A Survey on Resting State Functional Connectivity Analysis for Autism Spectrum Disorder Detection
Keywords:
Autoencoder, Autism Brain Imaging Data Exchange (ABIDE), Autism Spectrum Disorder (ASD), Convolutional neural networks, Deep learning, Graph neural networks, Multi-layer perceptron, Random forest, Support vector machinesAbstract
The term Autism Spectrum Disorder (ASD) describes a collection of neurodevelopmental diseases including Autism, Attention Deficit Hyperactivity Disorder (ADHD), Asperger’s syndrome, etc. Despite extensive research, ASD diagnosis remains a largely subjective assessment where clinicians assess behaviours, communication skills, and social interactions. Although standardized tools exist, there is no single biological marker that exists to confirm the diagnosis definitively. In recent years, Resting State functional MRI (rs-fMRI) data has shown promising results in ASD diagnosis, and has been extensively used in the detection of ASD. Resting state fMRI data captures connectivity patterns in the brain and can, therefore, be used to capture differences in brain connectivity between ASD and Typical controls. This method is also popular due to its non-invasive nature. The ABIDE dataset, containing rs-fMRI data of a varied demography, has been used extensively in research for the task of ASD diagnosis. In this paper, we present the various methodologies - Support Vector Machines (SVM), Random Forest (RF), Multi-Layer Perceptron (MLP), Autoencoder, Convolutional Neural Networks (CNN) and Graph Neural Networks (GNN), that has been used in ASD diagnosis. We further highlight the research gaps, limitations and challenges that are present in the current methodologies, therefore emphasizing the need for more robust and standardized approaches to enhance diagnostic accuracy and improve intervention strategies.
References
I. Rapin and R. F. Tuchman, "Autism: Definition, neurobiology, screening, diagnosis," Pediatric Clinics of North America, vol. 55, no. 5, pp. 1129–1146, Oct. 2008, doi: https://doi.org/10.1016/j.pcl.2008.07.005
V. L. Cherkassky, R. K. Kana, T. A. Keller, and M. A. Just, "Functional connectivity in a baseline resting-state network in autism," Neuroreport, vol. 17, no. 16, pp. 1687–1690, Nov. 6, 2006, doi: https://doi.org/10.1097/01.wnr.0000239956.45448.4c
C. Cameron, B. Yassine, C. Carlton, C. Francois, “The Neuro Bureau Preprocessing Initiative: open sharing of preprocessed neuroimaging data and derivatives,” Frontiers in Neuroinformatics, vol. 7, 2013, doi: https://doi.org/10.3389/conf.fninf.2013.09.00041.
L. Zhao, Y. K. Sun, S. W. Xue, H. Luo, X. D. Lu, and L. H. Zhang, "Identifying boys with autism spectrum disorder based on whole-brain resting-state interregional functional connections using a Boruta-based support vector machine approach," Frontiers in Neuroinformatics, vol. 16, p. 761942, Feb. 2022. doi: https://doi.org/10.3389/fninf.2022.761942
A. Brahim and N. Farrugia, "Graph Fourier transform of fMRI temporal signals based on an averaged structural connectome for the classification of neuroimaging," Artificial Intelligence in Medicine, vol. 106, p. 101870, Jun. 2020. doi: https://doi.org/10.1016/j.artmed.2020.101870
M. A. Reiter, A. Jahedi, A. J. Fredo, I. Fishman, B. Bailey, and R. A. Müller, "Performance of machine learning classification models of autism using resting-state fMRI is contingent on sample heterogeneity," Neural computing and applications, vol. 33, pp. 3299–3310, Apr. 2021, doi: https://doi.org/10.1007/s00521-020-05193-y
M. Ingalhalikar, S. Shinde, A. Karmarkar, A. Rajan, D. Rangaprakash, and G. Deshpande, "Functional connectivity-based prediction of autism on site harmonized ABIDE dataset," IEEE Transactions on Biomedical Engineering, vol. 68, no. 12, pp. 3628–3637, Dec. 2021, doi: https://doi.org/10.1109/tbme.2021.3080259
H. Sharif and R. A. Khan, "A novel machine learning based framework for detection of autism spectrum disorder (ASD)," Applied Artificial Intelligence, vol. 36, no. 1, Art. no. 2004655, Dec. 2022, doi: https://doi.org/10.1080/08839514.2021.2004655
B. S. Kumar and D. Jayaraj, "Zealous particle swarm optimization-based reliable multi-layer perceptron neural networks for autism spectrum disorder classification," Journal of Theoretical and Applied Information Technology, vol. 101, no. 1, pp. 202–209, Jan. 2023. Available: https://www.jatit.org/volumes/Vol101No1/26Vol101No1.pdf
Z. Sherkatghanad, M. Akhondzadeh, S. Salari, M. Zomorodi-Moghadam, M. Abdar, U. R. Acharya, R. Khosrowabadi, and V. Salari, "Automated detection of autism spectrum disorder using a convolutional neural network," Frontiers in Neuroscience, vol. 13, p. 1325, Jan. 2020, doi: https://doi.org/10.3389/fnins.2019.01325
L. Qiu and J. Zhai, "A hybrid CNN-SVM model for enhanced autism diagnosis," PLOS One, vol. 19, no. 5, p. e0302236, May 2024, doi: https://doi.org/10.1371/journal.pone.0302236
S. Gupta, M. R. Bhuiyan, S. S. Chowa, S. Montaha, R. Rahman, S. T. Mehedi, and Z. Rahman, "Enhancing autism spectrum disorder classification with lightweight quantized CNNs and federated learning on ABIDE-1 dataset," Mathematics, vol. 12, no. 18, p. 2886, Sep. 2024, doi: https://doi.org/10.3390/math12182886
Y. Wang, J. Liu, Y. Xiang, J. Wang, Q. Chen, and J. Chong, "MAGE: Automatic diagnosis of autism spectrum disorders using multi-atlas graph convolutional networks and ensemble learning," Neurocomputing, vol. 469, pp. 346–353, Jan. 2022, doi: https://doi.org/10.1016/j.neucom.2020.06.152
S. Liu, S. Wang, C. Sun, B. Li, S. Wang, and F. Li, "DeepGCN based on variable multi‐graph and multimodal data for ASD diagnosis," CAAI Transactions on Intelligence Technology, vol. 9, no. 4, pp. 879–893, Aug. 2024, doi: https://doi.org/10.1049/cit2.12340
C. Wang, Z. Xiao, Y. Xu, Q. Zhang, and J. Chen, "A novel approach for ASD recognition based on graph attention networks," Frontiers in Computational Neuroscience, vol. 18, Apr. 10, 2024, Art. no. 1388083, doi: https://doi.org/10.3389/fncom.2024.1388083
S. Liu, B. Liang, S. Wang, B. Li, L. Pan, and S.-H. Wang, "NF-GAT: A node feature-based graph attention network for ASD classification," in IEEE Open Journal of Engineering in Medicine and Biology, vol. 5, pp. 428–433, 2024, doi: https://doi.org/10.1109/ojemb.2023.3267612
