scholarly journals DarkASDNet: Classification of ASD on Functional MRI Using Deep Neural Network

2021 ◽  
Vol 15 ◽  
Author(s):  
Md Shale Ahammed ◽  
Sijie Niu ◽  
Md Rishad Ahmed ◽  
Jiwen Dong ◽  
Xizhan Gao ◽  
...  
Keyword(s):  
Performance Metrics ◽  
Binary Classification ◽  
Autism Spectrum ◽  
Fmri Data ◽  
Brain Scans ◽  
Avant Garde ◽  
Non Invasive ◽  
Time Correction ◽  
The Brain

Non-invasive whole-brain scans aid the diagnosis of neuropsychiatric disorder diseases such as autism, dementia, and brain cancer. The assessable analysis for autism spectrum disorders (ASD) is rationally challenging due to the limitations of publicly available datasets. For diagnostic or prognostic tools, functional Magnetic Resonance Imaging (fMRI) exposed affirmation to the biomarkers in neuroimaging research because of fMRI pickup inherent connectivity between the brain and regions. There are profound studies in ASD with introducing machine learning or deep learning methods that have manifested advanced steps for ASD predictions based on fMRI data. However, utmost antecedent models have an inadequacy in their capacity to manipulate performance metrics such as accuracy, precision, recall, and F1-score. To overcome these problems, we proposed an avant-garde DarkASDNet, which has the competence to extract features from a lower level to a higher level and bring out promising results. In this work, we considered 3D fMRI data to predict binary classification between ASD and typical control (TC). Firstly, we pre-processed the 3D fMRI data by adopting proper slice time correction and normalization. Then, we introduced a novel DarkASDNet which surpassed the benchmark accuracy for the classification of ASD. Our model's outcomes unveil that our proposed method established state-of-the-art accuracy of 94.70% to classify ASD vs. TC in ABIDE-I, NYU dataset. Finally, we contemplated our model by performing evaluation metrics including precision, recall, F1-score, ROC curve, and AUC score, and legitimize by distinguishing with recent literature descriptions to vindicate our outcomes. The proposed DarkASDNet architecture provides a novel benchmark approach for ASD classification using fMRI processed data.

Screening and Diagnosis of Autism Spectrum Disorder via Assistive Tools

2022 ◽  
pp. 1-21
Author(s):  
Gurkan Tuna ◽  
Ayşe Tuna
Keyword(s):  
Autism Spectrum Disorder ◽  
Random Forest ◽  
Performance Metrics ◽  
Autism Spectrum ◽  
Repetitive Behaviors ◽  
Spectrum Disorder ◽  
K Nearest Neighbors ◽  
Medical Test ◽  
And Behavior

Autism spectrum disorder (ASD) is a challenging developmental condition that involves restricted and/or repetitive behaviors and persistent challenges in social interaction and speech and nonverbal communication. There is not a standard medical test used to diagnose ASD; therefore, diagnosis is made by looking at the child's developmental history and behavior. In recent years, due to the increase in diagnosed cases of ASD, researchers proposed software-based tools to aid in and expedite the diagnosis. Considering the fact that most of these tools rely on the use of classifiers, in study, random forest, decision tree, k-nearest neighbors, and zero rule algorithms are used as classifiers, and their performances are compared using well-known performance metrics. As proven in the study, random forest algorithm can provide higher accuracy than the others in the classification of ASD and can be integrated into a computer- or humanoid-robot-based system for automated prescreening and diagnosis of ASD in preschool children groups.

scholarly journals Predictability changes what we remember in familiar temporal contexts

2018 ◽  
Author(s):  
Hyojeong Kim ◽  
Margaret L. Schlichting ◽  
Alison R. Preston ◽  
Jarrod A. Lewis-Peacock
Keyword(s):  
Human Brain ◽  
Pattern Classification ◽  
Prediction Error ◽  
Fmri Data ◽  
The Past ◽  
The Future ◽  
Abstract Level ◽  
Episodic Memories ◽  
The Brain

