Resting state functional magnetic resonance imaging and neural network classified autism and control

Brain structural connectomic topology predicts medication response in youth with bipolar disorder: A randomized clinical trial

BACKGROUND

Response to pharmacotherapy varies considerably among youths with bipolar disorder (BD) and is poorly predicted by clinical or demographic features. It can take several weeks to determine whether medication for BD is clinically effective. Although neuroimaging biomarkers are promising predictors, few studies examined the predictive value of the brain connectomic topology.

METHODS

BD-I youth (N = 121) with no prior psychopharmacotherapy were randomized to 6-weeks of double-blind quetiapine or lithium. Structural magnetic resonance imaging (MRI) was performed before medication and at one week after medication initiation. Brain structural connectome was established from the MRI scans, and topological metrics were calculated for each patient. Deep learning-based prediction model was built using baseline and one-week connectome topology to predict medication response at week 6.

RESULTS

Both baseline topological metrics and one-week topological changes could predict treatment response with significant accuracy (73.8 % - 86.8 %). A longitudinally joint model combining baseline and one-week topology provided the highest accuracy (91.3 %). The transferability between models for quetiapine and lithium was relatively poor. In addition, predictions for the two drugs were driven by similar baseline but distinct one-week salient topological patterns.

LIMITATIONS

Independent replication is needed to validate our preliminary findings.

CONCLUSION

Brain structural connectomic topology at baseline and its acute changes within the first week enable accurate BD medication response prediction. The most contributive brain regions differed between prediction models for quetiapine and lithium after one week. These findings provide preliminary evidence for the development of neuroimaging-based biomarkers for guiding therapeutic interventions in youth with BD.

What is the best brain state to predict autistic traits?

Autism is a heterogeneous condition, and functional magnetic resonance imaging-based studies have advanced understanding of neurobiological correlates of autistic features. Nevertheless, little work has focused on the optimal brain states to reveal brain-phenotype relationships. In addition, there is a need to better understand the relevance of attentional abilities in mediating autistic features. Using connectome-based predictive modelling, we interrogate three datasets to determine scanning conditions that can boost prediction of clinically relevant phenotypes and assess generalizability. In dataset one, a sample of youth with autism and neurotypical participants, we find that a sustained attention task (the gradual onset continuous performance task) results in high prediction performance of autistic traits compared to a free-viewing social attention task and a resting-state condition. In dataset two, we observe the predictive network model of autistic traits generated from the sustained attention task generalizes to predict measures of attention in neurotypical adults. In dataset three, we show the same predictive network model of autistic traits from dataset one further generalizes to predict measures of social responsiveness in data from the Autism Brain Imaging Data Exchange. In sum, our data suggest that an in-scanner sustained attention challenge can help delineate robust markers of autistic traits and support the continued investigation of the optimal brain states under which to predict phenotypes in psychiatric conditions.

MADE-for-ASD: A multi-atlas deep ensemble network for diagnosing Autism Spectrum Disorder

In response to the global need for efficient early diagnosis of Autism Spectrum Disorder (ASD), this paper bridges the gap between traditional, time-consuming diagnostic methods and potential automated solutions. We propose a multi-atlas deep ensemble network, MADE-for-ASD, that integrates multiple atlases of the brain's functional magnetic resonance imaging (fMRI) data through a weighted deep ensemble network. Our approach integrates demographic information into the prediction workflow, which enhances ASD diagnosis performance and offers a more holistic perspective on patient profiling. We experiment with the well-known publicly available ABIDE (Autism Brain Imaging Data Exchange) I dataset, consisting of resting state fMRI data from 17 different laboratories around the globe. Our proposed system achieves 75.20% accuracy on the entire dataset and 96.40% on a specific subset - both surpassing reported ASD diagnosis accuracy in ABIDE I fMRI studies. Specifically, our model improves by 4.4 percentage points over prior works on the same amount of data. The model exhibits a sensitivity of 82.90% and a specificity of 69.70% on the entire dataset, and 91.00% and 99.50%, respectively, on the specific subset. We leverage the F-score to pinpoint the top 10 ROI in ASD diagnosis, such as precuneus and anterior cingulate/ventromedial. The proposed system can potentially pave the way for more cost-effective, efficient and scalable strategies in ASD diagnosis. Codes and evaluations are publicly available at https://github.com/hasan-rakibul/MADE-for-ASD.

Machine Learning and Graph Signal Processing Applied to Healthcare: A Review

Signal processing is a very useful field of study in the interpretation of signals in many everyday applications. In the case of applications with time-varying signals, one possibility is to consider them as graphs, so graph theory arises, which extends classical methods to the non-Euclidean domain. In addition, machine learning techniques have been widely used in pattern recognition activities in a wide variety of tasks, including health sciences. The objective of this work is to identify and analyze the papers in the literature that address the use of machine learning applied to graph signal processing in health sciences. A search was performed in four databases (Science Direct, IEEE Xplore, ACM, and MDPI), using search strings to identify papers that are in the scope of this review. Finally, 45 papers were included in the analysis, the first being published in 2015, which indicates an emerging area. Among the gaps found, we can mention the need for better clinical interpretability of the results obtained in the papers, that is not to restrict the results or conclusions simply to performance metrics. In addition, a possible research direction is the use of new transforms. It is also important to make new public datasets available that can be used to train the models.

Recognition of autism spectrum disorder in children based on electroencephalogram network topology

Although our knowledge of autism spectrum disorder (ASD) has been deepened, the accurate diagnosis of ASD from normal individuals is still left behind. In this study, we proposed to apply the spatial pattern of the network topology (SPN) to identify children with ASD from normal ones. Based on two independent batches of electroencephalogram datasets collected separately, the accurate recognition of ASD from normal children was achieved by applying the proposed SPN features. Since decreased long-range connectivity was identified for children with ASD, the SPN features extracted from the distinctive topological architecture between two groups in the first dataset were used to validate the capacity of SPN in classifying ASD, and the SPN features achieved the highest accuracy of 92.31%, which outperformed the other features e.g., power spectrum density (84.62%), network properties (76.92%), and sample entropy (73.08%). Moreover, within the second dataset, by using the model trained in the first dataset, the SPN also acquired the highest sensitivity in recognizing ASD, when compared to the other features. These results consistently illustrated that the functional brain network, especially the intrinsic spatial network topology, might be the potential biomarker for the diagnosis of ASD.

