Skip to main content
Springer Nature Link
Log in

Are brain networks classifiable?

  • Original Article
  • Published:
Network Modeling Analysis in Health Informatics and Bioinformatics Aims and scope Submit manuscript

Abstract

Autism Spectrum Disorder (ASD) and Attention Deficit Hyperactivity Disorder (ADHD) are neurodevelopmental conditions that manifest early in life, impacting cognitive, social, and behavioral functioning. ASD is characterized by difficulties in social interaction, communication challenges, and repetitive behaviors, whereas ADHD is distinguished by patterns of inattention, hyperactivity, and impulsivity. Early diagnosis of ASD and ADHD is crucial as it enables timely intervention and can significantly improve outcomes. Toward this goal, this research explores the potential of functional Magnetic Resonance Imaging (fMRI) to identify biological markers of ASD and ADHD through the analysis of functional connectivity in the brain. This work makes several important contributions. It successfully replicates and improves a state-of-the-art methodology, Contrast Subgraphs. In pursuit of simplification and efficiency using graph-theoretic approaches, an innovative technique called Discriminative Edges (DE) is introduced. DE not only achieves comparable accuracy but also offers significant improvements in speed and explainability. Furthermore, this study explores alternative methodologies, including the representation of graphs as tables for classification purposes. This technique demonstrates performance close to more intricate, cutting-edge methods. Further investigation into the incorporation of higher-order connectivity patterns reveals that such additions do not improve classification outcomes. Finally, our study using similarity measures sheds light on the challenges associated with classifying brain networks, highlighting the need for further research in this domain.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Algorithm 1
Fig. 12
Algorithm 2
Fig. 13
Fig. 14

Similar content being viewed by others

Data availability

We have used two datasets in this study. The ASD dataset obtained from Lanciano et al. (2020) is available at (https://github.com/tlancian/contrast-subgraph). The ADHD dataset from Abrate and Bonchi (2021) is available at (https://github.com/carlo-abrate/CounterfactualGraphs). The code and charts for our results for RQ1 and RQ2 can be found at https://github.com/keanelekenns/brain-network-classification. The code and charts for our results for RQ3-RQ5 can be found at https://github.com/sowbalas/HIBIBI2023.git.

References

  • APA (2013) Diagnostic and statistical manual of mental disorders: DSM-V. The American Psychiatric Association

  • Abbas H, Garberson F, Liu-Mayo S, Glover E, Wall DP (2020) Multi-modular AI approach to streamline autism diagnosis in young children. Sci Rep 10(1):1–8

    Article  Google Scholar 

  • Abrate C, Bonchi F (2021) Counterfactual graphs for explainable classification of brain networks. In: KDD, pp 2495–2504

  • Adriana Di Martino SM (2016) ABIDE. http://fcon 1000.projects.nitrc.org/indi/abide/abideI.html

  • Agarwal S, Raj A, Chowdhury A, Aich G, Chatterjee R, Ghosh K (2024) Investigating the impact of standard brain atlases and connectivity measures on the accuracy of ADHD detection from FMRI data using deep learning. Multimed Tools Appl, 1–35

  • Arbabshirani MR, Plis S, Sui J, Calhoun VD (2017) Single subject prediction of brain disorders in neuroimaging: promises and pitfalls. NeuroImage 145:137–165

    Article  Google Scholar 

  • Asan O, Bayrak AE, Choudhury A (2020) Artificial intelligence and human trust in healthcare: focus on clinicians. J Med Internet Res 22(6):15154

    Article  Google Scholar 

  • Bullmore E, Sporns O (2009) Complex brain networks: graph theoretical analysis of structural and functional systems. Nat Rev Neurosci 10(3):186–198

    Article  Google Scholar 

  • Cadena J, Vullikanti AK, Aggarwal CC (2016) On dense subgraphs in signed network streams. In: ICDM, pp 51–60. https://doi.org/10.1109/ICDM.2016.0016

  • CDC (2024) https://www.cdc.gov/ncbddd/autism/data.html

  • Consortium TA- (2012) The ADHD-200 Sample. Accessed: 2024-05-21. https://fcon 1000.projects.nitrc.org/indi/adhd200/

  • Coupette C, Dalleiger S, Vreeken J (2022) Differentially describing groups of graphs. In: Proceedings of AAAI conference on artificial intelligence, vol 36, no 4, pp 3959–3967

