Classification of Attention Deficit Hyperactivity Disorder using Variational Autoencoder

2021 ◽  
Vol 11 (2) ◽  
pp. 81-87
Author(s):  
Azurah A Samah ◽  
Siti Nurul Aqilah Ahmad ◽  
Hairudin Abdul Majid ◽  
Zuraini Ali Shah ◽  
Haslina Hashim ◽  
...  
Keyword(s):  
Attention Deficit Hyperactivity Disorder ◽  
Functional Connectivity ◽  
Attention Deficit ◽  
Early Stage ◽  
Region Of Interest ◽  
Brain Regions ◽  
Physical Symptoms ◽  
Medical Test ◽  
Hyperactivity Disorder ◽  
Variational Autoencoder

Attention Deficit Hyperactivity Disorder (ADHD) categorize as one of the typical neurodevelopmental and mental disorders. Over the years, researchers have identified ADHD as a complicated disorder since it is not directly tested with a standard medical test such as a blood or urine test on the early-stage diagnosis. Apart from the physical symptoms of ADHD, clinical data of ADHD patients show that most of them have learning problems. Therefore, functional Magnetic Resonance Imaging (fMRI) is considered the most suitable method to determine functional activity in the brain region to understand brain disorders of ADHD. One of the ways to diagnose ADHD is by using deep learning techniques, which can increase the accuracy of predicting ADHD using the fMRI dataset. Past attempts of classifying ADHD based on functional connectivity coefficient using the Deep Neural Network (DNN) result in 95% accuracy. As Variational Autoencoder (VAE) is the most popular in extracting high-level data, this model is applied in this study. This study aims to enhance the performance of VAE to increase the accuracy in classifying ADHD using fMRI data based on functional connectivity analysis. The preprocessed fMRI dataset is used for decomposition to find the region of interest (ROI), followed by Independent Component Analysis (ICA) that calculates the correlation between brain regions and creates functional connectivity matrices for each subject. As a result, the VAE model achieved an accuracy of 75% on classifying ADHD.

scholarly journals Brain Relatively Inert Network: Taking Adult Attention Deficit Hyperactivity Disorder as an Example

2021 ◽  
Vol 15 ◽  
Author(s):  
Hua Zhang ◽  
Weiming Zeng ◽  
Jin Deng ◽  
Yuhu Shi ◽  
Le Zhao ◽  
...  
Keyword(s):  
Attention Deficit Hyperactivity Disorder ◽  
Functional Connectivity ◽  
Attention Deficit ◽  
Information Integration ◽  
Adult Adhd ◽  
Brain Regions ◽  
Hyperactivity Disorder ◽  
Left Brain ◽  
The Right ◽  
The Brain

Resting-state functional MRI (rs-fMRI) has been increasingly applied in the research of brain cognitive science and psychiatric diseases. However, previous studies only focused on specific activation areas of the brain, and there are few studies on the inactivation areas. This may overlook much information that explains the brain’s cognitive function. In this paper, we propose a relatively inert network (RIN) and try to explore its important role in understanding the cognitive mechanism of the brain and the study of mental diseases, using adult attention deficit hyperactivity disorder (ADHD) as an example. Here, we utilize methods based on group independent component analysis (GICA) and t-test to identify RIN and calculate its corresponding time series. Through experiments, alterations in the RIN and the corresponding activation network (AN) in adult ADHD patients are observed. And compared with those in the left brain, the activation changes in the right brain are greater. Further, when the RIN functional connectivity is introduced as a feature to classify adult ADHD patients from healthy controls (HCs), the classification accuracy rate is 12% higher than that of the original functional connectivity feature. This was also verified by testing on an independent public dataset. These findings confirm that the RIN of the brain contains much information that will probably be neglected. Moreover, this research provides an effective new means of exploring the information integration between brain regions and the diagnosis of mental illness.

scholarly journals Brain functional connectivity abnormalities in attention‐deficit hyperactivity disorder

2016 ◽  
Vol 6 (12) ◽  
Author(s):  
Richard B. Silberstein ◽  
Andrew Pipingas ◽  
Maree Farrow ◽  
Florence Levy ◽  
Con K. Stough ◽  
...  
Keyword(s):  
Attention Deficit Hyperactivity Disorder ◽  
Functional Connectivity ◽  
Attention Deficit ◽  
Hyperactivity Disorder ◽  
Brain Functional Connectivity

scholarly journals Causal connectivity abnormalities of regional homogeneity in children with attention deficit hyperactivity disorder: a rest-state fMRI study