Early autism diagnosis based on path signature and Siamese unsupervised feature compressor

Autism spectrum disorder has been emerging as a growing public health threat. Early diagnosis of autism spectrum disorder is crucial for timely, effective intervention and treatment. However, conventional diagnosis methods based on communications and behavioral patterns are unreliable for children younger than 2 years of age. Given evidences of neurodevelopmental abnormalities in autism spectrum disorder infants, we resort to a novel deep learning-based method to extract key features from the inherently scarce, class-imbalanced, and heterogeneous structural MR images for early autism diagnosis. Specifically, we propose a Siamese verification framework to extend the scarce data, and an unsupervised compressor to alleviate data imbalance by extracting key features. We also proposed weight constraints to cope with sample heterogeneity by giving different samples different voting weights during validation, and used Path Signature to unravel meaningful developmental features from the two-time point data longitudinally. We further extracted machine learning focused brain regions for autism diagnosis. Extensive experiments have shown that our method performed well under practical scenarios, transcending existing machine learning methods and providing anatomical insights for autism early diagnosis.

Intrinsic network abnormalities in children with autism spectrum disorder: an independent component analysis

Aberrant intrinsic brain networks are consistently observed in individuals with autism spectrum disorder. However, studies examining the strength of functional connectivity across brain regions have yielded conflicting results. Therefore, this study aimed to investigate the functional connectivity of the resting brain in children with low-functioning autism, including during the early developmental stages. We explored the functional connectivity of 43 children with autism spectrum disorder and 54 children with typical development aged 2 to 12 years using resting-state functional magnetic resonance imaging data. We used independent component analysis to classify the brain regions into six intrinsic networks and analyzed the functional connectivity within each network. Moreover, we analyzed the relationship between functional connectivity and clinical scores. In children with autism, the under-connectivities were observed within several brain networks, including the cognitive control, default mode, visual, and somatomotor networks. In contrast, we found over-connectivities between the subcortical, visual, and somatomotor networks in children with autism compared with children with typical development. Moderate effect sizes were observed in entire networks (Cohen's d = 0.43-0.77). These network alterations were significantly correlated with clinical scores such as the communication sub-score (r = - 0.442, p = 0.045) and the calibrated severity score (r = - 0.435, p = 0.049) of the Autism Diagnostic Observation Schedule. These opposing results observed based on the brain areas suggest that aberrant neurodevelopment proceeds in various ways depending on the functional brain regions in individuals with autism spectrum disorder.

A multi-view convolutional neural network method combining attention mechanism for diagnosing autism spectrum disorder

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition whose current psychiatric diagnostic process is subjective and behavior-based. In contrast, functional magnetic resonance imaging (fMRI) can objectively measure brain activity and is useful for identifying brain disorders. However, the ASD diagnostic models employed to date have not reached satisfactory levels of accuracy. This study proposes the use of MAACNN, a method that utilizes multi-view convolutional neural networks (CNNs) in conjunction with attention mechanisms for identifying ASD in multi-scale fMRI. The proposed algorithm effectively combines unsupervised and supervised learning. In the initial stage, we employ stacked denoising autoencoders, an unsupervised learning method for feature extraction, which provides different nodes to adapt to multi-scale data. In the subsequent stage, we perform supervised learning by employing multi-view CNNs for classification and obtain the final results. Finally, multi-scale data fusion is achieved by using the attention fusion mechanism. The ABIDE dataset is used to evaluate the model we proposed., and the experimental results show that MAACNN achieves superior performance with 75.12% accuracy and 0.79 AUC on ABIDE-I, and 72.88% accuracy and 0.76 AUC on ABIDE-II. The proposed method significantly contributes to the clinical diagnosis of ASD.

Confounding Effects on the Performance of Machine Learning Analysis of Static Functional Connectivity Computed from rs-fMRI Multi-site Data

Resting-state functional magnetic resonance imaging (rs-fMRI) is a non-invasive imaging technique widely used in neuroscience to understand the functional connectivity of the human brain. While rs-fMRI multi-site data can help to understand the inner working of the brain, the data acquisition and processing of this data has many challenges. One of the challenges is the variability of the data associated with different acquisitions sites, and different MRI machines vendors. Other factors such as population heterogeneity among different sites, with variables such as age and gender of the subjects, must also be considered. Given that most of the machine-learning models are developed using these rs-fMRI multi-site data sets, the intrinsic confounding effects can adversely affect the generalizability and reliability of these computational methods, as well as the imposition of upper limits on the classification scores. This work aims to identify the phenotypic and imaging variables producing the confounding effects, as well as to control these effects. Our goal is to maximize the classification scores obtained from the machine learning analysis of the Autism Brain Imaging Data Exchange (ABIDE) rs-fMRI multi-site data. To achieve this goal, we propose novel methods of stratification to produce homogeneous sub-samples of the 17 ABIDE sites, as well as the generation of new features from the static functional connectivity values, using multiple linear regression models, ComBat harmonization models, and normalization methods. The main results obtained with our statistical models and methods are an accuracy of 76.4%, sensitivity of 82.9%, and specificity of 77.0%, which are 8.8%, 20.5%, and 7.5% above the baseline classification scores obtained from the machine learning analysis of the static functional connectivity computed from the ABIDE rs-fMRI multi-site data.

Identification and analysis of autism spectrum disorder via large-scale dynamic functional network connectivity

Autism spectrum disorder (ASD) is a prevalent neurodevelopmental disorder with severe cognitive impairment. Several studies have reported that brain functional network connectivity (FNC) has great potential for identifying ASD from healthy control (HC) and revealing the relationships between the brain and behaviors of ASD. However, few studies have explored dynamic large-scale FNC as a feature to identify individuals with ASD. This study used a time-sliding window method to study the dynamic FNC (dFNC) on the resting-state fMRI. To avoid arbitrarily determining the window length, we set a window length range of 10-75 TRs (TR = 2 s). We constructed linear support vector machine classifiers for all window length conditions. Using a nested 10-fold cross-validation framework, we obtained a grand average accuracy of 94.88% across window length conditions, which is higher than those reported in previous studies. In addition, we determined the optimal window length using the highest classification accuracy of 97.77%. Based on the optimal window length, we found that the dFNCs were located mainly in dorsal and ventral attention networks (DAN and VAN) and exhibited the highest weight in classification. Specifically, we found that the dFNC between DAN and temporal orbitofrontal network (TOFN) was significantly negatively correlated with social scores of ASD. Finally, using the dFNCs with high classification weights as features, we construct a model to predict the clinical score of ASD. Overall, our findings demonstrated that the dFNC could be a potential biomarker to identify ASD and provide new perspectives to detect cognitive changes in ASD.

Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry

BACKGROUND

The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.

METHODS

Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses.

RESULTS

A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β =  - 2.75, p < .001, R²_adj = 0.40; r =  - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF₁₀ > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance.

CONCLUSIONS

Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.

FINDINGS

A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).

