Distributed Learning of Deep Learning Models for Cancer Research

癌症研究深度学习模型的分布式学习

• 批准号: 10018827
• 负责人: Jayashree Kalpathy-Cramer
• 金额: $ 39.48万
• 依托单位: STANFORD UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-09-16 至 2022-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10018827
• 关键词: Address; Adopted; Advanced Malignant Neoplasm; Brain; Cancer Model; Cancer Patient; Classification; Clinical; Clinical Data; Collaborations; Collection; Communities; Computational algorithm; Computer software; Custom; Data; Data Scientist; Data Security; Data Set; Decision Making; Development; Diagnosis; Disease; Ecosystem; Engineering; Ensure; Equipment; Face; Feedback; Fostering; Glioma; Health; Heterogeneity; Hospitals; Image; Impairment; Information Networks; Institution; Intuition; Isocitrate Dehydrogenase; Label; Lead; Magnetic Resonance Imaging; Malignant Neoplasms; Malignant neoplasm of brain; Medical Imaging; Methods; Modeling; Mutation; Patient imaging; Patients; Performance; Periodicity; Phenotype; Privacy; Rare Diseases; Research; Research Personnel; Resolution; Resources; Risk; Running; Secure; Security; Selection for Treatments; Site; System; Techniques; Technology; Testing; Training; Translating; Update; Variant; Weight; Work; anticancer research; base; cancer care; cancer type; care outcomes; clinical care; clinical decision support; clinical decision-making; cohort; cost; data privacy; data quality; data sharing; deep learning; improved; innovation; inter-institutional; learning strategy; molecular marker; multidisciplinary; novel; patient population; patient privacy; radiologist; research to practice; software systems; survival prediction; tool

Project Summary Deep learning methods are showing great promise for advancing cancer research and could potentially improve clinical decision making in cancers such as primary brain glioma, where deep learning models have recently shown promising results in predicting isocitrate dehydrogenase (IDH) mutation and survival in these patients. A major challenge thwarting this research, however, is the requirement for large quantities of labeled image data to train deep learning models. Efforts to create large public centralized collections of image data are hindered by barriers to data sharing, costs of image de-identification, patient privacy concerns, and control over how data are used. Current deep learning models that are being built using data from one or a few institutions are limited by potential overfitting and poor generalizability. Instead of centralizing or sharing patient images, we aim to distribute the training of deep learning models across institutions with computations performed on their local image data. Although our preliminary results demonstrate the feasibility of this approach, there are three key challenges to translating these methods into research practice: (1) data is heterogeneous among institutions in the amount and quality of data that could impair the distributed computations, (2) there are data security and privacy concerns, and (3) there are no software packages that implement distributed deep learning with medical images. We tackle these challenges by (1) optimizing and expanding our current methods of distributed deep learning to tackle challenges of data variability and data privacy/security, (2) creating a freely available software system for building deep learning models on multi- institutional data using distributed computation, and (3) evaluating our system to tackle deep learning problems in example use cases of classification and clinical prediction in primary brain cancer. Our approach is innovative in developing distributed deep learning methods that will address variations in data among different institutions, that protect patient privacy during distributed computations, and that enable sites to discover pertinent datasets and participate in creating deep learning models. Our work will be significant and impactful by overcoming critical hurdles that researchers face in tapping into multi-institutional patient data to create deep learning models on large collections of image data that are more representative of disease than data acquired from a single institution, while avoiding the hurdles to inter-institutional sharing of patient data. Ultimately, our methods will enable researchers to collaboratively develop more generalizable deep learning applications to advance cancer care by unlocking access to and leveraging huge amounts of multi-institutional image data. Although our clinical use case in developing this technology is primary brain cancer, our methods will generalize to all cancers, as well as to other types of data besides images for use in creating deep learning models, and will ultimately lead to robust deep learning applications that are expected to improve clinical care and outcomes in many types of cancer.

项目摘要 深度学习方法表现出巨大的前景，可以推进癌症研究，并有可能 改善癌症（例如原发性脑神经胶质瘤）的临床决策，深度学习模型具有 最近显示出有希望的结果，可以预测这些异氯酸酯脱氢酶（IDH）突变和其中的存活率 患者。但是，挫败这项研究的一个重大挑战是对大量标签的要求 图像数据训练深度学习模型。努力创建大量的图像数据集中集中集合 受到数据共享障碍，图像去识别成本，患者隐私问题和控制的阻碍 关于如何使用数据。当前使用一个或几个数据的数据正在构建的当前深度学习模型 机构受到潜在过度拟合和易于推广性的限制。而不是集中或共享患者 图像，我们旨在通过计算在机构上分发深度学习模型的培训 在其本地图像数据上执行。尽管我们的初步结果证明了这一点的可行性 方法，将这些方法转化为研究实践存在三个关键挑战：（1）数据是 机构之间的异质数据可能会损害分布式的数据的数量和质量 计算，（2）存在数据安全和隐私问题，（3）没有软件包 用医学图像实施分布式深度学习。我们通过（1）优化解决这些挑战和 扩展我们当前的分布式深度学习方法，以应对数据可变性和数据的挑战 隐私/安全性，（2）创建一个免费可用的软件系统 使用分布式计算的机构数据，以及（3）评估我们的系统以解决深度学习问题 例如，在原发性脑癌中分类和临床预测的用例。我们的方法是 开发分布式深度学习方法的创新性，该方法将解决不同的数据的变化 机构，保护在分布式计算过程中保护患者隐私的机构，并使站点能够发现 相关数据集并参与创建深度学习模型。我们的工作将是巨大而有影响力的 通过克服研究人员在利用多机构的患者数据时所面临的关键障碍以创建 大量图像数据收集的深度学习模型比数据更具疾病代表性 从单个机构获得，同时避免了障碍跨机构分享患者数据。 最终，我们的方法将使研究人员能够协作开发更广泛的深度学习 通过解锁访问并利用大量多机构的申请来提高癌症护理 图像数据。尽管我们开发该技术的临床用例是原发性脑癌，但我们的方法 将推广到所有癌症，以及除图像以外用于创建深度学习外的其他类型的数据 模型，并最终会导致强大的深度学习应用，这些应用有望改善临床护理 以及许多类型的癌症的结果。