  • De Silva S, Dayarathna SU, Ariyarathne G, Meedeniya D, Jayarathna S (2021) FMRI feature extraction model for ADHD classification using convolutional neural network. Int J E-Health Med Commun (IJEHMC) 12(1):81–105

    Article  Google Scholar 

  • Elkan C (2012) Evaluating classifiers. UC San Diego

  • Enns K, Srinivasan V, Thomo A (2023) Identifying autism spectrum disorder using brain networks: challenges and insights. In: IISA, pp 1–8

  • Enticott PG, Kennedy HA, Rinehart NJ, Tonge BJ, Bradshaw JL, Taffe JR, Daskalakis ZJ, Fitzgerald PB (2012) Mirror neuron activity associated with social impairments but not age in autism spectrum disorder. Biol Psychiatry 71(5):427–433

    Article  Google Scholar 

  • Fischbach G (2007) Leo Kanner’s 1943 paper on autism. https://www.spectrumnews.org/opinion/viewpoint/leo-kanners-1943-paper-on-autism/

  • Gulhan PG, Ozmen G (2024) The use of FMRI regional analysis to automatically detect ADHD through a 3D CNN-based approach. J Imaging Informat Med. https://doi.org/10.1007/s10278-024-01189-5

    Article  Google Scholar 

  • Gutiérrez-Gómez L, Delvenne J-C (2019) Unsupervised network embeddings with node identity awareness. Appl Netw Sci 4(1):1–21

    Article  Google Scholar 

  • Hassan A, Sulaiman R, Abdulgabber M, Kahtan H (2021) Towards user-centric explanations for explainable models: a review. J Inf Syst Technol Manage 6:36–50. https://doi.org/10.35631/JISTM.622004

    Article  Google Scholar 

  • Hernandez LM, Rudie JD, Green SA, Bookheimer S, Dapretto M (2015) Neural signatures of autism spectrum disorders: insights into brain network dynamics. Neuropsychopharmacology 40(1):171–189

    Article  Google Scholar 

  • Hyman SL, Levy SE, Myers SM, Kuo DZ, Apkon S, Davidson LF, Ellerbeck KA, Foster JE, Noritz GH, Leppert MO, et al (2020) Identification, evaluation, and management of children with autism spectrum disorder. Pediatrics 145(1)

  • Jurman G, Visintainer R, Filosi M, Riccadonna S, Furlanello C (2015) The HIM glocal metric and kernel for network comparison and classification. In: DSAA, pp 1–10

  • Kautzky A, Vanicek T, Philippe C, Kranz G, Wadsak W, Mitterhauser M, Hartmann A, Hahn A, Hacker M, Rujescu D (2020) Machine learning classification of ADHD and HC by multimodal serotonergic data. Transl Psychiatry 10(1):104

    Article  Google Scholar 

  • Khaouid W, Barsky M, Srinivasan V, Thomo A (2015) K-core decomposition of large networks on a single pc. PVLDB 9(1):13–23

    Google Scholar 

  • Khodatars M, Shoeibi A, Sadeghi D, Ghaasemi N, Jafari M, Moridian P, Khadem A, Alizadehsani R, Zare A, Kong Y, Khosravi A, Nahavandi S, Hussain S, Acharya UR, Berk M (2021) Deep learning for neuroimaging-based diagnosis and rehabilitation of autism spectrum disorder: a review. Comput Biol Med 139:104949–104949

    Article  Google Scholar 

  • Kong Y, Gao J, Xu Y, Pan Y, Wang J, Liu J (2019) Classification of autism spectrum disorder by combining brain connectivity and deep neural network classifier. Neurocomputing 324:63–68

    Article  Google Scholar 

  • Lanciano T, Bonchi F, Gionis A (2020) Explainable classification of brain networks via contrast subgraphs. In: KDD, pp 3308–3318

  • Lauritsen MB (2013) Autism spectrum disorders. Eur Child Adolesc Psychiatry 22:37–42

    Article  Google Scholar 

  • Linardatos P, Papastefanopoulos V, Kotsiantis S (2021) Explainable AI: a review of machine learning interpretability methods. Entropy 23(1):18

    Article  Google Scholar 

  • Liu Y, Xu L, Li J, Yu J, Yu X (2020) Attentional connectivity-based prediction of autism using heterogeneous RS-FMRI data from cc200 atlas. Exp Neurobiol 29(1):27–37

