Abstract
Autism spectrum disorder (ASD) is a complex, severe disorder related to brain development. It impairs patient language communication and social behaviors. In recent years, ASD researches have focused on a single-modal neuroimaging data, neglecting the complementarity between multi-modal data. This omission may lead to poor classification. Therefore, it is important to study multi-modal data of ASD for revealing its pathogenesis. Furthermore, recurrent neural network (RNN) and gated recurrent unit (GRU) are effective for sequence data processing. In this paper, we introduce a novel framework for a Multi-Kernel Learning Fusion algorithm based on RNN and GRU (MKLF-RAG). The framework utilizes RNN and GRU to provide feature selection for data of different modalities. Then these features are fused by MKLF algorithm to detect the pathological mechanisms of ASD and extract the most relevant the Regions of Interest (ROIs) for the disease. The MKLF-RAG proposed in this paper has been tested in a variety of experiments with the Autism Brain Imaging Data Exchange (ABIDE) database. Experimental findings indicate that our framework notably enhances the classification accuracy for ASD. Compared with other methods, MKLF-RAG demonstrates superior efficacy across multiple evaluation metrics and could provide valuable insights into the early diagnosis of ASD.
Graphical abstract
Similar content being viewed by others
Code Availability
https://github.com/1998cj/MKLF-RAG.
Data Availability
This study was carried out in accordance with the recommendations of Health Insurance Portability and Accountability Act (HIPAA) guidelines and 1000 Functional Connectomes Project /INDI protocols. All datasets are anonymous, with no protected health information included.
References
Parisot S, Ktena SI, Ferrante E et al (2018) Disease prediction using graph convolutional networks: application to autism spectrum disorder and Alzheimer’s disease. Med Image Anal 48:117–130. https://doi.org/10.1016/j.media.2018.06.001
Sen B, Borle NC, Greiner R et al (2018) A general prediction model for the detection of ADHD and Autism using structural and functional MRI. PLoS ONE 13:e0194856. https://doi.org/10.1371/journal.pone.0194856
Wang M, Huang J, Liu M et al (2021) Modeling dynamic characteristics of brain functional connectivity networks using resting-state functional MRI. Med Image Anal 71:102063. https://doi.org/10.1016/j.media.2021.102063
Wee CY, Yap PT, Zhang D et al (2012) Identification of MCI individuals using structural and functional connectivity networks. Neuroimage 59:2045–2056. https://doi.org/10.1016/j.neuroimage.2011.10.015
Gao S, Calhoun VD, Sui J (2020) Multi-modal component subspace-similarity-based multi-kernel SVM for schizophrenia classification. MICAD 11314:925–934. https://doi.org/10.1117/12.2550339
Pominova M, Artemov A, Sharaev M et al (2018) Voxelwise 3d convolutional and recurrent neural networks for epilepsy and depression diagnostics from structural and functional MRI data. ICDMW. https://doi.org/10.1109/ICDMW.2018.00050
Wang J, Wang Q, Peng J et al (2017) Multi-task diagnosis for autism spectrum disorders using multi-modality features: a multi-center study. Hum Brain Mapp 38:3081–3097. https://doi.org/10.1002/hbm.23575
Hao X, Li J, Guo Y et al (2021) Hypergraph neural network for skeleton-based action recognition. IEEE Trans Image Process 30:263–2275. https://doi.org/10.1109/TIP.2021.3051495
Peng L, He X, Zhang L et al (2022) A deep learning-based unsupervised learning method for spatially resolved transcriptomic data analysist. IEEE Int Conf Bioinform Biomed. https://doi.org/10.1109/BIBM55620.2022.9995207
B W Y A, C V C, B M S A et al (2019) Discriminating schizophrenia using recurrent neural network applied on time courses of multi-site FMRI data. EBioMedicine. https://doi.org/10.1016/j.ebiom.2019.08.023
Dvornek NC, Ventola P, Pelphrey KA et al (2017) Identifying autism from resting-state fMRI using long short-term memory networks. Mach Learn Med Imaging. https://doi.org/10.1007/978-3-319-67389-9_42
Yu C, Zhang S, Shang M et al (2023) A multi-task deep feature selection method for brain imaging genetics. IEEE/ACM Trans Comput Biol Bioinform. https://doi.org/10.1109/TCBB.2023.3294413
