探索联邦学习技术在医疗领域的创新应用  

Exploring the Innovative Application of Federated Learning Technology in the Medical Field

作　　者：李斌[1] 顾正敏 李向文 崔绍华 LI Bin;GU Zhengmin;LI Xiangwen;CUI Shaohua(The First Hospital of China Medical University,Shenyang Liaoning 110002;Shenyang NSFOCUS Network Security Technology Co.,Ltd.,Shenyang Liaoning 110167)

机构地区：[1]中国医科大学附属第一医院,辽宁沈阳110002 [2]沈阳绿盟网络安全技术有限公司,辽宁沈阳110167

出　　处：《软件》2023年第9期120-123,共4页Software

摘　　要：随着医疗数据的积累和数字化的发展,医疗领域对于数据的分析和利用变得越来越重要。然而,基于医疗数据的特殊性,它涉及了大量的患者隐私信息,如个人身份、病历、诊断结果等,对数据利用过程中的隐私保护提出了更为严格的要求。隐私计算作为一种保护隐私的技术手段,近年来在医疗领域得到了广泛应用。本文旨在探讨基于隐私计算的联邦学习技术在医疗领域的应用现状、优势、挑战和未来发展方向。With the accumulation of medical data and the development of digitization,the analysis and utilization of data have become increasingly important in the medical field.However,due to the sensitive nature of medical data,which involves a large amount of private patient information such as personal identities,medical records,and diagnostic results,there are stricter requirements for privacy protection during data utilization.Privacy-preserving computation,as a technical means of protecting privacy,has been widely applied in the medical field in recent years.This paper aims to explore the current applications,advantages,challenges,and future development directions of privacy-preserving federated learning technology in the medical field.

关 键 词：隐私计算 联邦学习 图像分析 数据共享 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]