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

Identification and Functional Analysis of an Epsilon Class Glutathione S-Transferase Gene Associated with α-Pinene Adaptation in <i>Monochamus alternatus</i>.

International journal of molecular sciences·2023
Same author

Myeloid ACE2 protects against septic hypotension and vascular dysfunction through Ang-(1-7)-Mas-mediated macrophage polarization.

Redox biology·2023
Same author

[Comparison on anti-inflammatory activity of Gynostemma pentaphyllum processed with different methods].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2023
Same author

Design scheme of a high dynamic semi-airborne transient electromagnetic receiving system based on a voltage-controlled amplifier.

The Review of scientific instruments·2023
Same author

A Synthetic Cytotoxic T cell Platform for Rapidly Prototyping TCR Function.

bioRxiv : the preprint server for biology·2023
Same author

Structure of the DDB1-AMBRA1 E3 ligase receptor complex linked to cell cycle regulation.

Nature communications·2023

Related Experiment Video

Updated: Dec 23, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

3.1K

Multi-Task Joint Learning Model for Segmenting and Classifying Tongue Images Using a Deep Neural Network.

Qiang Xu, Yu Zeng, Wenjun Tang

    IEEE Journal of Biomedical and Health Informatics
    |April 21, 2020
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel Multi-Task Learning (MTL) method for simultaneous tongue image segmentation and classification in Traditional Chinese Medicine (TCM). The approach enhances diagnostic accuracy by integrating deep learning models.

    More Related Videos

    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 Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.8K

    Related Experiment Videos

    Last Updated: Dec 23, 2025

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
    05:56

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

    Published on: April 14, 2023

    3.1K
    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 Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.8K

    Area of Science:

    • Computer Vision
    • Artificial Intelligence in Medicine
    • Traditional Chinese Medicine (TCM) Diagnostics

    Background:

    • Tongue image segmentation and classification are vital for TCM diagnostics but present significant challenges due to complexity and fine-grained details.
    • These tasks are inherently interrelated, suggesting the suitability of Multi-Task Learning (MTL) for improved performance.

    Purpose of the Study:

    • To develop and evaluate a novel MTL method for simultaneously performing tongue image segmentation and classification.
    • To leverage state-of-the-art deep neural network architectures within the MTL framework.

    Main Methods:

    • A Multi-Task Learning (MTL) framework was designed to share underlying parameters between segmentation and classification tasks.
    • Two distinct task-specific loss functions were incorporated into the MTL model.
    • The MTL approach integrated two advanced deep neural network variants: UNET for segmentation and Discriminative Filter Learning (DFL) for classification.

    Main Results:

    • The proposed joint MTL method demonstrated superior performance compared to existing individual tongue characterization techniques.
    • Extensive experiments validated the effectiveness and efficiency of the integrated approach.
    • Visualizations and ablation studies confirmed the method's consistency with human perception.

    Conclusions:

    • This study presents the first known MTL approach for simultaneous tongue segmentation and classification.
    • The developed method offers a significant advancement in automated tongue image analysis for TCM.
    • The findings suggest a promising direction for enhancing TCM diagnostic tools through integrated AI solutions.