Federated Learning for Optimal Decision Making in Radiotherapy Using Panomics Analytics

使用全景组学分析进行放射治疗最佳决策的联邦学习

• 批准号: 10417829
• 负责人: Issam M. El Naqa
• 金额: $ 15.87万
• 依托单位: H. LEE MOFFITT CANCER CTR & RES INST
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-06-06 至 2024-05-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10417829
• 关键词: Address; Algorithms; Awareness; Bayesian Network; Benchmarking; Benefits and Risks; Big Data; Big Data Methods; Biological Markers; Case Study; Characteristics; Clinical; Clinical Decision Support Systems; Complex; Computer software; Computers; Data; Data Aggregation; Data Set; Decision Making; Decision Support Systems; Disease; Dose; Environment; Ethics; Genomics; Goals; Graph; Hostage; Human; Image; Improve Access; Infrastructure; Institution; Intelligence; Learning; Legal; Liver; Lung; Machine Learning; Malignant Neoplasms; Malignant neoplasm of liver; Malignant neoplasm of lung; Methods; Modeling; Modernization; Nature; Normal tissue morphology; Outcome; Patient Preferences; Patients; Performance; Physicians; Play; Predictive Factor; Privacy; Procedures; Process; Proteomics; Psychological reinforcement; Quality of life; Radiation Dose Unit; Radiation therapy; Radiology Specialty; Reaction Time; Regimen; Rewards; Risk; Role; Sample Size; Schedule; Site; Software Tools; Supervision; System; Techniques; Testing; Time; Toxic effect; Training; Treatment Protocols; Uncertainty; Work; application programming interface; base; clinical decision support; clinical practice; computer human interaction; cost effective; data sharing; deep learning; deep reinforcement learning; demographics; experience; federated learning; fractionated radiation; heuristics; high reward; high risk; image guided; improved; individual patient; irradiation; knowledge base; learning algorithm; learning strategy; machine learning algorithm; machine learning method; machine learning model; neoplastic cell; open source; outcome prediction; personalized decision; personalized medicine; population based; predicting response; predictive modeling; profiles in patients; prototype; radiation risk; radiomics; rapid growth; response; socioeconomics; software systems; success; supervised learning; support tools; therapy outcome; tool; treatment choice; treatment duration; treatment optimization; treatment response; usability; user-friendly

The complex environment of modern radiation therapy (RT) comprises data from a rich combination of patient- specific information including: demographics, physical characteristics of high-energy dose, features subsequent to repeated application of image-guidance (radiomics), and biological markers (genomics, proteomics, etc.), generated before and/or over a treatment period that can span few days to several weeks. Rapid growth of these available and untapped “pan-Omics” data, invites ample opportunities for Big data analytics to deliver on the promise of personalized medicine in RT. This is particularly true in promising but high-risk RT procedures such as stereotactic body RT (SBRT), which have witnessed tremendous expansion due to clinical successes in early disease stages and socio-economic benefits of shortened high dose treatments. This has led to the desire to exploit these treatments into more advanced stages of cancer, however, the unknown risks associated with increased toxicities hamper its potential. Therefore, robust clinical decision support systems (CDSSs) capable of exploring the complex pan-Omics interaction landscape with the goal of exploiting known principles of treatment response before and during the course of fractionated RT are urgently needed. The long-term goal of this project is to overcome barriers related to prediction uncertainties and human-computer interactions, which are currently limiting the ability to make personalized clinical decisions for real-time response-based adaptation in radiotherapy from available data. To meet this need and overcome current challenges, we will develop and quantitively evaluate: (1) federated graph-based supervised machine learning algorithms for robust prediction outcomes before and during RT; (2) federated deep reinforcement learning to dynamically optimize treatment adaptation; and (3) a user-centered software prototype for RT decision support using the extendable XNAT platform, with the broader goal of building a comprehensive real-time framework for outcome modeling and response-based adaption in RT. We hypothesize that the use of advanced federated machine learning techniques and user-centered tools will unlock the potentials to move from current population-based approaches limited by subjective experiences and heuristic rules into robust, patient-specific, user-friendly CDSSs. This approach and its corresponding software tools will be tested within two clinical RT sites of lung and liver cancers, to demonstrate its versatility and highlight pertinent human-computer factors and cancer specific issues. Impact statement: Patient-specific big data are now available before and/or during RT courses, offering new and untapped opportunities for personalized treatment. This study will overcome current shortcomings of population-based approaches and data underuse in current RT practice by investigating and developing a federated user-centered, personalized CDSS with the need for centralized data sharing and test its performance in rewarding but high-risk RT scenarios. The approach is also applicable to other modern cancer regimens.

现代放射疗法（RT）的复杂环境包括来自患者丰富组合的数据 特定信息，包括：人口统计学，高能剂量的物理特征 重复应用图像引导（放射线学）和生物标记（基因组学，蛋白质组学等）， 在治疗期之前和/或可能跨越几天到几周的治疗期。这些快速增长 可用和未开发的“泛词”数据，邀请了大数据分析的充足机会。 在RT中对个性化医学的承诺。在承诺中尤其如此，但是高风险的RT程序此类 正如立体定向身体RT（SBRT），由于早期的临床成功而见证了巨大的扩张 疾病阶段和缩短高剂量治疗的社会经济益处。这导致了渴望 但是，这些治疗方法将这些治疗方法分为更高级的癌症，但是，与之相关的未知风险 毒性增加阻碍了其潜力。因此，强大的临床决策支持系统（CDSS） 探索复杂的泛媒体交互环境，目的是利用已知原理 迫切需要在分离RT过程中和期间的治疗反应。长期目标 该项目旨在克服与预测不确定性和人类计算机相互作用有关的障碍，这些障碍 目前正在限制做出个性化临床决策以进行实时响应适应的能力 在可用数据的放射疗法中。为了满足这一需求并克服当前的挑战，我们将发展和 定量评估：（1）基于图形的监督机器学习算法可靠的预测 RT之前和期间的结果； （2）联合深钢筋学习以动态优化治疗 适应; （3）使用可扩展的XNAT的以用户为中心的软件原型用于RT决策支持 平台，更广泛的目标是建立一个全面的实时框架，用于结果建模和 基于响应的适应RT。我们假设使用高级联合机器学习 技术和以用户为中心的工具将解锁从当前基于人群的方法中转移的潜力 受主题经验和启发式规则的限制，可用于鲁棒，特定于患者的用户友好的CDSSS。这 方法及其相应的软件工具将在肺癌和肝癌的两个临床RT部位进行测试， 证明其多功能性并突出相关的人类计算机因素和特定于癌症的问题。 影响声明：现在和/或在RT课程期间提供特定于患者的大数据，提供新的 以及未开发的个性化治疗机会。这项研究将克服当前的缺点 基于人群的方法和数据在当前的RT实践中通过调查和开发 联合以用户为中心的个性化CDS，需要集中数据共享并测试其性能 在奖励但高风险的RT场景中。该方法也适用于其他现代癌症方案。