Data-driven approaches to identify biomarkers from multimodal imaging big data

从多模态成像大数据中识别生物标志物的数据驱动方法

基本信息

批准号：
10473657
负责人：
Jing Sui
金额：
$ 38.59万
依托单位：
GEORGIA STATE UNIVERSITY
依托单位国家：
美国
项目类别：
财政年份：
2019
资助国家：
美国
起止时间：
2019-08-20 至 2024-07-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10473657
关键词：
Address Affect Age Algorithms Anterior Antidepressive Agents Area Attention Back Behavioral Benchmarking Big Data Biological Biological Markers Bipolar Disorder Brain Brain Diseases Brain imaging Cell Nucleus Classification Clinical Clinical Data Cognitive Cognitive deficits Collaborations Communities Complement Complex Corpus Callosum DSM-IV Data Data Pooling Data Set Diagnosis Diagnostic Disease Disease remission Electroconvulsive Therapy Engineering Functional disorder Gender Goals ICD-9 Image Impaired cognition Impairment Individual International Intervention Joints Judgment Knowledge Magnetic Resonance Imaging Major Depressive Disorder Manic Mathematics Measures Medical Care Costs Mental disorders Methods Mining Modality Modeling Moods Multimodal Imaging Outcome Patients Pharmaceutical Preparations Pharmacology Play Precision Medicine Initiative Probability Prognosis Psychiatric Diagnosis Psychiatry Psychoses Psychotic Disorders Recording of previous events Records Recurrence Relapse Reporting Research Personnel Role Schizophrenia Severities Site Structure Supervision Symptoms Syndrome System Techniques Testing Therapeutic Time Translations Treatment Efficacy Treatment outcome Validation Work base biomarker identification cingulate cortex clinical application clinical care clinical practice clinical predictors cognitive ability cohort common symptom convolutional neural network data mining data sharing deep field survey deep learning demographics depressed patient diagnostic tool diagnostic value disease classification effective intervention feature selection flexibility gray matter high dimensionality improved innovation insight learning strategy multimodal data multimodal neuroimaging multimodality neuroimaging neuroimaging marker novel open source optimal treatments outcome prediction patient subsets personalized care personalized predictions predicting response supervised learning tool translational impact translational medicine treatment response white matter

项目摘要

1. PROJECT SUMMARY/ABSTRACT The study of translational biomarkers in brain disorders is a very challenging and fruitful approach, which will empower a better understanding of healthy and diseased brains. This project will promote the translation of advanced engineering solutions and mathematic tools to novel neuroimaging applications in psychiatric disorders including major depression disorder (MDD), bipolar disorder (BD) and schizophrenia (SZ), allowing sophisticated and powerful analyses on highly complex datasets. To date, the unifying syndrome classification (ICD-9/10;DSM-IV/5) for these mental disorders obscures our knowledge of underlying pathophysiology and cannot guide optimal treatments. For example, there is no biomarker that is able to precisely predict response of MDD to some treatments. One reason for this is that most neuroimaging prediction studies to date have used a single imaging measure or reported simple correlation relationships, without considering multimodal cross- information, nonlinear relationships, or multi-site cross-validation. Hence, developing novel data mining techniques such as deep learning, fusion with reference, and sparse regression can complement and exploit the richness of neuroimaging data, providing promising avenues to identify objective biomarkers and going beyond a descriptive use of brain imaging as traditionally used in studies of brain disease to individualized prediction. We will facilitate the translational biomarker identification by developing 3 novel data-driven methods: 1) A supervised fusion model that can provide insight on how cognitive impairment may affect covarying brain function and structure in mental disorder, by using different clinical measures as a reference to guide multimodal MRI fusion; 2) A cutting-edge prediction framework with aggregated feature selection techniques that is able to estimate clinical outcome more precisely, e.g., remission/relapse status of individual MDD patient after electroconvulsive treatment(ECT) using baseline brain imaging and demographic measures of 3) We will draw on advances and ideas from deep learning combined with layer-wise relevance propagation (LRP) or attention modules, to classify multiple groups of psychiatric disorders by incorporating dynamic functional measures. The proposed (Deep/Recurrent/Convolutional Neural Network, DNN/RNN/CNN) models will have enhanced interpretability that is able to trace back and discover the most predictive functional networks from input. All above proposed methods will be applied to big data containing both multimodal imaging and behavioral information (n~5000) pooled from existing studies, and our developed open-source toolboxes will be shared publicly. This pioneering study may provide an urgently-needed paradigm shift in the treatment and diagnosis of psychiatric disorders, thereby guiding personalized clinical care. Accomplishment of this project has great potential to discover neuroimaging biomarkers that have been missed by existing approaches, leading to earlier and more effective interventions, and laying the groundwork for a significant translational impact.

1. 项目概要/摘要脑部疾病转化生物标志物的研究是一种非常具有挑战性且富有成效的方法，将有助于更好地了解健康和患病的大脑。该项目将促进翻译先进的工程解决方案和数学工具，用于精神病学中新颖的神经影像应用包括重度抑郁症 (MDD)、双相情感障碍 (BD) 和精神分裂症 (SZ) 在内的疾病，允许对高度复杂的数据集进行复杂而强大的分析。迄今为止，统一的综合征分类（ICD-9/10；DSM-IV/5）这些精神障碍掩盖了我们对潜在病理生理学和无法指导最佳治疗。例如，没有生物标志物能够精确预测反应 MDD 对某些治疗的影响。原因之一是迄今为止大多数神经影像预测研究都使用单一成像测量或报告的简单相关关系，而不考虑多模态交叉信息、非线性关系或多站点交叉验证。因此，开发新颖的数据挖掘深度学习、参考融合和稀疏回归等技术可以补充和利用丰富的神经影像数据，为识别客观生物标志物提供了有前途的途径，并超越传统上用于脑部疾病研究的脑成像的描述性用途，以进行个体化预测。我们将通过开发 3 种新颖的数据驱动方法来促进转化生物标志物的识别：1) A 监督融合模型可以深入了解认知障碍如何影响共变的大脑功能精神障碍的结构和结构，通过使用不同的临床测量作为参考来指导多模态MRI 融合； 2）具有聚合特征选择技术的尖端预测框架，能够更准确地估计临床结果，例如个体 MDD 患者治疗后的缓解/复发状态使用基线脑成像和人口统计测量的电惊厥治疗 (ECT) 3) 我们将绘制深度学习与分层相关性传播（LRP）或注意力相结合的进展和想法模块，通过结合动态功能测量对多组精神疾病进行分类。这提出的（深度/循环/卷积神经网络，DNN/RNN/CNN）模型将具有增强可解释性能够从输入中追溯并发现最具预测性的功能网络。全部上述方法将应用于包含多模态成像和行为的大数据从现有研究中汇集的信息（n~5000），我们开发的开源工具箱将被共享公开。这项开创性的研究可能为以下疾病的治疗和诊断提供迫切需要的范式转变：精神疾病，从而指导个性化临床护理。该项目的完成具有重大意义发现现有方法遗漏的神经影像生物标志物的潜力，从而导致更早的发现以及更有效的干预措施，并为产生重大转化影响奠定基础。