AbstractThe human brain constantly anticipates the future based on memories of the past. Encountering a familiar situation reactivates memory of previous encounters which can trigger a prediction of what comes next to facilitate responsiveness. However, a prediction error can lead to pruning of the offending memory, a process that weakens its representation in the brain and leads to forgetting. Our goal in this study was to evaluate whether memories are spared from pruning in situations that allow for more abstract yet reliable predictions. We hypothesized that when the category, but not the identity, of a new stimulus can be anticipated, this will reduce pruning of existing memories and also reduce encoding of the specifics of new memories. Participants viewed a sequence of objects, some of which reappeared multiple times (“cues”), followed always by novel items. Half of the cues were followed by new items from different (unpredictable) categories, while others were followed by new items from a single (predictable) category. Pattern classification of fMRI data was used to identify category-specific predictions after each cue. Pruning was observed only in unpredictable contexts, while encoding of new items suffered more in predictable contexts. These findings demonstrate that how episodic memories are updated is influenced by the reliability of abstract-level predictions in familiar contexts.

scholarly journals Predictability Changes What We Remember in Familiar Temporal Contexts

2020 ◽  
Vol 32 (1) ◽  
pp. 124-140 ◽  
Author(s):  
Hyojeong Kim ◽  
Margaret L. Schlichting ◽  
Alison R. Preston ◽  
Jarrod A. Lewis-Peacock
Keyword(s):  
Human Brain ◽  
Prediction Error ◽  
Fmri Data ◽  
Prediction Errors ◽  
Associative Memories ◽  
The Past ◽  
Item Level ◽  
Abstract Level ◽  
The Brain

The human brain constantly anticipates the future based on memories of the past. Encountering a familiar situation reactivates memory of previous encounters, which can trigger a prediction of what comes next to facilitate responsiveness. However, a prediction error can lead to pruning of the offending memory, a process that weakens its representation in the brain and leads to forgetting. Our goal in this study was to evaluate whether memories are spared from such pruning in situations that allow for accurate predictions at the categorical level, despite prediction errors at the item level. Participants viewed a sequence of objects, some of which reappeared multiple times (“cues”), followed always by novel items. Half of the cues were followed by new items from different (unpredictable) categories, while others were followed by new items from a single (predictable) category. Pattern classification of fMRI data was used to identify category-specific predictions after each cue. Pruning was observed only in unpredictable contexts, while encoding of new items was less robust in predictable contexts. These findings demonstrate that how associative memories are updated is influenced by the reliability of abstract-level predictions in familiar contexts.

scholarly journals Recognition of Gender using Gait Energy Image Projections Based on Random Forest Classifier

2019 ◽  
Vol 8 (12) ◽  
pp. 1518-1523
Keyword(s):  
Performance Metrics ◽  
Ensemble Classifier ◽  
Person Identification ◽  
Projection Model ◽  
Non Invasive ◽  
Second Stage ◽  
Gait Energy Image ◽  
Image Projections ◽  
The Individual

Identification of gender is a very fascinating criterion in the present day scenario. Especially, in the surveillance applications, gender recognition is very beneficial. With the use of face, speech, voice and gait, the gender of a person can be determined. Non-contact, non-invasive and easily acquired at distance, gait analysis has attracted the interest of many researchers in the classification of gender. For the identification of gender, 2 stages of the methodology are used in our proposed work. A new descriptor called Gait energy image projection model(GPM) is proposed which highlights all the gender-related parameters. In the second stage of methodology, proposed descriptor GPM is fused with already existing descriptors like GEI and FED for enhanced performance. For classifying the gender, an Ensemble classifier called Random Forests is applied to the individual and fused descriptors and the results are evaluated. Two datasets are used for experimentation namely CASIA B and OU-ISIR datasets which are standard datasets for person identification and different performance metrics such as accuracy, precision, recall and error rate are evaluated.

