人工智能在功能磁共振成像数据中的自闭症研究综述

doi:10.3778/j.issn.1002-8331.2303-0324

摘要/Abstract

摘要： 自闭症谱系障碍是一种严重的精神障碍疾病，多发于儿童时期，影响个体的社交和日常生活。近年来，基于功能磁共振成像（functional magnetic resonance imaging，fMRI）数据的自闭症人工智能诊断成为研究热点。机器学习、深度学习等先进技术已经被用于自闭症的智能辅助诊断研究中，旨在提高诊断的效率、准确性以及探索发病机制。首先介绍了自闭症智能诊断的背景、重要意义和面临的挑战；其次回顾了近5年智能诊断相关技术在自闭症分类识别中的进展，从机器学习和深度学习两方面总结、分析智能诊断不同方法的特点和局限性；最后探讨了自闭症智能诊断亟需解决的问题及未来研究趋势，为自闭症早期诊断和临床应用提供指导和参考。

关键词: 人工智能, 自闭症谱系障碍, 功能磁共振成像, 机器学习, 深度学习

Abstract: Autism spectrum disorder is a serious mental disorder that occurs in childhood and affects the social and daily life of individuals. In recent years, artificial intelligence diagnosis of autism based on functional magnetic resonance imaging（fMRI） data has become a current research hotspot. Advanced technologies such as machine learning and deep learning have been used in the research of intelligent assisted diagnosis of autism, aiming to improve the efficiency and accuracy of diagnosis as well as to explore the pathogenesis. This paper firstly introduces the background, importance and challenges of intelligent diagnosis of autism. Secondly, this paper reviews the progress of intelligent diagnosis-related technologies in the classification and identification of autism in the past five years, summarizes and analyzes the characteristics and limitations of different methods of intelligent diagnosis from two aspects：machine learning and deep learning. Finally, this paper discusses the urgent problems and future research trends of intelligent diagnosis of autism, and provides guidance for early diagnosis and clinical application of autism.

Key words: artificial intelligence, autism spectrum disorder, functional magnetic resonance imaging, machine learning, deep learning

顾剑, 钱育蓉, 王兰兰, 胡月, 陈嘉颖, 冷洪勇, 马梦楠. 人工智能在功能磁共振成像数据中的自闭症研究综述[J]. 计算机工程与应用, 2023, 59(22): 57-68.

GU Jian, QIAN Yurong, WANG Lanlan, HU Yue, CHEN Jiaying, LENG Hongyong, MA Mengnan. Survey of Artificial Intelligence in Functional Magnetic Resonance Imaging Data for Autism[J]. Computer Engineering and Applications, 2023, 59(22): 57-68.

参考文献

[1] American Psychiatric Association.Diagnostic and statistical manual of mental disorders：DSM-5[M].Washington：American Psychiatric Association，2013：212-219.
[2] NEVISON C D.A comparison of temporal trends in United States autism prevalence to trends in uspected environmental factors[J].Environmental Health，2014，13：73.
[3] LAI M C，LOMBARDO M V，BARON-COHEN S.Autism[J].Lancet，2014，383（9920）：896-910.
[4] LIU W，LI M，YI L.Identifying children with autism spectrum disorder based on their face processing abnormality：a machine learning framework[J].Autism Research，2016，9（8）：888-898.
[5] JAISWAL S，VALSTAR M F，GILLOTT A，et al.Automatic detection of ADHD and ASD from expressive behaviour in RGBD data[C]//Proceedings of the 2017 IEEE International Conference on Automatic Face & Gesture Recognition，Zurich，May 30-Jun 3，2017.Washington：IEEE，2017：372-379.
[6] MANOLI D S，STATE M W.Autism spectrum disorder genetics and the search for pathological mechanisms[J].American Journal of Psychiatry，2021，178（1）：30-38.
[7] PATEL M J，ANDREESCU C，PRICE J C，et al.Machine learning approaches for integrating clinical and imaging features in late‐life depression classification and response prediction[J].International Journal of Geriatric Psychiatry，2015，30（10）：1056-1067.
