Skip to main content

ORIGINAL RESEARCH article

Front. Neurorobot.
Volume 18 - 2024 | doi: 10.3389/fnbot.2024.1484038
This article is part of the Research Topic Advancing Neural Network-Based Intelligent Algorithms in Robotics: Challenges, Solutions, and Future Perspectives View all 12 articles

Real-time Location of Acupuncture points Based on Anatomical Landmarks and Pose Estimation models

Provisionally accepted
Hadi Sedigh Malekroodi Hadi Sedigh Malekroodi 1Seon-Deok Seo Seon-Deok Seo 1*Jinseong Choi Jinseong Choi 1*Chang-Soo Na Chang-Soo Na 2*Byeong-il Lee Byeong-il Lee 1,3*Myunggi Yi Myunggi Yi 1,3*
  • 1 Pukyong National University, Busan, Republic of Korea
  • 2 College of Korean Medicine, Dongshin University, Naju, North Jeolla, Republic of Korea
  • 3 Digital Healthcare Research Center, Institute of Information Technology and Convergence, Pukyong National University, Busan, Republic of Korea

The final, formatted version of the article will be published soon.

    Precise identification of acupuncture points (acupoints) is crucial for effective acupuncture treatment, but manual localization by the unskilled can lack accuracy and consistency. This study aims to propose two computer vision approaches leveraging artificial intelligence (AI) for automated real-time localization and visualization of facial and hand acupoints. The first approach employs a real-time landmark detection framework, detecting 38 acupoint locations on the face and hand by transforming anatomical landmark coordinates derived from image data. The second approach employs a state-ofthe-art convolutional neural network optimized for pose estimation to detect five key arm and hand acupoints (LI11, LI10, TE5, TE3, LI4) in constrained medical imaging datasets. Validation against expert annotations demonstrated less than 5 mm mean localization errors for both approaches, indicating high accuracy. These AI-driven techniques establish foundations for reliable, automated acupoint recognition systems. Enabling self-localization of acupoints through imaging data facilitates self-training for individuals, provides assistive localization for practitioners, potentially improving the accuracy and accessibility of acupuncture treatments.

    Keywords: deep learning, Acupuncture, traditional medicine, Computer Vision, Pose estimation

    Received: 21 Aug 2024; Accepted: 28 Oct 2024.

    Copyright: © 2024 Sedigh Malekroodi, Seo, Choi, Na, Lee and Yi. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Seon-Deok Seo, Pukyong National University, Busan, Republic of Korea
    Jinseong Choi, Pukyong National University, Busan, Republic of Korea
    Chang-Soo Na, College of Korean Medicine, Dongshin University, Naju, 520-714, North Jeolla, Republic of Korea
    Byeong-il Lee, Pukyong National University, Busan, Republic of Korea
    Myunggi Yi, Pukyong National University, Busan, Republic of Korea

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.