    Article  Google Scholar 

  • Loh HW, Ooi CP, Barua PD, Palmer EE, Molinari F, Acharya UR (2022) Automated detection of ADHD: Current trends and future perspective. Comput Biol Med 146:105525

    Article  Google Scholar 

  • Maximo JO, Cadena EJ, Kana RK (2014) The implications of brain connectivity in the neuropsychology of autism. Neuropsychol Rev 24(1):16–31

    Article  Google Scholar 

  • Miao B, Zhang L, Guan J, Meng Q, Zhang Y (2019) Classification of ADHD individuals and neurotypicals using reliable relief: a resting-state study. IEEE Access 7:62163–62171

    Article  Google Scholar 

  • Misman MF, Samah AA, Ezudin FA, Majid HA, Shah ZA, Hashim H, Harun M (2019) Classification of adults with autism spectrum disorder using deep neural network. In: AiDAS, pp 29–34

  • Mukherjee SB (2017) Autism spectrum disorders-diagnosis and management. Indian J Pediatr 84:307–314

    Article  Google Scholar 

  • Nikolentzos G, Meladianos P, Limnios S, Vazirgiannis M (2018) A degeneracy framework for graph similarity. In: IJCAI, pp 2595–2601

  • Nogay HS, Adeli H (2020) Machine learning (ML) for the diagnosis of autism spectrum disorder (ASD) using brain imaging. Rev Neurosci 31(8):825–841

    Article  Google Scholar 

  • Nunez-Garcia M, Simpraga S, Jurado MA, Garolera M, Pueyo R, Igual L (2015) FADR: functional-anatomical discriminative regions for rest fmri characterization. In: MLMI, pp 61–68

  • Perotti A, Bajardi P, Bonchi F, Panisson A (2022) Graphshap: Motif-based explanations for black-box graph classifiers. preprint arXiv:2202.08815

  • Preprocessed Connectomes Project: ABIDE Preprocessed DPARSF. Accessed: 2024-06-01 (2024). http://preprocessed-connectomes-project.org/abide/dparsf.html

  • Pržulj N (2007) Biological network comparison using graphlet degree distribution. Bioinformatics 23(2):177–183

    Article  Google Scholar 

  • Riaz A, Asad M, Alonso E, Slabaugh G (2018) Fusion of FMRI and non-imaging data for ADHD classification. Comput Med Imaging Graph 65:115–128

    Article  Google Scholar 

  • Riaz A, Asad M, Alonso E, Slabaugh G (2020) Deepfmri: end-to-end deep learning for functional connectivity and classification of ADHD using FMRI. J Neurosci Methods 335:108506

    Article  Google Scholar 

  • Rocco I, Corso B, Bonati M, Minicuci N (2021) Time of onset and/or diagnosis of ADHD in European children: a systematic review. BMC Psychiatry 21(1):1–24

    Article  Google Scholar 

  • Salah E, Shokair M, El-Samie FEA, Shalaby WA (2024) Utilization of fmri with optical amplification to diagnose attention deficit hyperactivity disorder. J Opt. https://doi.org/10.1007/s12596-023-01485-3

    Article  Google Scholar 

  • Santana CP, Carvalho EA, Rodrigues ID, Bastos GS, Souza AD, Brito LL (2022) RS-FMRI and machine learning for ASD diagnosis: a systematic review and meta-analysis. Sci Rep 12(1):6030–6030

    Article  Google Scholar 

  • Shervashidze P. Nino, f Schweitzer Van Leeuwen EJ, Mehlhorn K, Borgwardt KM (2011) Weisfeiler-lehman graph kernels. J Mach Learn Res 12(9)

  • Subah FZ, Deb K, Dhar PK, Koshiba T (2021) A deep learning approach to predict autism spectrum disorder using multisite resting-state FMRI. Appl Sci 11(8):3636

    Article  Google Scholar 

  • Tang Y, Wang C, Chen Y, Sun N, Jiang A, Wang Z (2021) Identifying ADHD individuals from resting-state functional connectivity using subspace clustering and binary hypothesis testing. J Atten Disord 25(5):736–748

    Article  Google Scholar 

  • Thapar A, Cooper M, Eyre O, Langley K (2013) Practitioner review: what have we learnt about the causes of ADHD? J Child Psychol Psychiatry 54(1):3–16

