Continuing Tool Development for Longitudinal Network Analysis: Enriching the Diagnostic Power of Disease-Specific Connectomic Biomarkers by Deep Graph Learning

纵向网络分析的持续工具开发：通过深度图学习丰富疾病特异性连接组生物标志物的诊断能力

• 批准号: 10359157
• 负责人: Guorong Wu
• 金额: $ 14.47万
• 依托单位: UNIV OF NORTH CAROLINA CHAPEL HILL
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-03-01 至 2024-02-29
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10359157
• 关键词: Address; Alzheimer' s Disease; Alzheimer' s disease diagnosis; Artificial Intelligence; Biological Markers; Brain; Clinical; Cognitive; Communities; Computer software; Computer-Assisted Diagnosis; Data; Databases; Diagnostic; Dimensions; Disease; Early Diagnosis; Event; Evolution; Frontotemporal Dementia; Goals; Graph; Image; Impaired cognition; Individual; Industry; Investigation; Label; Learning; Longitudinal Studies; Machine Learning; Measurement; Methods; Modeling; Nerve Degeneration; Network-based; Neural Network Simulation; Neurodegenerative Disorders; Neurofibrillary Tangles; Neurosciences; Outcome; Parkinson Disease; Pathway Analysis; Pattern; Population; Process; Prognosis; Research; Resolution; Resources; Sample Size; Senile Plaques; Sensitivity and Specificity; Source Code; Supervision; Symptoms; Syndrome; Techniques; Text; Time; United States National Institutes of Health; base; clinical practice; cohort; collaboratory; comparison group; computerized tools; data mining; data structure; deep learning; design; diagnostic value; graph learning; graph neural network; high dimensionality; machine learning method; method development; network dysfunction; neural network; neuroimaging; novel; software development; success; tool; tool development

Project Summary/Abstract A plethora of neuroscience studies shows mounting evidence that neurodegenerative diseases manifest distinct network dysfunction patterns much earlier prior to the onset of clinical symptoms. Since the subject-specific longitudinal network changes are more relevant to the neuropathological process than topological patterns derived from cross-sectional data, recognizing the subtle and dynamic longitudinal network biomarkers from noisy network data is of great demand to enhance the sensitivity and specificity of computer-assisted diagnosis in neurodegenerative diseases. However, current popular statistical inference or machine learning approaches used for neuroimages (in a regular data structure such as grid and lattice) are not fully optimized for the learning task on brain network data which is often encoded in a high dimensional graph (an irregular and non-linear data structure). Such gross adaption is partially responsible for the lack of reliable biomarkers that can be used to predict cognitive decline in routine clinical practice. To address this challenge, we aim to (1) develop a novel GNN (graph neural network) based learning framework to hierarchically discover the multi-scale network biomarkers that can recognize the disease-relevant network alterations over time, and (2) examine the diagnostic power of the new network biomarkers derived from our GNN-based machine learning engine across neurodegenerative diseases such as Alzheimer’s disease, Parkinson’s disease, and frontotemporal dementia. The success of this project will allow us to integrate the novel GNN-based learning component into our current longitudinal network analysis toolbox and release the AI (artificial intelligence) based network analysis software to the neuroscience and neuroimaging community.

项目总结/摘要 大量的神经科学研究表明，越来越多的证据表明，神经退行性疾病表现出明显的 网络功能障碍模式早于临床症状发作。由于特定主题 纵向网络变化与神经病理过程的关系比拓扑模式更密切 来自横截面数据，识别微妙和动态的纵向网络生物标志物， 噪声网络数据对于提高计算机辅助诊断的灵敏度和特异性具有很大的需求 神经退行性疾病然而，目前流行的统计推断或机器学习方法 用于神经图像（在常规数据结构中，如网格和晶格）并没有完全优化学习 通常编码在高维图（不规则和非线性数据）中的脑网络数据上的任务 结构）。这种严重的适应是缺乏可靠的生物标志物的部分原因，这些生物标志物可用于 在常规临床实践中预测认知能力下降。为了应对这一挑战，我们的目标是（1）开发一种新的 基于图神经网络（GNN）的分层发现多尺度网络的学习框架 可以识别疾病相关网络随时间变化的生物标志物，以及（2）检查诊断性生物标志物。 从我们基于GNN的机器学习引擎中获得的新网络生物标志物的强大功能， 神经退行性疾病，如阿尔茨海默病、帕金森病和额颞叶痴呆。 这个项目的成功将使我们能够将新的基于GNN的学习组件集成到我们目前的 纵向网络分析工具箱，并发布基于AI（人工智能）的网络分析软件 神经科学和神经影像学领域。

项目成果

Joint hub identification for brain networks by multivariate graph inference.

• DOI: 10.1016/j.media.2021.102162
• 发表时间: 2021-10
• 期刊: Medical image analysis
• 影响因子: 10.9
• 作者: Yang D;Zhu X;Yan C;Peng Z;Bagonis M;Laurienti PJ;Styner M;Wu G
• 通讯作者: Wu G

Group-Wise Hub Identification by Learning Common Graph Embeddings on Grassmannian Manifold.

通过学习格拉斯曼尼亚歧管上的常见图嵌入通过学习群中心的识别。

• DOI: 10.1109/tpami.2021.3081744
• 发表时间: 2022-11
• 期刊: IEEE transactions on pattern analysis and machine intelligence
• 影响因子: 23.6

Characterizing Network Selectiveness to the Dynamic Spreading of Neuropathological Events in Alzheimer's Disease.

• DOI: 10.3233/jad-215596
• 发表时间: 2022
• 期刊: JOURNAL OF ALZHEIMERS DISEASE
• 影响因子: 4
• 作者: Li, Wenchao;Yang, Defu;Yan, Chenggang;Chen, Minghan;Li, Quefeng;Zhu, Wentao;Wu, Guorong
• 通讯作者: Wu, Guorong

Multi-Band Brain Network Analysis for Functional Neuroimaging Biomarker Identification.

用于功能性神经影像生物标志物识别的多波段脑网络分析

• DOI: 10.1109/tmi.2021.3099641
• 发表时间: 2021-12
• 期刊: IEEE transactions on medical imaging
• 影响因子: 10.6
• 作者: Hu R;Peng Z;Zhu X;Gan J;Zhu Y;Ma J;Wu G
• 通讯作者: Wu G

Uncovering shape signatures of resting-state functional connectivity by geometric deep learning on Riemannian manifold.

• DOI: 10.1002/hbm.25897
• 发表时间: 2022-09
• 期刊: HUMAN BRAIN MAPPING
• 影响因子: 4.8
• 作者: Dan, Tingting;Huang, Zhuobin;Cai, Hongmin;Lyday, Robert G.;Laurienti, Paul J.;Wu, Guorong
• 通讯作者: Wu, Guorong