ADMET & DMPK ◽  
2017 ◽  
Vol 5 (4) ◽  
pp. 242-252 ◽  
Author(s):  
Dechun Zhao ◽  
Shuxing Zheng ◽  
Li Yang ◽  
Yin Tian
Keyword(s):  
Attention Deficit Hyperactivity Disorder ◽  
Attention Deficit ◽  
Low Frequency ◽  
Brain Regions ◽  
Regional Homogeneity ◽  
Support Vector ◽  
Attention And Memory ◽  
Causality Analysis ◽  
Hyperactivity Disorder ◽  
Significant Difference

The present study aimed to investigate individual differences of causal connectivity between brain regions in attention deficit hyperactivity disorder (ADHD) which was a psychiatric disorder. Resting-state functional magnetic resonance imaging (R-fMRI) data of typically-developing controls (TDC) children group and combined ADHD (ADHD-C) children group were distinguished by the support vector machine (SVM) with linear kernel function, based on regional homogeneity (ReHo), amplitude of low frequency fluctuation (ALFF) and fractional ALFF (FALFF). The highest classification accuracy yielded by ReHo was 90.91 %. Furthermore, the granger causality analysis (GCA) method based on the classified weight map of regions of interesting (ROIs) showed that five causal flows existed significant difference between TDC and ADHD-C. That is, the averaged GCA values of three causal connections (i.e. left VLPFC à left CC1, right PoCG à left CC1, and right PoCG à right CC2) for ADHD-C were separately stronger than those for TDC. And the other two connections (i.e. right FEF à right SOG and right CC1 à right SOG) were weaker for ADHD-C than those for TDC. In addition, only two causality flows (i.e. left VLPFC à left CC1 and right PoCG à right CC2) presented that their GCA values were positively correlation with ADHD index scores, respectively. Our findings revealed that ADHD children represented widespread abnormalities in the causality connectivity, especially involved in the attention and memory related regions. And further provided evidence that the potential neural causality flows could play a key role in characterizing individual’s ADHD.

scholarly journals Neural correlates of shared sensory symptoms in autism and attention-deficit/hyperactivity disorder

2020 ◽  
Vol 2 (2) ◽  
Author(s):  
Takashi Itahashi ◽  
Junya Fujino ◽  
Taku Sato ◽  
Haruhisa Ohta ◽  
Motoaki Nakamura ◽  
...  
Keyword(s):  
Autism Spectrum Disorder ◽  
Attention Deficit Hyperactivity Disorder ◽  
Functional Connectivity ◽  
Attention Deficit ◽  
Neural Correlates ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Hyperactivity Disorder ◽  
Sensory Symptom ◽  
Brain Functional Connectivity

Abstract Symptoms of autism spectrum disorder and attention-deficit/hyperactivity disorder often co-occur. Among these, sensory impairment, which is a core diagnostic feature of autism spectrum disorder, is often observed in children with attention-deficit/hyperactivity disorder. However, the underlying mechanisms of symptoms that are shared across disorders remain unknown. To examine the neural correlates of sensory symptoms that are associated with autism spectrum disorder and attention-deficit/hyperactivity disorder, we analysed resting-state functional MRI data obtained from 113 people with either autism spectrum disorder or attention-deficit/hyperactivity disorder (n = 78 autism spectrum disorder, mean age = 29.5; n = 35 attention-deficit/hyperactivity disorder, mean age = 31.2) and 96 neurotypical controls (mean age = 30.6, range: 20–55 years) using a cross-sectional study design. First, we used a multi-dimensional approach to examine intrinsic brain functional connectivity related to sensory symptoms in four domains (i.e. low registration, sensation seeking, sensory sensitivity and sensation avoidance), after controlling for age, handedness and head motion. Then, we used a partial least squares correlation to examine the link between sensory symptoms related to intrinsic brain functional connectivity and neurodevelopmental symptoms measured using the Autism Spectrum Quotient and Conners’ Adult Attention-Deficit/Hyperactivity Disorder Rating Scale, regardless of diagnosis. To test whether observed associations were specific to sensory symptoms related to intrinsic brain functional connectivity, we conducted a control analysis using a bootstrap framework. The results indicated that transdiagnostic yet distinct intrinsic brain functional connectivity neural bases varied according to the domain of the examined sensory symptom. Partial least squares correlation analysis revealed two latent components (latent component 1: q < 0.001 and latent component 2: q < 0.001). For latent component 1, a set of intrinsic brain functional connectivity was predominantly associated with neurodevelopmental symptom-related composite score (r = 0.64, P < 0.001), which was significantly correlated with Conners’ Adult Attention-Deficit/Hyperactivity Disorder Rating Scale total T scores (r = −0.99, q < 0.001). For latent component 2, another set of intrinsic brain functional connectivity was positively associated with neurodevelopmental symptom-related composite score (r = 0.58, P < 0.001), which was eventually positively associated with Autism Spectrum Quotient total scores (r = 0.92, q < 0.001). The bootstrap analysis showed that the relationship between intrinsic brain functional connectivity and neurodevelopmental symptoms was relative to sensory symptom-related intrinsic brain functional connectivity (latent component 1: P = 0.003 and latent component 2: P < 0.001). The current results suggest that sensory symptoms in individuals with autism spectrum disorder and those with attention-deficit/hyperactivity disorder have shared neural correlates. The neural correlates of the sensory symptoms were associated with the severity of both autism spectrum disorder and attention-deficit/hyperactivity disorder symptoms, regardless of diagnosis.

