Abstract
In the recent neuroscience and clinical research, neuroscientists and clinicians often utilize non-invasive imaging tools to diagnose brain diseases and observe brain activity. Functional magnetic resonance imaging (fMRI) is widely utilized for the categorization and automatic detection of brain diseases, human brain processes for brain disorder diagnosis, and therapy. Advances in the deep learning and artificial intelligence field have leveraged promising results for the better interpretation of fMRI data. The deep learning model provides an end-to-end solution by employing the automated feature extraction without any need for domain-specific knowledge, which is required for performing feature extraction in standard machine learning models. Deep learning models would be used to analyze and classify images, time series, or image sequences from the fMRI dataset. In this paper, the proposed hybrid (1D-CNN + LSTM) deep learning model has used temporal time series signal, which is extracted from 3D voxels at each time-point based on the efficient dictionaries of functional modes (DiFuMo) atlas with 64 bases function for the classification of control and autism spectrum disorder (ASD). The ABIDE-1 is a publicly available ASD fMRI dataset used in this study. The different eight pre-defined standard atlases including the DiFuMo atlas which has been used for extraction of the region of convergence (ROC) time series signals related to functional and anatomical information from raw fMRI multi-sites ABIDE-1 dataset. The proposed deep learning-based solution has produced an efficient performance when compared to state-of-the-art deep learning models. The code1 and preprocessed dataset functions are publicly available for the further improvements in results and contribution in fMRI ASD classification task. Code https://github.com/RespectKnowledge/ABIDE_Classification_DLModel.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Change history
01 January 2022
Correction to: Chapter “An Efficient 1DCNN–LSTM Deep Learning Model for Assessment and Classification of fMRI-Based Autism Spectrum Disorder” in: J. S. Raj et al. (eds.), Innovative Data Communication Technologies and Application, Lecture Notes on Data Engineering and Communications Technologies 96, https://doi.org/10.1007/978-981-16-7167-8_77
References
M.P. van den Heuvel, H.E. Hulshoff Pol, Exploring the brain network: a review on resting-state fMRI functional connectivity. Eur. Neuropsychopharmacol. 20(8), 519–534 (2010). https://doi.org/10.1016/j.euroneuro.2010.03.008
A. Riaz, M. Asad, E. Alonso, G. Slabaugh, Fusion of fMRI and non-imaging data for ADHD classification. Comput. Med. Imaging Graph. 65, 115–128 (2018). https://doi.org/10.1016/j.compmedimag.2017.10.002
K. Rajpoot, A. Riaz, W. Majeed, N. Rajpoot, Functional connectivity alterations in epilepsy from resting-state functional MRI. PLoS ONE 10(8), e0134944 (2015). https://doi.org/10.1371/journal.pone.0134944
A. Qayyum, I. Ahmad, W. Mumtaz, M.O. Alassafi, R. Alghamdi, M. Mazher, Automatic segmentation using a hybrid dense network integrated with an 3D-atrous spatial pyramid pooling module for computed tomography (CT) imaging. IEEE Access 8, 169794–169803 (2020). https://doi.org/10.1109/ACCESS.2020.3024277
A. Qayyum, I. Razzak, W. Mumtaz, Hybrid Deep Shallow Network for Assessment of Depression Using Electroencephalogram Signals (2020), pp. 245–257
J. Donahue et al., Long-term recurrent convolutional networks for visual recognition and description, in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015, pp. 2625–2634. https://doi.org/10.1109/CVPR.2015.7298878
U. Güçlü, M.A.J. van Gerven, Modeling the dynamics of human brain activity with recurrent neural networks. Front. Comput. Neurosci. (2017). https://doi.org/10.3389/fncom.2017.00007
L. Wang, K. Li, X. Chen, X.P. Hu, Application of convolutional recurrent neural network for individual recognition based on resting state fMRI data. Front. Neurosci. 13 (2019). https://doi.org/10.3389/fnins.2019.00434
X. Li, Y. Gu, N. Dvornek, L.H. Staib, P. Ventola, J.S. Duncan, Multi-site fMRI analysis using privacy-preserving federated learning and domain adaptation: ABIDE results. Med. Image Anal. 65, 101765 (2020). https://doi.org/10.1016/j.media.2020.101765
A. El-Gazzar, M. Quaak, L. Cerliani, P. Bloem, G. van Wingen, R. Mani Thomas, A Hybrid 3DCNN and 3DC-LSTM Based Model for 4D Spatio-Temporal fMRI Data: An ABIDE Autism Classification Study (2019), pp. 95–102
X. Yang, M.S. Islam, A.M.A. Khaled, Functional connectivity magnetic resonance imaging classification of autism spectrum disorder using the multisite ABIDE dataset, in 2019 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), May 2019, pp. 1–4. https://doi.org/10.1109/BHI.2019.8834653
A. Riaz et al., Deep fMRI: an end-to-end deep network for classification of fMRI data, in 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Apr 2018, pp. 1419–1422. https://doi.org/10.1109/ISBI.2018.8363838
A. El Gazzar, L. Cerliani, G. van Wingen, R.M. Thomas, Simple 1-D convolutional networks for resting-state fMRI based classification in Autism, in 2019 International Joint Conference on Neural Networks (IJCNN), July 2019, pp. 1–6. https://doi.org/10.1109/IJCNN.2019.8852002
J. Dakka, P. Bashivan, M. Gheiratmand, I. Rish, S. Jha, R. Greiner, Learning neural markers of schizophrenia disorder using recurrent neural networks, Dec 2017 (Online). Available: http://arxiv.org/abs/1712.00512
M. Bengs, N. Gessert, A. Schlaefer, 4D Spatio-Temporal Deep Learning with 4D fMRI Data for Autism Spectrum Disorder Classification (2019)
W. Yan et al., Discriminating schizophrenia using recurrent neural network applied on time courses of multi-site FMRI data. EBioMedicine 47, 543–552 (2019). https://doi.org/10.1016/j.ebiom.2019.08.023
W. Li, X. Lin, X. Chen, Detecting Alzheimer’s disease based on 4D fMRI: an exploration under deep learning framework. Neurocomputing 388, 280–287 (2020). https://doi.org/10.1016/j.neucom.2020.01.053
R.S. Desikan et al., An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest. Neuroimage 31(3), 968–980 (2006). https://doi.org/10.1016/j.neuroimage.2006.01.021
P. Bellec, P. Rosa-Neto, O.C. Lyttelton, H. Benali, A.C. Evans, Multi-level bootstrap analysis of stable clusters in resting-state fMRI. Neuroimage 51(3), 1126–1139 (2010). https://doi.org/10.1016/j.neuroimage.2010.02.082
K. Dadi et al., Fine-grain atlases of functional modes for fMRI analysis. Neuroimage 221, 117126 (2020). https://doi.org/10.1016/j.neuroimage.2020.117126
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Qayyum, A. et al. (2022). An Efficient 1DCNN–LSTM Deep Learning Model for Assessment and Classification of fMRI-Based Autism Spectrum Disorder. In: Raj, J.S., Kamel, K., Lafata, P. (eds) Innovative Data Communication Technologies and Application. Lecture Notes on Data Engineering and Communications Technologies, vol 96. Springer, Singapore. https://doi.org/10.1007/978-981-16-7167-8_77
Download citation
DOI: https://doi.org/10.1007/978-981-16-7167-8_77
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7166-1
Online ISBN: 978-981-16-7167-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)