FEDMEKI:一个通过联邦知识注入扩展医学基础模型的基准
FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injection
AI总结:
本研究推出联邦医学知识注入基准FEDMEKI,采用跨机构联邦学习规避隐私法规限制,支持多模态多任务医学数据的去中心化训练,可在保护隐私的同时提升医学基础模型能力,为医疗领域基础模型应用设立新基准。
摘要:
本研究推出了联邦医学知识注入(Federated Medical Knowledge Injection,FEDMEKI)平台,这是一个全新基准,旨在解决隐私约束下将医学知识整合到基础模型所面临的独特挑战。通过采用跨机构联邦学习方法,FEDMEKI规避了集中式数据收集相关的问题——这类数据收集通常受美国《健康保险流通与责任法案》(Health Insurance Portability and Accountability Act,HIPAA)等健康法规禁止。\n该平台经过精心设计,可处理多站点、多模态、多任务的医学数据,涵盖7种医学模态,包括图像、信号、文本、实验室检测结果、生命体征、输入变量和输出变量。用于验证FEDMEKI的 curated 数据集覆盖8项医学任务,包括6项分类任务(肺部混浊检测、COVID-19检测、心电图(electrocardiogram,ECG)异常检测、死亡率预测、脓毒症预测、纵隔增宽检测)和2项生成任务(医学视觉问答(medical visual question answering,MedVQA)和ECG噪声净化)。\n这个综合数据集被划分到多个客户端,以支持16种基准方法下的去中心化训练过程。FEDMEKI不仅能保护数据隐私,还能通过让医学基础模型在不直接接触数据的情况下学习更广泛的医学知识,提升其能力,从而为基础模型在医疗保健领域的应用设立了新基准。
英文摘要:
This study introduces the Federated Medical Knowledge Injection (FEDMEKI) platform, a new benchmark designed to address the unique challenges of integrating medical knowledge into foundation models under privacy constraints. By leveraging a cross-silo federated learning approach, FEDMEKI circumvents the issues associated with centralized data collection, which is often prohibited under health regulations like the Health Insurance Portability and Accountability Act (HIPAA) in the USA. The platform is meticulously designed to handle multi-site, multi-modal, and multi-task medical data, which includes 7 medical modalities, including images, signals, texts, laboratory test results, vital signs, input variables, and output variables. The curated dataset to validate FEDMEKI covers 8 medical tasks, including 6 classification tasks (lung opacity detection, COVID-19 detection, electrocardiogram (ECG) abnormal detection, mortality prediction, sepsis prediction, and enlarged cardiomediastinum detection) and 2 generation tasks (medical visual question answering (MedVQA) and ECG noise clarification). This comprehensive dataset is partitioned across several clients to facilitate the decentralized training process under 16 benchmark approaches. FEDMEKI not only preserves data privacy but also enhances the capability of medical foundation models by allowing them to learn from a broader spectrum of medical knowledge without direct data exposure, thereby setting a new benchmark in the application of foundation models within the healthcare sector.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。