改进YOLOv5框架的血细胞检测算法  

Improved YOLOv5 Algorithm for Blood Cell Detection

作　　者：张昊 郑广海[1] 张鑫 吕娜 ZHANG Hao;ZHENG Guang-Hai;ZHANG Xin;LYU Na(Software Technology Institute,Dalian Jiaotong University,Dalian 116052,China)

机构地区：[1]大连交通大学软件学院,大连116052

出　　处：《计算机系统应用》2023年第5期123-131,共9页Computer Systems & Applications

基　　金：辽宁省教育厅服务地方项目(JDL2020004)。

摘　　要：对于血液中红细胞、白细胞、血小板等成分的观察和计数是临床医学诊断的重要依据.血细胞的异常意味着可能存在凝血异常、感染、炎症等与血液相关的问题.人工检测血细胞不仅耗费人力,且容易出现误检、漏检的情况.因此,针对上述情况,提出一种新颖的血细胞检测算法—YOLOv5-CBF.该算法在YOLOv5框架的基础上,通过在主干网络中加入坐标注意力(coordinate attention,CA)机制,提高检测精度;将颈部网络中的FPN+PAN结构中改为结合了跨尺度特征融合方法(bidirectional feature pyramid network,BiFPN)思想的特征融合结构,使目标多尺度特征有效融合;在三尺度检测的基础上增加了一个小目标检测层,提高对数据集中小目标血小板的识别精度.通过在数据集BCCD上进行的大量的实验结果表明:与传统的YOLOv5算法相比较,该算法在3类血细胞检测的平均精度提升2.7%,试验效果良好,该算法对血细胞检测具有很高的实用性.The observation and counting of red blood cells,white blood cells,and platelets in the blood are an important basis for clinical medical diagnosis.Abnormal blood cells mean that there may be blood-related problems such as clotting abnormalities,infections,and inflammation.As artificial blood cell detection is not only labor-intensive but also prone to false detection and misses,a novel blood cell detection algorithm YOLOv5-CBF is proposed to address the above problem.On the basis of the YOLOv5 framework,the algorithm improves detection accuracy by adding a coordinate attention(CA)mechanism to the backbone network.The FPN+PAN structure in the neck network is changed to the feature fusion structure combining the idea of the bidirectional feature pyramid network(BiFPN),a cross-scale feature fusion method;in this way,the multi-scale features of the target can be effectively fused.In addition to the three-scale detection,a small target detection layer is added to improve the identification accuracy of small target platelets in the dataset.The results of a large number of experiments conducted on the dataset BCCD show that the algorithm presents an average accuracy improvement of 2.7%in the detection of the three blood cells compared to the conventional YOLOv5 algorithm,demonstrating good performance.The algorithm is highly practical for blood cell detection.

关 键 词：深度学习 血细胞检测 YOLOv5 多尺度特征融合 注意力机制 

分 类 号：R446.113[医药卫生—诊断学] TP391.41[医药卫生—临床医学]