自闭症谱系障碍（Autism Spectrum Disorder, ASD）是一种中枢神经系统广泛性发育障碍，主要在儿童期发病，以非典型行为和重复行为为特征。目前的诊断方法主要依赖问卷调查和行为观察，因其主观性易导致误诊。随着医学成像技术的进步，基于磁共振成像的诊断已成为更具客观性的替代方案。本文提出了一种用于ASD识别的分层神经网络模型，命名为ASD-HNet，该模型基于静息态功能磁共振成像（resting-state functional magnetic resonance imaging, rs-fMRI）数据从脑功能网络中分层提取特征。这种分层方法增强了脑表征的提取能力，提高了诊断准确率，并有助于识别与ASD相关的脑区。具体而言，特征在三个层级上提取：（1）局部感兴趣区（region of interest, ROI）尺度，（2）社区尺度，（3）全局表征尺度。在ROI尺度，采用图卷积在各ROI之间传递特征。在社区尺度，引入功能梯度，并应用K-Means聚类算法将功能梯度相似的ROI划分为社区，随后提取同一社区内ROI的特征以表征社区。在全局表征尺度，我们从整个社区尺度的脑网络中提取全局特征以表征全脑。我们使用公开的Autism Brain Imaging Data Exchange I（ABIDE-I）数据集验证了所提方法的有效性。实验结果表明，ASD-HNet的性能优于现有方法。代码可在https://github.com/LYQbyte/ASD-HNet获取。
英文摘要：
Autism Spectrum Disorder (ASD) is a pervasive developmental disorder of the central nervous system, primarily manifesting in childhood. It is characterized by atypical and repetitive behaviors. Currently, diagnostic methods mainly rely on questionnaire surveys and behavioral observations, which are prone to misdiagnosis due to their subjective nature. With advancements in medical imaging, MR imaging-based diagnostics have emerged as a more objective alternative. In this paper, we propose a Hierarchical Neural Network model for ASD identification, termed ASD-HNet, which hierarchically extracts features from functional brain networks based on resting-state functional magnetic resonance imaging (rs-fMRI) data. This hierarchical approach enhances the extraction of brain representations, improving diagnostic accuracy and aiding in the identification of brain regions associated with ASD. Specifically, features are extracted at three levels: (1) the local region of interest (ROI) scale, (2) the community scale, and (3) the global representation scale. At the ROI scale, graph convolution is employed to transfer features between ROIs. At the community scale, functional gradients are introduced, and a K-Means clustering algorithm is applied to group ROIs with similar functional gradients into communities. Features from ROIs within the same community are then extracted to characterize the communities. At the global representation scale, we extract global features from the whole community-scale brain networks to represent the entire brain. We validate the effectiveness of our method using the publicly available Autism Brain Imaging Data Exchange I (ABIDE-I) dataset. Experimental results demonstrate that ASD-HNet outperforms existing methods. The code is available at https://github.com/LYQbyte/ASD-HNet.
In this paper we review the preprocessing pipeline through which fMRI data is transformed into a network. We discuss three parameters that mostly affect our understanding of the existence of functional correlations between the brain regions. In the end, we conclude that the existence of functional correlations between pairs of the brain's regions can be modeled with probabilistic edges, not to lose the uncertainty that is inherent in the network generation process.