CONCLUSIONS AND RELEVANCE

This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

Classification of Autism Spectrum Disorder Using rs-fMRI data and Graph Convolutional Networks

Autism spectrum disorder (ASD) affects large number of children and adults in the US, and worldwide. Early and quick diagnosis of ASD can improve the quality of life significantly both for patients and their families. Prior research provides strong evidence that structural and functional magnetic resonance imaging (MRI) data collected from individuals with ASD exhibit distinguishing characteristics that differ in local and global, spatial and temporal neural patterns of the brain - and therefore can be used for diagnostic purposes for various mental disorders. However, the data from MRI are high-dimensional and advanced methods are needed to make sense out of these datasets. In this paper, we present a novel model based on graph convolutional network (GCN) that can utilize resting state fMRI (rs-fMRI) data to classify ASD subjects from health controls (HC). In addition to using the graph from traditional correlation matrices, our proposed GCN model incorporates graphlet topological counting as one of the training features. Our results show that graphlets can preserve the topological information of the graphs obtained from fMRI data. Combined with our GCN, the graphlets retain enough topological information to differentiate between the ASD and HC. Our proposed model gives an average accuracy of 64.27% on the whole ABIDE-I data sets (1035 subjects) and highest site-specific accuracy of 75.9%, which is comparable to other state-of-the-art methods - while potentially open to being more interpretable.

Topological analysis of brain dynamics in autism based on graph and persistent homology

Autism spectrum disorder (ASD) is a heterogeneous disorder with a rapidly growing prevalence. In recent years, the dynamic functional connectivity (DFC) technique has been used to reveal the transient connectivity behavior of ASDs' brains by clustering connectivity matrices in different states. However, the states of DFC have not been yet studied from a topological point of view. In this paper, this study was performed using global metrics of the graph and persistent homology (PH) and resting-state functional magnetic resonance imaging (fMRI) data. The PH has been recently developed in topological data analysis and deals with persistent structures of data. The structural connectivity (SC) and static FC (SFC) were also studied to know which one of the SC, SFC, and DFC could provide more discriminative topological features when comparing ASDs with typical controls (TCs). Significant discriminative features were only found in states of DFC. Moreover, the best classification performance was offered by persistent homology-based metrics and in two out of four states. In these two states, some networks of ASDs compared to TCs were more segregated and isolated (showing the disruption of network integration in ASDs). The results of this study demonstrated that topological analysis of DFC states could offer discriminative features which were not discriminative in SFC and SC. Also, PH metrics can provide a promising perspective for studying ASD and finding candidate biomarkers.

Functional Connectome-Based Predictive Modeling in Autism

Autism is a heterogeneous neurodevelopmental condition, and functional magnetic resonance imaging-based studies have helped advance our understanding of its effects on brain network activity. We review how predictive modeling, using measures of functional connectivity and symptoms, has helped reveal key insights into this condition. We discuss how different prediction frameworks can further our understanding of the brain-based features that underlie complex autism symptomatology and consider how predictive models may be used in clinical settings. Throughout, we highlight aspects of study interpretation, such as data decay and sampling biases, that require consideration within the context of this condition. We close by suggesting exciting future directions for predictive modeling in autism.

Machine Learning and rs-fMRI to Identify Potential Brain Regions Associated with Autism Severity

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized primarily by social impairments that manifest in different severity levels. In recent years, many studies have explored the use of machine learning (ML) and resting-state functional magnetic resonance images (rs-fMRI) to investigate the disorder. These approaches evaluate brain oxygen levels to indirectly measure brain activity and compare typical developmental subjects with ASD ones. However, none of these works have tried to classify the subjects into severity groups using ML exclusively applied to rs-fMRI data. Information on ASD severity is frequently available since some tools used to support ASD diagnosis also include a severity measurement as their outcomes. The aforesaid is the case of the Autism Diagnostic Observation Schedule (ADOS), which splits the diagnosis into three groups: ‘autism’, ‘autism spectrum’, and ‘non-ASD’. Therefore, this paper aims to use ML and fMRI to identify potential brain regions as biomarkers of ASD severity. We used the ADOS score as a severity measurement standard. The experiment used fMRI data of 202 subjects with an ASD diagnosis and their ADOS scores available at the ABIDE I consortium to determine the correct ASD sub-class for each one. Our results suggest a functional difference between the ASD sub-classes by reaching 73.8% accuracy on cingulum regions. The aforementioned shows the feasibility of classifying and characterizing ASD using rs-fMRI data, indicating potential areas that could lead to severity biomarkers in further research. However, we highlight the need for more studies to confirm our findings.

Collaborative learning of graph generation, clustering and classification for brain networks diagnosis

PURPOSE

Accurate diagnosis of autism spectrum disorder (ASD) plays a key role in improving the condition and quality of life for patients. In this study, we mainly focus on ASD diagnosis with functional brain networks (FBNs). The major challenge for brain networks modeling is the high dimensional connectivity in brain networks and limited number of subjects, which hinders the classification capability of graph convolutional networks (GCNs).

METHOD

To alleviate the influence of the limited data and high dimensional connectivity, we introduce a unified three-stage graph learning framework for brain network classification, involving multi-graph clustering, graph generation and graph classification. The framework combining Graph Generation, Clustering and Classification Networks (GraphCGC-Net) enhances the critical connections by multi-graph clustering (MGC) with a supervision scheme, and generates realistic brain networks by simultaneously preserving the global consistent distribution and local topology properties.

RESULTS

To demonstrate the effectiveness of our approach, we evaluate the performance of the proposed method on the Autism Brain Imaging Data Exchange (ABIDE) dataset and conduct extensive experiments on the ASD classification problem. Our proposed method achieves an average accuracy of 70.45% and an AUC of 72.76% on ABIDE. Compared with the traditional GCN model, the proposed GraphCGC-Net obtains 9.3%, and 10.64% improvement in terms of accuracy and AUC metrics, respectively.

