There has been an unanticipated increase in the number of cases of Autism Spectrum Disorder (ASD) in the present era. Its late detection due to the negligence of its early symptoms aggravates the complications in the day-to-day life of an autistic person. Artificial Intelligence (AI)-based classification framework can assist doctors in its early detection, and it can help autistic people to ameliorate their lifestyle. The less number of works using Structural Magnetic Resonance Imaging (sMRI) compared to the Functional Magnetic Resonance Imaging (fMRI) with AI-based approaches gives the motivation to develop the classification system for the detection of ASD with sMRI scans. In the past few years, huge numbers of involvement of CNN-based approaches in the computer-vision application have been witnessed by the research community. The Vision Transformer (ViT) network based on the idea of Transformers in Natural Language Processing has done revelation with its performances in image recognition. The proposed work focuses on the development of a classification system utilizing the ViT network for ASD detection. The two different variants of ViT i.e., ViT-B16 and ViT-B32 have been utilized with additional modification for the experimentation. The proposed Prediction Level Fusion of Vision Transformers (PF-ViTs) based network has exhibited impressive performances compared to the sMRI-based state-of-the-art works (SOTAW) by achieving an accuracy of 94.24%, a precision of 96.03%, a sensitivity of 92.36%, a specificity of 96.14%, a F1 score of 94.16%, and AUC score of 98.45% towards the detection of ASD.
AlzubaidiLZhangJHumaidiAJ, et al.Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data2021; 8: 1–74.
2.
RavìDWongCDeligianniF, et al.Deep learning for health informatics. IEEE J Biomed Health Inform2017; 21: 4–21.
3.
YuHYangLTZhangQ, et al.Convolutional neural networks for medical image analysis: state-of-the-art, comparisons, improvement and perspectives. Neurocomputing2021; 444: 92–110.
4.
YuXWangJHongQQ, et al.Transfer learning for medical images analyses: a survey. Neurocomputing2022; 489: 230–254.
5.
MirbabaieMStieglitzSFrickNR. Artificial intelligence in disease diagnostics: a critical review and classification on the current state of research guiding future direction. Health Technol2021; 11: 693–731.
6.
LiuXGaoKLiuB, et al.Advances in deep learning-based medical image analysis. Health Data Sci2021; 2021: 1–14.
7.
ArdalanZSubbianV. Transfer learning approaches for neuroimaging analysis: a scoping review. Front Artif Intell2022; 5: 15.
8.
WangJZhuHWangSH,et al.A review of deep learning on medical image analysis. Mob Netw Appl2021; 26: 351–380.
9.
OzturkTTaloMYildirimEA, et al.Automated detection of COVID-19 cases using deep neural networks with X-ray images. Comput Biol Med2020; 121: 103792.
10.
ChaudharyPKPachoriRB. FBSED Based automatic diagnosis of COVID-19 using X-ray and CT images. Comput Biol Med2021; 134: 104454.
11.
KazemiAShiriMESheikhahmadiA. Classifying tumor brain images using parallel deep learning algorithms. Comput Biol Med2022; 148: 105775.
12.
GaurPMalaviyaVGuptaA, et al.COVID-19 disease identification from chest CT images using empirical wavelet transformation and transfer learning. Biomed Sig Process Control2022; 71: 103076.
13.
KaplanEBayginMBaruaPD, et al.Exhif: Alzheimer's disease detection using exemplar histogram-based features with CT and MR images. Med Eng Phys2023; 115: 103971.
14.
RumalaDJvan OoijenPRachmadiRF, et al.Deep-Stacked convolutional neural networks for brain abnormality classification based on MRI images. J Digit Imaging2023; 36: 460–1479.
15.
ShahHASaeedFYunS, et al.A robust approach for brain tumor detection in magnetic resonance images using finetuned EfficientNet. IEEE Access2022; 10: 65426–65438.
16.
OhYParkSYeJC. Deep learning COVID-19 features on CXR using limited training data sets. IEEE Trans Med Imaging2020; 39: 2688–2700.
17.
WuPShenJ. Brain tumor diagnosis based on convolutional neural network improved by a new version of political optimizer. Biomed Sig Process Control2023; 85: 104853.
18.
KhanMSIRahmanADebnathT, et al.Accurate brain tumor detection using deep convolutional neural network. Comput Struct Biotechnol J2022; 20: 4733–4745.
19.
GautamRSharmaM. Prevalence and diagnosis of neurological disorders using different deep learning techniques: a meta-analysis. J Med Syst2020; 44: 49.
20.
SegatoAMarzulloACalimeriF,et al.Artificial intelligence for brain diseases: a systematic review. APL Bioeng2020; 4: 041503.
21.