Brownlee J (2019) The promise of recurrent neural networks for time series forecasting. Machine Learning Mastery. https://machinelearningmastery.com/promise-recurrent-neural-n
Lee G, Nho K, Kang B et al (2019) Predicting Alzheimer’s disease progression using multi-modal deep learning approach. Sci Rep 9:1952. https://doi.org/10.1038/s41598-018-37769-z
Zhang L, Wu J, Wang L et al (2023) Brain anatomy prior modeling to forecast clinical progression of cognitive impairment with structural MRI. arXiv. https://doi.org/10.48550/arXiv.2306.11837
Hao X, Yao X, Risacher SL et al (2018) Identifying candidate genetic associations with MRI-derived AD-related ROI via tree-guided sparse learning. IEEE/ACM Trans Comput Biol Bioinform 16:1986–1996. https://doi.org/10.1109/TCBB.2018.2833487
Tzourio-Mazoyer N, Landeau B, Papathanassiou D et al (2002) Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain. Neuroimage 15:273–289. https://doi.org/10.1006/nimg.2001.0978
Teuho J, Linden J, Johansson J et al (2016) Tissue probability-based attenuation correction for brain PET/MR by using SPM8. IEEE Trans Nucl Sci 63:2452–2463. https://doi.org/10.1109/TNS.2015.2513064
Zhou X, Wu R, Zeng Y et al (2022) Choice of voxel-based morphometry processing pipeline drives variability in the location of neuroanatomical brain markers. Commun Biolog 5:913. https://doi.org/10.1038/s42003-022-03880-1
Cui H, Sun Y, Zhao D et al (2023) Radiogenomic analysis of prediction HER2 status in breast cancer by linking ultrasound radiomic feature module with biological functions. J Transl Med 21:1–15. https://doi.org/10.1186/s12967-022-03840-7
Zhang J, Shang M, e Q et al (2022) A sparse multi-task contrastive and discriminative learning method with feature selection for brain imaging genetics. In: IEEE Int Conf Bioinformatics Biome, pp 660–665. https://doi.org/10.1109/BIBM55620.2022.9995050
Huang J, Zhu Q, Hao X et al (2018) Identifying resting-state multifrequency biomarkers via tree-guided group sparse learning for schizophrenia classification. IEEE J Biomed Health Inform 23:342–350. https://doi.org/10.1109/JBHI.2018.2796588
Logothetis NK (2008) What we can do and what we cannot do with fMRI. Nature 453:869–878. https://doi.org/10.1038/nature06976
Li ZW, Wang QK, Yuan CA et al (2022) Predicting MiRNA-disease associations by graph representation learning based on jumping knowledge networks. IEEE/ACM Trans Comput Biol Bioinform. https://doi.org/10.1109/TCBB.2022.3196394
Chen L, Wu Z, Zhao F et al (2023) An attention-based context-informed deep framework for infant brain subcortical segmentation. Neuroimage 269:119931. https://doi.org/10.1016/j.neuroimage.2023.119931
Wei Q, Wang R, Jiang Y et al (2023) ConPep: prediction of peptide contact maps with pre-trained biological language model and multi-view feature extracting strategy. Comput Biol Med 167:107631. https://doi.org/10.1016/j.compbiomed.2023.107631
Wang L, Wong L, You ZH et al (2022) NSECDA: natural semantic enhancement for circRNA-disease association prediction. IEEE J Biomed Health Inform 26:5075–5084. https://doi.org/10.1019/JBHI.2022.3199462
Huang L, Zhang L, Chen X (2022) Updated review of advances in microRNAs and complex diseases: experimental results, databases, webservers and data fusion. Brief Bioinform 23:bbac397. https://doi.org/10.1093/bib/bbac397
Chu Y, Wang X, Dai Q et al (2021) MDA-GCNFTG: identifying miRNA-disease associations based on graph convolutional networks via graph sampling through the feature and topology graph. Brief Bioinform 22:bbab165. https://doi.org/10.1093/bib/bbab165
Li GP, Du PF, Shen ZA et al (2020) DPPN-SVM: computational identification of mis-localized proteins in cancers by integrating differential gene expressions with dynamic protein-protein interaction networks. Front Genet 11:600454. https://doi.org/10.3389/fgene.2020.600454
Wang W, Dai QY, Li F et al (2021) MLCDForest: multi-label classification with deep forest in disease prediction for long non-coding RNAs. Brief Bioinform 22:bbaa104. https://doi.org/10.1093/bib/bbaa104
Liu J, Su R, Zhang J et al (2021) Classification and gene selection of triple-negative breast cancer subtype embedding gene connectivity matrix in deep neural network. Brief Bioinform 22:bbaa395. https://doi.org/10.1093/bib/bbaa395