[8] GRECUCCI A，SIUGZDAITE R，JOB R.Advanced neuroimaging methods for studying autism disorder[J].Frontiers in Neuroscience，2017，11（1）：533.
[9] DU Y，FU Z，CALHOUN V D.Classification and prediction of brain disorders using functional connectivity：promising but challenging[J].Frontiers in Neuroscience，2018，12：525.
[10] HENRY J C.Electroencephalography：basic principles，clinical applications，and related fields[J].Neurology，2006，67（11）：2092-2092.
[11] MARHL U，JODKO-WLADZINSKA A，BRüHL R，et al.Application of source localization algorithms in magnetoencephalography：test on a new generation of magnetometers[C]//Proceedings of the 2019 IEEE International Convention on Information and Communication Technology，Electronics and Microelectronics，Opatija，May 20-24，2019：357-362.
[12] JEZZARD P，MATTHEWS P M，SMITH S M.Functional MRI：an introduction to methods[M].Oxford：Oxford University Press，2001：1-10.
[13] HE Y，EVANS A.Graph theoretical modeling of brain connectivity[J].Current Opinion in Neurology，2010，23（4）：341-350.
[14] POLDRACK R A，MUMFORD J A，NICHOLS T E.Handbook of functional MRI data analysis[M].Cambridge：Cambridge University Press，2011：1-10.
[15] ANDERSON J S，NIELSEN J A，FROEHLICH A L，et al.Functional connectivity magnetic resonance imaging classification of autism[J].Brain，2011，134（12）：3742-3754.
[16] NIELSEN J A，ZIELINSKI B A，FLETCHER P T，et al.Multisite functional connectivity MRI classification of autism：ABIDE results[J].Frontiers in Human Neuroscience，2013，7：599.
[17] PRICE T，WEE C Y，GAO W，et al.Multiple-network classification of childhood autism using functional connectivity dynamics[C]//Proceedings of the 17th International Conference on Medical Image Computing and Computer-Assisted Intervention，Boston，Sep 14-18，2014.Berlin：Springer International Publishing，2014：177-184.
[18] NEUFELD J，KUJA-HALKOLA R，MEVEL K，et al.Alterations in resting state connectivity along the autism trait continuum：a twin study[J].Molecular Psychiatry，2018，23（7）：1659-1665.
[19] CHERKASSKY V L，KANA R K，KELLER T A，et al.Functional connectivity in a baseline resting-state network in autism[J].Neuroreport，2006，17（16）：1687-1690.
[20] PAGNOZZI A M，CONTI E，CALDERONI S，et al.A systematic review of structural MRI biomarkers in autism spectrum disorder：a machine learning perspective[J].International Journal of Developmental Neuroscience，2018，71（1）：68-82.
[21] NOGAY H S，ADELI H.Machine learning （ML） for the diagnosis of autism spectrum disorder （ASD） using brain imaging[J].Reviews in the Neurosciences，2020，31（8）：825-841.
[22] PARLETT-PELLERITI C M，STEVENS E，DIXON D，et al.Applications of unsupervised machine learning in autism spectrum disorder research：a review[J].Review Journal of Autism and Developmental Disorders，2023，10：406-421.
[23] DI MARTINO A，YAN C G，LI Q，et al.The autism brain imaging data exchange：towards a large-scale evaluation of the intrinsic brain architecture in autism[J].Molecular Psychiatry，2014，19（6）：659-667.
[24] KHODATARS M，SHOEIBI A，SADEGHI D，et al.Deep learning for neuroimaging-based diagnosis and rehabilitation of autism spectrum disorder：a review[J].Computers in Biology and Medicine，2021，139：104949.
[25] KUNDA M，ZHOU S，GONG G，et al.Improving multi-site autism classification via site-dependence minimization and second-order functional connectivity[J].IEEE Transactions on Medical Imaging，2022，42（1）：55-65.
[26] SUBAH F Z，DEB K，DHAR P K，et al.A deep learning approach to predict autism spectrum disorder using multisite resting-state fMRI[J].Applied Sciences，2021，11（8）：3636.