Psychiatric Neuroethics II

2015 ◽  
Author(s):  
Walter Glannon
Keyword(s):  
Effective Treatment ◽  
Psychiatric Disorders ◽  
Genetic Screening ◽  
Ethical Issues ◽  
Clinical Settings ◽  
Intracranial Surgery ◽  
Non Invasive ◽  
Invasive Techniques ◽  
The Brain

I discuss ethical issues relating to interventions other than intracranial surgery and psychopharmacology for psychiatric disorders. I question the distinction between “invasive” and “non-invasive” techniques applying electrical stimulation to the brain, arguing that this should be replaced by a distinction between more and less invasive techniques. I discuss electroconvulsive therapy (ECT); it can be a relatively safe and effective treatment for some patients with depression. I consider transcranial magnetic stimulation (TMS) and transcranial current stimulation (tCS); the classification of these techniques as non-invasive may lead to underestimation of their risks. I discuss how placebos can justifiably be prescribed non-deceptively and even deceptively in clinical settings. An analysis of neurofeedback as the neuromodulating technique most likely to promote autonomy/control for some conditions follows. Finally, I examine biomarkers identified through genetic screening and neuroimaging; they might contribute to more accurate prediction and diagnosis, more effective treatment, and possibly prevention of psychiatric disorders.

scholarly journals A Convolutional Neural Network Model to Differentiate Attention Deficit Hyperactivity Disorder and Autism Spectrum Disorder Based on the Resting State fMRI Data

2021 ◽  
Author(s):  
Azadeh Mozhdehfarahbakhsh ◽  
Amirsaeid Moloodi ◽  
Prasun Chakrabarti ◽  
KS Jagannatha Rao ◽  
Babak Kateb ◽  
...  
Keyword(s):  
Neural Network ◽  
Autism Spectrum Disorder ◽  
Attention Deficit Hyperactivity Disorder ◽  
Convolutional Neural Network ◽  
Neural Network Model ◽  
Resting State ◽  
Autism Spectrum ◽  
Fmri Data ◽  
Hyperactivity Disorder ◽  
The Brain

Background and Objectives: Attention Deficit Hyperactivity Disorder (ADHD) and Autism Spectrum Disorder (ASD) are the two most common neurodevelopmental disorders often with overlapping symptoms. Misdiagnosis of these disorders is the leading cause of a variety of problems including inappropriate interventions and improper treatment outcome. Over the last few years, resting state functional magnetic Resonance imaging (rs-fMRI) has received clinical attention among other beneficial brain scan techniques to extract functional connectivity in the brain. However, extracting useful information by human observation is prone to errors. Material and Methods: The above unmet need prompted us to design the present investigation to construct a convolutional neural network model with 12 layers architecture in rsFMRI data aiming to differentiate the two conditions. The rs-fMRI data was collected from the ADHD-200 and ABIDE to feed into a convolutional neural network. Over the preprocessing phase, we have removed undesirable data and coordinated the remaining to MSDL atlas to recruit 39 regions of the brain. Results: Ultimately, out results obtained a 0.92 accuracy, an AUC of 0.97 and loss of 0.17 in classification and discrimination of ADHD and ASD. Conclusion: Though cross-validity with larger datasets is deemed required, the results obtained from the present investigation suggest that convolutional neural network may serve as a beneficial tool to differentiate ADHD and ASD from relatively small fMRI datasets. This further highlights the potential application of deep neural networks for serving the above purpose.

scholarly journals Comparing fMRI inter-subject correlations between groups using permutation tests

2018 ◽  
Author(s):  
Jussi Tohka ◽  
Frank E. Pollick ◽  
Juha Pajula ◽  
Jukka-Pekka Kauppi
Keyword(s):  
Open Source Software ◽  
Permutation Tests ◽  
Autism Spectrum ◽  
Fmri Data ◽  
Data Sets ◽  
Adult Males ◽  
Functional Magnetic Resonance ◽  
Null Distributions ◽  
Open Source Software Package ◽  
The Brain

