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: Dec 22, 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

3.2K

Multi-Task Pre-Training of Deep Neural Networks for Digital Pathology.

Romain Mormont, Pierre Geurts, Raphael Maree

    IEEE Journal of Biomedical and Health Informatics
    |May 10, 2020
    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

    Recent Advances in Bioimage Analysis Methods for Detecting Skeletal Deformities in Biomedical and Aquaculture Fish Species.

    Biomolecules·2023
    Same author

    Validating instructional design and predicting student performance in histology education: Using machine learning via virtual microscopy.

    Anatomical sciences education·2023
    Same author

    Bioimage analysis workflows: community resources to navigate through a complex ecosystem.

    F1000Research·2021
    Same author

    Error curves for evaluating the quality of feature rankings.

    PeerJ. Computer science·2021
    Same author

    BIAFLOWS: A Collaborative Framework to Reproducibly Deploy and Benchmark Bioimage Analysis Workflows.

    Patterns (New York, N.Y.)·2020
    Same author

    Open Practices and Resources for Collaborative Digital Pathology.

    Frontiers in medicine·2019
    Same journal

    AdaWGAN: Data Augmentation for Few-Shot HD-sEMG Gesture Recognition Using Single-Trial Data.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    NeuroBooster: a domain-informed self-supervised learning paradigm tailored for brain MRI analysis.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    Graph Convolutional Neural Network based Depression Detection using Brain Functional Connectivity Measures.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    Improving Multi-Sensor Non-Invasive Glucose Detection through AI: A Domain Generalization Approach.

    IEEE journal of biomedical and health informatics·2026
    Same journal

    Unmixing the Neck: Accurate Jugular Venous Pulse Detection From Wearable PPG.

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

    Multi-task learning effectively pre-trains digital pathology models using diverse datasets, outperforming or matching ImageNet pre-training for classification tasks.

    Area of Science:

    • Digital pathology
    • Machine learning
    • Computer vision

    Background:

    • Lack of large-scale datasets in digital pathology hinders model pre-training.
    • Existing small and medium-sized datasets are fragmented.
    • ImageNet, a large-scale dataset, is commonly used for pre-training but may lack domain specificity.

    Purpose of the Study:

    • Investigate multi-task learning (MTL) for pre-training digital pathology classification models.
    • Develop a transferable model using a unified dataset.
    • Evaluate the performance of MTL pre-trained models against ImageNet pre-trained models.

    Main Methods:

    • Assembled and transformed 22 digital pathology datasets into a unified pool of nearly 900,000 images.
    • Proposed a simple architecture and training scheme for MTL.

    More Related Videos

    Deep Learning-Based Segmentation of Cryo-Electron Tomograms
    10:25

    Deep Learning-Based Segmentation of Cryo-Electron Tomograms

    Published on: November 11, 2022

    10.4K

    Related Experiment Videos

    Last Updated: Dec 22, 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

    3.2K
    Deep Learning-Based Segmentation of Cryo-Electron Tomograms
    10:25

    Deep Learning-Based Segmentation of Cryo-Electron Tomograms

    Published on: November 11, 2022

    10.4K
  • Implemented a robust evaluation and selection protocol.
  • Compared performance using models as feature extractors and through fine-tuning.

    • Main Results:

    • MTL pre-trained models significantly improved performance over ImageNet pre-trained models as feature extractors on specific target tasks.
    • Comparable performance was achieved between MTL and ImageNet pre-trained models.
    • Fine-tuning further enhanced performance, mitigating the domain specificity limitations of ImageNet features.
    • Both pre-training approaches yielded comparable performance after fine-tuning.

    Conclusions:

    • Multi-task learning offers a viable strategy for pre-training models in digital pathology.
    • MTL effectively leverages diverse, smaller datasets to create transferable representations.
    • Fine-tuning is crucial for optimizing performance and adapting pre-trained features to specific downstream tasks.