[27] RAHMAN M M，USMAN O L，MUNIYANDI R C，et al.A review of machine learning methods of feature selection and classification for autism spectrum disorder[J].Brain Sciences，2020，10（12）：949.
[28] LANCASTER J L，WOLDORFF M G，PARSONS L M，et al.Automated Talairach atlas labels for functional brain mapping[J].Human Brain Mapping，2000，10（3）：120-131.
[29] ARTIPI S，SHAYESTEH M G，KALBKHANI H.Diag-nosing of autism spectrum disorder based on GARCH variance series for rs-fMRI data[C]//Proceedings of the 2018 IEEE International Symposium on Telecommunications，Singapore，Dec 28-30，2018：86-90.
[30] WANG C，XIAO Z，WU J.Functional connectivity-based classification of autism and control using SVM-RFECV on rs-fMRI data[J].Physica Medica，2019，65（1）：99-105.
[31] MOSTAFA S，TANG L，WU F X.Diagnosis of autism spectrum disorder based on eigenvalues of brain networks[J].IEEE Access，2019，7：128474-128486.
[32] REITER M A，JAHEDI A，FREDO A R J，et al.Performance of machine learning classification models of autism using resting-state fMRI is contingent on sample heterogeneity[J].Neural Computing Applications，2021，33（8）：3299-3310.
[33] KAZEMINEJAD A，SOTERO R C.The importance of anti-correlations in graph theory based classification of autism spectrum disorder[J].Frontiers in Neuroscience，2020，14：676.
[34] LIU Y，XU L，LI J，et al.Attentional connectivity-based prediction of autism using heterogeneous rs-fMRI data from CC200 atlas[J].Experimental Neurobiology，2020，29：27.
[35] SUN L，XUE Y，ZHANG Y，et al.Estimating sparse functional connectivity networks via hyperparameter-free learning model[J].Artificial Intelligence in Medicine，2021，111：102004.
[36] WANG N，YAO D，MA L，et al.Multi-site clustering and nested feature extraction for identifying autism spectrum disorder with resting-state fMRI[J].Medical Image Analysis，2022，75：102279.
[37] PARIKH M N，LI H，HE L.Enhancing diagnosis of autism with optimized machine learning models and personal characteristic data[J].Frontiers in Computational Neuroscience，2019，13：9.
[38] PLITT M，BARNES K A，MARTIN A.Functional connectivity classification of autism identifies highly predictive brain features but falls short of biomarker standards[J].NeuroImage：Clinical，2015，7：359-366.
[39] EMERSON R W，ADAMS C，NISHINO T，et al.Functional neuroimaging of high-risk 6-month-old infants predicts a diagnosis of autism at 24 months of age[J].Science Translational Medicine，2017，9（393）：eaag2882.
[40] SPERA G，RETICO A，BOSCO P，et al.Evaluation of altered functional connections in male children with autism spectrum disorders on multiple-site data optimized with machine learning[J].Frontiers in Psychiatry，2019，10：620.
[41] NOBLE W S.What is a support vector machine?[J].Nature Biotechnology，2006，24（12）：1565-1567.
[42] CHEN C P，KEOWN C L，JAHEDI A，et al.Diagnostic classification of intrinsic functional connectivity highlights somatosensory，default mode，and visual regions in autism[J].NeuroImage：Clinical，2015，8：238-245.
[43] KATUWAL G J，BAUM S A，CAHILL N D，et al.Divide and conquer：sub-grouping of ASD improves ASD detection based on brain morphometry[J].PLoS ONE，2016，11（4）：e0153331.
[44] FECZKO E，BALBA N M，MIRANDA-DOMINGUEZ O，et al.Subtyping cognitive profiles in autism spectrum disorder using a functional random forest algorithm[J].Neuroimage，2018，172：674-688.
[45] THABTAH F.Machine learning in autistic spectrum disorder behavioral research：a review and ways forward[J].Informatics for Health and Social Care，2019，44（3）：278-297.
[46] DU X，CAI Y，WANG S，et al.Overview of deep learning[C]//Proceedings of the 2016 IEEE Youth Academic Annual Conference of Chinese Association of Automation，Wuhan，Nov 11-13，2016：159-164.
