully supervised Convolutional Neural Networks (CNNs) require extensive manual annotation, which is time-consuming and labor-intensive.
    • Weakly supervised learning offers a promising alternative to reduce annotation burden.

    Purpose of the Study:

    • To develop an efficient weakly supervised learning framework for 3D medical image segmentation.
    • To minimize the annotation effort required for training segmentation models.
    • To achieve performance comparable to fully supervised methods with significantly less annotation.

    Main Methods:

    • Proposed a two-stage weakly supervised framework, PA-Seg, utilizing only seven seed points for annotation.
    • Employed geodesic distance transform for initial supervision signal expansion.
    • Introduced multi-view Conditional Random Field (mCRF) and Variance Minimization (VM) losses for contextual regularization.
    • Implemented a Self and Cross Monitoring (SCM) strategy combining self-training and Cross Knowledge Distillation (CKD) to refine pseudo-labels.

    Main Results:

    • The first stage of PA-Seg significantly outperformed existing weakly supervised methods on Vestibular Schwannoma (VS) and Brain Tumor Segmentation (BraTS) datasets.
    • Additional training with the SCM strategy brought the model's performance close to fully supervised counterparts on the BraTS dataset.
    • Demonstrated the effectiveness of minimal annotation in achieving high-performance 3D medical image segmentation.

    Conclusions:

    • PA-Seg offers a highly effective solution for 3D medical image segmentation with minimal annotation requirements.
    • The proposed framework addresses the challenges of limited annotated data in medical imaging.
    • This approach has the potential to accelerate clinical applications by reducing data preparation time and cost.