Dynamic Functional Image-based Deep Learning for Therapy Assessment in Autism

基于动态功能图像的深度学习用于自闭症治疗评估

基本信息

批准号：
10439304
负责人：
JAMES S DUNCAN
金额：
$ 63.72万
依托单位：
YALE UNIVERSITY
依托单位国家：
美国
项目类别：
财政年份：
1996
资助国家：
美国
起止时间：
1996-06-01 至 2027-03-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10439304
关键词：
Accounting Anxiety Attention deficit hyperactivity disorder Behavior Therapy Biological Markers Brain Brain Diseases Brain Pathology Brain imaging Brain region Categories Characteristics Child Child Behavior Checklist Classification Clinical Clinical assessments Cognitive Therapy Communities Data Data Set Databases Dependence Development Disease Functional Imaging Functional Magnetic Resonance Imaging Functional disorder Genetic Goals Graph Heterogeneity Image Analysis Impairment Individual Institution Judgment Learning Literature Machine Learning Magnetic Resonance Imaging Measurement Measures Mental Depression Methodological Studies Methodology Methods Modeling Molecular Biology Neurosciences Outcome Measure Oxytocin Patients Performance Pharmacotherapy Phenotype Poly(ADP-ribose) Polymerases Prevalence Privacy Rest Secure Services Severities Signal Transduction Social Interaction Subcategory Subgroup Supportive care Techniques Technology Testing Time Training Treatment outcome United States Universities Virginia Work autism spectrum disorder base biomarker identification childhood anxiety cohort comorbidity convolutional neural network cost data exchange deep learning design developmental disease evidence base federated learning graph neural network improved improved outcome innovation large datasets learning network learning strategy long short term memory long short term memory network neuroimaging marker novel novel strategies outcome prediction personalized medicine personalized predictions predicting response privacy preservation psychiatric comorbidity psychoeducation quantitative imaging recurrent neural network repetitive behavior social social communication spatial relationship spatiotemporal therapy outcome tool treatment response treatment strategy

项目摘要

Project Summary Autism spectrum disorder (ASD) is a developmental disorder characterized by impairment of social interaction and communication, as well as repetitive behaviors, with severity ranging from mild to signiﬁcantly disabling. The prevalence in the United States is rising (currently about 1 in 54 children) and the associated costs are enormous. In our most recent previous efforts on this project, we have advanced methods for the analysis of functional magnetic resonance imaging (fMRI), using both task-based and resting-state data, for classiﬁcation, facilitating identiﬁcation of ASD biomarkers, and using these biomarkers for personalized outcome prediction for Pivotal Response Treatment (PRT), an evidence-based form of behavioral therapy for ASD. We have made great strides with our most recent work focusing on deep learning techniques for extracting biomarkers and predicting outcome using novel strategies focusing on temporal characteristics with Long Short Term Memory (LSTM) networks as well as spatial characteristics using Graph Neural Networks (GNNs). Improved use and characterization of the dynamic changes in connectivity appear crucial for advancing performance based both on our work and the literature. Thus, in our proposed work, we intend to develop a richer, integrated model that can more fully exploit the complete spatiotemporal characteristics of the data and its inherent dynamics. In addition, a key issue in deep learning strategies is access to large datasets which remains a challenge, especially given that ASD is a spectrum with a range of characteristics, severity and comorbidities and that fMRI is a powerful tool that encompasses many task-based and resting state acquisition paradigms. Comorbidities are a particular challenge and opportunity in that they have the potential to increase our understanding of the heterogeneous manifestations of ASD. We propose to further develop and expand the power and impact of our methodology by broadening our subject base to include ASD comorbidities (e.g. anxiety, ADHD, depression) and multiple treatment strategies. We will advance our technology by creating a more integrated spatiotemporal analysis combining our LSTM and GNN approaches. We will use domain adaptation methods to properly exploit multiple fMRI paradigms in conjunction with secure federated learning strategies to facilitate multi-institutional data usage with privacy. These innovative approaches will allow us to improve the practicability of predicting quantitative treatment outcomes in ASD and measuring associated neuroimaging biomarkers.

项目概要自闭症谱系障碍（ASD）是一种以社交互动障碍为特征的发育障碍和沟通，以及重复行为，其严重程度从轻微到严重失能不等。在美国，该病的患病率正在上升（目前大约每 54 名儿童中就有 1 名），相关费用为在我们最近对该项目的努力中，我们拥有先进的分析方法。功能磁共振成像（fMRI），使用基于任务的数据和静息态数据进行分类，促进 ASD 生物标志物的识别，并使用这些生物标志物进行个性化结果预测关键反应治疗 (PRT)，这是一种针对 ASD 的循证行为疗法。我们最近的工作取得了巨大进步，重点是提取生物标记物的深度学习技术使用关注长短期记忆时间特征的新颖策略来预测结果（LSTM）网络以及使用图神经网络（GNN）的空间特征的改进使用和。连接动态变化的表征对于基于以下方面的性能提升至关重要因此，在我们提出的工作中，我们打算开发一个更丰富、集成的模型，可以更充分地利用数据的完整时空特征及其内在动态。深度学习策略的关键问题是访问大型数据集，这仍然是一个挑战，特别是考虑到自闭症谱系障碍 (ASD) 是一个具有一系列特征、严重程度和合并症的谱系，功能磁共振成像 (fMRI) 是一个强大的工具，涵盖许多基于任务和静息状态的习得范例，合并症是一个特殊的挑战。和机会，因为它们有潜力增加我们对异质表现的理解我们建议通过扩大我们的方法来进一步发展和扩大我们方法的力量和影响。我们的主题基础包括 ASD 合并症（例如焦虑、多动症、抑郁症）和多种治疗策略。将通过结合我们的 LSTM 和 GNN 创建更加集成的时空分析来推进我们的技术我们将使用领域适应方法来正确地结合使用多个功能磁共振成像范式。通过安全的联合学习策略来促进多机构数据的隐私使用。这些方法将使我们能够提高预测 ASD 定量治疗结果的实用性测量相关的神经影像生物标志物。