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

• 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
• 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

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.

项目摘要 自闭症谱系障碍（ASD）是一种发育障碍，其特征是社会互动的损害 和沟通以及重复行为，严重性从轻度到显着性残疾。 美国的患病率正在上升（目前约有54名儿童），相关费用是 巨大的。在我们对该项目的最新努力中，我们采用了高级方法来分析 使用基于任务和静止状态数据的功能磁共振成像（fMRI）进行分类， 促进对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 对于关键反应治疗（PRT），这是ASD的行为疗法的基于证据的形式。我们做了 我们最近的工作着重于提取生物标志物和的深度学习技术的伟大进步 使用专注于具有长期记忆的临时特征的新型策略来预测结果 （LSTM）使用图神经网络（GNN）网络以及空间特征。改进的使用和 连通性外观动态变化的表征对于推进性能至关重要 我们的作品和文学。在我们提出的工作中，我们打算开发一个更丰富，综合的模型，可以 更充分利用数据的完整时空特性及其固有的动力学。另外， 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，尤其是考虑到这一点 ASD是具有一系列特征，严重性和合并症的频谱，fMRI是一个强大的工具 包括许多基于任务的和休息状态的采集范例。合并症是一个特别的挑战 和机会，因为他们有潜力增加我们对异质表现的理解 ASD。我们建议通过扩大我们的方法进一步发展和扩大我们方法的力量和影响 主题基础包括ASD合并症（例如焦虑，ADHD，抑郁症）和多种治疗策略。我们 将通过创建更集成的时空分析来推进我们的技术 方法。我们将使用域的适应方法正确利用多个fMRI范式连词 采用安全的联合学习策略，以促进具有隐私的多机构数据使用。这些创新的 方法将使我们能够改善预测ASD和ASD定量治疗结果的实用性 测量相关的神经成像生物标志物。