[47] HINTON G E，SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J].Science，2006，313（5786）：504-507.
[48] XIAO Z，WANG C，JIA N，et al.SAE-based classification of school-aged children with autism spectrum disorders using functional magnetic resonance imaging[J].Multimedia Tools and Applications，2018，77：22809-22820.
[49] KHOSLA M，JAMISON K，KUCEYESKI A，et al.3D convolutional neural networks for classification of functional connectomes[C]//Proceedings of the 4th International Workshop on Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support，and the 8th International Workshop，ML-CDS 2018，Held in Conjunction with MICCAI 2018，Granada，Sep 20，2018：137-145.
[50] BROWN C J，KAWAHARA J，HAMARNEH G.Connectome priors in deep neural networks to predict autism[C]//Proceedings of the 2018 IEEE International Symposium on Biomedical Imaging，Washington，Apr 4-7，2018：110-113.
[51] AKHAVAN AGHDAM M，SHARIFI A，PEDRAM M M.Combination of rs-fMRI and sMRI data to discriminate autism spectrum disorders in young children using deep beief network[J].Journal of Digital Imaging，2018，31：895-903.
[52] LI X，DVORNEK N C，ZHUANG J，et al.Brain biomarker interpretation in ASD using deep learning and fMRI[C]//Proceedings of the 21st International Conference on Medical Image Computing and Computer Assisted Intervention，Granada，Sep 16-20，2018：206-214.
[53] LU H，LIU S，WEI H，et al.Multi-kernel fuzzy clustering based on auto-encoder for fMRI functional network[J].Expert Systems with Applications，2020，159：113513.
[54] RAKI? M，CABEZAS M，KUSHIBAR K，et al.Improving the detection of autism spectrum disorder by combining structural and functional MRI information[J].NeuroImage：Clinical，2020，25：102181.
[55] AHMED M R，ZHANG Y，LIU Y，et al.Single volume image generator and deep learning-based ASD classification[J].IEEE Journal of Biomedical and Health Informatics，2020，24（11）：3044-3054.
[56] EL-GAZZAR A，QUAAK M，CERLIANI L，et al.A hybrid 3DCNN and 3DC-LSTM based model for 4D spatiotemporal fMRI data：an ABIDE autism classification study[C]//Proceedings of the 2nd International Workshop on OR 2.0 Context-Aware Operating Theaters and Machine Learning in Clinical Neuroimaging，and the 2nd International Workshop，MLCN 2019，Held in Conjunction with MICCAI 2019，Shenzhen，Oct 13-17，2019：95-102.
[57] YANG X，SCHRADER P T，ZHANG N.A deep neural network study of the ABIDE repository on autism spectrum classification[J].International Journal of Advanced Computer Science and Applications，2020.DOI：10.14569/
IJACSA.2020.0110401.
[58] ALMUQHIM F，SAEED F.ASD-SAENet：a sparse autoencoder，and deep-neural network model for detecting autism spectrum disorder （ASD） using fMRI data[J].Frontiers in Computational Neuroscience，2021，15：654315.
[59] YIN W，MOSTAFA S，WU F X.Diagnosis of autism spectrum disorder based on functional brain networks with deep learning[J].Journal of Computational Biology，2021，28（2）：146-165.
[60] INGALHALIKAR M，SHINDE S，KARMARKAR A，et al.Functional connectivity-based prediction of Autism on site harmonized ABIDE dataset[J].IEEE Transactions on Biomedical Engineering，2021，68（12）：3628-3637.
[61] ZHANG J，FENG F，HAN T，et al.Detection of autism spectrum disorder using fMRI functional connectivity with feature selection and deep learning[J].Cognitive Computation，2023，15：1106-1117.
[62] RUMELHART D E，HINTON G E，WILLIAMS R J.Learning representations by back-propagating errors[J].Nature，1986，323（6088）：533-536.
[63] HEINSFELD A S，FRANCO A R，CRADDOCK R C，et al.Identification of autism spectrum disorder using deep learning and the ABIDE dataset[J].NeuroImage：Clinical，2018，17：16-23.
