[1]田昌锐,廖薇,徐震.改进YOLOv5s的堆叠医疗器械检测算法[J].中国医学物理学杂志,2025,42(2):220-226.[doi:DOI:10.3969/j.issn.1005-202X.2025.02.012]
　TIAN Changrui,LIAO Wei,XU Zhen.Detection of stacked medical devices using improved YOLOv5s[J].Chinese Journal of Medical Physics,2025,42(2):220-226.[doi:DOI:10.3969/j.issn.1005-202X.2025.02.012]
点击复制

改进YOLOv5s的堆叠医疗器械检测算法()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
42
期数:
2025年第2期
页码:
220-226
栏目:
医学信号处理与医学仪器
出版日期:
2025-01-20

文章信息/Info

Title:
Detection of stacked medical devices using improved YOLOv5s
文章编号:
1005-202X（2025）02-0220-07
作者:
田昌锐1; 廖薇1; 徐震2
1.上海工程技术大学电子电气工程学院， 上海 201620； 2.上海工程技术大学机械与汽车工程学院， 上海 201620
Author(s):
TIAN Changrui1;  LIAO Wei1;  XU Zhen2
1. School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China 2. School of Mechanical and Automotive Engineering, Shanghai University of Engineering Science, Shanghai 201620, China
关键词:
医疗器械; YOLOv5s; 注意力机制; α-DIOU; 深度学习
Keywords:
Keywords: medical device YOLOv5s attention mechanism α-DIOU deep learning
分类号:
R318；TP391.41
DOI:
DOI:10.3969/j.issn.1005-202X.2025.02.012
文献标志码:
A
摘要:
针对医疗器械堆叠问题和提升医疗器械识别准确率，提出一种改进YOLOv5s的医疗器械检测方法。首先使用C2f模块优化YOLOv5s网络提升模型识别精度，其次在特征融合网络引入SENet，提升模型对有效信息的关注度，最后在DIOU损失函数的基础上引入Alpha交并比（α?OU）构成α-DIOU，使边界框回归更加准确，精确定位图像中的医疗器械。实验结果表明，改进后的模型在验证集中对医疗器械的精确率、召回率、平均精度均值分别达到81.8%、93.7%、91.5%，相比于YOLOv5s模型分别提升3.2%、3.4%、4.6%。本研究方法简单有效，有望为医疗器械的检测方法提供新思路。
Abstract:
Abstract: A medical device detection method based on improved YOLOv5s was proposed to solve the problem of medical device stacking and further improve the detection accuracy of medical devices. The proposed method uses C2f module to optimize YOLOv5s network for improving the detection accuracy, introduces squeeze-and-excitation network into the feature fusion network for improving the models attention to effective information, and constructs α-DIOU by introducing Alpha intersection union ratio (α?OU) on the basis of the distance-intersection over union (DIOU) loss function, which makes the bounding box regression more accurate and enables the accurate detection of medical devices in the image. Experimental results show that the improved model has precision, recall rate and mean average precision of 81.8%, 93.7% and 91.5%, respectively, for medical device detection on the validation set, which are 3.2%, 3.4% and 4.6% higher than YOLOv5s model. The proposed method is simple and effective, and is expected to provide new ideas for the detection methods of medical devices.

相似文献/References:

[1]喻海中,陈兆学.基于双目视觉的医疗器械3D数据模型获取方法研究[J].中国医学物理学杂志,2014,31(01):4639.[doi:10.3969/j.issn.1005-202X.2014.01.011]
[2]陈星月,贾子彦,李青,等.基于改进YOLOv5s的免疫组化阳性细胞计数方法[J].中国医学物理学杂志,2025,42(2):167.[doi:DOI:10.3969/j.issn.1005-202X.2025.02.005]
　CHEN Xingyue,JIA Ziyan,LI Qing,et al.Improved YOLOv5s based method for immunohistochemically positive cell counting[J].Chinese Journal of Medical Physics,2025,42(2):167.[doi:DOI:10.3969/j.issn.1005-202X.2025.02.005]

备注/Memo

备注/Memo:
【收稿日期】2024-09-04 【基金项目】国家自然科学基金（62001282） 【作者简介】田昌锐，硕士研究生，研究方向：计算机视觉，E-mail: 1877132138@qq.com 【通信作者】廖薇，博士，副教授，研究方向：计算机视觉，E-mail: liaowei54@126.com；徐震，博士，副教授，研究方向：计算机视觉，E-mail: lcxuzhen@163.com
更新日期/Last Update: 2025-01-22