Skip to content
2000
Volume 21, Issue 6
  • ISSN: 1570-1646
  • E-ISSN: 1875-6247

Abstract

Background and Objective

The integration of multi-site functional Magnetic Resonance Imaging (fMRI) datasets with deep learning frameworks has yielded substantial advancements in the realm of Autism Spectrum Disorder (ASD) research. However, existing graph convolutional neural networks (GCNs) only aggregate neighbor information at a fixed scale and cannot adjust the scale parameters to aggregate the best information.

Methods

In this study, a population graph-based framework, homogeneous graph wavelet neural network (H-GWNN), is proposed to learn representations for graph classification in an end-to-end manner. Specifically, the multi-site heterogeneous data are handled with a balance homogenization algorithm (BHA), which is developed based on location and scale effects. Both image data and phenotypic data are fused to construct a population graph, and the most discriminative information on the graph is extracted by adjusting the scale in a graph wavelet neural network (GWNN).

Results

The experiments on the autism dataset ABIDE show that the classification accuracy of H-GWNN on autism is 83.58%, which exceeds that of other related GCN frameworks.

Conclusion

The findings demonstrate that H-GWNN can not only tackle data heterogeneity but also analyze node features at the optimal scale. It captures discriminative features to improve classification performance for ASD identification.

© 2024 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/cp/10.2174/0115701646346401250221080035
2024-06-01
2025-09-30

