Neural Network Modeling and Correlation Analysis of Brain Plasticity Mechanisms in Stroke Patients

Full Text (PDF, 509KB), PP.28-39

Views: 0 Downloads: 0


Stepanyan I.V. 1,* Mayorova L.A. 2,3 Alferova V.V. 3 Ivanova E.G. 3 Nesmeyanova E.S. 4 Petrushevsky A.G. 3 Tiktinsky-Shklovsky V.M. 3

1. A.A. Blagonravov Mechanical Engineering Institute of the RAS, Moscow, Russian Federation

2. The Institute of Higher Nervous Activity and Neurophysiology of the RAS Moscow, Russian Federation

3. The Center of Speech Pathology and Neurorehabilitation, Moscow, Russian Federation

4. The Lomonosov Moscow State University, Moscow, Russian Federation

* Corresponding author.


Received: 29 Nov. 2018 / Revised: 6 Feb. 2019 / Accepted: 11 Apr. 2019 / Published: 8 Jun. 2019

Index Terms

Post-stroke neuroplasticity, functional and structural connectivity, brain structures, motor and higher cognitive functions, PNN, GRNN, Kohonen neural network, correlation analysis, machine learning


The aim of this research is the study of pathogenic signs, prognostically significant for the outcome of the disease and restoration of impaired functions at various stages of recovery after a stroke. This work describes a new method of applying a group of artificial neural network algorithms for each of the criteria and for each period of rehabilitation, and it is aimed at analyzing the structural and functional support of motor and higher cognitive functions, including speech and language as well as brain plasticity after ischemic stroke. The functional magnetic resonance imaging (fMRI, DTI) and clinical data machine learning algorithms were used. Self-organizing Kohonen and probabilistic neural network-based models with different structures and parameters were developed and applied for each criterion for periods of 3, 6, and 12 months of rehabilitation. For correlation analyses and modeling additional classifiers, we used: Decision Tree (DT), Support Vector Machine (SUM), k-Nearest Neighbor (KNN) clustering, and Logistic Regression (LR). In the performance evaluation, sensitivity, specificity, accuracy, error rate, and f-measure were used. The using of clinical parameters and mathematical modeling for analysis of brain plasticity mechanisms in stroke patients allowed in some cases to predict cognitive functions within the accuracy of 85-97%. Moreover, it is shown that the functional systems is represented by various brain structures, its synchronous activity and structural connectivity ensures the rapid and most complete restoration of motor and higher cognitive functions, including speech and language (effective post-stroke plasticity of the brain) after a course of neurorehabilitation.

Cite This Paper

Stepanyan I.V., Mayorova L.A., Alferova V.V., Ivanova E.G., Nesmeyanova E.S., Petrushevsky A.G.3 Tiktinsky-Shklovsky V.M., "Neural Network Modeling and Correlation Analysis of Brain Plasticity Mechanisms in Stroke Patients", International Journal of Intelligent Systems and Applications(IJISA), Vol.11, No.6, pp.28-39, 2019. DOI:10.5815/ijisa.2019.06.03


