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 深度学习方法在推进癌症研究方面显示出巨大的潜力， 改善癌症（如原发性脑胶质瘤）的临床决策，其中深度学习模型 最近在预测异柠檬酸脱氢酶（IDH）突变和这些患者的存活率方面显示出有希望的结果。 患者然而，阻碍这项研究的一个主要挑战是需要大量的标记 图像数据来训练深度学习模型。努力创建大型公共集中图像数据集 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 如何使用数据。当前的深度学习模型正在使用来自一个或几个 机构受到潜在的过度拟合和较差的普遍性的限制。而不是集中或共享患者 图像，我们的目标是通过计算将深度学习模型的训练分布在机构之间。 在本地图像数据上执行。虽然我们的初步结果证明了这一点的可行性， 方法，有三个关键的挑战，将这些方法转化为研究实践：（1）数据是 机构之间在数据的数量和质量方面存在差异，这可能会损害分布式 计算，（2）存在数据安全和隐私问题，以及（3）没有软件包， 用医学图像实现分布式深度学习。我们通过以下方式应对这些挑战：（1）优化和 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 隐私/安全，（2）创建一个免费的软件系统，用于在多个 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 在原发性脑癌中分类和临床预测的示例使用情况中。我们的做法是 在开发分布式深度学习方法方面具有创新性，这些方法将解决不同组织之间数据的差异， 机构，在分布式计算过程中保护患者隐私，并使网站能够发现 相关数据集，并参与创建深度学习模型。我们的工作将是重要和有影响力的 通过克服研究人员在利用多机构患者数据以创建 深度学习在大量图像数据上建立模型，这些图像数据比数据更能代表疾病 从单一机构获得，同时避免了机构间共享患者数据的障碍。 最终，我们的方法将使研究人员能够合作开发更具普遍性的深度学习 通过解锁和利用大量的多机构应用程序来推进癌症护理 图像数据。虽然我们开发这项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，以及图像以外的其他类型的数据，用于创建深度学习 模型，并最终导致强大的深度学习应用程序，预计将改善临床护理 和许多癌症的结果。