  • From This Site

    /content/journals/cp/10.2174/0115701646346401250221080035
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. LordC. Autism spectrum disorder.Nat Rev Dis Primers202061510.1038/s41572‑019‑0138‑431949163
     [Google Scholar]
  2. NielsenJ.A. ZielinskiB.A. FletcherP.T. AlexanderA.L. LangeN. BiglerE.D. LainhartJ.E. AndersonJ.S. Multisite functional connectivity MRI classification of autism: ABIDE results.Front. Hum. Neurosci.2013759910.3389/fnhum.2013.0059924093016
     [Google Scholar]
  3. LiuM. LiB. HuD. Autism spectrum disorder studies using fMRI data and Machine Learning: A review.Front Neurosci20211569787010.3389/fnins.2021.697870
     [Google Scholar]
  4. FristonK.J. JezzardP. TurnerR. Analysis of functional MRI time‐series.Hum. Brain Mapp.19941215317110.1002/hbm.460010207
     [Google Scholar]
  5. WangJ. ZhuH. WangS.H. ZhangY.D. A review of Deep Learning on medical image analysis.Mob. Netw. Appl.202126135138010.1007/s11036‑020‑01672‑7
     [Google Scholar]
  6. HeinsfeldA.S. FrancoA.R. CraddockR.C. BuchweitzA. MeneguzziF. Identification of autism spectrum disorder using deep learning and the ABIDE dataset.Neuroimage Clin.201817162310.1016/j.nicl.2017.08.01729034163
     [Google Scholar]
  7. YangG. ZhangY. YangJ. JiG. DongZ. WangS. FengC. WangQ. Automated classification of brain images using wavelet-energy and biogeography-based optimization.Multimedia Tools Appl.20167523156011561710.1007/s11042‑015‑2649‑7
     [Google Scholar]
  8. DunJ. WangJ. LiJ. YangQ. HangW. LuX. YingS. ShiJ. A trustworthy curriculum learning guided multi-target domain adaptation network for autism spectrum disorder classification.IEEE J. Biomed. Health Inform.2024PP11410.1109/JBHI.2024.347607639378247
     [Google Scholar]
  9. LiJ. ZhongY. HanJ. OuyangG. LiX. LiuH. Classifying ASD children with LSTM based on raw videos.Neurocomputing202039022623810.1016/j.neucom.2019.05.106
     [Google Scholar]
  10. El-GazzarA. QuaakM. CerlianiL. BloemP. van WingenG. ThomasR.M. A Hybrid 3DCNN and 3DC-LSTM based model for 4D Spatio-temporal fMRI data: An ABIDE autism classification study.arXiv:2002.059812020
     [Google Scholar]
  11. DvornekN.C. VentolaP. PelphreyK.A. DuncanJ.S. Identifying autism from resting-state fMRI using long short-term memory networks.Mach Learn Med Imaging20171054136237010.1007/978‑3‑319‑67389‑9_4229104967
     [Google Scholar]
  12. XiaoY. YinH. ZhangY. QiH. ZhangY. LiuZ. A dual‐stage attention‐based Conv‐LSTM network for spatio‐temporal correlation and multivariate time series prediction.Int. J. Intell. Syst.20213652036205710.1002/int.22370
     [Google Scholar]
  13. WenG. CaoP. BaoH. YangW. ZhengT. ZaianeO. MVS-GCN: A prior brain structure learning-guided multi-view graph convolution network for autism spectrum disorder diagnosis.Comput. Biol. Med.202214210523910.1016/j.compbiomed.2022.10523935066446
     [Google Scholar]
  14. ParisotS. KtenaS.I. FerranteE. LeeM. GuerreroR. GlockerB. RueckertD. Disease prediction using graph convolutional networks: Application to Autism Spectrum Disorder and Alzheimer’s disease.Med. Image Anal.20184811713010.1016/j.media.2018.06.00129890408
     [Google Scholar]
  15. ZhuH. WangJ. ZhaoY.P. LuM. ShiJ. Contrastive multi-view composite graph convolutional networks based on contribution learning for autism spectrum disorder classification.IEEE Trans. Biomed. Eng.20237061943195410.1109/TBME.2022.323210437015677
     [Google Scholar]
  16. KipfT.N. WellingM. Semi-supervised classification with graph convolutional networks.arXiv:1609.029072017
     [Google Scholar]
  17. HuK. DongG. ZhaoY. LiR. JiangD. ChaoY. LiuH. GeY. Dual graph wavelet neural network for graph-based semi-supervised classification.J. Intell. Fuzzy Syst.20224265177518810.3233/JIFS‑211729
     [Google Scholar]
  18. Abu-El-HaijaS. KapoorA. PerozziB. LeeJ. N-GCN: Multi-scale graph convolution for semi-supervised node classification.arXiv:1802.088882020
     [Google Scholar]
  19. GhoshP. YaoY. DavisL. DivakaranA. Stacked spatio-temporal graph convolutional networks for action segmentation.Proceedings of the IEEE/CVF winter conference on applications of computer visionSnowmass, CO, USA, 01-05 March 2020, pp. 565-57410.1109/WACV45572.2020.9093361
     [Google Scholar]
  20. QiS. WangW. JiaB. ShenJ. ZhuS-C. Learning human-object interactions by graph parsing neural networks.Proceedings of the European conference on computer vision (ECCV)Springer, Cham, 2018, vol 11213, pp. 401-417.10.1007/978‑3‑030‑01240‑3_25
     [Google Scholar]
  21. HuangY. HuP. ChanK.C.C. YouZ.H. Graph convolution for predicting associations between miRNA and drug resistance.Bioinformatics202036385185810.1093/bioinformatics/btz62131397851
     [Google Scholar]
  22. ZhangY.D. SatapathyS.C. GutteryD.S. GórrizJ.M. WangS.H. Improved breast cancer classification through combining graph convolutional network and convolutional neural network.Inf. Process. Manage.202158210243910.1016/j.ipm.2020.102439
     [Google Scholar]
  23. HammondD.K. VandergheynstP. GribonvalR. Wavelets on graphs via spectral graph theory.arXiv:0912.38482009
     [Google Scholar]
  24. ShumanD.I. WiesmeyrC. HolighausN. VandergheynstP. Spectrum-adapted tight graph wavelet and vertex-frequency frames.arXiv:1311.08972013
     [Google Scholar]
  25. XuB. ShenH. CaoQ. QiuY. ChengX. Graph wavelet neural network.arXiv:1904.077852019
     [Google Scholar]
