Related Experiment Video
Updated: May 21, 2025
08:18
Visualizing Motion Patterns in Acupuncture Manipulation
Published on: July 16, 2016
8.7K
[Development of an abdominal acupoint localization system based on AI deep learning].
Mo Zhang1, Yuming Li2, Zongming Shi1
1Department of TCM, Integration of Traditional Chinese and Western Medicine, First Hospital of Peking University, Beijing 100034, China.
Zhongguo Zhen Jiu = Chinese Acupuncture & Moxibustion
|March 17, 2025
Summary
This study introduces a computer vision system using convolutional neural networks (CNNs) to accurately locate abdominal acupoints. The system enhances Traditional Chinese Medicine (TCM) education and diagnostics.
Area of Science:
- Medical Imaging
- Computer Vision
- Artificial Intelligence
Context:
- Accurate abdominal acupoint localization is crucial for Traditional Chinese Medicine (TCM) practices.
- Existing methods face challenges in precision and standardization.
- Technological integration is needed for advancing TCM diagnostics and education.
Purpose:
- To develop an automated system for precise abdominal acupoint localization using computer vision and CNNs.
- To create a multi-task CNN architecture capable of identifying key anatomical landmarks and acupoints.
- To enable accurate mapping of image coordinates to a standardized acupoint template space.
Summary:
- A novel multi-task CNN architecture was developed to identify the Shenque (CV8) acupoint and body boundaries.
- Based on Shenque (CV8) localization, the system deduces the positions of four additional acupoints: Shangwan (CV13), Qugu (CV2), and bilateral Daheng (SP15).
- An affine transformation matrix ensures accurate mapping to a template space, achieving precise acupoint identification in images.
Impact:
- Provides technical support for remote TCM education and diagnostic assistance.
- Facilitates the development of advanced TCM equipment, including intelligent acupuncture robots.
- Promotes the standardization and intelligent advancement of acupuncture practices.