[64] ESLAMI T，MIRJALILI V，FONG A，et al.ASD-DiagNet：a hybrid learning approach for detection of autism spectrum disorder using fMRI data[J].Frontiers in Neuroinformatics，2019，13：70.
[65] PINAYA W H L，MECHELLI A，SATO J R.Using deep autoencoders to identify abnormal brain structural patterns in neuropsychiatric disorders：a large‐scale multi‐sample study[J].Human Brain Mapping，2019，40（3）：944-954.
[66] WANG Y，WANG J，WU F X，et al.AIMAFE：autism spectrum disorder identification with multi-atlas deep feature representation and ensemble learning[J].Journal of Neuroscience Methods，2020，343：108840.
[67] LECUN Y，BOSER B，DENKER J，et al.Handwritten digit recognition with a back-propagation network[C]//Proceedings of the 2nd International Conference on Neural Information Processing Systems，1989：396-404.
[68] THOMAS R M，GALLO S，CERLIANI L，et al.Classifying autism spectrum disorder using the temporal statistics of resting-state functional MRI data with 3D convolutional neural networks[J].Frontiers in Psychiatry，2020，11：440-440.
[69] RONICKO J F A，THOMAS J，THANGAVEL P，et al.Diagnostic classification of autism using resting-state fMRI data improves with full correlation functional brain connectivity compared to partial correlation[J].Journal of Neuroscience Methods，2020，345：108884.
[70] VASWANI A，SHAZEER N，PARMAR N，et al.Attention is all you need[C]//Advances in Neural Information Processing Systems 30，2017.
[71] DENG X，ZHANG J，LIU R，et al.Classifying ASD based on time-series fMRI using spatial-temporal transformer[J].Computers in Biology and Medicine，2022，151：106320.
[72] JHA R R，BHARDWAJ A，GARG D，et al.MHATC：autism spectrum disorder identification utilizing multi-head attention encoder along with temporal consolidation modules[C]//Proceedings of the 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society，Glasgow，Jul 11-15，2022.Washington：IEEE，2022：337-341.
[73] YANG M，CAO M，CHEN Y，et al.Large-scale brain functional network integration for discrimination of autism using a 3-D deep learning model[J].Frontiers in Human Neuroscience，2021，15：687288.
[74] NIU K，GUO J，PAN Y，et al.Multichannel deep attention neural networks for the classification of autism spectrum disorder using neuroimaging and personal characteristic data[J].Complexity，2020.DOI：10.1155/2020/1357853.
[75] 蒋玉英，陈心雨，李广明，等.图神经网络及其在图像处理领域的研究进展[J].计算机工程与应用，2023，59（7）：15-30.
JIANG Y Y，CHEN X Y，LI G M，et al.Graph neural network and its research progress in field of image processing[J].Computer Engineering and Applications，2023，59（7）：15-30.
[76] WU Z，PAN S，CHEN F，et al.A comprehensive survey on graph neural networks[J].IEEE Transactions on Neural Networks and Learning Systems，2020，32（1）：4-24.
[77] PARISOT S，KTENA S I，FERRANTE E，et al.Disease prediction using graph convolutional networks：application to autism spectrum disorder and Alzheimer’s disease[J].Medical Image Analysis，2018，48（1）：117-130.
[78] KAZI A，SHEKARFOROUSH S，ARVIND KRISHNA S，et al.InceptionGCN：receptive field aware graph convolutional network for disease prediction[C]//Proceedings of the 26th International Conference on Information Processing in Medical Imaging，Hong Kong，China，Jun 2-7，2019：73-85.
[79] FELOUAT H，OUKID-KHOUAS S.Graph convolutional networks and functional connectivity for identification of autism spectrum disorder[C]//Proceedings of the 2nd International Conference on Embedded & Distributed Systems，Oran，Nov 3，2020：27-32.
[80] WEN G，CAO P，BAO H，et al.MVS-GCN：a prior brain structure learning-guided multi-view graph convolution network for autism spectrum disorder diagnosis[J].Computers in Biology and Medicine，2022，142：105239.