CONCLUSION

The comprehensive experiments demonstrate that our GraphCGC-Net is effective for graph classification in brain disorders diagnosis. Moreover, we find that MGC can generate biologically meaningful subnetworks, which is highly consistent with the previous neuroimaging-derived biomarker evidence of ASD. More importantly, the promising results suggest that applying generative adversarial networks (GANs) in brain networks to improve the classification performance is worth further investigation.

rs-fMRI and machine learning for ASD diagnosis: a systematic review and meta-analysis

Autism Spectrum Disorder (ASD) diagnosis is still based on behavioral criteria through a lengthy and time-consuming process. Much effort is being made to identify brain imaging biomarkers and develop tools that could facilitate its diagnosis. In particular, using Machine Learning classifiers based on resting-state fMRI (rs-fMRI) data is promising, but there is an ongoing need for further research on their accuracy and reliability. Therefore, we conducted a systematic review and meta-analysis to summarize the available evidence in the literature so far. A bivariate random-effects meta-analytic model was implemented to investigate the sensitivity and specificity across the 55 studies that offered sufficient information for quantitative analysis. Our results indicated overall summary sensitivity and specificity estimates of 73.8% and 74.8%, respectively. SVM stood out as the most used classifier, presenting summary estimates above 76%. Studies with bigger samples tended to obtain worse accuracies, except in the subgroup analysis for ANN classifiers. The use of other brain imaging or phenotypic data to complement rs-fMRI information seems promising, achieving higher sensitivities when compared to rs-fMRI data alone (84.7% versus 72.8%). Finally, our analysis showed AUC values between acceptable and excellent. Still, given the many limitations indicated in our study, further well-designed studies are warranted to extend the potential use of those classification algorithms to clinical settings.

Individualized spatial network predictions using Siamese convolutional neural networks: A resting-state fMRI study of over 11,000 unaffected individuals

Individuals can be characterized in a population according to their brain measurements and activity, given the inter-subject variability in brain anatomy, structure-function relationships, or life experience. Many neuroimaging studies have demonstrated the potential of functional network connectivity patterns estimated from resting functional magnetic resonance imaging (fMRI) to discriminate groups and predict information about individual subjects. However, the predictive signal present in the spatial heterogeneity of brain connectivity networks is yet to be extensively studied. In this study, we investigate, for the first time, the use of pairwise-relationships between resting-state independent spatial maps to characterize individuals. To do this, we develop a deep Siamese framework comprising three-dimensional convolution neural networks for contrastive learning based on individual-level spatial maps estimated via a fully automated fMRI independent component analysis approach. The proposed framework evaluates whether pairs of spatial networks (e.g., visual network and auditory network) are capable of subject identification and assesses the spatial variability in different network pairs' predictive power in an extensive whole-brain analysis. Our analysis on nearly 12,000 unaffected individuals from the UK Biobank study demonstrates that the proposed approach can discriminate subjects with an accuracy of up to 88% for a single network pair on the test set (best model, after several runs), and 82% average accuracy at the subcortical domain level, notably the highest average domain level accuracy attained. Further investigation of our network's learned features revealed a higher spatial variability in predictive accuracy among younger brains and significantly higher discriminative power among males. In sum, the relationship among spatial networks appears to be both informative and discriminative of individuals and should be studied further as putative brain-based biomarkers.

Improving Between-Group Effect Size for Multi-Site Functional Connectivity Data via Site-Wise De-Meaning

Background: Multi-site functional MRI (fMRI) databases are becoming increasingly prevalent in the study of neurodevelopmental and psychiatric disorders. However, multi-site databases are known to introduce site effects that may confound neurobiological and measures such as functional connectivity (FC). Although studies have been conducted to mitigate site effects, these methods often result in reduced effect size in FC comparisons between controls and patients.

Methods: We present a site-wise de-meaning (SWD) strategy in multi-site FC analysis and compare its performance with two common site-effect mitigation methods, i.e., generalized linear model (GLM) and Combining Batches (ComBat) Harmonization. For SWD, after FC was calculated and Fisher z-transformed, the site-wise FC mean was removed from each subject before group-level statistical analysis. The above methods were tested on two multi-site psychiatric consortiums [Autism Brain Imaging Data Exchange (ABIDE) and Bipolar and Schizophrenia Network on Intermediate Phenotypes (B-SNIP)]. Preservation of consistent FC alterations in patients were evaluated for each method through the effect sizes (Hedge’s g) of patients vs. controls.

Results: For the B-SNIP dataset, SWD improved the effect size between schizophrenic and control subjects by 4.5–7.9%, while GLM and ComBat decreased the effect size by 22.5–42.6%. For the ABIDE dataset, SWD improved the effect size between autistic and control subjects by 2.9–5.3%, while GLM and ComBat decreased the effect size by up to 11.4%.

Conclusion: Compared to the original data and commonly used methods, the SWD method demonstrated superior performance in preserving the effect size in FC features associated with disorders.

Identification of Autism Spectrum Disorder With Functional Graph Discriminative Network

Autism spectrum disorder (ASD) is a specific brain disease that causes communication impairments and restricted interests. Functional connectivity analysis methodology is widely used in neuroscience research and shows much potential in discriminating ASD patients from healthy controls. However, due to heterogeneity of ASD patients, the performance of conventional functional connectivity classification methods is relatively poor. Graph neural network is an effective graph representation method to model structured data like functional connectivity. In this paper, we proposed a functional graph discriminative network (FGDN) for ASD classification. On the basis of pre-built graph templates, the proposed FGDN is able to effectively distinguish ASD patient from health controls. Moreover, we studied the size of training set for effective training, inter-site predictions, and discriminative brain regions. Discriminative brain regions were determined by the proposed model to investigate its applicability and biomarkers for ASD identification. For functional connectivity classification and analysis, FGDN is not only an effective tool for ASD identification but also a potential technique in neuroscience research.

Using deep learning to classify pediatric posttraumatic stress disorder at the individual level

BACKGROUND

Children exposed to natural disasters are vulnerable to developing posttraumatic stress disorder (PTSD). Previous studies using resting-state functional neuroimaging have revealed alterations in graph-based brain topological network metrics in pediatric PTSD patients relative to healthy controls (HC). Here we aimed to apply deep learning (DL) models to neuroimaging markers of classification which may be of assistance in diagnosis of pediatric PTSD.

METHODS

We studied 33 pediatric PTSD and 53 matched HC. Functional connectivity between 90 brain regions from the automated anatomical labeling atlas was established using partial correlation coefficients, and the whole-brain functional connectome was constructed by applying a threshold to the resultant 90 * 90 partial correlation matrix. Graph theory analysis was used to examine the topological properties of the functional connectome. A DL algorithm then used this measure to classify pediatric PTSD vs HC.

RESULTS

Graphic topological measures using DL provide a potentially clinically useful classifier for differentiating pediatric PTSD and HC (overall accuracy 71.2%). Frontoparietal areas (central executive network), cingulate cortex, and amygdala contributed the most to the DL model's performance.

CONCLUSIONS

Graphic topological measures based on fMRI data could contribute to imaging models of clinical utility in distinguishing pediatric PTSD from HC. DL model may be a useful tool in the identification of brain mechanisms PTSD participants.

