Robust AI to develop risk models in retinopathy of prematurity using deep learning

强大的人工智能利用深度学习开发早产儿视网膜病变的风险模型

• 批准号: 10254429
• 负责人: Jayashree Kalpathy-Cramer
• 金额: $ 19.69万
• 依托单位: MASSACHUSETTS GENERAL HOSPITAL
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-30 至 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10254429
• 关键词: Affect; Architecture; Blindness; Blood Vessels; Childhood; Clinical; Collection; Communities; Data; Data Set; Data Storage and Retrieval; Databases; Disease; Drops; Ecosystem; Eye diseases; Future; Gestational Age; Grant; Heterogeneity; Image; Infant; Institution; Intellectual Property; Label; Lead; Learning; Left; Logistic Regressions; Low Birth Weight Infant; Machine Learning; Measures; Methods; Modeling; Patient imaging; Patients; Performance; Premature Birth; Premature Infant; Protocols documentation; Publishing; Rare Diseases; Regulation; Research; Research Personnel; Retina; Retinal Detachment; Retinopathy of Prematurity; Risk; Risk Factors; Sensitivity and Specificity; Severities; Severity of illness; Site; Techniques; Testing; Time; Training; Update; Vascular Diseases; Vascular Proliferation; Weight; Work; base; clinical decision-making; clinical risk; cohort; convolutional neural network; cost; data de-identification; data repository; data sharing; deep learning; deep learning algorithm; experience; improved; individual patient; large datasets; learning strategy; multiple data sources; neovascular; open source tool; patient population; patient privacy; patient subsets; predictive modeling; repository; risk prediction; risk prediction model; screening guidelines; secondary analysis; supplemental oxygen

ROP is a retinal neovascular disease affecting preterm infants, and is a leading cause of childhood blindness worldwide. Known clinical risk factors include preterm birth, low birthweight and use of supplemental oxygen but improved risk models are needed to identify infants that progress to treatment requiring disease and blindness. Deep learning techniques have been used to successfully identify “plus” disease in multi- institutional cohorts and to provide a continuous measure of disease severity. A major limitation of deep learning, however, is the need for large amounts of well curated datasets. Other limitations include overfitting and “brittleness” that can cause model performance to drop on external data. There are, however, numerous barriers to building and hosting these large central repositories with multi-institutional data required for robust deep learning including concerns about data sharing, regulations costs, patient privacy and intellectual property. In this project, we aim to demonstrate the utility of distributed/federated deep learning approaches where the data are located within institutions, but model parameters are shared with a central server. 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. Specifically, we seek to build robust risk models for predicting treatment requiring disease. Two large cohorts will be used to validate the hypothesis that the performance of the risk models using distributed learning approaches that of centrally hosted and is more robust than models built on single institutional datasets. Grants Admin Updated 04.01.2019 JBou

ROP是一种影响早产儿的视网膜新生血管疾病，是儿童失明的主要原因 全世界。已知的临床危险因素包括早产，低出生体重和补充氧气的使用 但是需要改善的风险模型来确定发展为需要疾病和疾病治疗的婴儿 失明。深度学习技术已被用来成功识别多种多样的“加人”疾病 机构人群，并提供连续的疾病严重程度衡量。深处的主要局限 但是，学习是需要大量精心策划的数据集。其他限制包括过度拟合 以及可能导致模型性能下降外部数据的“脆性”。但是，有很多 建立和托管这些大型中央存储库的障碍，具有强大的多机构数据 深度学习包括有关数据共享，法规成本，患者隐私和智力的担忧 财产。在这个项目中，我们旨在展示分布式/联合深度学习方法的实用性 数据位于机构内，但模型参数与中央服务器共享。 但是，挫败这项研究的一个重大挑战是对大量标记图像的要求 数据训练深度学习模型。创建大型公共集中式图像数据集的努力是 受到数据共享的障碍，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。 具体而言，我们试图建立强大的风险模型来预测需要疾病的治疗。两个大型队列 将用于验证以下假设：使用分布式学习的风险模型的性能 与在单个机构数据集上构建的模型相比，接近中央托管的方法更强大。 赠款管理员 更新了2019年1月1日