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

Clinicopathological features, management and outcome of patients with poorly-differentiated oral and oropharyngeal squamous cell carcinoma.

Journal of cranio-maxillo-facial surgery : official publication of the European Association for Cranio-Maxillo-Facial Surgery·2017
Same author

Detection of Methanol with Fast Response by Monodispersed Indium Tungsten Oxide Ellipsoidal Nanospheres.

ACS sensors·2017
Same author

Randomized, controlled trial evaluating the effect of multi-strain probiotic on the mucosal microbiota in canine idiopathic inflammatory bowel disease.

Gut microbes·2017
Same author

Automatic segmentation of nine retinal layer boundaries in OCT images of non-exudative AMD patients using deep learning and graph search.

Biomedical optics express·2017
Same author

Sulfation of the Extracellular Polysaccharide Produced by the King Oyster Culinary-Medicinal Mushroom, Pleurotus eryngii (Agaricomycetes), and Its Antioxidant Properties In Vitro.

International journal of medicinal mushrooms·2017
Same author

Cryogenic 3D printing for producing hierarchical porous and rhBMP-2-loaded Ca-P/PLLA nanocomposite scaffolds for bone tissue engineering.

Biofabrication·2017

Related Experiment Video

Updated: May 24, 2025

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
08:40

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

12.7K

SegAnyPath: A Foundation Model for Multi- Resolution Stain-Variant and Multi-Task Pathology Image Segmentation.

Chong Wang, Yajie Wan, Shuxin Li

    IEEE Transactions on Medical Imaging
    |March 3, 2025
    PubMed
    Summary

    SegAnyPath, a new foundation model, significantly improves pathology image segmentation accuracy. It outperforms general models like SAM by addressing multi-scale complexity and staining variations in medical images.

    More Related Videos

    Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions
    11:27

    Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions

    Published on: September 22, 2013

    9.3K
    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

    24.5K

    Related Experiment Videos

    Last Updated: May 24, 2025

    Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
    08:40

    Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

    Published on: April 8, 2016

    12.7K
    Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions
    11:27

    Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions

    Published on: September 22, 2013

    9.3K
    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

    24.5K

    Area of Science:

    • Digital pathology
    • Medical image analysis
    • Computer vision

    Background:

    • Foundation models like Segment Anything Model (SAM) show promise in general image segmentation.
    • Pathology image segmentation faces challenges due to multi-scale structures and staining heterogeneity, limiting general model performance.

    Purpose of the Study:

    • Introduce SegAnyPath, a foundation model tailored for pathology image segmentation.
    • Enhance zero-shot generalization for diverse pathology analysis tasks.

    Main Methods:

    • Trained SegAnyPath on a large public pathology dataset (1.5M+ images, 3.5M+ masks).
    • Employed a multi-scale proxy task for diverse image resolutions and a self-distillation scheme for stain variations.
    • Utilized a task-guided Mixture of Experts (MoE) architecture for efficient handling of cell, tissue, and tumor segmentation.

    Main Results:

    • SegAnyPath achieved a 0.6797 Dice score across datasets and organs in zero-shot settings.
    • Demonstrated consistent performance across varying stain styles and resolutions.
    • Outperformed fine-tuned SAM by 29.27% (0.6797 vs. 0.5258 Dice score) on external test sets.

    Conclusions:

    • SegAnyPath offers superior performance and generalization for pathology image segmentation compared to existing foundation models.
    • The model shows potential for advancing pathology analysis and improving clinical diagnostic accuracy.
    • Developed SegAnyPath addresses key limitations of general models in specialized medical imaging domains.