Research of Children Dyslexia Classification Recognition based on Graph Convolutional Neural Networks

Maoyun Wang

doi:10.62051/ijepes.v4n1.06

Authors

Maoyun Wang

DOI:

https://doi.org/10.62051/ijepes.v4n1.06

Keywords:

fMRI, Developmental Dyslexia, GCN, Feature Extraction

Abstract

Developmental dyslexia is a common neurodevelopmental disorder that significantly affects children' normal learning and life. Early identification and intervention are crucial for patients. However, current models for classifying dyslexia fail to automatically extract features based on patient data and overlook the interrelationships between brain nodes in patients. Therefore, this paper proposes a graph convolutional neural network model that constructs a brain network from patients' fMRI data as an adjacency matrix, calculates node feature matrices, trains GCN models for classification, and achieves the diagnosis of dyslexia patients. Experimental results show that the model has an identification accuracy of 94%, precision of 95%, recall of 94%, and F1 score of 94%. This study provides a new approach for identifying and diagnosing dyslexia, which is beneficial for early intervention in dyslexia patients.

References

[1] Peterson R L, Pennington B F J T L. Developmental dyslexia[J]. The lancet, 2012, 379(9830): 1997-2007.

[2] Li Kaiqian, Liang Dandan Brain abnormalities and early neural markers of developmental reading disorders in children at risk [J]. Advances in psychological science , 2023, 31(10): 1912.

[3] Stein J J B S. Theories about developmental dyslexia[J]. Brain sciences, 2023, 13(2): 208.

[4] Wilmot A, Hasking P, Leitão S, et al. Understanding mental health in developmental dyslexia: a scoping review[J]. International journal of environmental research and public health, 2023, 20(2): 1653.

[5] Zhang L, Xia Z, Zhao Y, et al. Recent advances in Chinese developmental dyslexia[J]. Annual Review of Linguistics, 2023, 9: 439-461.

[6] Appadurai J P, Bhargavi R J I J O C I, Intelligence N. Eye movement feature set and predictive model for dyslexia: Feature set and predictive model for dyslexia[J]. International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 2021, 15(4): 1-22.

[7] Ortiz A, Martinez-Murcia F J, Formoso M A, et al. Dyslexia detection from EEG signals using SSA component correlation and convolutional neural networks[C]//. International Conference on Hybrid Artificial Intelligence Systems, 2020: 655-664.

[8] Kohli M, Prasad T. Identifying dyslexic students by using artificial neural networks[C]//. Proceedings of the world congress on engineering, 2010: 1-4.

[9] Zahia S, Garcia-Zapirain B, Saralegui I, et al. Dyslexia detection using 3D convolutional neural networks and functional magnetic resonance imaging[J]. Computer methods and programs in biomedicine, 2020, 197: 105726.

[10] Cui Z, Xia Z, Su M, et al. Disrupted white matter connectivity underlying developmental dyslexia: a machine learning approach[J]. Human brain mapping, 2016, 37(4): 1443-1458.

[11] Płoński P, Gradkowski W, Altarelli I, et al. Multi‐parameter machine learning approach to the neuroanatomical basis of developmental dyslexia[J]. Human Brain Mapping, 2017, 38(2): 900-908.

[12] Alqahtani N D, Alzahrani B, Ramzan M S J a S. Deep learning applications for dyslexia prediction[J]. Applied Sciences, 2023, 13(5): 2804.

[13] Usman O L, Muniyandi R C. CryptoDL: Predicting Dyslexia Biomarkers from Encrypted Neuroimaging Dataset Using Energy-Efficient Residue Number System and Deep Convolutional Neural Network[J]. Symmetry, 2020, 12(5): 836.

[14] Tomaz Da Silva L, Esper N B, Ruiz D D, et al. Visual explanation for identification of the brain bases for developmental dyslexia on fMRI data[J]. Frontiers in computational neuroscience, 2021, 15: 594659.

[15] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks[J]. arXiv preprint arXiv:1609.02907, 2016.

[16] Bhatti U A, Tang H, Wu G, et al. Deep learning with graph convolutional networks: An overview and latest applications in computational intelligence[J]. International Journal of Intelligent Systems, 2023, 2023(1): 8342104.

[17] Zhang L, Zhao Y, Che T, et al. Graph neural networks for image‐guided disease diagnosis: A review[J]. iRADIOLOGY, 2023, 1(2): 151-166.

[18] Zhang X, Chou J, Wang F. Integrative analysis of patient health records and neuroimages via memory-based graph convolutional network[C]//. 2018 IEEE International Conference on Data Mining (ICDM), 2018: 767-776.

[19] Yin G, Chang Y, Zhao Y, et al. Automatic recognition of schizophrenia from brain-network features using graph convolutional neural network[J]. Asian Journal of Psychiatry, 2023, 87: 103687.

[20] Arya D, Olij R, Gupta D K, et al. Fusing structural and functional MRIs using graph convolutional networks for autism classification[C]//. Medical imaging with deep learning, 2020: 44-61.

[21] Yang B, Pan H, Yu J, et al. Classification of medical images with synergic graph convolutional networks[C]//. 2019 IEEE 35th International Conference on Data Engineering Workshops (ICDEW), 2019: 253-258.

[22] Jenkinson M, Beckmann C F, Behrens T E, et al. Fsl[J]. Neuroimage, 2012, 62(2): 782-790.

[23] Yin Z, Li J, Zhang Y, et al. Functional brain network analysis of schizophrenic patients with positive and negative syndrome based on mutual information of EEG time series[J]. Biomedical Signal Processing and Control, 2017, 31: 331-338.

[24] Zhu H, Qiu C, Meng Y, et al. Altered topological properties of brain networks in social anxiety disorder: a resting-state functional MRI study[J]. Scientific reports, 2017, 7(1): 43089.

[25] Murphy K, Fox M D J N. Towards a consensus regarding global signal regression for resting state functional connectivity MRI[J]. Neuroimage, 2017, 154: 169-173.

[26] Tamboer P, Vorst H, Ghebreab S, et al. Machine learning and dyslexia: Classification of individual structural neuro-imaging scans of students with and without dyslexia[J]. NeuroImage: Clinical, 2016, 11: 508-514.