    Article  Google Scholar 

  • Thapar A, Cooper M, Jefferies R, Stergiakouli E (2012) What causes attention deficit hyperactivity disorder? Arch Dis Child 97(3):260–265

    Article  Google Scholar 

  • Thomas RM, Gallo S, Cerliani L, Zhutovsky P, El-Gazzar A, Wingen G (2020) Classifying autism spectrum disorder using the temporal statistics of resting-state functional MRI data with 3d convolutional neural networks. Front Psychiatry 11:440

    Article  Google Scholar 

  • Tonekaboni S, Joshi S, McCradden MD, Goldenberg A (2019) What clinicians want: contextualizing explainable machine learning for clinical end use. In: Machine learning for healthcare conference, pp 359–380

  • Torre-Ubieta L, Won H, Stein JL, Geschwind DH (2016) Advancing the understanding of autism disease mechanisms through genetics. Nat Med 22(4):345–361

    Article  Google Scholar 

  • Tsourakakis C, Bonchi F, Gionis A, Gullo F, Tsiarli M (2013) Denser than the densest subgraph: extracting optimal quasi-cliques with quality guarantees. In: KDD, pp 104–112. https://doi.org/10.1145/2487575.2487645

  • Wang L, Dai Z, Peng H, Tan L, Ding Y, He Z, Zhang Y, Xia M, Li Z, Li W (2014) Overlapping and segregated resting-state functional connectivity in patients with major depressive disorder with and without childhood neglect. Hum Brain Mapp 35(4):1154–1166

    Article  Google Scholar 

  • Woo C-W, Chang LJ, Lindquist MA, Wager TD (2017) Building better biomarkers: brain models in translational neuroimaging. Nat Neurosci 20(3):365–377

    Article  Google Scholar 

  • Xia M, Wang J, He Y (2013) Brainnet viewer: a network visualization tool for human brain connectomics. PLoS ONE 8(7):68910

    Article  Google Scholar 

  • Yan C, Zang Y (2010) DPARSF: a MATLAB toolbox for pipeline data analysis of resting-state FMRI. Front Syst Neurosci 4:1377

    Google Scholar 

  • Yang G, Ye Q, Xia J (2022) Unbox the black-box for the medical explainable AI via multi-modal and multi-centre data fusion: a mini-review, two showcases and beyond. Inf Fus 77:29–52. https://doi.org/10.1016/j.inffus.2021.07.016

    Article  Google Scholar 

  • Zhao Y, Chen H, Ogden RT (2015) Wavelet-based weighted lasso and screening approaches in functional linear regression. J Comput Graph Stat 24(3):655–675

    Article  MathSciNet  Google Scholar 

Download references

Acknowledgements

We would like to thank Bryan Maruyama for many interesting discussions on brain network classification and for his help with experimental results for the ADHD dataset.

Author information

Author notes

  1. Keanelek Enns, Kazi Tabassum Ferdous, Sowmya Balasubramanian, Smita Ghosh, Venkatesh Srinivasan and Alex Thomo have contributed equally to this work.

Authors and Affiliations

  1. Department of Computer Science, University of Victoria, Victoria, BC, Canada

    Keanelek Enns, Kazi Tabassum Ferdous, Sowmya Balasubramanian & Alex Thomo

  2. Department of Mathematics and Computer Science, Santa Clara University, Santa Clara, CA, USA

    Smita Ghosh & Venkatesh Srinivasan

Authors
  1. Keanelek Enns
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Kazi Tabassum Ferdous
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Sowmya Balasubramanian
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Smita Ghosh
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Venkatesh Srinivasan
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Alex Thomo
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Venkatesh Srinivasan.

Additional information

A preliminary version of this work appeared in the Proceedings of the International Symposium on Network Enabled Health Informatics, Biomedicine and Bioinformatics HI-BI-BI 2023. This extended version introduces the DE method for brain network classification (RQ1). It also shows how to improve the performance of the original CS method (RQ2).

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Enns, K., Ferdous, K.T., Balasubramanian, S. et al. Are brain networks classifiable?. Netw Model Anal Health Inform Bioinforma 13, 44 (2024). https://doi.org/10.1007/s13721-024-00482-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s13721-024-00482-1

Keywords