摘要
设计了一种基于目标检测的肺癌早期智能筛查系统,其运用YOLOv5s模型对去噪后肺CT图像中的肺结节进行目标检测,以实现肺癌早期的智能筛查。数据分析显示,试验的准确率、召回率无线接近于1,证明了肺结节检测的准确率较高,验证了肺癌早期智能筛查系统的可靠性。该系统既能降低医师的工作难度,又能提升肺癌诊断的准确率,可成为辅助肺癌早期诊断的重要工具。
A lung cancer early intelligent screening system based on object detection was designed,which uses the YOLOv5s model to detect lung nodules in denoised lung CT images,in order to achieve early intelligent screening of lung cancer.Data analysis shows that the accuracy and recall of the experiment are close to 1,which proves the high accuracy of lung nodule detection and verifies the reliability of the early intelligent screening system for lung cancer.This system can not only reduce the workload of physicians,but also improve the accuracy of lung cancer diagnosis,making it an important tool to assist in the early diagnosis of lung cancer.
作者
张春茜
刘华康
任俊龙
栗梦媛
张丽娟
回振桥
ZHANG Chunqian;LIU Huakang;REN Junlong;LI Mengyuan;ZHANG Lijuan;HUI Zhenqiao(Department of Electrical Automation,Hebei University of Water Resources and Electric Engineering,Cangzhou,Hebei 061001,China;Infectious Diseases Department,Hebei Cangzhou Hospital of Integrated Traditional Chinese Medicine and Western Medicine,Cangzhou,Hebei 061001,China)
出处
《自动化应用》
2024年第2期190-192,共3页
Automation Application
基金
2022年河北省教育厅科学研究项目资助(ZC2022018)。