[1]V. V. Alferova, L. A. Mayorova, E. G. Ivanova, A. B. Gekht, and V. M. Shllovskii, “Functional neuroimaging of the brain structures associated with language in healthy individuals and patients with Post-Stroke aphasia,” Neurosci. Behav. Physiol., vol. 48, no. 8, pp. 939–946, 2017.
[2]L. A. Mayorova, V. V. Alferova, A. G. Petrushevsky, and S. A. Varlamov, “Poststroke plasticity in sensory aphasia,” Collect. New Inf. Technol. Med. Biol. Pharmacol. Ecol. Proc. Int. Conf., pp. 51–54, 2018.
[3]V. V. Alferova et al., “The prognosis for post-stroke aphasia,” Zhurnal Nevrol. i psikhiatrii Im. S.S. Korsakova, vol. 118, no. 4, pp. 20–29, 2018.
[4]L. A. Mayorova, A. G. Petrushevsky, S. V. Kuptsova, and V. M. Shklovskii, “Functional and anatomical connectivity of the brain in post-stroke aphasia,” J. High. Nerv. Act., vol. 68, no. 2, pp. 141–151, 2018.
[5]V. M. Shklovsky, L. A. Mayorova, V. V. Alferova, A. G. Petrushevsky, E. G. Ivanova, and S. V. Kuptsova, “Functional magnetic resonance imaging of rest in the assessment of speech recovery in post-stroke sensory aphasia,” Biomed. Radioelectron., vol. 1, pp. 39–46, 2018.
[6]L. A. Mayorova, V. M. Shklovskii, V. V. Alferova, E. G. Ivanova, A. G. Petrushevsky, and E. A. Kondratyeva, “Poststroke brain plasticity in speech recognition recovery: an fMRI data,” J. High. Nerv. Act. in press
[7]V. M. Shklovskii, L. A. Mayorova, V. V. Alferova, E. G. Ivanova, and A. G. Petrushevsky, “Functional connectivity of speech regions in patients with isolated poststroke sensory aphasia: resting state fMRI,” J. High. Nerv. Act. in press
[8]V. M. Shklovsky et al., “Regression of post-stroke aphasia and related nonverbal syndromes caused by a course of rehabilitation treatment including intensive speech therapy.,” Zhurnal Nevrol. i psikhiatrii Im. S.S. Korsakova. in press
[9]X. Wang, Y. Ren, and W. Zhang, “Depression Disorder Classification of fMRI Data Using Sparse Low-Rank Functional Brain Network and Graph-Based Features,” Comput. Math. Methods Med., vol. 2017, pp. 1–11, 2017.
[10]X. Geng, J. Xu, B. Liu, and Y. Shi, “Multivariate Classification of Major Depressive Disorder Using the Effective Connectivity and Functional Connectivity,” Front. Neurosci., vol. 12, Feb. 2018.
[11]R. J. Meszlényi, K. Buza, and Z. Vidnyánszky, “Resting State fMRI Functional Connectivity-Based Classification Using a Convolutional Neural Network Architecture,” Front. Neuroinform., vol. 11, Oct. 2017.
[12]M. Plitt, K. A. Barnes, and A. Martin, “Functional connectivity classification of autism identifies highly predictive brain features but falls short of biomarker standards,” NeuroImage Clin., vol. 7, pp. 359–366, 2015.
[13]T. M. Nir et al., “Diffusion weighted imaging-based maximum density path analysis and classification of Alzheimer’s disease,” Neurobiol. Aging, vol. 36, pp. S132–S140, Jan. 2015.
[14]R. Chowdhury and A. F. M. Saifuddin Saif, “Efficient Mathematical Procedural Model for Brain Signal Improvement from Human Brain Sensor Activities,” Int. J. Image, Graph. Signal Process., vol. 10, no. 10, pp. 46–53, Oct. 2018.
[15]A. Q. Alyahya and A. A. Abu-Shareha, “Accuracy Evaluation of Brain Tumor Detection using Entropy-based Image Thresholding,” Int. J. Inf. Technol. Comput. Sci., vol. 10, no. 3, pp. 9–17, Mar. 2018.
[16]K. T, K. N, and S. P, “Automatic Brain Tissues Segmentation based on Self Initializing K-Means Clustering Technique,” Int. J. Intell. Syst. Appl., vol. 9, no. 11, pp. 52–61, Nov. 2017.
[17]K. Bhima and A. Jagan, “An Improved Method for Automatic Segmentation and Accurate Detection of Brain Tumor in Multimodal MRI,” Int. J. Image, Graph. Signal Process., vol. 9, no. 5, pp. 1–8, May 2017.
[18]N. Reddy P, C. P. V. N. J. M. Rao, and C. Satyanarayana, “Optimal Segmentation Framework for Detection of Brain Anomalies,” Int. J. Eng. Manuf., vol. 6, no. 6, pp. 26–37, Nov. 2016.
[19] A. A. Anbarasa Pandian and R. Balasubramanian, “Analysis on Shape Image Retrieval Using DNN and ELM Classifiers for MRI Brain Tumor Images,” Int. J. Inf. Eng. Electron. Bus., vol. 8, no. 4, pp. 63–72, Jul. 2016.
[20]N. Shamli and B. Sathiyabhama, “Parkinson’s Brain Disease Prediction Using Big Data Analytics,” Int. J. Inf. Technol. Comput. Sci., vol. 8, no. 6, pp. 73–84, Jun. 2016.
[21]L. Torgo, Data mining with R: learning with case studies. Boca Raton: Chapman & Hall/CRC, 2011.
[22]A. Painsky and S. Rosset, “Cross-Validated Variable Selection in Tree-Based Methods Improves Predictive Performance,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 11, pp. 2142–2153, Nov. 2017.
[23]R. C. Barros, M. P. Basgalupp, A. C. P. L. F. de Carvalho, and A. A. Freitas, “A Survey of Evolutionary Algorithms for Decision-Tree Induction,” IEEE Trans. Syst. Man, Cybern. Part C (Applications Rev., vol. 42, no. 3, pp. 291–312, May 2012.
