检索结果-内蒙古大学图书馆

58th Asilomar Conference on Signals, Systems and Computers, ACSSC 2024

作者： Xu, Shuai Jin, Rui Kim, Seung-Jun Adali, Tülay Calhoun, Vince D. University of Maryland Baltimore County Department of Computer Science and Electrical Engineering United States Tri-institutional Center for Translational Research in Neuroimaging and Data Science Georgia State University Georgia Institute of Technology United States Emory University United States

ISBN: (纸本)9798350354058

A dictionary learning (DL)-based method for mul-tisubject functional magnetic resonance imaging (fMRI) data analysis is proposed. The method can incorporate group attributes to find the neural activation maps that are common across groups as well as those that are explanatory of the group differences. The key contribution is to significantly improve the map estimation performance by mitigating undesirable local optima obtained from a supervised DL formulation for fMRI data analysis. We introduce two novel ideas, namely, developing a variant of Fisher's discriminant cost, which is imposed on the non-discriminative features, and optimally permuting the dictionary and the sparse factor such that the solution is not trapped to unwanted local optima. Preliminary tests on synthetic and real data sets verify the effectiveness of the proposed approach. © 2024 IEEE.

关键词： Functional neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Advanced machine learning in neuroimaging studies via federated learning

Advanced machine learning in neuroimaging studies via federa...

引用

2024 IEEE International Conference on Big data, Bigdata 2024

作者： Basodi, Sunitha Romero, Javier Panta, Sandeep Martin, Dylan Plis, Sergey Sarwate, Anand D. Calhoun, Vince D. Georgia State University Georgia Institute of Technology Emory University Tri-Institutional Center for Translational Research in Neuroimaging and Data Science AtlantaGA United States Rutgers University Department of Electrical & Computer Engineering NJ United States

ISBN: (纸本)9798350362480

Federated analysis can help perform large-scale analyses using neuroimaging datasets across various research groups overcoming the limitations of institutional data-sharing policies, privacy or regulatory concerns as it requires no data sharing. In this work, we employ a federated neuromark algorithm to generate independent component analysis (ICA) time courses data from functional magnetic resonance imaging (fMRI) data and feed it to a federated deep neural network (DNN) model to perform classification of schizophrenia patients versus controls. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Beyond Artifacts: Rethinking Motion-Related Signals in Resting-state fMRI Analysis

Beyond Artifacts: Rethinking Motion-Related Signals in Resti...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Samujjwal Kumar Spencer Kinsey Kyle M. Jensen Prerana Bajracharya Vince D. Calhoun Armin Iraji Tri-Institutional Center for Translational Research in Neuroimaging and Data Science Georgia State University

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Resting-state functional magnetic resonance imaging (rsfMRI) plays a pivotal role in estimating intrinsic brain functional connectivity within healthy and clinical populations. However, the pervasive impact of head motion confounds the interpretation of rsfMRI data and is typically addressed through preprocessing without further exploration. This investigation aims to scrutinize the intricate interplay between head motion and neurobiologically relevant BOLD signal as well as its potential clinical implications. Here, we use independent component analysis (ICA) to extract large-scale brain networks from BOLD fMRI and modeled head motion time series for 508 subjects sourced from three major psychosis projects. Our approach uncovers the presence of latent network information within modeled head motion data. Moreover, we find altered functional network connectivity (FNC) between healthy controls (HC) and individuals with schizophrenia (SZ) for BOLD and motion networks, revealing that projections of BOLD time series onto network features extracted from head motion data reflect cohort-specific information. Our approach challenges conventional perspectives by treating motion-related signals not as mere noise, but as potential repositories of valuable insights into functional brain connectivity across diverse populations.

关键词： Head Time series analysis Noise Independent component analysis Functional magnetic resonance imaging Feature extraction Brain modeling Magnetic heads data models Engineering in medicine and biology

来源：评论

学校读者我要写书评

暂无评论

Graph-based deep learning models in the prediction of early-stage Alzheimers 46

Graph-based deep learning models in the prediction of early-...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Thapaliya, Bishal Wu, Zundong Sapkota, Ram Ray, Bhaskar Suresh, Pranav Ghimire, Santosh Calhoun, Vince Liu, Jingyu Georgia State University Department of Computer Science Atlanta United States Tri-Institutional Center for Translational Research in Neuroimaging and Data Science United States Georgia Institute of Technology School of Electrical and Computer Engineering Atlanta United States Tribhuvan University Department of Applied Sciences and Chemical Engineering Nepal