  26. WuZ. PanS. ChenF. LongG. ZhangC. YuP.S. A comprehensive survey on graph neural networks.IEEE Trans. Neural Netw. Learn. Syst.202132142410.1109/TNNLS.2020.297838632217482
     [Google Scholar]
  27. ZhangS. DongQ. ZhangW. HuangH. ZhuD. LiuT. Discovering hierarchical common brain networks via multimodal deep belief network.Med. Image Anal.20195423825210.1016/j.media.2019.03.01130954851
     [Google Scholar]
  28. KanX. CuiH. LukemireJ. GuoY. YangC. FBNetGen: Task-aware GNN-based fMRI analysis via functional brain network generation.arXiv:2205.124652022
     [Google Scholar]
  29. KaziA. InceptionGCN: Receptive field aware graph convolutional network for disease prediction.arXiv:1903.04233201910.1007/978‑3‑030‑20351‑1_6
     [Google Scholar]
  30. WangM. GuoJ. WangY. YuM. GuoJ. Multimodal autism spectrum disorder diagnosis method based on DeepGCN.IEEE Trans. Neural Syst. Rehabil. Eng.2023313664367410.1109/TNSRE.2023.331451637698959
     [Google Scholar]
  31. PomponioR. ErusG. HabesM. DoshiJ. SrinivasanD. MamourianE. BashyamV. NasrallahI.M. SatterthwaiteT.D. FanY. LaunerL.J. MastersC.L. MaruffP. ZhuoC. VölzkeH. JohnsonS.C. FrippJ. KoutsoulerisN. WolfD.H. GurR. GurR. MorrisJ. AlbertM.S. GrabeH.J. ResnickS.M. BryanR.N. WolkD.A. ShinoharaR.T. ShouH. DavatzikosC. Harmonization of large MRI datasets for the analysis of brain imaging patterns throughout the lifespan.Neuroimage202020811645010.1016/j.neuroimage.2019.11645031821869
     [Google Scholar]
  32. FortinJ.P. ParkerD. TunçB. WatanabeT. ElliottM.A. RuparelK. RoalfD.R. SatterthwaiteT.D. GurR.C. GurR.E. SchultzR.T. VermaR. ShinoharaR.T. Harmonization of multi-site diffusion tensor imaging data.Neuroimage201716114917010.1016/j.neuroimage.2017.08.04728826946
     [Google Scholar]
  33. JohnsonW.E. LiC. RabinovicA. Adjusting batch effects in microarray expression data using empirical Bayes methods.Biostatistics20078111812710.1093/biostatistics/kxj03716632515
     [Google Scholar]
  34. CaoM. YangM. QinC. ZhuX. ChenY. WangJ. LiuT. Using DeepGCN to identify the autism spectrum disorder from multi-site resting-state data.Biomed. Signal Process. Control20217010301510.1016/j.bspc.2021.103015
     [Google Scholar]
  35. RaschkaS. Model evaluation, model selection, and algorithm selection in Machine Learning.arXiv:1811.128082018
     [Google Scholar]
  36. Di MartinoA. YanC-G. LiQ. DenioE. CastellanosF.X. AlaertsK. AndersonJ.S. AssafM. BookheimerS.Y. DaprettoM. DeenB. DelmonteS. DinsteinI. Ertl-WagnerB. FairD.A. GallagherL. KennedyD.P. KeownC.L. KeysersC. LainhartJ.E. LordC. LunaB. MenonV. MinshewN.J. MonkC.S. MuellerS. MüllerR-A. NebelM.B. NiggJ.T. O’HearnK. PelphreyK.A. PeltierS.J. RudieJ.D. SunaertS. ThiouxM. TyszkaJ.M. UddinL.Q. VerhoevenJ.S. WenderothN. WigginsJ.L. MostofskyS.H. MilhamM.P. The autism brain imaging data exchange: Towards a large-scale evaluation of the intrinsic brain architecture in autism.Mol. Psychiatry201419665966710.1038/mp.2013.7823774715
     [Google Scholar]
  37. CraddockR.C. JamesG.A. HoltzheimerP.E.III HuX.P. MaybergH.S. A whole brain fMRI atlas generated via spatially constrained spectral clustering.Hum. Brain Mapp.20123381914192810.1002/hbm.2133321769991
     [Google Scholar]
  38. KundaM. ZhouS. GongG. LuH. Improving multi-site autism classification via site-dependence minimization and second-order functional connectivity.IEEE Trans. Med. Imaging2023421556510.1109/TMI.2022.320389936054402
     [Google Scholar]
  39. HuangY. ChungA.C.S. Edge-variational graph convolutional networks for uncertainty-aware disease predictionarXiv:2009.02759202010.1007/978‑3‑030‑59728‑3_55
     [Google Scholar]
  40. JiangH. CaoP. XuM. YangJ. ZaianeO. Hi-GCN: A hierarchical graph convolution network for graph embedding learning of brain network and brain disorders prediction.Comput. Biol. Med.202012710409610.1016/j.compbiomed.2020.10409633166800
     [Google Scholar]
  41. EslamiT. MirjaliliV. FongA. LairdA.R. SaeedF. ASD-DiagNet: A hybrid learning approach for detection of autism spectrum disorder using fMRI data.Front. Neuroinform.2019137010.3389/fninf.2019.0007031827430
     [Google Scholar]
  42. ZhuZ. A survey of gnn in bioinformation data.Preprints202210.20944/preprints202209.0226.v1
     [Google Scholar]
  43. Van der MaatenL. HintonG. Visualizing data using t-SNE.J. Mach. Learn. Res.2008911
     [Google Scholar]
  44. SheldrickR.C. MayeM.P. CarterA.S. Age at first identification of autism spectrum disorder: An analysis of two US surveys.J. Am. Acad. Child Adolesc. Psychiatry201756431332010.1016/j.jaac.2017.01.01228335875
     [Google Scholar]
  45. ZhangY.D. DongZ. WangS.H. YuX. YaoX. ZhouQ. HuH. LiM. Jiménez-MesaC. RamirezJ. MartinezF.J. GorrizJ.M. Advances in multimodal data fusion in neuroimaging: Overview, challenges, and novel orientation.Inf. Fusion20206414918710.1016/j.inffus.2020.07.00632834795
     [Google Scholar]
/content/journals/cp/10.2174/0115701646346401250221080035
Loading
H-GWNN: A Population Graph-Based Autism Spectrum Disorders Identification Framework for Tackling Data Heterogeneity
Curr. Proteomics 21, 580 (2024); https://doi.org/10.2174/0115701646346401250221080035
/content/journals/cp/10.2174/0115701646346401250221080035
/content/journals/cp/10.2174/0115701646346401250221080035
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Autism spectrum disorder; balance homogenization algorithm (BHA); data heterogeneity; functional magnetic resonance imaging; graph wavelet neural network; population graph

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test