A Fully Decentralized Federated Learning Framework for Automated Image Segmentation in Cancer Radiotherapy
用于癌症放射治疗自动图像分割的完全去中心化联合学习框架
基本信息
- 批准号:10303437
- 负责人:
- 金额:$ 21.06万
- 依托单位:
- 依托单位国家:美国
- 项目类别:
- 财政年份:2021
- 资助国家:美国
- 起止时间:2021-09-01 至 2023-03-31
- 项目状态:已结题
- 来源:
- 关键词:AddressAdoptionAnatomyAppearanceAreaArtificial IntelligenceClientClinicalCollaborationsCommunitiesDataData AggregationData PoolingData SetData SourcesDatabasesDecentralizationDevelopmentEnvironmentEthicsGoalsHealth systemHealthcare SystemsHospitalsImageImage AnalysisInstitutionLearningLegalLiverLocationMachine LearningMedicalMedical ImagingMedical centerMedicineMethodsModelingNational Institute of Biomedical Imaging and BioengineeringOrganOwnershipParticipantPatientsPerformancePrivacyProcessRadiation OncologyRadiation therapyResearch PriorityResourcesRiskSchemeShapesSoftware ToolsSourceTechniquesTimeTrainingValidationX-Ray Computed Tomographyautomated segmentationbasecancer radiation therapyclinical practicedata sharingdeep learningdeep learning algorithmflexibilityhead and neck cancer patientimaging Segmentationimprovedinteroperabilityliver imagingmetropolitannovelopen sourcepatient privacypeerprecision medicinesoft tissuesoftware infrastructuresuccesstask analysistreatment planningtumor
项目摘要
PROJECT SUMMARY While the recent surge of artificial intelligence (AI) has made remarkable progress in
various image analysis tasks, their performance in a broad range of clinical environment is largely restricted by
the limited generalization capability when being applied to new data, primarily because most models have been
generated using data from a single institution or public datasets with limited training data. Aggregating data from
different institutions could improve model training, but such centralized data sharing is practically challenging
due to various technical, legal, privacy and data ownership barriers. This proposal aims to address these barriers
by developing a novel gossip federated learning (GFL) framework to build an effective AI model by learning from
different data sources without the need of sharing patient data. As compared to the traditional client/server
federated learning such as FedAvg, the proposed framework is fully decentralized in that the models trained in
local datasets will directly communicate to each other in a peer-to-peer manner, making our method more robust
and efficient. We will develop and evaluate the proposed scheme in the task of automated organ segmentation
in CT images for liver and head and neck (H&N) cancer patients treated with radiation therapy (RT) because
accurate, robust and efficient delineation of those organs at risk (OARs) is a clinically important but technically
challenging problem. We hypothesize that the model trained with our framework can achieve segmentation
performance not inferior to a model with data pooled from all the resources. The dynamics of our recently created
healthcare system mimic a diverse multi-institutional environment, which places us in an ideal setting to
systematically evaluate our framework. Our specific aims include: 1) Establish the GFL-based automated OAR
segmentation framework, and develop the supporting software infrastructure; 2) Optimize the GFL-based auto-
segmentation; 3) Evaluate GFL-based OAR segmentation framework with 400 liver and 400 H&N cancer patients
collected from four hospitals within a metropolitan health system. This proposal addresses two key research
priorities for NIBIB: machine learning based segmentation and approaches that facilitate interoperability among
annotations used in image training databases. The success of this project will substantially increase the number
and variety of data for model training without sacrificing the patient privacy, and thus improve the performance
and generalization of the segmentation model on new data. We will open-source this framework, which may
enable a larger scale of multi-institutional collaboration and could expedite the clinical adoption of AI-driven auto-
segmentation in RT. More importantly, this framework provides a flexible and robust solution to the primary
barrier of applying AI to the medical domain where learning on multi-institutional data sharing is impeded by
patient privacy concerns, and is expected to have a catalytic impact on precision medicine by generalizing it to
broader applications within medicine where a model needs to learn across multi-institutional data without
sacrificing patient privacy.