Autism Spectrum Disorder Studies Using fMRI Data and Machine Learning: A Review

Machine learning methods have been frequently applied in the field of cognitive neuroscience in the last decade. A great deal of attention has been attracted to introduce machine learning methods to study the autism spectrum disorder (ASD) in order to find out its neurophysiological underpinnings. In this paper, we presented a comprehensive review about the previous studies since 2011, which applied machine learning methods to analyze the functional magnetic resonance imaging (fMRI) data of autistic individuals and the typical controls (TCs). The all-round process was covered, including feature construction from raw fMRI data, feature selection methods, machine learning methods, factors for high classification accuracy, and critical conclusions. Applying different machine learning methods and fMRI data acquired from different sites, classification accuracies were obtained ranging from 48.3% up to 97%, and informative brain regions and networks were located. Through thorough analysis, high classification accuracies were found to usually occur in the studies which involved task-based fMRI data, single dataset for some selection principle, effective feature selection methods, or advanced machine learning methods. Advanced deep learning together with the multi-site Autism Brain Imaging Data Exchange (ABIDE) dataset became research trends especially in the recent 4 years. In the future, advanced feature selection and machine learning methods combined with multi-site dataset or easily operated task-based fMRI data may appear to have the potentiality to serve as a promising diagnostic tool for ASD.

Cost-effectiveness of neuroimaging technologies in management of psychiatric and insomnia disorders: A meta-analysis and prospective cost analysis

BACKGROUND

The optimal diagnostic strategy for patients with psychiatric and insomnia disorders has not been established yet.

PURPOSE

The purpose of this study was to perform cost-effectiveness analysis of six neuroimaging technologies in diagnosis of patients with psychiatric and insomnia disorders.

METHODS

An economic evaluation study was conducted in three parts, including a systematic review for determining diagnostic accuracy, a descriptive cross-sectional study with Activity-Based Costing (ABC) technique for tracing resource consumption, and a cost-effectiveness analysis using a short-term decision-analytic model.

RESULTS

In the first phase, 93 diagnostic accuracy studies were included in the systematic review. The accumulated results (meta-analysis) showed that the highest diagnostic accuracy for psychiatric and insomnia disorders was attributed to PET (sensitivity of 90% and specificity of 80%) and MRI (sensitivity of 76% and specificity of 78%) respectively. In the second phase of the study, we calculated the cost of each technology. The results showed that MRI has the lowest cost. Based on the results in the model of cost-effectiveness sMRI ($ 50.08 per accurate diagnosis) and MRI ($ 58.54 per accurate diagnosis) were more cost-effective neuroimaging technologies.

CONCLUSION

In psychiatric disorders, no single strategy was characterized by both low cost and high accuracy. However, MRI and PET scan had lower cost and higher accuracy for psychiatric disorders, respectively. MRI was the least costly with the highest diagnostic accuracy in insomnia disorders. Based on our model, sMRI in psychiatric disorders and MRI in insomnia disorders were the most cost-effective technologies.

Machine learning with neuroimaging data to identify autism spectrum disorder: a systematic review and meta-analysis

PURPOSE

Autism Spectrum Disorder (ASD) is diagnosed through observation or interview assessments, which is time-consuming, subjective, and with questionable validity and reliability. Thus, we aimed to evaluate the role of machine learning (ML) with neuroimaging data to provide a reliable classification of ASD.

METHODS

A systematic search of PubMed, Scopus, and Embase was conducted to identify relevant publications. Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) was used to assess the studies' quality. A bivariate random-effects model meta-analysis was employed to evaluate the pooled sensitivity, the pooled specificity, and the diagnostic performance through the hierarchical summary receiver operating characteristic (HSROC) curve of ML with neuroimaging data in classifying ASD. Meta-regression was also performed.

RESULTS

Forty-four studies (5697 ASD and 6013 typically developing individuals [TD] in total) were included in the quantitative analysis. The pooled sensitivity for differentiating ASD from TD individuals was 86.25 95% confidence interval [CI] (81.24, 90.08), while the pooled specificity was 83.31 95% CI (78.12, 87.48) with a combined area under the HSROC (AUC) of 0.889. Higgins I² (> 90%) and Cochran's Q (p < 0.0001) suggest a high degree of heterogeneity. In the bivariate model meta-regression, a higher pooled specificity was observed in studies not using a brain atlas (90.91 95% CI [80.67, 96.00], p = 0.032). In addition, a greater pooled sensitivity was seen in studies recruiting both males and females (89.04 95% CI [83.84, 92.72], p = 0.021), and combining imaging modalities (94.12 95% [85.43, 97.76], p = 0.036).

CONCLUSION

ML with neuroimaging data is an exciting prospect in detecting individuals with ASD but further studies are required to improve its reliability for usage in clinical practice.

Identification of Autism Subtypes Based on Wavelet Coherence of BOLD FMRI Signals Using Convolutional Neural Network

The functional connectivity (FC) patterns of resting-state functional magnetic resonance imaging (rs-fMRI) play an essential role in the development of autism spectrum disorders (ASD) classification models. There are available methods in literature that have used FC patterns as inputs for binary classification models, but the results barely reach an accuracy of 80%. Additionally, the generalizability across multiple sites of the models has not been investigated. Due to the lack of ASD subtypes identification model, the multi-class classification is proposed in the present study. This study aims to develop automated identification of autism spectrum disorder (ASD) subtypes using convolutional neural networks (CNN) using dynamic FC as its inputs. The rs-fMRI dataset used in this study consists of 144 individuals from 8 independent sites, labeled based on three ASD subtypes, namely autistic disorder (ASD), Asperger’s disorder (APD), and pervasive developmental disorder not otherwise specified (PDD-NOS). The blood-oxygen-level-dependent (BOLD) signals from 116 brain nodes of automated anatomical labeling (AAL) atlas are used, where the top-ranked node is determined based on one-way analysis of variance (ANOVA) of the power spectral density (PSD) values. Based on the statistical analysis of the PSD values of 3-level ASD and normal control (NC), putamen_R is obtained as the top-ranked node and used for the wavelet coherence computation. With good resolution in time and frequency domain, scalograms of wavelet coherence between the top-ranked node and the rest of the nodes are used as dynamic FC feature input to the convolutional neural networks (CNN). The dynamic FC patterns of wavelet coherence scalogram represent phase synchronization between the pairs of BOLD signals. Classification algorithms are developed using CNN and the wavelet coherence scalograms for binary and multi-class identification were trained and tested using cross-validation and leave-one-out techniques. Results of binary classification (ASD vs. NC) and multi-class classification (ASD vs. APD vs. PDD-NOS vs. NC) yielded, respectively, 89.8% accuracy and 82.1% macro-average accuracy, respectively. Findings from this study have illustrated the good potential of wavelet coherence technique in representing dynamic FC between brain nodes and open possibilities for its application in computer aided diagnosis of other neuropsychiatric disorders, such as depression or schizophrenia.