A defense of using resting state fMRI as null data for estimating false positive rates
Slotnick（2017）最近的一篇社论重新考虑了我们关于fMRI中聚类推断的假阳性率控制准确性的论文的研究结果（Eklund et al，2016），特别是批评我们使用静息状态fMRI数据作为评估任务fMRI方法的空数据来源。我们为这种使用静息功能磁共振成像数据进行辩护，因为虽然这些数据中有很多结构，但我们认为它代表了任务数据噪声，因此分析软件应该能够适应这种噪声。我们还讨论了一个潜在的问题与Slotnick自己的方法。
Searching for biomarkers has been a chief pursuit of the field of psychiatry. Toward this end, studies have catalogued candidate resting-state biomarkers in nearly all forms of mental disorder. However, it is becoming increasingly clear that these biomarkers lack specificity, limiting their capacity to yield clinical impact. We discuss three avenues of research that are overcoming this limitation: (i) the adoption of transdiagnostic research designs, which involve studying and explicitly comparing multiple disorders from distinct diagnostic axes of psychiatry; (ii) dimensional models of psycho…
What makes a network complex, in addition to its size, is the interconnected interactions between elements, disruption of which inevitably results in dysfunction. Likewise, the brain networks' complexity arises from interactions beyond pair connections, as it is simplistic to assume that in complex networks state of a link is independently determined only according to its two constituting nodes. This is particularly of note in genetically complex brain impairments, such as the autism spectrum disorder (ASD), which has a surprising heterogeneity in manifestations with no clear-cut neuropatholog…
Mesial temporal lobe epilepsy (mTLE) is the most common form of epilepsy. While it is characterized by an epileptogenic focus in the mesial temporal lobe, it is increasingly understood as a network disorder. Hence, understanding the nature of impairments on a network level is essential for its diagnosis and treatment. In this work, we review recent works that apply resting-state functional MRI to provide key insights into the impairments to the functional architecture in mTLE. We discuss changes on both regional and global scales. Finally, we describe how Machine Learning can be applied to rs-…
a Division of Medical Informatics, Department of Biomedical Engineering b Division of Statistics \& Machine Learning, Department of Computer；Information Science c Center for Medical Image Science；Visualization (CMIV) \ \" o ping University, Sweden
Classifying subjects as healthy or diseased using neuroimaging data has gained a lot of attention during the last 10 years. Here we apply deep learning to derivatives from resting state fMRI data, and investigate how different 3D augmentation techniques affect the test accuracy. Specifically, we use resting state derivatives from 1,112 subjects in ABIDE preprocessed to train a 3D convolutional neural network (CNN) to perform the classification. Our results show that augmentation only provide minor improvements to the test accuracy.
Memorial Sloan Kettering Cancer Center（纪念斯隆凯特琳癌症中心）；New York University Langone Medical Center（纽约大学朗格尼医学中心）；Indian Institute of Technology, Madras（印度理工学院马德拉斯分校）
Purpose : Because functional MRI (fMRI) data sets are in general small, we sought a data efficient approach to resting state fMRI classification of autism spectrum disorder (ASD) versus neurotypical (NT) controls. We hypothesized that a Deep Reinforcement Learning (DRL) classifier could learn effectively on a small fMRI training set. Methods : We trained a Deep Reinforcement Learning (DRL) classifier on 100 graph-label pairs from the Autism Brain Imaging Data Exchange (ABIDE) database. For comparison, we trained a Supervised Deep Learning (SDL) classifier on the same training set. Results : DR…
Circadian rhythms synchronize a variety of physiological processes ranging from neural activity and hormone secretion to sleep cycles and feeding habits. Despite significant diurnal variation, time-of-day (TOD) is rarely recorded or analyzed in human brain research. Moreover, sleep-wake patterns, diurnal preferences, and daytime alertness vary across individuals, known as sleep chronotypes. Here, we performed graph-theory network analysis on resting-state functional MRI (rs-fMRI) data to explore topological differences in whole-brain functional networks between morning and evening sessions (TO…
Deep Learning Inductive Biases for fMRI Time Series Classification during Resting-state and Movie-watching
School of Electrical and Computer Engineering, University of Tehran（埃特瓦尔大学电气与计算机工程学院）；School of Cognitive Sciences, Institute for Research in Fundamental Sciences (IPM)（基础科学研究所（IPM）认知科学学院）