ISBN: (纸本)9798350371499

Alzheimer's disease is the most common age-related problem and progresses in different stages, from cognitively normal to early mild cognitive impairment, and severe dementia. This study investigates the predictive potential of resting-state functional magnetic resonance imaging (rs-fMRI) and its derived functional connectivity (FC) in understanding Alzheimer's progression. Leveraging deep learning and graph-based models, we introduce two key contributions: 1) a comparative analysis of rs-fMRI time points and FC for Alzheimer's prediction. 2) an innovative graph transformer variant incorporating self-clustering for enhanced prediction accuracy. Experiments on the Alzheimer's Disease neuroimaging Initiative dataset with 830 subjects reveal two notable conclusions. Firstly, rs-fMRI time points offer limited utility compared to functional network connectivity for transformer-based models, even when considering temporal information. Secondly, a clustering-based attention module proves effective for classifying brain networks in predicting Alzheimer's disease progression, providing valuable insights for future research and clinical applications. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Evaluating Augmentation Approaches for Deep Learning-based Major Depressive Disorder Diagnosis with Raw Electroencephalogram data*

Evaluating Augmentation Approaches for Deep Learning-based M...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Charles A. Ellis Robyn L. Miller Vince D. Calhoun Center for Translational Research in Neuroimaging and Data Science Georgia State University Emory University Georgia Institute of Technology Atlanta USA

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

While deep learning methods are increasingly applied in research contexts for neuropsychiatric disorder diagnosis, small dataset size limits their potential for clinical translation. data augmentation (DA) could address this limitation, but the utility of EEG DA methods remains relatively underexplored in neuropsychiatric disorder diagnosis. In this study, we train a model for major depressive disorder diagnosis. We then evaluate the utility of 6 EEG DA approaches. Importantly, to remove the bias that could be introduced by comparing performance for models trained on larger augmented training sets to models trained on smaller baseline sets, we also introduce a new baseline trained on duplicate training data. We lastly examine the effects of the DA approaches upon representations learned by the model with a pair of explainability analyses. We find that while most approaches boost model performance, they do not improve model performance beyond that of simply using a duplicate training set without DA. The exception to this is channel dropout augmentation, which does improve model performance. These findings suggest the importance of comparing EEG DA methods to a baseline with a duplicate training set of equal size to the augmented training set. We also found that some DA methods increased model robustness to frequency (Fourier transform surrogates) and channel (channel dropout) perturbation. While our findings on EEG DA efficacy are restricted to our dataset and model, we hope that future studies on deep learning for small EEG datasets and on new EEG DA methods will find our findings helpful.

关键词： Training Deep learning Analytical models Perturbation methods Training data Brain modeling Depression Electroencephalography data models Robustness

来源：评论

学校读者我要写书评

暂无评论

Cross-Sampling Rate Transfer Learning for Enhanced Raw EEG Deep Learning Classifier Performance in Major Depressive Disorder Diagnosis

Cross-Sampling Rate Transfer Learning for Enhanced Raw EEG D...

引用

IEEE International Symposium on Biomedical Imaging

作者： Charles A. Ellis Robyn L. Miller Vince D. Calhoun Tri-Institutional Center for Translational Research in Neuroimaging Data Science at Georgia State University Emory University and Georgia Institute of Technology

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Transfer learning offers a route for developing robust deep learning models on small raw electroencephalography (EEG) datasets. Nevertheless, the utility of transferring representations from large datasets with lower sampling rates to smaller datasets with higher sampling rates is relatively unexplored. In this study, we transfer representations learned by a convolutional neural network on a large, publicly available sleep dataset (100 Hertz sampling rate) to a major depressive disorder (MDD) diagnosis task (200 Hertz sampling rate) and examine their effects upon the MDD models via spectral and spatial explainability analyses. Importantly, we find that the early convolutional layers have representations that are generalizable across tasks. Moreover, our approach significantly increases mean model accuracy from 82.33% to 86.99%, increases use of lower frequencies, (θ-band), and increases robustness to channel loss. We expect this analysis to provide useful guidance and enable more widespread use of transfer learning in EEG deep learning studies.

关键词： Deep learning Sleep Biological system modeling Transfer learning Brain modeling Depression Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Functionally-Adaptive Gray and White Matter Structural Basis Sets via Dynamic Fusion of Multimodal MRI data

Functionally-Adaptive Gray and White Matter Structural Basis...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Marlena Duda Vince D. Calhoun Center for Translational Research in Neuroimaging and Data Science Georgia State University Georgia Tech and Emory University Atlanta GA USA

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

The exact nature of the coupling of brain structure and function has long been an open area of research. Often, this question is approached by first defining a single structural basis set, and then estimating functional brain activation time courses as a linear combination of these structural bases. However, knowing that functional brain activity and connectivity vary over time, so might the nature of these structural/functional couplings. Thus, a single rigidly defined, "functionally unaware" structural manifold may be insufficient to describe structure/function linkages across a whole functional time series. Here, we introduce dynamic fusion, an ICA-based symmetric fusion, and show evidence that challenges current approaches and suggests time-resolved structural basis sets can better represent changing functional manifolds. We perform dynamic fusion using measures of both gray matter (GM) and white matter (WM) structure and present results that may indicate a stronger link between WM structure and dynamic brain function than in GM.

