Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Mar 18;25(1):108.
doi: 10.1186/s12906-025-04853-7.

Developing a deep learning model for the automated monitoring of acupuncture needle insertion: enhancing safety in traditional acupuncture practices

Shun-Ku Lin  1   2   3   4 , Chien-Kun Su  5 , Melnard Rome C Mercado  5 , Syu-Jyun Peng  6   7
Affiliations

Developing a deep learning model for the automated monitoring of acupuncture needle insertion: enhancing safety in traditional acupuncture practices

Shun-Ku Lin et al. BMC Complement Med Ther. .

Abstract

Background: Acupuncture is a widely practiced traditional therapy, yet safety concerns, particularly needle breakage and retention, remain critical issues that can lead to complications such as infections, organ injury, or chronic pain. This study aimed to develop a deep learning model to monitor acupuncture needle insertion, detect instances of needle breakage, and prevent needle retention, ultimately improving patient safety and treatment outcomes.

Methods: A deep learning model based on the YOLOv8 architecture was trained using a dataset comprising 192 images from a commercial image library and 73 clinical images captured during real-world acupuncture sessions. Images were preprocessed through cropping and annotation, and augmented to enhance model generalizability. Five-fold cross-validation was employed to ensure robust performance. Model evaluation metrics included precision, recall, F1 score, and mean average precision (mAP) at Intersection over Union (IoU) thresholds of 50% (mAP@50) and 50-95% (mAP@50-95).

Results: The model demonstrated strong performance, achieving an average precision of 88.0% and a recall of 82.9%. The mean average precision was 88.6% at mAP@50 and 62.9% at mAP@50-95, indicating high reliability in detecting acupuncture needles across diverse scenarios. These results highlight the potential of the model to enhance clinical safety by minimizing risks associated with needle breakage and retention, regardless of practitioner experience or patient demographics.

Conclusions: The proposed YOLOv8-based deep learning model offers a reliable method for real-time needle monitoring in acupuncture. Its integration into clinical workflows can improve safety and efficiency, especially in underserved regions or settings with less experienced practitioners. Future research should validate the model with larger, more diverse datasets and explore its application in various healthcare settings.

Trial registration: Not applicable; this study did not involve a healthcare intervention requiring registration. Data collection adhered to ethical standards with institutional approval (TCHIRB-11310004).

Keywords: Acupuncture needle; Acupuncture practice; Deep learning; Needle detection; Safety.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethics approval and consent to participate: All methods were performed in accordance with the relevant guidelines and regulations in the Declaration of Helsinki. Informed consent was obtained from all subjects. The research protocol was approved by the Taipei City Hospital Research Ethics Committee under approval number TCHIRB-11310004. Informed consent was obtained from all subjects. Consent for publication: Not Applicable as there were no identifiable details of individuals reported in the manuscript. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Instances of misclassification and missing detection when assessing the performance of the proposed model using an external test dataset. This visual comparison of the ground truth and predicted bounding boxes illustrates the challenges typically encountered in needle detection, such as occlusion or a lack of contrast between the needles and the background. The figure includes the following: (a) Image 01 with 1 missed detection; (b) Image 06 with 2 misclassified detections; (c) Image 07 with 3 misclassified detections; and (d) Image 08 with 1 misclassified detection and 1 missed detection
See this image and copyright information in PMC

References

    1. Vickers AJ, Vertosick EA, Lewith G, MacPherson H, Foster NE, Sherman KJ, Irnich D, Witt CM, Linde K. Acupuncture for chronic pain: update of an individual patient data Meta-Analysis. J Pain. 2018;19(5):455–74. - PMC - PubMed
    1. Kim TH, Lee MS, Birch S, Alræk T, Norheim AJ, Kang JW. Publication status and reporting quality of case reports on acupuncture-related adverse events: A systematic reviews of case studies. Heliyon. 2023;9(10):e20577. - PMC - PubMed
    1. Fang X, Tian Z, Xie B, Guo H. Removal of an acupuncture needle accidentally broken in the neck. Asian J Surg. 2019;42(4):582–3. - PubMed
    1. Kawamura I, Tominaga H, Tokumoto H, Sakuma D, Sanada M, Ogura T, Taniguchi N. Removal of a migrated acupuncture needle from the cervical spinal Canal with removal confirmation by cone-beam computed tomography in a hybrid operating room. Trauma Case Rep. 2023;43:100772. - PMC - PubMed
    1. Wong TH, Wei J, Chen H, Ng BFL. A novel deep learning based cloud service system for automated acupuncture needle counting: a strategy to improve acupuncture safety. Digit Chin Med. 2024;7(1):40–6.

LinkOut - more resources