A Framework for Exploring Non-Linear Functional Connectivity and Causality in the Human Brain: Mutual Connectivity Analysis (MCA) of Resting-State Functional MRI with Convergent Cross-Mapping and Non-Metric Clustering
Coevolutionary balance of resting-state brain networks in autism
Institute for Cognitive and Brain Sciences, Shahid Beheshti University（认知与脑科学学院，沙希德贝赫什提大学）；Department of Physics, Shahid Beheshti University（物理系，沙希德贝赫什提大学）
Middle Tennessee State University（中田纳西州立大学）；St. Ambrose University（圣安布罗斯大学）
The objective of this study is to derive functional networks for the autism spectrum disorder (ASD) population using the group ICA and dictionary learning model together and to classify ASD and typically developing (TD) participants using the functional connectivity calculated from the derived functional networks. In our experiments, the ASD functional networks were derived from resting-state functional magnetic resonance imaging (rs-fMRI) data. We downloaded a total of 120 training samples, including 58 ASD and 62 TD participants, which were obtained from the public repository: Autism Brain I…
We conduct an imaging genetics study to explore how effective brain connectivity in the default mode network (DMN) may be related to genetics within the context of Alzheimer's disease and mild cognitive impairment. We develop an analysis of longitudinal resting-state functional magnetic resonance imaging (rs-fMRI) and genetic data obtained from a sample of 111 subjects with a total of 319 rs-fMRI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. A Dynamic Causal Model (DCM) is fit to the rs-fMRI scans to estimate effective brain connectivity within the DMN and related…
VarCoNet: A variability-aware self-supervised framework for functional connectome extraction from resting-state fMRI
Department of Biomedical Engineering and Biotechnology, and the Health Engineering Innovation Group (HEIG), Khalifa University（生物医学工程与生物技术系，以及健康工程创新小组（HEIG），卡利法大学）；Department of Electrical and Computer Engineering, Aristotle University of Thessaloniki（电气与计算机工程系，阿尔基洛斯大学）
The study of hierarchy in networks of the human brain has been of significant interest among the researchers as numerous studies have pointed out towards a functional hierarchical organization of the human brain. This paper provides a novel method for the extraction of hierarchical connectivity components in the human brain using resting-state fMRI. The method builds upon prior work of Sparse Connectivity Patterns (SCPs) by introducing a hierarchy of sparse overlapping patterns. The components are estimated by deep factorization of correlation matrices generated from fMRI. The goal of the pape…
Resting-state functional connectivity-based biomarkers and functional MRI-based neurofeedback for psychiatric disorders: a challenge for developing theranostic biomarkers
Multi-Scale Graph Theoretical Analysis of Resting-State fMRI for Classification of Alzheimer's Disease, Mild Cognitive Impairment, and Healthy Controls
University of Bojnord（博季努尔德大学）；Munster Technological University（芒斯特理工大学）
Point process analysis of large-scale brain fMRI dynamics
功能性磁共振成像（fMRI）技术为我们了解大脑功能做出了重大贡献。目前的方法是基于脑血氧水平依赖性（BOLD）信号中的\emph{gradual and continuous}变化的分析。与该方法不同，最近的工作表明，通过仅检查相对大幅度的BOLD信号峰值可以获得等效的结果，这表明相关信息可以浓缩在\emph{discrete}事件中。这里进一步探讨了这个想法，以证明如何通过这些事件的时间和位置来捕获静息状态下的大脑动力学，即，在时空点过程中。作为原理证明，我们表明可以从这样的点过程中提取静息状态网络（RSN）映射。此外，分析揭示了雪崩的活动，这是由相同的动力学和统计特性之前所描述的神经元事件在较小的尺度。鉴于静息状态脑动力学的功能相关性，其表示为离散过程可能有助于大规模分析健康和疾病中的脑功能。
Functional Brain Network Identification in Opioid Use Disorder Using Machine Learning Analysis of Resting-State fMRI BOLD Signals
Old Dominion University（奥多明尼昂大学）；Institute of Drug and Alcohol Studies（药物与酒精研究所）；Virginia Commonwealth University（弗吉尼亚联邦大学）；C. Kenneth and Dianne Wright Center for Clinical and Translational Research（C.肯尼斯和黛安·赖特临床与转化研究中心）；Data Science Institute（数据科学研究所）
This paper compares three feature representation techniques used to represent resting state functional magnetic resonance (fMRI) scans. The proposed models of feature representation consider the time averaged fMRI scans as raw representation of image data. The effectiveness of the representation is evaluated by using these features for classification of Attention Deficit Hyperactivity Disorder (ADHD) patients from healthy controls. The dimensionality reduction methods used for feature representation are maximum-variance unfolding, locally linear embedding and auto-encoders. The classifiers tes…