关键词： Couplings Manifolds Brain Magnetic resonance imaging Current measurement Time series analysis Grey matter White matter Engineering in medicine and biology Periodic structures

来源：评论

学校读者我要写书评

暂无评论

Identifying Neuropsychiatric Disorder Subtypes and Subtype-Dependent Variation in Diagnostic Deep Learning Classifier Performance

Identifying Neuropsychiatric Disorder Subtypes and Subtype-D...

引用

IEEE International Symposium on Biomedical Imaging

作者： Charles A. Ellis Robyn L. Miller Vince D. Calhoun Tri-Institutional Center for Translational Research in Neuroimaging and Data Science Georgia State University Emory University and the Georgia Institute of Technology

Clinicians and developers of deep learning-based neuroimaging clinical decision support systems (CDSS) need to know whether those systems will perform well for specific individuals. However, relatively few methods provide this capability. Identifying neuropsychiatric disorder subtypes for which CDSS may have varying performance could offer a solution. Dynamic functional network connectivity (dFNC) is often used to study disorders and develop neuroimaging classifiers. Unfortunately, few studies have identified neurological disorder subtypes using dFNC. In this study, we present a novel approach with which we identify 4 states of dFNC activity and 4 schizophrenia subtypes based on their time spent in each state. We also show how the performance of an explainable diagnostic deep learning classifier is subtype-dependent. We lastly examine how the dFNC features used by the classifier vary across subtypes. Our study provides a novel approach for subtyping disorders that (1) has implications for future scientific studies and (2) could lead to more reliable CDSS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Confirmatory Factor Analysis on Mental Health Status using ABCD Cohort

Confirmatory Factor Analysis on Mental Health Status using A...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Britny Farahdel Bishal Thapaliya Pranav Suresh Bhaskar Ray Vince D. Calhoun Jingyu Liu Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) Georgia State University Atlanta USA

ISBN: (纸本)9781665429825

The general psychopathology factor (p factor), derived from a wide range of psychological symptoms, is proposed to approximate an individual’s tendency to develop a broad range of psychiatric disorders. The aim of this study was to extract the general p factor in a bifactor model from confirmatory factor analysis (CFA), as well as internalizing and externalizing factors, and test the stability of the factors derived from different behavioral measures. Using data from the Adolescent Brain and Cognitive Development (ABCD) study, we compared the latent factors derived from Child Behavior Checklist measure (a standard approach) with those from broader measures. Multiple linear regression was used to assess the relationship of the p factor with other behavioral or cognition measures and clinical diagnoses. The results showed that the p factor had greater stability and a higher correlation between models (r=0.87) than internalizing and externalizing factors (r=0.32,0.02, respectively). The p factor explained significant variances in all dimensional behavioral variables as well as neurocognition and was significantly related to all mental disorders available. A mixed-effects model was constructed to measure the association of the p factor with screen time activity, sleep duration, physical activity, household income, and gender (altogether, these explained 8.02% of the variance in the p factor). The findings from this study also show that the general p factor defined in the bifactor model has sufficient determinacy.

关键词： Correlation Mental disorders Conferences Linear regression Mental health Biomedical measurement Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Learnt dynamics generalizes across tasks, datasets, and populations

arXiv

引用

arXiv 2019年

作者： Mahmood, U. Rahman, M.M. Fedorov, A. Fu, Z. Calhoun, V.D. Plis, S.M. Georgia State University Tri-institutional Center for Translational Research in Neuroimaging and Data Science AtlantaGA United States Georgia Institute of Technology Tri-institutional Center for Translational Research in Neuroimaging and Data Science AtlantaGA United States Emory University Tri-institutional Center for Translational Research in Neuroimaging and Data Science AtlantaGA United States

Differentiating multivariate dynamic signals is a difficult learning problem as the feature space may be large yet often only a few training examples are available. Traditional approaches to this problem either proceed from handcrafted features or require large datasets to combat the m >> n problem. In this paper, we show that the source of the problem-signal dynamics-can be used to our advantage and noticeably improve classification performance on a range of discrimination tasks when training data is scarce. We demonstrate that self-supervised pre-training guided by signal dynamics produces embedding that generalizes across tasks, datasets, data collection sites, and data distributions. We perform an extensive evaluation of this approach on a range of tasks including simulated data, keyword detection problem, and a range of functional neuroimaging data, where we show that a single embedding learnt on healthy subjects generalizes across a number of disorders, age groups, and datasets. Copyright © 2019, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：