MRI and Deep Learning for Early Prediction of Neurodevelopmental Deficits in Very Preterm Infants

MRI 和深度学习用于早期预测极早产儿神经发育缺陷

• 批准号: 10468770
• 负责人: Lili He
• 金额: $ 53.39万
• 依托单位: CINCINNATI CHILDRENS HOSP MED CTR
• 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 2024-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10468770
• 关键词: 5 year old; Address; Adult; Age; Anatomic Models; Anatomy; Artificial Intelligence; Birth; Brain; Child; Child Welfare; Clinical; Clinical Data; Cognitive; Communities; Crowding; Data; Data Set; Detection; Diagnosis; Diffusion Magnetic Resonance Imaging; Dimensions; Distant; Early Diagnosis; Early Intervention; Early identification; Family; Functional Magnetic Resonance Imaging; Funding; Gestational Age; Goals; Health; Image; Image Analysis; Individual; Infant; Institution; Intervention; Knowledge; Language; Magnetic Resonance Imaging; Maps; Medical; Methods; Modeling; Motor; Neonatal Intensive Care Units; Neurodevelopmental Deficit; Neurodevelopmental Problem; Neuronal Plasticity; Outcome; Pathologic; Pathology; Patients; Pattern; Performance; Personal Satisfaction; Pregnancy; Premature Infant; Prognosis; Public Health; Quality of life; Research; Rest; Risk; Risk Factors; Series; Social outcome; Structural defect; Techniques; Therapeutic Intervention; Tissues; Training; United States; United States National Institutes of Health; Work; accurate diagnosis; base; brain magnetic resonance imaging; brain tissue; classification algorithm; clinical risk; cohort; computer program; connectome; convolutional neural network; deep learning; deep learning model; deep neural network; feeding; high dimensionality; high risk; improved; insight; large datasets; multimodality; multitask; neonate; nervous system disorder; neurodevelopment; novel; outcome prediction; precision medicine; prognostic model; public repository; risk prediction model; risk stratification; success; transfer learning

Project Summary/Abstract About 100,000 very preterm infants (VPI; ≤32 weeks gestational age) are born every year in the United States. Up to 35% develop noteworthy neurodevelopmental deficits, thereby increasing their risk for poor educational, health, and social outcomes. Unfortunately, neurodevelopmental deficits cannot currently be reliably diagnosed until 3 to 5 years of age. The imminent challenge lies in early identification of infants that are more likely to develop later deficits. Advances in magnetic resonance imaging (MRI) and deep learning (DL) provide means to address this challenge. Application of DL to infant brain MRI data can open up new windows into early prediction of neurodevelopmental outcomes in at-risk infants and facilitate the move towards precision medicine. Our objective is to apply DL to MRI acquired at term equivalent age for early prediction of neurodevelopment deficits (cognitive, language, and motor) at age 2 in VPI. Our group has identified three key components necessary for accurate prognostic models of later neurodevelopment. DL analysis of 1) anatomical features derived from structural MRI (sMRI) allowing detection of brain structural abnormalities and tissue pathologies; 2) brain connectivity features derived from resting-state functional MRI (rs-fMRI) and diffusion MRI (dMRI) giving insights into atypical brain connectivity patterns; and 3) integration of anatomical and connectivity features, thus enhancing abnormal neurodevelopment prediction. In this project, we will dedicate our efforts in accomplishing the following specific aims. In Aim 1 and Aim 2, we will develop deepAna and deepConn models analyzing anatomical and connectivity features independently to predict adverse neurodevelopmental outcomes. By decoding each model, we will identify, validate and disseminate a series of the most discriminative anatomical and connectivity features to the research community. In Aim 3, we will develop an ensemble deepAnaConn model analyzing both anatomical and connectivity features, together with clinical risk factors, for early prediction of neurodevelopmental deficits. This model will help clinicians to predict later outcomes for those at-risk prematurely born infants before initial neonatal intensive care unit discharge. We will validate the models using both internal and independent external data and will open the ‘black-box’ of DL to aid interpretation of imaging and clinical findings. The techniques we develop are expected to improve the modelling fidelity in medical diagnosis/ prognosis in the same way as DL has revolutionized other fields. The DL models we develop will not only benefit early detection of neurodevelopmental deficits in VPI, but also likely benefit individuals with other neurodevelopmental and neurological diseases. This study will significantly impact public health because it will allow clinicians to target clinical and experimental intervention therapies to the most at-risk infants during periods of optimal neuroplasticity, and thus ultimately improve medical outcomes and patient well-being.

项目总结/摘要 在美国，每年约有10万名极早产儿（VPI;胎龄≤32周）出生。 高达35%的人出现了值得注意的神经发育缺陷，从而增加了他们受教育程度低的风险， 健康和社会成果。不幸的是，目前还无法可靠地诊断神经发育缺陷 直到3到5岁。迫在眉睫的挑战在于早期识别更有可能 发展后期赤字。磁共振成像（MRI）和深度学习（DL）的进步提供了手段 来应对这一挑战。DL应用于婴儿大脑MRI数据可以为早期诊断打开新的窗口。 预测高危婴儿的神经发育结果，并促进向精确方向发展 药我们的目标是将DL应用于在足月年龄获得的MRI，以早期预测 2岁时VPI的神经发育缺陷（认知、语言和运动）。我们的团队已经确定了三个关键点 这些成分是后期神经发育的准确预后模型所必需的。DL分析1） 来自结构MRI（sMRI）的解剖学特征，允许检测大脑结构异常， 组织病理学; 2）来自静息态功能MRI（rs-fMRI）的脑连接特征，以及 弥散MRI（dMRI）提供了对非典型脑连接模式的见解;以及3）解剖结构的整合 和连接特征，从而增强异常神经发育预测。在这个项目中，我们将 致力于实现以下具体目标。在目标1和目标2中，我们将开发deepAna 和deepConn模型独立分析解剖和连接特征， 神经发育结果。通过解码每个模型，我们将识别，验证和传播一系列 最具鉴别力的解剖学和连通性特征。在目标3中，我们 开发一个整体deepAnaConn模型，分析解剖和连接特征，以及 临床风险因素，用于早期预测神经发育缺陷。该模型将帮助临床医生预测 在新生儿重症监护病房出院前，这些高危早产儿的后期结局。 我们将使用内部和独立的外部数据来验证模型，并将打开 DL有助于解释成像和临床结果。我们开发的技术有望改进 医学诊断/预后中的建模保真度以与DL相同的方式已经彻底改变了其他领域。 我们开发的DL模型不仅有利于早期发现VPI中的神经发育缺陷， 可能有益于患有其他神经发育和神经系统疾病的个体。这项研究将大大 影响公共卫生，因为它将使临床医生有针对性的临床和实验干预治疗， 在最佳神经可塑性时期最有风险的婴儿，从而最终改善医疗结果 和病人的幸福感