A Machine Learning fMRI Approach in the Diagnosis of Autism

Karampasi, Aikaterini S.; Kakkos, Ioannis; Miloulis, Stavros Theofanis; Zorzos, Ioannis; Dimitrakopoulos, Georgios; Gkiatis, Kostakis; Asvestas, Pantelis A.; Matsopoulos, George K.

doi:10.1109/bigdata50022.2020.9378453

Cited by 16 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All the studies have utilized physiological FC features, with the exception of [42] that has also utilized sex, age, and IQs. Furthermore, most works utilize only sFC features; although, in our previous analysis [26], we additionally incorporated texture features to identify biological variables that might affect ASD identification, in an image-related analysis of the BOLD signals. On the contrary, in the proposed approach, we employ a more sophisticated method, by combining static and dynamic connectivity fused with non-physiological characteristics to investigate their associations towards automated autism detection.…”

Section: Evaluation Of the Adopted Framework And Relationship To Prior Workmentioning

confidence: 99%

“…Moreover, an implementation of a multi-atlas classification scheme employing FC along with a neural network obtained 78.7% accuracy [25]. In our previous work [26], static FC and image-related features were incorporated (i.e., the Haralick texture features and the Kullback-Leibler divergence) to discriminate between ASD and TD individulars resulting in 72.5% accuracy. Our results demonstrated that additional characteristics, when applied to machine learning paradigms, can enhance classification performance and provide additional indicators of the autism-regulated mechanisms that govern brain functions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Informative Biomarkers for Autism Spectrum Disorder Diagnosis in Functional Magnetic Resonance Imaging Data on the Default Mode Network

et al. 2021

Self Cite

View full text Add to dashboard Cite

Effective detection of autism spectrum disorder (ASD) is a complicated procedure, due to the hundreds of parameters suggested to be implicated in its etiology. As such, machine learning methods have been consistently applied to facilitate diagnosis, although the scarcity of potent autism-related biomarkers is a bottleneck. More importantly, the variability of the imported attributes among different sites (e.g., acquisition parameters) and different individuals (e.g., demographics, movement, etc.) pose additional challenges, eluding adequate generalization and universal modeling. The present study focuses on a data-driven approach for the identification of efficacious biomarkers for the classification between typically developed (TD) and ASD individuals utilizing functional magnetic resonance imaging (fMRI) data on the default mode network (DMN) and non-physiological parameters. From the fMRI data, static and dynamic connectivity were calculated and fed to a feature selection and classification framework along with the demographic, acquisition and motion information to obtain the most prominent features in regard to autism discrimination. The acquired results provided high classification accuracy of 76.63%, while revealing static and dynamic connectivity as the most prominent indicators. Subsequent analysis illustrated the bilateral parahippocampal gyrus, right precuneus, midline frontal, and paracingulate as the most significant brain regions, in addition to an overall connectivity increment.

show abstract

Section: Evaluation Of the Adopted Framework And Relationship To Prior Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Informative Biomarkers for Autism Spectrum Disorder Diagnosis in Functional Magnetic Resonance Imaging Data on the Default Mode Network

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Researchers have turned to machine learning over traditional statistical methods for data analysis due to the high prevalence rate and heterogeneous nature of ASD. Machine Learning techniques have been employed on various biomarkers in the field of ASD diagnosis of which Resting State Functional Magnetic Resonance Imaging (rs-fMRI) has come out as a potential biomarker [3], [4], [5]. Resting state functional magnetic resonance imaging is a non-invasive brain imaging technique which uses blood-oxygenation-level dependent (BOLD) as a neurophysiologic indicator to measure brain activity.…”

Section: Introductionmentioning

confidence: 99%

TransLearning ASD: Detection of Autism Spectrum Disorder Using Domain Adaptation and Transfer Learning-Based Approach on RS-FMRI Data

Singh¹,

Malhotra²,

Mengi³

2023

Artificial Intelligence and Communication Technologies

View full text Add to dashboard Cite

Autism Spectrum Disorder abbreviated as ASD, is a complex neuro-developmental disease specifically linked to nervous system that influences patients’ communicationand social behavior. Traditional clinical techniques used for the discovery of ASD fall short of definite and early ASD diagnosis. Consequently, biomarkers have been introduced in the field of ASD diagnosis and particularly, resting-state functional Magnetic Resonance Imaging (rs-fMRI) has posed as a valuable biomarker. Researchers have focused on utilizing the vast span of Artificial Intelligence techniques in combination with rs-fMRI, to build an effective framework for ASD detection. However, these systems have not been able to generalize to a larger set of patients, because of theheterogeneity in the available f-MRI dataset for ASD. Motivated from the aforementioned discussion, this study performs a comprehensive literature review of the existing systems covering a period of 2019-2021, thereby identifying several research gaps. To overcome the effect of existing implications, this paper expounds a TransLearning ASD framework which will achieve normalization of the heterogeneous fMRI data using domain adaptation followed by transfer learning technique for effective ASD prediction and to overcome the model generalization problem.

show abstract

“…By integrating the traditional functional connectivity network, the low-order dynamic functional connectivity network and features were extracted from the high-order dynamic functional connectivity network, and a linear kernel-based SVM classifier was used to obtain up to 83.00% accuracy in 45 ASD patients and 47 TCs. In the same year, Karampasi et al (2020) used the time series extracted by the CC200 atlas, demographic information, texture and divergence features of the BOLD signal as manually extracted features. Then, five feature selection algorithms such as recursive feature elimination with correlation bias reduction, local learning, infinite feature selection, minimum redundancy maximum correlation and Laplace score were used for feature selection.…”

Section: Introductionmentioning

confidence: 99%

CNNG: A Convolutional Neural Networks With Gated Recurrent Units for Autism Spectrum Disorder Classification

Jiang

Liu

Zhang

et al. 2022

Front. Aging Neurosci.

View full text Add to dashboard Cite

As a neurodevelopmental disorder, autism spectrum disorder (ASD) severely affects the living conditions of patients and their families. Early diagnosis of ASD can enable the disease to be effectively intervened in the early stage of development. In this paper, we present an ASD classification network defined as CNNG by combining of convolutional neural network (CNN) and gate recurrent unit (GRU). First, CNNG extracts the 3D spatial features of functional magnetic resonance imaging (fMRI) data by using the convolutional layer of the 3D CNN. Second, CNNG extracts the temporal features by using the GRU and finally classifies them by using the Sigmoid function. The performance of CNNG was validated on the international public data—autism brain imaging data exchange (ABIDE) dataset. According to the experiments, CNNG can be highly effective in extracting the spatio-temporal features of fMRI and achieving a classification accuracy of 72.46%.

show abstract

A Machine Learning fMRI Approach in the Diagnosis of Autism

Cited by 16 publications

References 17 publications

Informative Biomarkers for Autism Spectrum Disorder Diagnosis in Functional Magnetic Resonance Imaging Data on the Default Mode Network

Informative Biomarkers for Autism Spectrum Disorder Diagnosis in Functional Magnetic Resonance Imaging Data on the Default Mode Network

TransLearning ASD: Detection of Autism Spectrum Disorder Using Domain Adaptation and Transfer Learning-Based Approach on RS-FMRI Data

CNNG: A Convolutional Neural Networks With Gated Recurrent Units for Autism Spectrum Disorder Classification

Contact Info

Product

Resources

About