Construction of an artificial intelligence-assisted system for auxiliary detection of auricular point features based on the YOLO neural network

WANG Ganhong; ZHANG Zihao; XIA Kaijian; ZHOU Yanting; XI Meijuan; CHEN Jian

doi:10.13703/j.0255-2930.20240611-0001

您当前的位置：

首页 >

文章列表页 >

Construction of an artificial intelligence-assisted system for auxiliary detection of auricular point features based on the YOLO neural network

Acupuncture and Intelligent Medicine | 更新时间：2025-04-11

- Construction of an artificial intelligence-assisted system for auxiliary detection of auricular point features based on the YOLO neural network
- Chinese Acupuncture & Moxibustion Vol. 45, Issue 4, Pages: 413-420(2025)
- 作者机构：
  
  常熟市中医院消化内科，江苏常熟　215500
  上海豪兄教育科技有限公司
  常熟市医学人工智能与大数据重点实验室
  常熟市第一人民医院消化内科，江苏常熟　215500
- 作者简介：
- 基金信息：
- DOI：10.13703/j.0255-2930.20240611-0001
  CLC：
- Received：11 June 2024，
  
  Online First：07 January 2025，
  
  Published：12 April 2025
- 稿件说明：
移动端阅览
WANG Ganhong, ZHANG Zihao, XIA Kaijian, et al. Construction of an artificial intelligence-assisted system for auxiliary detection of auricular point features based on the YOLO neural network[J]. Chinese Acupuncture & Moxibustion, 2025, 45(4): 413-420.
DOI：

WANG Ganhong, ZHANG Zihao, XIA Kaijian, et al. Construction of an artificial intelligence-assisted system for auxiliary detection of auricular point features based on the YOLO neural network[J]. Chinese Acupuncture & Moxibustion, 2025, 45(4): 413-420. DOI： 10.13703/j.0255-2930.20240611-0001.

摘要

目的：

基于YOLOv8神经网络开发用于21个常用耳穴特征点自动检测的人工智能辅助系统。

方法：

收集2019年6月至2024年2月来自3个中心的人体耳部图像数据，共计660张。使用LabelMe5.3.1图形标注工具进行图像的矩形框和特征点标注，并转换为YOLO模型兼容的格式。利用这些数据，进行不同规模YOLO神经网络预训练模型的迁移学习和微调训练。在验证集和测试集上进行模型的性能评估，包括不同阈值下的平均精度（mAP）、召回率（recall）、推理速度（FPS）、混淆矩阵等。最后，将模型部署于本地计算机，并通过摄像头对人体耳部图像进行实时检测。

结果：

本研究开发了5种不同版本的YOLOv8关键点检测模型，包括YOLOv8n、YOLOv8s、YOLOv8m、YOLOv8l、YOLOv8x。在验证集上，YOLOv8n在速度（225.736帧/s）和精确率（0.998）

上均表现最佳。在外部测试集上，YOLOv8n识别耳部的准确率为0.991、敏感性为1.0、F1分数为0.995。耳穴特征点定位性能结果显示，50%交并比阈值下的平均精度（mAP

）为0.990，精确率为0.995，召回率为0.997。

结论：

基于YOLOv8n构建的21个常用耳穴关键点检测模型具有良好的预测性能，能够自动快速地对耳穴进行定位和分类。

Abstract

Objective

To develop an artificial intelligence-assisted system for the automatic detection of the features of common 21 auricular points based on the YOLOv8 neural network.

Methods

A total of 660 human auricular images from three research centers were collected from June 2019 to February 2024. The rectangle boxes and features of images were annotated using the LabelMe5.3.1 tool and converted them into a format compatible with the YOLO model. Using these data

transfer learning and fine-tuning training were conducted on different scales of pretrained YOLO neural network models. The model's performance was evaluated on validation and test sets

including the mean average precision (mAP) at various thresholds

recall rate (recall)

frames per second (FPS) and confusion matrices. Finally

the model was deployed on a local computer

and the real-time detection of human auricular images was conducted using a camera.

Results

Five different versions of the YOLOv8 key-point detection model were developed

including YOLOv8n

YOLOv8s

YOLOv8m

YOLOv8l

and YOLOv8x. On the validation set

YOLOv8n showed the best performance in terms of speed (225.736 frames per second) and precision (0.998). On the external test set

YOLOv8n achieved the accuracy of 0.991

the sensitivity of 1.0

and the F1 score of 0.995. The localization performance of auricular point features showed the average accuracy of 0.990

the precision of 0.995

and the recall of 0.997 under 50% intersection ration (mAP

Conclusion

The key-point detection model of 21 common auricular points based on YOLOv8n exhibits the excellent predictive performance

which is capable of rapidly and automatically locating and classifying auricular points.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Auricular electroacupuncture for post-stroke dysphagia in pharyngeal phase: a randomized controlled trial

Research status of automatic localization of acupoint based on deep learning

Application and considerations of artificial intelligence and neuroimaging in the study of brain effect mechanisms of acupuncture and moxibustion

Effect of moxibustion-induced deqi on hippocampal autophagy function in APPswe/PSEN1dE9 transgenic Alzheimer′s disease mice

Clinical experience in treatment of dysmyotonia with the combination of acupuncture and herbal medicine based on the theory of "kidney deficiency, impairment of governor vessel and meridian damage by toxin"

Related Author

JI Youhong

WANG Yong

ZHUANG Xuan

GAO Ling

JIN Haipeng

ZHANG Yuhong

LI Xiangliang

LI Zhongzheng

Related Institution

Department of Rehabilitation, Xiamen Hospital of TCM

School of Acupuncture-Moxibustion and Tuina, Fujian University of TCM

Xiamen Dianqian Street Community Health Service Center

School of Acupuncture-Moxibustion and Tuina, Tianjin University of TCM

Experimental Acupuncture Research Center, Tianjin University of TCM

⁰