Identifying Autism Spectrum Disorder From Resting-State fMRI Using Deep Belief Network

With the increasing prevalence of autism spectrum disorder (ASD), it is important to identify ASD patients for effective treatment and intervention, especially in early childhood. Neuroimaging techniques have been used to characterize the complex biomarkers based on the functional connectivity anomalies in the ASD. However, the diagnosis of ASD still adopts the symptom-based criteria by clinical observation. The existing computational models tend to achieve unreliable diagnostic classification on the large-scale aggregated data sets. In this work, we propose a novel graph-based classification model using the deep belief network (DBN) and the Autism Brain Imaging Data Exchange (ABIDE) database, which is a worldwide multisite functional and structural brain imaging data aggregation. The remarkable connectivity features are selected through a graph extension of K -nearest neighbors and then refined by a restricted path-based depth-first search algorithm. Thanks to the feature reduction, lower computational complexity could contribute to the shortening of the training time. The automatic hyperparameter-tuning technique is introduced to optimize the hyperparameters of the DBN by exploring the potential parameter space. The simulation experiments demonstrate the superior performance of our model, which is 6.4% higher than the best result reported on the ABIDE database. We also propose to use the data augmentation and the oversampling technique to identify further the possible subtypes within the ASD. The interpretability of our model enables the identification of the most remarkable autistic neural correlation patterns from the data-driven outcomes.

Brain imaging-based machine learning in autism spectrum disorder: methods and applications

Autism spectrum disorder (ASD) is a neurodevelopmental condition with early childhood onset and high heterogeneity. As the pathogenesis is still elusive, ASD diagnosis is comprised of a constellation of behavioral symptoms. Non-invasive brain imaging techniques, such as magnetic resonance imaging (MRI), provide a valuable objective measurement of the brain. Many efforts have been devoted to developing imaging-based diagnostic tools for ASD based on machine learning (ML) technologies. In this survey, we review recent advances that utilize machine learning approaches to classify individuals with and without ASD. First, we provide a brief overview of neuroimaging-based ASD classification studies, including the analysis of publications and general classification pipeline. Next, representative studies are highlighted and discussed in detail regarding different imaging modalities, methods and sample sizes. Finally, we highlight several common challenges and provide recommendations on future directions. In summary, identifying discriminative biomarkers for ASD diagnosis is challenging, and further establishing more comprehensive datasets and dissecting the individual and group heterogeneity will be critical to achieve better ADS diagnosis performance. Machine learning methods will continue to be developed and are poised to help advance the field in this regard.

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

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.

Single-participant structural similarity matrices lead to greater accuracy in classification of participants than function in autism in MRI

BACKGROUND

Autism has previously been characterized by both structural and functional differences in brain connectivity. However, while the literature on single-subject derivations of functional connectivity is extensively developed, similar methods of structural connectivity or similarity derivation from T1 MRI are less studied.

METHODS

We introduce a technique of deriving symmetric similarity matrices from regional histograms of grey matter volumes estimated from T1-weighted MRIs. We then validated the technique by inputting the similarity matrices into a convolutional neural network (CNN) to classify between participants with autism and age-, motion-, and intracranial-volume-matched controls from six different databases (29,288 total connectomes, mean age = 30.72, range 0.42-78.00, including 1555 subjects with autism). We compared this method to similar classifications of the same participants using fMRI connectivity matrices as well as univariate estimates of grey matter volumes. We further applied graph-theoretical metrics on output class activation maps to identify areas of the matrices that the CNN preferentially used to make the classification, focusing particularly on hubs.

LIMITATIONS

While this study used a large sample size, the majority of data was from a young age group; furthermore, to make a viable machine learning study, we treated autism, a highly heterogeneous condition, as a binary label. Thus, these results are not necessarily generalizable to all subtypes and age groups in autism.

RESULTS

Our models gave AUROCs of 0.7298 (69.71% accuracy) when classifying by only structural similarity, 0.6964 (67.72% accuracy) when classifying by only functional connectivity, and 0.7037 (66.43% accuracy) when classifying by univariate grey matter volumes. Combining structural similarity and functional connectivity gave an AUROC of 0.7354 (69.40% accuracy). Analysis of classification performance across age revealed the greatest accuracy in adolescents, in which most data were present. Graph analysis of class activation maps revealed no distinguishable network patterns for functional inputs, but did reveal localized differences between groups in bilateral Heschl's gyrus and upper vermis for structural similarity.

CONCLUSION

This study provides a simple means of feature extraction for inputting large numbers of structural MRIs into machine learning models. Our methods revealed a unique emphasis of the deep learning model on the structure of the bilateral Heschl's gyrus when characterizing autism.

Automatic classification of children with autism spectrum disorder by using a computerized visual-orienting task

Early screening and diagnosis of autism spectrum disorder (ASD) primarily rely on behavioral observations by qualified clinicians whose decision process can benefit from the combination of machine learning algorithms and sensor data. We designed a computerized visual-orienting task with gaze-related or non-gaze-related directional cues, which triggered participants' gaze-following behavior. Based on their eye-movement data registered by an eye tracker, we applied the machine learning algorithms to classify high-functioning children with ASD (HFA), low-functioning children with ASD (LFA), and typically developing children (TD). We found that TD children had higher success rates in obtaining rewards than HFA children, and HFA children had higher rates than LFA children. Based on raw eye-tracking data, our machine learning algorithm could classify the three groups with an accuracy of 81.1% and relatively high sensitivity and specificity. Classification became worse if only data from the gaze or nongaze conditions were used, suggesting that "less-social" directional cues also carry useful information for distinguishing these groups. Our findings not only provide insights about visual-orienting deficits among children with ASD but also demonstrate the promise of combining classical behavioral paradigms with machine learning algorithms for aiding the screening for individuals with ASD.

ASD-SAENet: A Sparse Autoencoder, and Deep-Neural Network Model for Detecting Autism Spectrum Disorder (ASD) Using fMRI Data

Autism spectrum disorder (ASD) is a heterogenous neurodevelopmental disorder which is characterized by impaired communication, and limited social interactions. The shortcomings of current clinical approaches which are based exclusively on behavioral observation of symptomology, and poor understanding of the neurological mechanisms underlying ASD necessitates the identification of new biomarkers that can aid in study of brain development, and functioning, and can lead to accurate and early detection of ASD. In this paper, we developed a deep-learning model called ASD-SAENet for classifying patients with ASD from typical control subjects using fMRI data. We designed and implemented a sparse autoencoder (SAE) which results in optimized extraction of features that can be used for classification. These features are then fed into a deep neural network (DNN) which results in superior classification of fMRI brain scans more prone to ASD. Our proposed model is trained to optimize the classifier while improving extracted features based on both reconstructed data error and the classifier error. We evaluated our proposed deep-learning model using publicly available Autism Brain Imaging Data Exchange (ABIDE) dataset collected from 17 different research centers, and include more than 1,035 subjects. Our extensive experimentation demonstrate that ASD-SAENet exhibits comparable accuracy (70.8%), and superior specificity (79.1%) for the whole dataset as compared to other methods. Further, our experiments demonstrate superior results as compared to other state-of-the-art methods on 12 out of the 17 imaging centers exhibiting superior generalizability across different data acquisition sites and protocols. The implemented code is available on GitHub portal of our lab at: https://github.com/pcdslab/ASD-SAENet.

