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 Videos

Histopathological image classification with bilinear convolutional neural networks.

Chaofeng Wang, Jun Shi, Qi Zhang

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |October 25, 2017
    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

    Seasonal and spatial variations of microplastics in surface waters of Sansha Bay, a typical mariculture bay in the East China Sea.

    Marine pollution bulletin·2026
    Same author

    Risk Factors for Postoperative Complications in Different Fusion Surgical Approaches for Lumbar Degenerative Diseases.

    Journal of clinical medicine·2026
    Same author

    Nanoarmored Probiotic for Inflammatory Bowel Disease Bacteriotherapy via a Dual-Targeting Host-Microbiota Reprogramming.

    ACS nano·2026
    Same author

    Physicochemical Parameters Govern Winter Pelagic Microbial Food Web Dynamics in China's Marginal Seas.

    Microbial ecology·2026
    Same author

    A "Seesaw Effect" resolving the paradox in microzooplanktonic ciliate-environment interactions in the tropical Qinzhou Bay estuary-offshore continuum.

    Marine environmental research·2026
    Same author

    The RING-Type Ubiquitin Ligase XBAT35.2 Positively Modulates Plant Immunity by Promoting FLS2 Protein Accumulation.

    Molecular plant-microbe interactions : MPMI·2026

    This study introduces a novel bilinear convolutional neural network (BCNN) method for histopathological image analysis. The approach enhances cancer classification by first decomposing images and then applying BCNN for improved feature representation.

    Area of Science:

    • Digital Pathology
    • Computational Imaging
    • Machine Learning in Histopathology

    Background:

    • Computer-aided quantitative analysis of histopathological images is crucial.
    • Stain decomposition is often necessary to resolve issues in histopathological image analysis.
    • Traditional convolutional neural networks (CNNs) are applied directly to images, potentially missing benefits from stain decomposition.

    Purpose of the Study:

    • To propose a novel bilinear CNN (BCNN) based method for histopathological image classification.
    • To leverage stain decomposition to improve feature representation in histopathological image analysis.
    • To evaluate the performance of the proposed BCNN method against traditional CNNs.

    Main Methods:

    • Histopathological images were decomposed into hematoxylin and eosin stain components.

    Related Experiment Videos

  • A bilinear CNN (BCNN) model was applied to the decomposed stain components.
  • The BCNN model fuses features from decomposed images to enhance representation.
  • The method was tested on a colorectal cancer dataset with eight classes.

    • Main Results:

    • The proposed BCNN-based method demonstrated superior performance compared to traditional CNNs.
    • Feature fusion from decomposed stain components improved classification accuracy.
    • The BCNN approach effectively handled challenges in histopathological image analysis.

    Conclusions:

    • The novel BCNN-based method offers an effective approach for histopathological image classification.
    • Stain decomposition combined with BCNN enhances feature representation and classification accuracy.
    • This method shows significant potential for computer-aided diagnosis in digital pathology.