智能科学与技术学报2025，Vol.7Issue(3)：396-407,12.DOI:10.11959/j.issn.2096-6652.202535
RadiFlow:AI Agents重构放射科工作流程
RadiFlow:AI agents reconstructing radiology workflow
摘要
Abstract
With the rapid advancement of modern medicine and the increasing demand for clinical diagnosis and treat-ment,radiology,as a core department of clinical diagnostics,faces multiple challenges.These are particularly reflected in the complexity of patient scheduling across multi-device environments,workflow inefficiencies caused by manual opera-tions,the lack of multimodal clinical information integration for diagnostic reasoning,and the time-consuming nature of report writing.To address these issues,RadiFlow,an end-to-end intelligent radiology workflow system based on Agentic AI,was proposed.The system was composed of four cooperative agents:scheduling agents,radiological examination agents,diagnostic reasoning agents,and report generation and interpretation agents.Through agents collaboration,Radi-Flow can efficiently handle complex patient scheduling and cross-regional equipment allocation,achieve standardized and fault-tolerant imaging acquisition,provide accurate diagnostic assistance,and automatically generate and interpret standardized reports.However,this work remains a preliminary research report,validated through case studies.RadiFlow demonstrates significant potential for improving radiology efficiency,diagnostic accuracy,patient satisfaction,and reducing the workload of healthcare professionals.Future work will extend this framework to build a multi-agent radiology system for real-world deployment and validation,aiming to provide innovative insights into developing a more intelligent and ef-ficient radiology practice.关键词
智能体/放射科/人工智能/大语言模型Key words
agent/radiology/artificial intelligence/large language model分类
信息技术与安全科学引用本文复制引用
张濛濛,薛华丹,王飞跃,丛福泽,王静,张慧,李娟娟,倪清桦,丁炫婷,田永林,吕宜生..RadiFlow:AI Agents重构放射科工作流程[J].智能科学与技术学报,2025,7(3):396-407,12.基金项目
国家自然科学基金项目(No.82372051) （No.82372051）
澳门特别行政区科学与技术发展基金(No.0093/2023/RIA2,No.0145/2023/RIA3,No.0157/2024/RIA2) （No.0093/2023/RIA2,No.0145/2023/RIA3,No.0157/2024/RIA2）
北京市自然科学基金海淀联合基金(No.L222099) （No.L222099）
首都卫生发展科研专项(No.2024-2-4015) （No.2024-2-4015）
四川省科技厅重点研发计划项目(No.2024YFHZ0011)The National Natural Science Foundation of China(No.82372051),The Science and Technology Develop-ment Fund,Macao SAR(No.0093/2023/RIA2,No.0145/2023/RIA3,No.0157/2024/RIA2),Beijing Natural Science Foundation(No.L222099),Capital's Funds for Health Improvement and Research(No.2024-2-4015),Sichuan Key-Area Research and Develop-ment Program(No.2024YFHZ0011) （No.2024YFHZ0011）