Machine Learning Methods for Diagnosing Autism Spectrum Disorder and Attention- Deficit/Hyperactivity Disorder Using Functional and Structural MRI: A Survey

Here we summarize recent progress in machine learning model for diagnosis of Autism Spectrum Disorder (ASD) and Attention-deficit/Hyperactivity Disorder (ADHD). We outline and describe the machine-learning, especially deep-learning, techniques that are suitable for addressing research questions in this domain, pitfalls of the available methods, as well as future directions for the field. We envision a future where the diagnosis of ASD, ADHD, and other mental disorders is accomplished, and quantified using imaging techniques, such as MRI, and machine-learning models.

Clustering of Multiple Psychiatric Disorders Using Functional Connectivity in the Data-Driven Brain Subnetwork

Recently, the dimensional approach has attracted much attention, bringing a paradigm shift to a continuum of understanding of different psychiatric disorders. In line with this new paradigm, we examined whether there was common functional connectivity related to various psychiatric disorders in an unsupervised manner without explicitly using diagnostic label information. To this end, we uniquely applied a newly developed network-based multiple clustering method to resting-state functional connectivity data, which allowed us to identify pairs of relevant brain subnetworks and subject cluster solutions accordingly. Thus, we identified four subject clusters, which were characterized as major depressive disorder (MDD), young healthy control (young HC), schizophrenia (SCZ)/bipolar disorder (BD), and autism spectrum disorder (ASD), respectively, with the relevant brain subnetwork represented by the cerebellum-thalamus-pallidum-temporal circuit. The clustering results were validated using independent datasets. This study is the first cross-disorder analysis in the framework of unsupervised learning of functional connectivity based on a data-driven brain subnetwork.

Deep learning approaches for neural decoding across architectures and recording modalities

Decoding behavior, perception or cognitive state directly from neural signals is critical for brain-computer interface research and an important tool for systems neuroscience. In the last decade, deep learning has become the state-of-the-art method in many machine learning tasks ranging from speech recognition to image segmentation. The success of deep networks in other domains has led to a new wave of applications in neuroscience. In this article, we review deep learning approaches to neural decoding. We describe the architectures used for extracting useful features from neural recording modalities ranging from spikes to functional magnetic resonance imaging. Furthermore, we explore how deep learning has been leveraged to predict common outputs including movement, speech and vision, with a focus on how pretrained deep networks can be incorporated as priors for complex decoding targets like acoustic speech or images. Deep learning has been shown to be a useful tool for improving the accuracy and flexibility of neural decoding across a wide range of tasks, and we point out areas for future scientific development.

Supervised machine learning for diagnostic classification from large-scale neuroimaging datasets

There are growing concerns about the generalizability of machine learning classifiers in neuroimaging. In order to evaluate this aspect across relatively large heterogeneous populations, we investigated four disorders: Autism spectrum disorder (N = 988), Attention deficit hyperactivity disorder (N = 930), Post-traumatic stress disorder (N = 87) and Alzheimer's disease (N = 132). We applied 18 different machine learning classifiers (based on diverse principles) wherein the training/validation and the hold-out test data belonged to samples with the same diagnosis but differing in either the age range or the acquisition site. Our results indicate that overfitting can be a huge problem in heterogeneous datasets, especially with fewer samples, leading to inflated measures of accuracy that fail to generalize well to the general clinical population. Further, different classifiers tended to perform well on different datasets. In order to address this, we propose a consensus-classifier by combining the predictive power of all 18 classifiers. The consensus-classifier was less sensitive to unmatched training/validation and holdout test data. Finally, we combined feature importance scores obtained from all classifiers to infer the discriminative ability of connectivity features. The functional connectivity patterns thus identified were robust to the classification algorithm used, age and acquisition site differences, and had diagnostic predictive ability in addition to univariate statistically significant group differences between the groups. A MATLAB toolbox called Machine Learning in NeuroImaging (MALINI), which implements all the 18 different classifiers along with the consensus classifier is available from Lanka et al. (2019) The toolbox can also be found at the following URL: https://github.com/pradlanka/malini .

Diagnostic classification of autism using resting-state fMRI data improves with full correlation functional brain connectivity compared to partial correlation

BACKGROUND

Autism Spectrum Disorder (ASD) is a neurodevelopmental disability with altered connectivity in brain networks.

NEW METHOD

In this study, brain connections in Resting-state functional Magnetic Resonance Imaging (Rs-fMRI) of ASD and Typical Developing (TD) are analyzed by partial and full correlation methods such as Gaussian Graphical Least Absolute Shrinkage and Selection Operator (GLASSO), Max-Det Matrix Completion (MDMC), and Pearson Correlation Co-Efficient (PCCE). We investigated Functional Connectivity (FC) of ASD and TD brain from 238 functionally defined regions of interest. Furthermore, we constructed a series of feature sets by applying conditional random forests and conditional permutation importance. We built classifier models by Random Forest (RF), Oblique RF (ORF), Support Vector Machine (SVM), and Convolutional Neural Network (CNN) for each feature set. FC features are ranked based on p-value and we analyzed the top 20 FC features.

RESULTS

We achieved a single-trial test accuracy of 72.5 %, though MDMC-SVM and PCCE-CNN pipelines. Further, PCCE-CNN pipeline gives better average test accuracy (70.31 %) and area under the curve (0.73) compared to other pipelines. We found that top-20 PCCE based FC features are from networks such as Dorsal Attention (DA), Cingulo-Opercular Task Control (COTC), somatosensory motor hand and subcortical. In addition, among top 20 PCCE features, many FC links are found between COTC and DA (4 connections) which helped to discriminate the ASD and TD.

COMPARISON WITH EXISTING METHODS AND CONCLUSIONS

The generalized classifier models built in our study for highly heterogeneous participants perform better than previous studies with similar data sets and diagnostic groups.