BhateleKRBhadauriaSS. Brain structural disorders detection and classification approaches: a review. Artif Intell Rev2020; 53: 3349–3401.
BrašićJRMohamedM. Human brain imaging of autism spectrum disorders. In: Imaging of the human brain in health and disease. USA: Academic Press, 2014, pp.373–406.
24.
MasdeuJC. Neuroimaging in psychiatric disorders. Neurotherapeutics2011; 8: 93–102.
25.
EckerCGinestetCFengY, et al.Brain surface anatomy in adults with autism: the relationship between surface area, cortical thickness, and autistic symptoms. JAMA Psychiatry2013; 70: 59–70.
26.
KhundrakpamBSLewisJDKostopoulosP, et al.Cortical thickness abnormalities in autism spectrum disorders through late childhood, adolescence, and adulthood: a large-scale MRI study. Cereb Cortex2017; 27: 1721–1731.
27.
CourchesneEKarnsCMDavisHR, et al.Unusual brain growth patterns in early life in patients with autistic disorder: an MRI study. Neurology2001; 57: 245–254.
28.
StiglerKAMcDonaldBCAnandA, et al.Structural and functional magnetic resonance imaging of autism spectrum disorders. Brain Res2011; 1380: 146–161.
29.
KhodatarsMShoeibiASadeghiD, et al.Deep learning for neuroimaging-based diagnosis and rehabilitation of autism spectrum disorder: a review. Comput Biol Med2021; 139: 104949.
30.
XuMCalhounVJiangR, et al.Brain imaging-based machine learning in autism spectrum disorder: methods and applications. J Neurosci Methods2021; 361: 109271.
31.
EslamiTAlmuqhimFRaikerJS,et al.Machine learning methods for diagnosing autism spectrum disorder and attention-deficit/hyperactivity disorder using functional and structural MRI: a survey. Front Neuroinform2021; 62: 1–20.
32.
MoridianPGhassemiNJafariM, et al.Automatic autism spectrum disorder detection using artificial intelligence methods with MRI neuroimaging: A review. arXiv preprint arXiv:2206.11233, 2022.
33.
HydeKKNovackMNLaHayeN, et al.Applications of supervised machine learning in autism spectrum disorder research: a review. Rev J Autism Dev Disord2019; 6: 128–146.
34.
JoudarSSAlbahriASHamidRA. Triage and priority-based healthcare diagnosis using artificial intelligence for autism spectrum disorder and Gene contribution: a systematic review. Comput Biol Med2022; 146: 105553.
35.
Parlett-PelleritiCMStevensEDixonD,et al.Applications of unsupervised machine learning in autism spectrum disorder research: a review. Rev J Autism Dev Disord2022; 10: 1–16.
36.
KatuwalGJCahillNDBaumSA,et al.The predictive power of structural MRI in Autism diagnosis. In: 2015 37th annual international conference of the ieee engineering in medicine and biology society (EMBC), August 2015, pp.4270–4273. IEEE. 10.1109/EMBC.2015.7319338.
37.
KatuwalGJBaumSACahillND,et al.Divide and conquer: sub-grouping of ASD improves ASD detection based on brain morphometry. PloS One2016; 11: e0153331.
38.
GhiassianSGreinerRJinP,et al.Using functional or structural magnetic resonance images and personal characteristic data to identify ADHD and autism. PloS One2016; 11: e0166934.
39.
KeFLiuHZhouM, et al.Diagnostic biomarker exploration of autistic patients with different ages and different verbal intelligence quotients based on random forest model. IEEE Access2021; 9: 123861–123872.
40.
AnirudhRThiagarajanJJ. Bootstrapping graph convolutional neural networks for autism spectrum disorder classification. In: ICASSP 2019–2019 IEEE international conference on acoustics, speech and signal processing (ICASSP), May 2019, pp.3197–3201. IEEE. 10.1109/ICASSP.2019.8683547.
41.
LiHParikhNAHeL. A novel transfer learning approach to enhance deep neural network classification of brain functional connectomes. Front Neurosci2018; 12: 491.
42.
DemirhanA. The effect of feature selection on multivariate pattern analysis of structural brain MR images. Phys Med2018; 47: 103–111.
43.
SenBBorleNCGreinerR,et al.A general prediction model for the detection of ADHD and autism using structural and functional MRI. PloS One2018; 13: e0194856.
44.
HeinsfeldASFrancoARCraddockRC, et al.Identification of autism spectrum disorder using deep learning and the ABIDE dataset. NeuroImage: Clin2018; 17: 16–23.
45.
ParisotSKtenaSIFerranteE, et al.Disease prediction using graph convolutional networks: application to autism spectrum disorder and Alzheimer’s disease. Med Image Anal2018; 48: 117–130.
