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

Decoding amino acid metabolism in hepatocellular carcinoma: critical nodes and novel therapeutic strategy.

Frontiers in oncology·2026
Same author

Bioinspired enzymatic polyphenolic nanoplatform for redox modulation and functional renal restoration in diabetic nephropathy.

Regenerative biomaterials·2026
Same author

Cerebellar Repetitive Transcranial Magnetic Stimulation (rTMS) With Modified Proprioceptive Neuromuscular Facilitation (PNF) Balloon Dilation for Dysphagia After Brainstem and Cerebellar Infarction: A Case Report.

Cureus·2026
Same author

The in vivo inhibitory function of the MHC-I α3 domain-CD8α interaction.

bioRxiv : the preprint server for biology·2026
Same author

SARS-CoV-2 ORF3a suppresses host antiviral interferon responses by promoting STUB1-mediated PTEN proteasomal degradation.

Journal of virology·2026
Same author

The mediating effect of meaning in life on fear of death and attitudes toward caring for the dying among oncology nurses.

BMC nursing·2026

Related Experiment Video

Updated: Jul 5, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

405

Two-stream vision transformer based multi-label recognition for TCM prescriptions construction.

Zijuan Zhao1, Yan Qiang2, Fenghao Yang1

  • 1College of Computer Science and Technology(College of Data Science), Taiyuan University of Technology, Taiyuan, 030002, Shanxi, China.

Computers in Biology and Medicine
|January 20, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces an automated framework for Traditional Chinese Medicine (TCM) herbal prescription construction using visual diagnosis images. The model achieves significant precision and recall, demonstrating the feasibility of integrating visual data for TCM recommendations.

Keywords:
Facial and tongue imagesGraph convolutional networkMulti-label image recognitionPrescriptions constructionVisual transformer

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

2.8K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

Related Experiment Videos

Last Updated: Jul 5, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

405
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

2.8K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

Area of Science:

  • Integrative Medicine
  • Artificial Intelligence in Healthcare
  • Computational Biology

Background:

  • Traditional Chinese Medicine (TCM) relies on visual diagnosis (facial, tongue images) for treatment.
  • Automating herbal prescription construction from visual data is valuable for mobile healthcare and understanding feature-herb correlations.

Purpose of the Study:

  • To propose a novel framework for automated multi-herb recommendation based on visual diagnosis images.
  • To explore the integration of multi-perspective visual data for accurate TCM prescription generation.

Main Methods:

  • A multi-herb recommendation framework utilizing Visual Transformer and multi-label classification.
  • Key components include a dual-stream Visual Transformer for image encoding, Graph Convolutional Networks for label embedding, and Multi-Modal Factorized Bilinear modules for cross-modal fusion.
  • An end-to-end multi-label image-herb recommendation model was developed.

Main Results:

  • The framework achieved a precision of 50.06%, recall of 48.33%, and F1-score of 49.18% on real facial and tongue images.
  • Generated prescription data closely resembled real-world samples.

Conclusions:

  • The study validates the feasibility of automated herbal prescription construction using visual diagnosis information.
  • Provides valuable insights for developing automated TCM prescription systems leveraging physical and visual data.