Liu K, Cao L, Du P et al (2020) im6A-TS-CNN: identifying the N6-methyladenine site in multiple tissues by using the convolutional neural network. Mol Ther Nucleic Acids 21:1044–1049. https://doi.org/10.1016/j.omtn.2020.07.034
Li Y, Hu XG, Li PP et al (2022) Predicting circRNA-disease associations using similarity assessing graph convolution from multi-source information networks. In: IEEE Int Conf Bioinformatics Biomed, pp 94–101. https://doi.org/10.1109/BIBM55620.2022.9995674
Zhang X, Hao Y, Zhang J et al (2021) Improved multi-task SCCA for brain imaging genetics via joint consideration of the diagnosis, parameter decomposition and network constraints. In: IEEE Int Conf Bioinformatics Biomed, pp 1159–1164. https://doi.org/10.1109/BIBM52615.2021.9669899
Cerliani L, Mennes M, Thomas RM et al (2015) Increased functional connectivity between subcortical and cortical resting-state networks in autism spectrum disorder. JAMA Psychiat 72:767–777. https://doi.org/10.1001/jamapsychiatry.2015.0101
Urbain CM, Pang EW, Taylor MJ (2015) Atypical spatiotemporal signatures of working memory brain processes in autism. Transl Psychiatry 5:e617–e617. https://doi.org/10.1038/tp.2015.107
Mundy P (2003) Annotation: The neural basis of social impairments in autism: the role of the dorsal medial-frontal cortex and anterior cingulate system. J Child Psychol Psychiatry 44:793–809. https://doi.org/10.1111/1469-7610.00165
Wang Y, Xu Q, Zuo C et al (2020) Longitudinal changes of cerebellar thickness in autism spectrum disorder. Neurosci Lett 728:134949. https://doi.org/10.1016/j.neulet.2020.134949
Yu H, Shen ZA, Zhou YK et al (2022) Recent advances in predicting protein-lncRNA interactions using machine learning methods. Curr Gene Ther 22:228–244. https://doi.org/10.2174/1566523221666210712190718
Liang S, Zhao Y, Jin J et al (2023) Rm-LR: a long-range-based deep learning model for predicting multiple types of RNA modifications. Comput Biol Med 164:107238. https://doi.org/10.1016/j.compbiomed.2023.107238
Ahmed MR, Zhang Y, Liu Y et al (2020) Single volume image generator and deep learning-based ASD classification. IEEE J Biomed Health Inform 24:3044–3054. https://doi.org/10.1109/JBHI.2020.2998603
El-Gazzar A, Quaak M, Cerliani L et al (2019) A hybrid 3DCNN and 3DC-LSTM based model for 4D spatio-temporal fMRI data: an ABIDE autism classification study. In: International Workshop on OR 2.0 Context-Aware Operating Theaters, pp 95–102. https://doi.org/10.1007/978-3-030-32695-1_11
Li X, Gu Y, Dvornek N et al (2020) Multi-site fMRI analysis using privacy-preserving federated learning and domain adaptation: ABIDE results. Med Image Anal 65:101765. https://doi.org/10.1016/j.media.2020.101765
Shi C, Xin X, Zhang J (2021) Domain adaptation using a three-way decision improves the identification of autism patients from multisite fMRI data. Brain Sci 11:603. https://doi.org/10.3390/brainsci11050603
Acknowledgements
This work was supported by National Key R and D Program of China (No. 2020YFB2104400); National Nature Science Foundation of China (Grant Nos 62362027, 62362028, 62072173, and 62372169); and Natural Science Foundation of Hainan, China (Grant Nos 121RC538 and 120RC588); the Key Open Project of Key Laboratory of Data Science and Intelligence Education (Hainan Normal University), Ministry of Education (No. DSIE202101); Natural Science Foundation of Hunan Province, China (No. DSIE202101); the Innovation and Entrepreneurship Training Program of Hunan Xiangjiang Artificial Intelligence Academy; and the project grant from the College of Mathematics and Statistics, Hainan Normal University (styc202205, styc202206).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors declare that they have no competing interests.
Ethical Approval
This article does not contain any studies with human participants performed by any of authors.
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.
About this article
Cite this article
Chen, J., Zhang, H., Zou, Q. et al. Multi-kernel Learning Fusion Algorithm Based on RNN and GRU for ASD Diagnosis and Pathogenic Brain Region Extraction. Interdiscip Sci Comput Life Sci (2024). https://doi.org/10.1007/s12539-024-00629-8
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12539-024-00629-8