[81] CAO M，YANG M，QIN C，et al.Using DeepGCN to identify the autism spectrum disorder from multi-site resting-state data[J].Biomedical Signal Processing and Control，2021，70：103015.
[82] PAN J，LIN H，DONG Y，et al.MAMF-GCN：multi-scale adaptive multi-channel fusion deep graph convolutional network for predicting mental disorder[J].Computers in Biology and Medicine，2022，148：105823.
[83] YAO D，LIU M，WANG M，et al.Triplet graph convolutional network for multi-scale analysis of functional connectivity using functional MRI[C]//Proceedings of the 1st International Workshop on Graph Learning in Medical Imaging，Held in Conjunction with MICCAI 2019，Shenzhen，Oct 17，2019：70-78.
[84] WANG Y，LIU J，XIANG Y，et al.MAGE：automatic diagnosis of autism spectrum disorders using multi-atlas graph convolutional networks and ensemble learning[J].Neurocomputing，2022，469：346-353.
[85] KTENA S I，PARISOT S，FERRANTE E，et al.Metric learning with spectral graph convolutions on brain connectivity networks[J].NeuroImage，2018，169：431-442.
[86] RAKHIMBERDINA Z，MURATA T.Linear graph convolutional model for diagnosing brain disorders[C]//Proceedings of the 8th International Conference on Complex Networks and Their Applications，Berlin，Aug 26-27，2019：815-826.
[87] BRAHIM A，FARRUGIA N.Graph Fourier transform of fMRI temporal signals based on an averaged structural connectome for the classification of neuroimaging[J].Artificial Intelligence in Medicine，2020，106：101870.
[88] JIANG H，CAO P，XU M Y，et al.Hi-GCN：a hierarchical graph convolution network for graph embedding learning of brain network and brain disorders prediction[J].Computers in Biology and Medicine，2020，127：104096.
[89] SHAO L，FU C，YOU Y，et al.Classification of ASD based on fMRI data with deep learning[J].Cognitive Neurodynamics，2021，15（6）：961-974.
[90] ZHOU H，ZHANG D.Graph in graph convolutional networks for brain disease diagnosis[C]//Proceedings of the 2021 IEEE International Conference on Image Processing，Anchorage，Sep 19-22，2021：111-115.
[91] ZHENG S，ZHU Z，LIU Z，et al.Multi-modal graph learning for disease prediction[J].IEEE Transactions on Medical Imaging，2022，41（9）：2207-2216.
[92] YANG X，ZHANG N，SCHRADER P.A study of brain networks for autism spectrum disorder classification using resting-state functional connectivity[J].Machine Learning with Applications，2022，8：100290.
[93] ESLAMI T，ALMUQHIM F，RAIKER J S，et al.Machine learning methods for diagnosing autism spectrum disorder and attention-deficit/hyperactivity disorder using functional and structural MRI：a survey[J].Frontiers in Neuroinformatics，2021.DOI：10.3389/fninf.2020.575999.
[94] QI S，MORRIS R，TURNER J A，et al.Common and unique multimodal covarying patterns in autism spectrum disorder subtypes[J].Molecular Autism，2020，11（1）：1-15.
[95] SADIQ A，AL-HIYALI M I，YAHYA N，et al.Non-oscillatory connectivity approach for classification of autism spectrum disorder subtypes using resting-state fMRI[J].IEEE Access，2022，10：14049-14061.
[96] HONG S J，VOGELSTEIN J T，GOZZI A，et al.Toward neurosubtypes in autism[J].Biological Psychiatry，2020，88：111-128.
[97] KAUR P，KAUR A.Review of progress in diagnostic studies of autism spectrum disorder using neuroimaging[J].Interdisciplinary Sciences：Computational Life Sciences，2023，15：111-130.
[98] ABROL A，FU Z，SALMAN M，et al.Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning[J].Nature Communications，2021，12：353.
[99] ZHANG L，WANG M，LIU M，et al.A survey on deep learning for neuroimaging-based brain disorder analysis[J].Frontiers in Neuroscience，2020，14：779.