摘要
本文针对医院PACS(Picture Archiving and Communication Systems,影像存档与通信系统)影像数据存储成本高、扩展性差、管理复杂且与云存储对接困难等问题,提出基于智能网关优化的医疗影像云存储解决方案。该方案融合智能存储网关、云专线和对象存储,借助rclone开源存储网关实现协议转换,实现PACS影像数据上传至对象存储。同时,针对存储网关内存消耗问题,采用Python脚本调用API清除旧文件缓存、重建目录缓存,结合AI驱动的LSTM时序预测算法和K-means聚类算法进行缓存优化,提升缓存命中率并降低内存占用。为医院提供了安全、快速、稳定的数据上云存储方案。
This paper proposes an optimized medical image cloud storage solution based on an intelligent gateway to solve the problems of high storage cost,poor scalability,complex management,and difficult docking with cloud storage of hospital PACS image data.The solution integrates an intelligent storage gateway,cloud dedicated line,and object storage,and realizes protocol conversion through the rclone open-source storage gateway to enable PACS image data to be uploaded to the object storage.Meanwhile,aiming at the memory consumption problem of the storage gateway,a Python script is used to call the API to clear the old file cache and rebuild the directory cache.Combined with the AI-driven LSTM time series prediction algorithm and K-means clustering algorithm,cache optimization is carried out to improve the cache hit rate and reduce memory occupation,providing a safe,fast,and stable data cloud storage solution for hospitals.
作者
徐冬卫
陈杰君
XU Dongwei;CHEN Jiejun(China Mobile Communications Group Jiangsu Co.,Ltd.Zhenjiang Branch)
出处
《江苏通信》
2025年第3期63-67,共5页
Jiangsu Communication