项目摘要 虽然最近人工智能 (AI) 的蓬勃发展在以下方面取得了显着进展:
各种图像分析任务,它们在广泛的临床环境中的性能在很大程度上受到限制
应用于新数据时泛化能力有限,主要是因为大多数模型已经被
使用来自单个机构的数据或训练数据有限的公共数据集生成。聚合数据来自
不同的机构可以改进模型训练,但这种集中的数据共享实际上具有挑战性
由于各种技术、法律、隐私和数据所有权障碍。该提案旨在解决这些障碍
通过开发一种新颖的八卦联邦学习(GFL)框架,通过学习来构建有效的人工智能模型
不同的数据源,无需共享患者数据。与传统的客户端/服务器相比
联邦学习,例如 FedAvg,所提出的框架是完全去中心化的,因为训练的模型
本地数据集将以点对点的方式直接相互通信,使我们的方法更加稳健
和高效。我们将在自动器官分割任务中开发和评估所提出的方案
在接受放射治疗 (RT) 治疗的肝癌和头颈 (H&N) 癌症患者的 CT 图像中,因为
准确、稳健和有效地描绘那些处于危险中的器官(OAR)在临床上很重要,但在技术上
具有挑战性的问题。我们假设用我们的框架训练的模型可以实现分割
性能不亚于从所有资源汇集数据的模型。我们最近创建的动态
医疗保健系统模仿多元化的多机构环境,这使我们处于理想的环境中
系统地评估我们的框架。我们的具体目标包括:1)建立基于GFL的自动化OAR
细分框架,开发配套软件基础设施; 2)优化基于GFL的自动
分割; 3) 使用 400 名肝癌患者和 400 名 H&N 癌症患者评估基于 GFL 的 OAR 分割框架
从大都市卫生系统内的四家医院收集。该提案涉及两项关键研究
NIBIB 的优先事项:基于机器学习的细分和促进互操作性的方法
图像训练数据库中使用的注释。该项目的成功将大幅增加
和各种数据用于模型训练而不牺牲患者隐私,从而提高性能
以及新数据上分割模型的推广。我们将开源这个框架,这可能
实现更大规模的多机构协作,并可以加快人工智能驱动的自动驾驶技术的临床采用
RT 中的分割。更重要的是,该框架为主要问题提供了灵活而强大的解决方案
将人工智能应用到医疗领域的障碍是多机构数据共享的学习受到阻碍
患者隐私问题,并有望通过将其推广到对精准医疗产生催化影响
医学领域更广泛的应用,其中模型需要跨多个机构的数据进行学习,而无需
牺牲患者隐私。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Yading Yuan其他文献
Yading Yuan的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
相似海外基金
Investigating the Adoption, Actual Usage, and Outcomes of Enterprise Collaboration Systems in Remote Work Settings.
调查远程工作环境中企业协作系统的采用、实际使用和结果。
- 批准号:
24K16436 - 财政年份:2024
- 资助金额:
$ 21.06万 - 项目类别:
Grant-in-Aid for Early-Career Scientists
WELL-CALF: optimising accuracy for commercial adoption
WELL-CALF:优化商业采用的准确性
- 批准号:
10093543 - 财政年份:2024
- 资助金额:
$ 21.06万 - 项目类别:
Collaborative R&D
Unraveling the Dynamics of International Accounting: Exploring the Impact of IFRS Adoption on Firms' Financial Reporting and Business Strategies
揭示国际会计的动态:探索采用 IFRS 对公司财务报告和业务战略的影响
- 批准号:
24K16488 - 财政年份:2024
- 资助金额:
$ 21.06万 - 项目类别:
Grant-in-Aid for Early-Career Scientists
ERAMET - Ecosystem for rapid adoption of modelling and simulation METhods to address regulatory needs in the development of orphan and paediatric medicines
ERAMET - 快速采用建模和模拟方法的生态系统,以满足孤儿药和儿科药物开发中的监管需求
- 批准号:
10107647 - 财政年份:2024
- 资助金额:
$ 21.06万 - 项目类别:
EU-Funded
Assessing the Coordination of Electric Vehicle Adoption on Urban Energy Transition: A Geospatial Machine Learning Framework
评估电动汽车采用对城市能源转型的协调:地理空间机器学习框架
- 批准号:
24K20973 - 财政年份:2024
- 资助金额:
$ 21.06万 - 项目类别:
Grant-in-Aid for Early-Career Scientists
Ecosystem for rapid adoption of modelling and simulation METhods to address regulatory needs in the development of orphan and paediatric medicines
快速采用建模和模拟方法的生态系统,以满足孤儿药和儿科药物开发中的监管需求
- 批准号:
10106221 - 财政年份:2024
- 资助金额:
$ 21.06万 - 项目类别:
EU-Funded
De-Adoption Beta-Blockers in patients with stable ischemic heart disease without REduced LV ejection fraction, ongoing Ischemia, or Arrhythmias: a randomized Trial with blinded Endpoints (ABbreviate)
在没有左心室射血分数降低、持续性缺血或心律失常的稳定型缺血性心脏病患者中停用β受体阻滞剂:一项盲法终点随机试验(ABbreviate)
- 批准号:
481560 - 财政年份:2023
- 资助金额:
$ 21.06万 - 项目类别:
Operating Grants
Our focus for this project is accelerating the development and adoption of resource efficient solutions like fashion rental through technological advancement, addressing longer in use and reuse
我们该项目的重点是通过技术进步加快时装租赁等资源高效解决方案的开发和采用,解决更长的使用和重复使用问题
- 批准号:
10075502 - 财政年份:2023
- 资助金额:
$ 21.06万 - 项目类别:
Grant for R&D
Engage2innovate – Enhancing security solution design, adoption and impact through effective engagement and social innovation (E2i)
Engage2innovate — 通过有效参与和社会创新增强安全解决方案的设计、采用和影响 (E2i)
- 批准号:
10089082 - 财政年份:2023
- 资助金额:
$ 21.06万 - 项目类别:
EU-Funded
Collaborative Research: SCIPE: CyberInfrastructure Professionals InnoVating and brOadening the adoption of advanced Technologies (CI PIVOT)
合作研究:SCIPE:网络基础设施专业人员创新和扩大先进技术的采用 (CI PIVOT)
- 批准号:
2321091 - 财政年份:2023
- 资助金额:
$ 21.06万 - 项目类别:
Standard Grant