scholarly journals Increased Gray Matter Volume and Resting-State Functional Connectivity in Somatosensory Cortex and their Relationship with Autistic Symptoms in Young Boys with Autism Spectrum Disorder

2017 ◽  
Vol 8 ◽  
Author(s):  
Jia Wang ◽  
Kuang Fu ◽  
Lei Chen ◽  
Xujun Duan ◽  
Xiaonan Guo ◽  
...  
Keyword(s):  
Autism Spectrum Disorder ◽  
Functional Connectivity ◽  
Somatosensory Cortex ◽  
Gray Matter ◽  
Resting State ◽  
Gray Matter Volume ◽  
Autism Spectrum ◽  
Resting State Functional Connectivity ◽  
Matter Volume ◽  
Autistic Symptoms

scholarly journals Interpretable Learning Approaches in Resting-State Functional Connectivity Analysis: The Case of Autism Spectrum Disorder

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Jinlong Hu ◽  
Lijie Cao ◽  
Tenghui Li ◽  
Bin Liao ◽  
Shoubin Dong ◽  
...  
Keyword(s):  
Neural Network ◽  
Autism Spectrum Disorder ◽  
Functional Connectivity ◽  
Resting State ◽  
Piecewise Linear ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Fmri Data ◽  
Support Vector ◽  
Resting State Functional Connectivity

Deep neural networks have recently been applied to the study of brain disorders such as autism spectrum disorder (ASD) with great success. However, the internal logics of these networks are difficult to interpret, especially with regard to how specific network architecture decisions are made. In this paper, we study an interpretable neural network model as a method to identify ASD participants from functional magnetic resonance imaging (fMRI) data and interpret results of the model in a precise and consistent manner. First, we propose an interpretable fully connected neural network (FCNN) to classify two groups, ASD versus healthy controls (HC), based on input data from resting-state functional connectivity (rsFC) between regions of interests (ROIs). The proposed FCNN model is a piecewise linear neural network (PLNN) which uses piecewise linear function LeakyReLU as its activation function. We experimentally compared the FCNN model against widely used classification models including support vector machine (SVM), random forest, and two new classes of deep neural network models in a large dataset containing 871 subjects from ABIDE I database. The results show the proposed FCNN model achieves the highest classification accuracy. Second, we further propose an interpreting method which could explain the trained model precisely with a precise linear formula for each input sample and decision features which contributed most to the classification of ASD versus HC participants in the model. We also discuss the implications of our proposed approach for fMRI data classification and interpretation.

scholarly journals Association between cytomegalovirus infection, reduced gray matter volume, and resting-state functional hypoconnectivity in major depressive disorder: a replication and extension

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Haixia Zheng ◽  
Bart N. Ford ◽  
Rayus Kuplicki ◽  
Kaiping Burrows ◽  
Peter W. Hunt ◽  
...  
Keyword(s):  
Major Depressive Disorder ◽  
Depressive Disorder ◽  
Gray Matter ◽  
Resting State ◽  
Gray Matter Volume ◽  
Brain Regions ◽  
Affective Processing ◽  
Resting State Functional Connectivity ◽  
Major Depressive ◽  
Matter Volume

AbstractHuman cytomegalovirus (HCMV) is a neurotropic herpes virus known to cause neuropathology in patients with impaired immunity. Previously, we reported a reduction in the gray matter volume (GMV) of several brain regions in two independent samples of participants who were seropositive for HCMV (HCMV+) compared to matched participants who were seronegative for HCMV (HCMV−). In addition to an independent replication of the GMV findings, this study aimed to examine whether HCMV+ was associated with differences in resting-state functional connectivity (rsfMRI-FC). After balancing on 11 clinical/demographic variables using inverse probability of treatment weighting (IPTW), GMV and rsfMRI-FC were obtained from 99 participants with major depressive disorder (MDD) who were classified into 42 HCMV+ and 57 HCMV− individuals. Relative to the HCMV− group, the HCMV+ group showed a significant reduction of GMV in nine cortical regions. Volume reduction in the right lateral orbitofrontal cortex (standardized beta coefficient (SBC) = −0.32, [95%CI, −0.62 to −0.02]) and the left pars orbitalis (SBC = −0.34, [95%CI, −0.63 to −0.05]) in the HCMV+ group was also observed in the previous study. Regardless of the parcellation method or analytical approach, relative to the HCMV− group, the HCMV+ group showed hypoconnectivity between the hubs of the sensorimotor network (bilateral postcentral gyrus) and the hubs of the salience network (bilateral insula) with effect sizes ranging from SBC = −0.57 to −0.99. These findings support the hypothesis that a positive HCMV serostatus is associated with altered connectivity of regions that are important for stress and affective processing and further supports a possible etiological role of HCMV in depression.

Sign in / Sign up

Export Citation Format

Share Document