CRII: RI: Learning novel multi-resolution representations of graphs: Applications to Brain Connectivity analysis for Alzheimer's Disease

CRII：RI：学习图形的新颖多分辨率表示：在阿尔茨海默氏病大脑连接分析中的应用

• 批准号: 1948510
• 负责人: Hong Jiang
• 金额: $ 17.5万
• 依托单位: University of Texas at Arlington
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1948510&HistoricalAwards=false
• 关键词: CRII; RI; Learning; novel; multi

This project aims to identify disease-specific changes in human brain connectivity in early stages by developing a novel Deep Learning framework applicable to data with arbitrary structure such as graphs. This is important because regional brain variations often do not manifest as cognitive changes until significant brain pathology has accumulated, and a better understanding of the brain may be possible by characterizing changes in connectivity defined by relationships between different brain regions. Recent techniques with Deep Learning have demonstrated successful results with human-level precision in various image analysis tasks such as image classification, object detection, and image segmentation, but they cannot be directly applied to analyze brain connectivity because of its arbitrary structure. The key is to derive effective representation of the data; however, it is still unclear how to derive sophisticated representations for complex data such as graphs and it often requires large-scale datasets. A novel Graph Deep Learning technique that can detect subtle changes in brain connectivity with small numbers of samples is therefore necessary. Success of this project will facilitate understanding of the relationship between brain connectivity and neurodegenerative disease, mechanisms for early diagnosis, and discovery of new treatments. Technically, the overarching goal of this project is to design a Convolution Neural Network (CNN) model for graph data and to determine the extent to which it yields new scientific findings in neuroscience. To meet the goal, this project will focus on: 1) Developing a novel transform for graphs (e.g., brain networks) for their novel multi-resolution representations that are theoretically described by convolution, 2) Developing an efficient deep learning architecture for graphs that operates within a small sample-size regime to improve performance of disease diagnosis and sensitivity of statistical inferences, and 3) Validating the developed models on a simulation study as well as real brain network datasets for Alzheimer’s Disease to characterize disease-specific patterns in the brain connectivity. The developed framework will benefit various areas of neuroimaging research with functional and structural brain connectivity that are locally carried at small scales, and spur development of further studies.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

该项目旨在通过开发一种适用于具有任意结构（例如图形）的数据的新型深度学习框架来识别早期阶段人类大脑连接的特定疾病变化。这很重要，因为区域大脑变化通常不会表现为认知变化，直到出现显着的大脑变化。病理学已经积累起来，通过表征不同大脑区域之间关系所定义的连接变化，可以更好地了解大脑。最近的深度学习技术已经在各种图像分析任务（例如图像分类）中证明了具有人类水平精度的成功结果。 、目标检测、图像分割，但不能直接应用由于其任意结构，分析大脑连接性的关键是导出数据的有效表示；然而，目前尚不清楚如何导出复杂数据（例如图）的复杂表示，并且通常需要大规模数据集。因此，能够用少量样本检测大脑连接的细微变化的深度学习技术是必要的，该项目的成功将有助于理解大脑连接与神经退行性疾病之间的关系、早期诊断的机制以及新疗法的发现。该项目的总体目标是设计用于图数据的卷积神经网络（CNN）模型，并确定其在神经科学领域产生新科学发现的程度。为了实现这一目标，该项目将重点关注：1）开发一种新颖的图变换（例如，大脑网络）。 ) 理论上通过卷积描述的新颖的多分辨率表示，2) 开发一种在小样本范围内运行的图深度学习架构，以提高有效疾病诊断的性能和统计的敏感性3) 在模拟研究以及阿尔茨海默病的真实大脑网络数据集上验证开发的模型，以表征大脑连接中的疾病特定模式。开发的框架将有利于神经影像研究的各个领域的功能和结构大脑连接。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Learning Covariance-based Multi-scale Representation of NeuroImaging Measures for Alzheimer Classification

学习基于协方差的阿尔茨海默病分类神经影像测量的多尺度表示

• 发表时间: 2023-01
• 期刊: IEEE International Symposium on Biomedical Imaging (ISBI
• 作者: Seunghun Baek; Injun Choi
• 通讯作者: Injun Choi

Image-Label Recovery on Fashion Data Using Image Similarity from Triple Siamese Network

使用三连体网络的图像相似性对时尚数据进行图像标签恢复

• DOI: 10.3390/technologies9010010
• 发表时间: 2021-01-21
• 期刊: Technologies
• 影响因子: 3.6
• 作者: Debapriya Banerjee;Maria Kyrarini;Won Hwa Kim
• 通讯作者: Won Hwa Kim

Locally Normalized Soft Contrastive Clustering for Compact Clusters

紧凑簇的局部归一化软对比聚类

• DOI: 10.24963/ijcai.2022/460
• 发表时间: 2022-07-01
• 作者: Xin Ma;Won Hwa Kim
• 通讯作者: Won Hwa Kim

Dynamic covariance estimation via predictive Wishart process with an application on brain connectivity estimation

通过预测 Wishart 过程进行动态协方差估计并应用于大脑连接估计

• DOI: 10.1016/j.csda.2023.107763
• 发表时间: 2023-04-01
• 期刊: Comput. Stat. Data Anal.
• 作者: Rui Meng;Fan Yang;Won Hwa Kim
• 通讯作者: Won Hwa Kim

Learning Multi-resolution Graph Edge Embedding for Discovering Brain Network Dysfunction in Neurological Disorders

学习多分辨率图边缘嵌入以发现神经系统疾病中的大脑网络功能障碍

• 发表时间: 2021-06
• 期刊: Lecture notes in computer science
• 作者: Ma, Xin;Wu, Guorong;Hwang, Seongjae;Kim, Won Hwa
• 通讯作者: Kim, Won Hwa