scholarly journals BrainNET: Inference of Brain Network Topology Using Machine Learning

2020 ◽  
Vol 10 (8) ◽  
pp. 422-435
Author(s):  
Gowtham Krishnan Murugesan ◽  
Chandan Ganesh ◽  
Sahil Nalawade ◽  
Elizabeth M. Davenport ◽  
Ben Wagner ◽  
...  
Keyword(s):  
Machine Learning ◽  
Network Topology ◽  
Brain Network

scholarly journals BrainNET: Inference of brain network topology using Machine Learning

2019 ◽  
Author(s):  
Gowtham Krishnan Murugesan ◽  
Chandan Ganesh ◽  
Sahil Nalawade ◽  
Elizabeth M Davenport ◽  
Ben Wagner ◽  
...  
Keyword(s):  
Machine Learning ◽  
Network Topology ◽  
Network Inference ◽  
Learning Algorithm ◽  
Ground Truth ◽  
Brain Network ◽  
Fmri Data ◽  
Method Performance ◽  
Graph Metrics ◽  
Network Topologies

AbstractObjectiveTo develop a new fMRI network inference method, BrainNET, that utilizes an efficient machine learning algorithm to quantify contributions of various regions of interests (ROIs) in the brain to a specific ROI.MethodsBrainNET is based on Extremely Randomized Trees (ERT) to estimate network topology from fMRI data and modified to generate an adjacency matrix representing brain network topology, without reliance on arbitrary thresholds. Open source simulated fMRI data of fifty subjects in twenty-eight different simulations under various confounding conditions with known ground truth was used to validate the method. Performance was compared with correlation and partial correlation (PC). The real-world performance was then evaluated in a publicly available Attention-deficit/hyperactivity disorder (ADHD) dataset including 134 Typically Developing Children (mean age: 12.03, males: 83), 75 ADHD Inattentive (mean age: 11.46, males: 56) and 93 ADHD Combined (mean age: 11.86, males: 77) subjects. Network topologies in ADHD were inferred using BrainNET, correlation, and PC. Graph metrics were extracted to determine differences between the ADHD groups.ResultsBrainNET demonstrated excellent performance across all simulations and varying confounders in identifying true presence of connections. In the ADHD dataset, BrainNET was able to identify significant changes (p< 0.05) in graph metrics between groups. No significant changes in graph metrics between ADHD groups was identified using correlation and PC.

Machine Learning Enables Rapid Screening of Reactive Fly Ashes Based on Their Network Topology

2021 ◽  
Vol 9 (7) ◽  
pp. 2639-2650
Author(s):  
Yu Song ◽  
Kai Yang ◽  
Jingyi Chen ◽  
Kaixin Wang ◽  
Gaurav Sant ◽  
...  
Keyword(s):  
Machine Learning ◽  
Network Topology ◽  
Rapid Screening ◽  
Fly Ashes

scholarly journals Distinct network topology in Alzheimer’s disease and behavioral variant frontotemporal dementia

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Adeline Su Lyn Ng ◽  
Juan Wang ◽  
Kwun Kei Ng ◽  
Joanna Su Xian Chong ◽  
Xing Qian ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Frontotemporal Dementia ◽  
Network Topology ◽  
Neuropsychiatric Symptoms ◽  
Brain Network ◽  
Salience Network ◽  
Behavioral Variant Frontotemporal Dementia ◽  
Control Networks ◽  
And Control

Abstract Background Alzheimer’s disease (AD) and behavioral variant frontotemporal dementia (bvFTD) cause distinct atrophy and functional disruptions within two major intrinsic brain networks, namely the default network and the salience network, respectively. It remains unclear if inter-network relationships and whole-brain network topology are also altered and underpin cognitive and social–emotional functional deficits. Methods In total, 111 participants (50 AD, 14 bvFTD, and 47 age- and gender-matched healthy controls) underwent resting-state functional magnetic resonance imaging (fMRI) and neuropsychological assessments. Functional connectivity was derived among 144 brain regions of interest. Graph theoretical analysis was applied to characterize network integration, segregation, and module distinctiveness (degree centrality, nodal efficiency, within-module degree, and participation coefficient) in AD, bvFTD, and healthy participants. Group differences in graph theoretical measures and empirically derived network community structures, as well as the associations between these indices and cognitive performance and neuropsychiatric symptoms, were subject to general linear models, with age, gender, education, motion, and scanner type controlled. Results Our results suggested that AD had lower integration in the default and control networks, while bvFTD exhibited disrupted integration in the salience network. Interestingly, AD and bvFTD had the highest and lowest degree of integration in the thalamus, respectively. Such divergence in topological aberration was recapitulated in network segregation and module distinctiveness loss, with AD showing poorer modular structure between the default and control networks, and bvFTD having more fragmented modules in the salience network and subcortical regions. Importantly, aberrations in network topology were related to worse attention deficits and greater severity in neuropsychiatric symptoms across syndromes. Conclusions Our findings underscore the reciprocal relationships between the default, control, and salience networks that may account for the cognitive decline and neuropsychiatric symptoms in dementia.

scholarly journals Characterization of the resting-state brain network topology in the 6-hydroxydopamine rat model of Parkinson’s disease

PLoS ONE ◽  
2017 ◽  
Vol 12 (3) ◽  
pp. e0172394 ◽  
Author(s):  
Robert Westphal ◽  
Camilla Simmons ◽  
Michel B. Mesquita ◽  
Tobias C. Wood ◽  
Steve C. R. Williams ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Network Topology ◽  
Rat Model ◽  
Resting State ◽  
Brain Network ◽  
6 Hydroxydopamine

scholarly journals Alterations in Brain Network Topology and Structural-Functional Connectome Coupling Relate to Cognitive Impairment

2018 ◽  
Vol 10 ◽  
Author(s):  
Juan Wang ◽  
Reza Khosrowabadi ◽  
Kwun Kei Ng ◽  
Zhaoping Hong ◽  
Joanna Su Xian Chong ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Network Topology ◽  
Brain Network ◽  
Functional Connectome

scholarly journals RESEARCH ON BRAIN NETWORK CLASSIFICATION METHOD BASED ON INTEGRATED MODEL

2020 ◽  
pp. 1-2
Author(s):  
Zhang- sensen
Keyword(s):  
Machine Learning ◽  
Classification Accuracy ◽  
Brain Network ◽  
Classification Model ◽  
Comparative Experiment ◽  
Machine Learning Methods ◽  
Healthy Elderly ◽  
Healthy Elderly People ◽  
The Brain

mild cognitive impairment (MCI) is a condition between healthy elderly people and alzheimer's disease (AD). At present, brain network analysis based on machine learning methods can help diagnose MCI. In this paper, the brain network is divided into several subnets based on the shortest path,and the feature vectors of each subnet are extracted and classified. In order to make full use of subnet information, this paper adopts integrated classification model for classification.Each base classification model can predict the classification of a subnet,and the classification results of all subnets are calculated as the classification results of brain network.In order to verify the effectiveness of this method,a brain network of 66 people was constructed and a comparative experiment was carried out.The experimental results show that the classification accuracy of the integrated classification model proposed in this paper is 19% higher than that of SVM,which effectively improves the classification accuracy

Sign in / Sign up

Export Citation Format

Share Document