46.
SoussiaMRekikI. Unsupervised manifold learning using high-order morphological brain networks derived from T1-w MRI for autism diagnosis. Front Neuroinform2018; 12: 70.
47.
AghdamMASharifiAPedramMM. Diagnosis of autism spectrum disorders in young children based on resting-state functional magnetic resonance imaging data using convolutional neural networks. J Digit Imaging2019; 32: 899–918.
48.
ParikhMNLiHHeL. Enhancing diagnosis of autism with optimized machine learning models and personal characteristic data. Front Comput Neurosci2019; 13: 9.
49.
DekhilOAliMEl-NakiebY, et al.A personalized autism diagnosis CAD system using a fusion of structural MRI and resting-state functional MRI data. Front Psychiatry2019; 10: 1–16. https://doi.org/10.3389/fpsyt.2019.00392
50.
RonickoJFAThomasJThangavelP, et al.Diagnostic classification of autism using resting-state fMRI data improves with full correlation functional brain connectivity compared to partial correlation. J Neurosci Methods2020; 345: 108884.
51.
RakićMCabezasMKushibarK, et al.Improving the detection of autism spectrum disorder by combining structural and functional MRI information. NeuroImage Clin2020; 25: 102181.
52.
SherkatghanadZAkhondzadehMSalariS, et al.Automated detection of autism spectrum disorder using a convolutional neural network. Front Neurosci2020; 13: 1325.
53.
DekhilOAliMHaweelR, et al.A comprehensive framework for differentiating autism spectrum disorder from neurotypicals by fusing structural MRI and resting state functional MRI. In: Seminars in pediatric neurology, July 2020, Vol. 34, p.100805. WB Saunders. 10.1016/j.spen.2020.100805.
54.
NiuKGuoJPanY, et al.Multichannel deep attention neural networks for the classification of autism spectrum disorder using neuroimaging and personal characteristic data. Complexity2020; 2020: –9.
55.
MostafaSYinWWuFX. Autoencoder based methods for diagnosis of autism spectrum disorder. In: International conference on computational advances in bio and medical sciences, November 2019, pp.39–51. Springer, Cham. 10.1007/978-3-030-46165-2_4.
56.
JiangHCaoPXuM, et al.Hi-GCN: a hierarchical graph convolution network for graph embedding learning of brain network and brain disorders prediction. Comput Biol Med2020; 127: 104096.
57.
ShahamatHAbadehMS. Brain MRI analysis using a deep learning based evolutionary approach. Neur Netw2020; 126: 218–234.
58.
AhmedMRZhangYLiuY,et al.Single volume image generator and deep learning-based ASD classification. IEEE J Biomed Health Inform2020; 24: 3044–3054.
59.
HuangZAZhuZYauCH,et al.Identifying autism spectrum disorder from resting-state fMRI using deep belief network. IEEE Trans Neur Netw Learn Syst2021; 32: 2847–2861.
60.
HaweelRShalabyAMahmoudA, et al.A robust DWT–CNN-based CAD system for early diagnosis of autism using task-based fMRI. Med Phys2021; 48: 2315–2326.
61.
YinWMostafaSWuFX. Diagnosis of autism spectrum disorder based on functional brain networks with deep learning. J Comput Biol2021; 28: 146–165.
62.
MostafaSWuFX. Diagnosis of autism spectrum disorder with convolutional autoencoder and structural MRI images. In: Neural engineering techniques for autism Spectrum disorder. USA: Academic Press, 2021, pp.23–38.
63.
YangCWangPTanJ, et al.Autism spectrum disorder diagnosis using graph attention network based on spatial-constrained sparse functional brain networks. Comput Biol Med2021; 139: 104963.
64.
ShaoLFuCYouY,et al.Classification of ASD based on fMRI data with deep learning. Cogn Neurodyn2021; 15: 961–974.
65.
SharifHKhanRA. A novel machine learning based framework for detection of autism spectrum disorder (ASD). Appl Artif Intell2022; 36: 2004655.
66.
CaoMYangMQinC, et al.Using DeepGCN to identify the autism spectrum disorder from multi-site resting-state data. Biomed Sig Process Control2021; 70: 103015.
67.
AliMTElNakiebYElnakibA, et al.The role of structure MRI in diagnosing autism. Diagnostics2022; 12: 65.
68.
ItaniSThanouD. Combining anatomical and functional networks for neuropathology identification: a case study on autism spectrum disorder. Med Image Anal2021; 69: 101986.
69.
LuPLiXHuL,et al.Integrating genomic and resting state fMRI for efficient autism spectrum disorder classification. Multim Tools Appl2022; 81: 1–12.
70.