AbstractInter-subject correlation (ISC) based analysis is a conceptually simple approach to analyze functional magnetic resonance imaging (fMRI) data acquired under naturalistic stimuli such as a movie. We describe and validate the statistical approaches for comparing ISCs between two groups of subjects implemented in the ISC toolbox, which is an open source software package for ISC-based analysis of fMRI data. The approaches are based on permutation tests. We validated the approaches using five different data sets from the ICBM functional reference battery tasks. First, we created five null datasets (one for each task) by dividing the subjects into two matched groups and assumed that no group difference exists. Second, based on one null dataset, we created datasets with simulated ISC differences of varying size between the two groups. Based on the experiments with these two types of data, we recommend the use of subject-wise permutations, instead of element-wise permutations. The tests based on subject-wise permutations led to correct false positive rates. We observed that the null-distributions should be voxel-specific and not based on pooling all voxels across the brain as is typical in fMRI. This was the case even if studentized permutation tests were used. Additionally, we experimented with an fMRI dataset acquired using a dance movie stimulus for comparison of a group of adult males on the autism spectrum to a matched typically developed group. The experiment confirmed the differences between voxel-based permutation tests and global model based permutation tests.

scholarly journals Aberrant neuroplasticity in autism spectrum disorder

2021 ◽  
Vol 6 (8) ◽  
Keyword(s):  
Autism Spectrum Disorder ◽  
Transcranial Magnetic Stimulation ◽  
Magnetic Stimulation ◽  
Therapeutic Potential ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Future Directions ◽  
Non Invasive ◽  
Repetitive Tms ◽  
The Brain

Developments have taken place within the neurobiology research in Autism spectrum disorder (ASD), and results from these studies indicate that the brain in ASD is related to aberrant neuroplasticity. Transcranial magnetic stimulation (TMS) has quickly evolved to become a widely used, safe, and non-invasive neuroscientific tool to analyze a spread of neuroscience processes, as neuroplasticity. The diagnostic and therapeutic potential of TMS in ASD is setting out to be realized. during this article, we concisely reviewed the proof of aberrant neuroplasticity in ASD, steered future directions in assessing neuroplasticity exploitation repetitive TMS (rTMS), and mentioned the potential of rTMS in rectifying aberrant neuroplasticity in ASD.

scholarly journals Electroencephalogram (EEG) for Delineating Objective Measure of Autism Spectrum Disorder

2019 ◽  
pp. 34-65 ◽  
Author(s):  
Sampath Jayarathna ◽  
Yasith Jayawardana ◽  
Mark Jaime ◽  
Sashi Thapaliya
Keyword(s):  
Autism Spectrum Disorder ◽  
Negative Impact ◽  
Objective Measure ◽  
Autism Spectrum ◽  
Machine Learning Algorithms ◽  
Spectrum Disorder ◽  
The Us ◽  
Electric Signals ◽  
The Brain

Autism spectrum disorder (ASD) is a developmental disorder that often impairs a child's normal development of the brain. According to CDC, it is estimated that 1 in 6 children in the US suffer from development disorders, and 1 in 68 children in the US suffer from ASD. This condition has a negative impact on a person's ability to hear, socialize, and communicate. Subjective measures often take more time, resources, and have false positives or false negatives. There is a need for efficient objective measures that can help in diagnosing this disease early as possible with less effort. EEG measures the electric signals of the brain via electrodes placed on various places on the scalp. These signals can be used to study complex neuropsychiatric issues. Studies have shown that EEG has the potential to be used as a biomarker for various neurological conditions including ASD. This chapter will outline the usage of EEG measurement for the classification of ASD using machine learning algorithms.

Sign in / Sign up

Export Citation Format

Share Document