Population Graph-Based Multi-Model Ensemble Method for Diagnosing Autism Spectrum Disorder

With the advancement of brain imaging techniques and a variety of machine learning methods, significant progress has been made in brain disorder diagnosis, in particular Autism Spectrum Disorder. The development of machine learning models that can differentiate between healthy subjects and patients is of great importance. Recently, graph neural networks have found increasing application in domains where the population's structure is modeled as a graph. The application of graphs for analyzing brain imaging datasets helps to discover clusters of individuals with a specific diagnosis. However, the choice of the appropriate population graph becomes a challenge in practice, as no systematic way exists for defining it. To solve this problem, we propose a population graph-based multi-model ensemble, which improves the prediction, regardless of the choice of the underlying graph. First, we construct a set of population graphs using different combinations of imaging and phenotypic features and evaluate them using Graph Signal Processing tools. Subsequently, we utilize a neural network architecture to combine multiple graph-based models. The results demonstrate that the proposed model outperforms the state-of-the-art methods on Autism Brain Imaging Data Exchange (ABIDE) dataset.

A Three-Stage Teacher, Student Neural Networks and Sequential Feed Forward Selection-Based Feature Selection Approach for the Classification of Autism Spectrum Disorder

Autism disorder, generally known as Autism Spectrum Disorder (ASD) is a brain disorder characterized by lack of communication skills, social aloofness and repetitions in the actions in the patients, which is affecting millions of the people across the globe. Accurate identification of autistic patients is considered a challenging task in the domain of brain disorder science. To address this problem, we have proposed a three-stage feature selection approach for the classification of ASD on the preprocessed Autism Brain Imaging Data Exchange (ABIDE) rs-fMRI Dataset. In the first stage, a large neural network which we call a “Teacher ” was trained on the correlation-based connectivity matrix to learn the latent representation of the input. In the second stage an autoencoder which we call a “Student” autoencoder was given the task to learn those trained “Teacher” embeddings using the connectivity matrix input. Lastly, an SFFS-based algorithm was employed to select the subset of most discriminating features between the autistic and healthy controls. On the combined site data across 17 sites, we achieved the maximum 10-fold accuracy of 82% and for the individual site-wise data, based on 5-fold accuracy, our results outperformed other state of the art methods in 13 out of the total 17 site-wise comparisons.

An Autoencoder-Based Deep Learning Classifier for Efficient Diagnosis of Autism

Autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by a lack of social communication and social interaction. Autism is a mental disorder investigated by social and computational intelligence scientists utilizing advanced technologies such as machine learning models to enhance clinicians’ ability to provide robust diagnosis and prognosis of autism. However, with dynamic changes in autism behaviour patterns, these models’ quality and accuracy have become a great challenge for clinical practitioners. We applied a deep neural network learning on a large brain image dataset obtained from ABIDE (autism brain imaging data exchange) to provide an efficient diagnosis of ASD, especially for children. Our deep learning model combines unsupervised neural network learning, an autoencoder, and supervised deep learning using convolutional neural networks. Our proposed algorithm outperforms individual-based classifiers measured by various validations and assessment measures. Experimental results indicate that the autoencoder combined with the convolution neural networks provides the best performance by achieving 84.05% accuracy and Area under the Curve (AUC) value of 0.78.

A Two Consequent Multi-layers Deep Discriminative Approach for Classifying fMRI Images

Functional Magnetic Resonance Imaging (fMRI), for many decades acts as a potential aiding method for diagnosing medical problems. Several successful machine learning algorithms have been proposed in literature to extract valuable knowledge from fMRI. One of these algorithms is the convolutional neural network (CNN) that competent with high capabilities for learning optimal abstractions of fMRI. This is because the CNN learns features similarly to human brain where it preserves local structure and avoids distortion of the global feature space. Focusing on the achievements of using the CNN for the fMRI, and accordingly, the Deep Convolutional Auto-Encoder (DCAE) benefits from the data-driven approach with CNN’s optimal features to strengthen the fMRI classification. In this paper, a new two consequent multi-layers DCAE deep discriminative approach for classifying fMRI Images is proposed. The first DCAE is unsupervised sub-model that is composed of four CNN. It focuses on learning weights to utilize discriminative characteristics of the extracted features for robust reconstruction of fMRI with lower dimensional considering tiny details and refining by its deep multiple layers. Then the second DCAE is a supervised sub-model that focuses on training labels to reach an outperformed results. The proposed approach proved its effectiveness and improved literately reported results on a large brain disorder fMRI dataset.

Machine learning (ML) for the diagnosis of autism spectrum disorder (ASD) using brain imaging

Autism spectrum disorder (ASD) is a neurodevelopmental incurable disorder with a long diagnostic period encountered in the early years of life. If diagnosed early, the negative effects of this disease can be reduced by starting special education early. Machine learning (ML), an increasingly ubiquitous technology, can be applied for the early diagnosis of ASD. The aim of this study is to examine and provide a comprehensive state-of-the-art review of ML research for the diagnosis of ASD based on (a) structural magnetic resonance image (MRI), (b) functional MRI and (c) hybrid imaging techniques over the past decade. The accuracy of the studies with a large number of participants is in general lower than those with fewer participants leading to the conclusion that further large-scale studies are needed. An examination of the age of the participants shows that the accuracy of the automated diagnosis of ASD is higher at a younger age range. ML technology is expected to contribute significantly to the early and rapid diagnosis of ASD in the coming years and become available to clinicians in the near future. This review is aimed to facilitate that.

Machine-learning classification using neuroimaging data in schizophrenia, autism, ultra-high risk and first-episode psychosis

Neuropsychiatric disorders are diagnosed based on behavioral criteria, which makes the diagnosis challenging. Objective biomarkers such as neuroimaging are needed, and when coupled with machine learning, can assist the diagnostic decision and increase its reliability. Sixty-four schizophrenia, 36 autism spectrum disorder (ASD), and 106 typically developing individuals were analyzed. FreeSurfer was used to obtain the data from the participant's brain scans. Six classifiers were utilized to classify the subjects. Subsequently, 26 ultra-high risk for psychosis (UHR) and 17 first-episode psychosis (FEP) subjects were run through the trained classifiers. Lastly, the classifiers' output of the patient groups was correlated with their clinical severity. All six classifiers performed relatively well to distinguish the subject groups, especially support vector machine (SVM) and Logistic regression (LR). Cortical thickness and subcortical volume feature groups were most useful for the classification. LR and SVM were highly consistent with clinical indices of ASD. When UHR and FEP groups were run with the trained classifiers, majority of the cases were classified as schizophrenia, none as ASD. Overall, SVM and LR were the best performing classifiers. Cortical thickness and subcortical volume were most useful for the classification, compared to surface area. LR, SVM, and DT's output were clinically informative. The trained classifiers were able to help predict the diagnostic category of both UHR and FEP Individuals.