WenGCaoPBaoH, et al.MVS-GCN: a prior brain structure learning-guided multi-view graph convolution network for autism spectrum disorder diagnosis. Comput Biol Med2022; 142: 105239.
71.
KangLChenJHuangJ,et al.Autism spectrum disorder recognition based on multi-view ensemble learning with multi-site fMRI. Cogn Neurodyn2023; 17: 345–355.
72.
ZhangFWeiYLiuJ, et al.Identification of Autism spectrum disorder based on a novel feature selection method and Variational Autoencoder. Comput Biol Med2022; 148: 105854.
73.
KashefR. ECNN: enhanced convolutional neural network for efficient diagnosis of autism spectrum disorder. Cogn Syst Res2022; 71: 41–49.
74.
ZhangJFengFHanT, et al.Detection of autism spectrum disorder using fMRI functional connectivity with feature selection and deep learning. Cogn Comput2022; 15: 1–12.
KuttalaDMahapatraDSubramanianR,et al.Dense attentive GAN-based one-class model for detection of autism and ADHD. J King Saud Univ-Comput Inform Sci2022; 34: 10444–10458.
77.
MishraMPatiUC. Autism spectrum disorder detection using surface morphometric feature of sMRI in machine learning. In: 2021 8th international conference on smart computing and communications (ICSCC), July 2021, pp.17–20. IEEE. 10.1109/ICSCC51209.2021.9528240.
78.
MishraMPatiUC. Autism detection using surface and volumetric morphometric feature of sMRI with Machine learning approach. In: International conference on advanced network technologies and intelligent computing, December 2021, pp.625–633. Springer, Cham.10.1007/978-3-030-96040-7_47.
79.
MishraMPatiUC. A classification framework for Autism Spectrum Disorder detection using sMRI: optimizer based ensemble of deep convolution neural network with on-the-fly data augmentation. Biomed Sig Process Control2023; 84: 104686.
80.
YousefianAShayeghFMalekiZ. Detection of autism spectrum disorder using graph representation learning algorithms and deep neural network, based on fMRI signals. Front Syst Neurosci2023; 16: 904770.
81.
TangYTongGXiongX, et al.Multi-site diagnostic classification of autism spectrum disorder using adversarial deep learning on resting-state fMRI. Biomed Sig Process Control2023; 85: 104892.
JönemoJAbramianDEklundA. Evaluation of augmentation methods in classifying autism spectrum disorders from fMRI data with 3D convolutional neural networks. Diagnostics2023; 13: 2773.
84.
ManikantanKJaganathanS. A model for diagnosing autism patients using spatial and statistical measures using rs-fMRI and sMRI by adopting graphical neural networks. Diagnostics2023; 13: 1143.
85.
AbbasSQChiLChenYPP. Deepmnf: deep multimodal neuroimaging framework for diagnosing autism spectrum disorder. Artif Intell Med2023; 136: 102475.
SachdevaJMittalRMehtaJ, et al.Resolving autism spectrum disorder (ASD) through brain topologies using fMRI dataset with multi-layer perceptron (MLP). Psychiatry Res, Neuroimaging2024; 343: 111858.
88.
ElakkiyaMK. Novel deep learning models with novel integrated activation functions for autism screening: autiNet and MinAutiNet. Expert Syst Appl2024; 238: 122102.
89.
BandyopadhyaySPeddiSSarmaM,et al.Decoding autism: uncovering patterns in brain connectivity through sparsity analysis with rs-fMRI data. J Neurosci Methods2024; 405: 110100.
90.
NajafpourZFatemiAGoudarziZ, et al.Cost-effectiveness of neuroimaging technologies in management of psychiatric and insomnia disorders: a meta-analysis and prospective cost analysis. J Neuroradiol2021; 48: 348–358.
91.
Di MartinoAYanCGLiQ, et al.The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism. Molecul Psychiatry2014; 19: 659–667.
92.
ScottACourtneyWWoodD, et al.COINS: an innovative informatics and neuroimaging tool suite built for large heterogeneous datasets. Front Neuroinform2011; 5: 33.
93.
VaswaniAShazeerNParmarN, et al.Attention is all you need. Adv Neur Inform Process Syst2017; 30.
94.
DosovitskiyABeyerLKolesnikovA, et al.An image is worth 16(16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
95.
DengJDongWSocherR, et al.Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, June 2009, pp.248–255.
96.
KaselimiMVoulodimosADaskalopoulosI, et al.A vision transformer model for convolution-free multilabel classification of satellite imagery in deforestation monitoring. IEEE Trans Neur Netw Learn Syst2022; 34.
97.
GaoJChenMLiY, et al.Multisite autism spectrum disorder classification using convolutional neural network classifier and individual morphological brain networks. Front Neurosci2021; 14: 629630.