[24]J. R. Quinlan, “Induction of decision trees,” Mach. Learn., vol. 1, no. 1, pp. 81–106, Mar. 1986.
[25]T. Kohonen and T. Honkela, “Kohonen network,” Scholarpedia, vol. 2, no. 1, p. 1568, 2007.
[26]I. V. Stepanyan and E. I. Denisov, “Application of neural network technologies in physiology, occupational medicine and human ecology,” Vestn. Tver state un-that. Ser. Biol. Ecol., vol. 23, no. 20, pp. 37–47, 2011.
[27]A. C. Laska, A. Hellblom, V. Murray, T. Kahan, and M. Von Arbin, “Aphasia in acute stroke and relation to outcome.,” J. Intern. Med., vol. 249, no. 5, pp. 413–22, May 2001.
[28]D. F. Muresanu, A. Buzoianu, S. I. Florian, and T. von Wild, “Towards a roadmap in brain protection and recovery,” J. Cell. Mol. Med., vol. 16, no. 12, pp. 2861–2871, Dec. 2012.
[29]K. C. Johnston, A. F. Connors, D. P. Wagner, W. A. Knaus, X. Wang, and E. C. Haley, “A predictive risk model for outcomes of ischemic stroke.,” Stroke, vol. 31, no. 2, pp. 448–55, Feb. 2000.
[30]J. M. Veerbeek, G. Kwakkel, E. E. H. van Wegen, J. C. F. Ket, and M. W. Heymans, “Early Prediction of Outcome of Activities of Daily Living After Stroke,” Stroke, vol. 42, no. 5, pp. 1482–1488, May 2011.
[31]I. R. König et al., “Predicting long-term outcome after acute ischemic stroke: a simple index works in patients from controlled clinical trials,” Stroke, vol. 39, no. 6, pp. 1821–1826, 2008.
[32]A. Muscari, G. M. Puddu, N. Santoro, and M. Zoli, “A simple scoring system for outcome prediction of ischemic stroke,” Acta Neurol. Scand., vol. 124, no. 5, pp. 334–342, Nov. 2011.
[33]G. Ntaios, M. Faouzi, J. Ferrari, W. Lang, K. Vemmos, and P. Michel, “An integer-based score to predict functional outcome in acute ischemic stroke: The ASTRAL score,” Neurology, vol. 78, no. 24, pp. 1916–1922, Jun. 2012.
[34]K.-G. Cao, C.-H. Fu, H.-Q. Li, X.-Y. Xin, and Y. Gao, “A new prognostic scale for the early prediction of ischemic stroke recovery mainly based on traditional Chinese medicine symptoms and NIHSS score: a retrospective cohort study,” BMC Complement. Altern. Med., vol. 15, no. 1, p. 407, Dec. 2015.
[35]D. Haselbach, A. Renggli, S. Carda, and A. Croquelois, “Determinants of Neurological Functional Recovery Potential after Stroke in Young Adults,” Cerebrovasc. Dis. Extra, vol. 4, no. 1, pp. 77–83, Apr. 2014.
[36]B. Kim and C. Winstein, “Can Neurological Biomarkers of Brain Impairment Be Used to Predict Poststroke Motor Recovery? A Systematic Review,” Neurorehabil. Neural Repair, vol. 31, no. 1, pp. 3–24, Jan. 2017.
[37]L. Kwah and R. Herbert, “Prediction of Walking and Arm Recovery after Stroke: A Critical Review,” Brain Sci., vol. 6, no. 4, p. 53, Nov. 2016.
[38]R. Cuingnet et al., “Spatial regularization of SVM for the detection of diffusion alterations associated with stroke outcome,” Med. Image Anal., vol. 15, no. 5, pp. 729–737, Oct. 2011.
[39]Y. Ghanbari, A. R. Smith, R. T. Schultz, and R. Verma, “Identifying group discriminative and age regressive sub-networks from DTI-based connectivity via a unified framework of non-negative matrix factorization and graph embedding,” Med. Image Anal., vol. 18, no. 8, pp. 1337–1348, Dec. 2014.
[40]B. C. Munsell et al., “Evaluation of machine learning algorithms for treatment outcome
prediction in patients with epilepsy based on structural connectome data,” Neuroimage, vol. 118, pp. 219–230, Sep. 2015.
[41]D. Zhu, D. Shen, X. Jiang, and T. Liu, “Connectomics signature for characterizaton of mild cognitive impairment and schizophrenia,” in 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI), 2014, pp. 325–328.
[42]E. Ziv, O. Tymofiyeva, D. M. Ferriero, A. J. Barkovich, C. P. Hess, and D. Xu, “A Machine Learning Approach to Automated Structural Network Analysis: Application to Neonatal Encephalopathy,” PLoS One, vol. 8, no. 11, p. e78824, Nov. 2013.
[43]C. J. Brown et al., “Prediction of Motor Function in Very Preterm Infants Using Connectome Features and Local Synthetic Instances,” 2015, pp. 69–76.
[44]Y. Yoo, T. Brosch, A. Traboulsee, D. K. B. Li, and R. Tam, “Deep Learning of Image Features from Unlabeled Data for Multiple Sclerosis Lesion Segmentation,” 2014, pp. 117–124.
[45]H.-I. Suk, S.-W. Lee, and D. Shen, “Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis,” Neuroimage, vol. 101, pp. 569–582, Nov. 2014.
[46]T. Brosch, R. Tam, and Initiative for the Alzheimers Disease Neuroimaging, “Manifold learning of brain MRIs by deep learning.,” Med. Image Comput. Comput. Assist. Interv., vol. 16, no. Pt 2, pp. 633–40, 2013.
[47]S. M. Plis et al., “Deep learning for neuroimaging: a validation study,” Front. Neurosci., vol. 8, Aug. 2014.