Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jan 18, 2026

Visualizing Motion Patterns in Acupuncture Manipulation

Visualizing Motion Patterns in Acupuncture Manipulation

Published on: July 16, 2016

Structure-guided deep learning for back acupoint localization via bone-measuring constraints.

Yulong Wang¹, Tian Lan², Wenjian Dou³

¹School of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing, China.

Frontiers in Physiology

|September 11, 2025

Summary

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

The high pCR rate of sandwich neoadjuvant treatment in locally advanced rectal cancer may translate into a better long-term survival benefit: 5-year outcome of a Phase II clinical trial.

Cancer management and research·2018

Same author

Pretreatment TACC3 expression in locally advanced rectal cancer decreases the response to neoadjuvant chemoradiotherapy.

Aging·2018

Same author

Persistently Transmitted Viruses Restrict the Transmission of Other Viruses by Affecting Their Vectors.

Frontiers in physiology·2018

Same author

Prenatal war exposure and schizophrenia in adulthood: evidence from the Sino-Japanese War of 1937-1945.

Social psychiatry and psychiatric epidemiology·2018

Same author

Identification and localization of SAS-6 in the microsporidium Nosema bombycis.

Infection, genetics and evolution : journal of molecular epidemiology and evolutionary genetics in infectious diseases·2018

Same author

Using Human Plasma as an Assay Medium in Caco-2 Studies Improves Mass Balance for Lipophilic Compounds.

Pharmaceutical research·2018

This study presents an AI framework for precise acupoint localization in Traditional Chinese Medicine (TCM), integrating bone measurement principles with deep learning for accurate, real-time identification of back acupoints.

Area of Science:

Medical Imaging
Artificial Intelligence
Traditional Chinese Medicine

Background:

Accurate acupoint localization is essential for effective acupuncture and Traditional Chinese Medicine (TCM) therapies.
Current methods may lack precision across diverse body types and conditions.

Purpose of the Study:

To develop and validate a novel automated framework for recognizing back acupoints using deep learning.
To integrate traditional TCM bone-measuring principles with advanced AI for enhanced accuracy.

Main Methods:

The framework utilizes an HRFormer backbone with a Structure-Guided Keypoint Estimation Module (SG-KEM).
A structure-constrained loss function ensures anatomically consistent predictions within a standardized spatial coordinate system.
The model was trained and evaluated on 430 high-resolution back images with 19 annotated acupoints.

Keywords:

HRFormer acupoint localization anatomical landmark detection artificial intelligence bone-measuring method medical imaging

More Related Videos

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

Related Experiment Videos

Last Updated: Jan 18, 2026

Visualizing Motion Patterns in Acupuncture Manipulation

Visualizing Motion Patterns in Acupuncture Manipulation

Published on: July 16, 2016

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

Main Results:

The framework achieved a normalized mean error (NME) of 0.6% and a failure rate (FR@1 cm) of 1.2%.
Real-time performance was demonstrated at 18 frames per second with high precision (93.8%) and AUC (0.97).
The SG-KEM module and structure-constrained loss significantly reduced mean error, showing robustness in obese individuals and under varying illumination.

Conclusions:

The developed framework offers a clinically viable and computationally efficient solution for intelligent acupoint localization.
This AI-assisted approach supports accurate diagnosis and personalized treatment strategies in modern TCM.
The study highlights the potential of integrating traditional principles with deep learning for advancing TCM healthcare.