scholarly journals Stepwise functional connectivity reveals altered sensory‐multimodal integration in medication‐naïve adults with attention deficit hyperactivity disorder

2019 ◽  
Vol 40 (16) ◽  
pp. 4645-4656 ◽  
Author(s):  
Clara Pretus ◽  
Luis Marcos‐Vidal ◽  
Magdalena Martínez‐García ◽  
Marisol Picado ◽  
Josep Antoni Ramos‐Quiroga ◽  
...  
Keyword(s):  
Attention Deficit Hyperactivity Disorder ◽  
Functional Connectivity ◽  
Attention Deficit ◽  
Multimodal Integration ◽  
Hyperactivity Disorder

Brain development in attention deficit hyperactivity disorder: A neuroimaging perspective review

2016 ◽  
Vol 33 (S1) ◽  
pp. S357-S357 ◽  
Author(s):  
V. Pereira ◽  
P. de Castro-Manglano ◽  
C. Soutullo Esperon
Keyword(s):  
Attention Deficit Hyperactivity Disorder ◽  
Functional Connectivity ◽  
Brain Development ◽  
Attention Deficit ◽  
Default Mode Network ◽  
Brain Connectivity ◽  
Child And Adolescent Psychiatry ◽  
Global Perspective ◽  
Default Mode ◽  
Hyperactivity Disorder

IntroductionAttention deficit hyperactivity disorder (ADHD) is a challenge in child and adolescent psychiatry. In the recent decades many studies with longitudinal designs have used neuroimaging with ADHD patients, suggesting its neurodevelopmental origin.ObjectivesStudy the findings of neuroimaging (MRI, fMRI, DTI, PET) techniques on ADHD patients from a longitudinal point of view, looking also for the potential influence of treatments and other predictors (i.e. genetics).AimsTo provide a global perspective of all the recent findings on ADHD patients with the neuroimaging technics, focusing on longitudinal measurements of the changes in brain development.MethodsWe conducted a review of the literature in the databases Pubmed and ScienceDirect (terms ADHD, neuroimaging, MRI, fMRI, DTI, PET, functional connectivity, metilphenidate and cortical thickness). We focused on studies using neuroimaging techniques with ADHD patients, looking at their populations, methodologies and results.ResultsThe studies found abnormalities in the structure of grey matter, activity and brain connectivity in many neural networks, with particular involvement of the fronto-parietal and Default Mode Network. There is also convergent evidence for white matter pathology and disrupted anatomical connectivity in ADHD. In addition, dysfunctional connectivity during rest and during cognitive tasks has been demonstrated.ConclusionsThis evidence describe ADHD as a brain development disorder, with delays and disruptions in the global development of the central nervous system that compromises grey and white matters, most evident in the prefrontal cortex, parietal and posterior cingulate cortices, as well as basal ganglia, damaging activity and structural and functional connectivity of various brain networks, especially the fronto-striato-parietal and default mode network.Disclosure of interestThe authors have not supplied their declaration of competing interest.

Sign in / Sign up

Export Citation Format

Share Document