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

Comparison study of supercritical water gasification for hydrogen production on a continuous flow versus a batch reactor.

Bioresource technology·2023
Same author

Passive Internet of Events Enabled by Broadly Compatible Self-Powered Visualized Platform Toward Real-Time Surveillance.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2023
Same author

Slow-light silicon modulator with 110-GHz bandwidth.

Science advances·2023
Same author

Glycerol-weighted chemical exchange saturation transfer nanoprobes allow <sup>19</sup>F<sup>/1</sup>H dual-modality magnetic resonance imaging-guided cancer radiotherapy.

Nature communications·2023
Same author

Pectic oligosaccharides ameliorate high-fat diet-induced obesity and hepatic steatosis in association with modulating gut microbiota in mice.

Food & function·2023
Same author

The value of ultrasound combined with CT in identifying early low-grade appendiceal mucinous neoplasm and appendicitis.

Frontiers in oncology·2023
Same journal

ASSR-Net: Anisotropic Structure-Aware and Spectrally Recalibrated Network for Hyperspectral Image Fusion.

IEEE transactions on neural networks and learning systems·2026
Same journal

PIMPC-GNN: Physics-Informed Multiphase Consensus Learning for Enhancing Imbalanced Node Classification in Graph Neural Networks.

IEEE transactions on neural networks and learning systems·2026
Same journal

Quantum Rényi α-Entropies for Graph Characterization.

IEEE transactions on neural networks and learning systems·2026
Same journal

LANet: A Lightweight and Accurate Balanced Network Based on State Space Models for Real-Time Semantic Segmentation.

IEEE transactions on neural networks and learning systems·2026
Same journal

MENDNet: Memory-Enhanced Dependency Network for Multistock Movement Prediction.

IEEE transactions on neural networks and learning systems·2026
Same journal

Temporal Mask-Embedding Learning and Query-Refined Head Network for Visual Tracking.

IEEE transactions on neural networks and learning systems·2026
See all related articles

Related Experiment Video

Updated: Sep 13, 2025

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.2K

SAM-Med3D: A Vision Foundation Model for General-Purpose Segmentation on Volumetric Medical Images.

Haoyu Wang, Sizheng Guo, Jin Ye

    IEEE Transactions on Neural Networks and Learning Systems
    |July 31, 2025
    PubMed
    Summary
    This summary is machine-generated.

    We introduce SAM-Med3D, a versatile vision foundation model (VFM) for segmenting 3D medical images. This general-purpose AI model accurately segments diverse structures across modalities using minimal prompts, advancing medical AI applications.

    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

    24.7K
    Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
    14:15

    Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

    Published on: January 11, 2020

    7.2K

    Related Experiment Videos

    Last Updated: Sep 13, 2025

    Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
    06:18

    Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

    Published on: April 5, 2024

    1.2K
    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

    24.7K
    Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
    14:15

    Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

    Published on: January 11, 2020

    7.2K

    Area of Science:

    • Artificial Intelligence
    • Medical Imaging
    • Computer Vision

    Background:

    • Current volumetric medical image segmentation models are often task-specific, limiting their clinical applicability across different anatomical structures and imaging modalities.
    • A need exists for general-purpose segmentation models that can adapt to diverse medical imaging tasks.

    Purpose of the Study:

    • To introduce SAM-Med3D, a vision foundation model (VFM) designed for general-purpose segmentation of volumetric medical images.
    • To demonstrate the model's ability to accurately segment diverse anatomical structures and lesions across various modalities using minimal 3D prompts.

    Main Methods:

    • Development of SAM-Med3D, a promptable segmentation model with a fully learnable 3D structure.
    • Creation and preprocessing of a large-scale 3D medical image segmentation dataset (SA-Med3D-140K) comprising 22K images and 143K masks from public and private sources.
    • Training SAM-Med3D using a two-stage procedure on the SA-Med3D-140K dataset.

    Main Results:

    • SAM-Med3D demonstrated impressive performance on both familiar and novel segmentation targets.
    • Comprehensive evaluation across 16 datasets showed efficiency, efficacy, and zero-shot transferability to unseen tasks.
    • The model proved effective for diverse medical scenarios, including various anatomical structures, modalities, and targets.

    Conclusions:

    • SAM-Med3D represents a significant advancement in general-purpose medical image segmentation, overcoming limitations of task-specific models.
    • The developed model shows promising potential as a pretrained model for diverse downstream medical AI applications.
    • This work highlights the feasibility of leveraging extensive medical data resources to create adaptable, general-purpose medical AI tools.