Advertisement

New Features for Neuron Classification

  • Leonardo A. Hernández-Pérez
  • Duniel Delgado-Castillo
  • Rainer Martín-Pérez
  • Rubén Orozco-Morales
  • Juan V. Lorenzo-Ginori
Article

Abstract

This paper addresses the problem of obtaining new neuron features capable of improving results of neuron classification. Most studies on neuron classification using morphological features have been based on Euclidean geometry. Here three one-dimensional (1D) time series are derived from the three-dimensional (3D) structure of neuron instead, and afterwards a spatial time series is finally constructed from which the features are calculated. Digitally reconstructed neurons were separated into control and pathological sets, which are related to three categories of alterations caused by epilepsy, Alzheimer’s disease (long and local projections), and ischemia. These neuron sets were then subjected to supervised classification and the results were compared considering three sets of features: morphological, features obtained from the time series and a combination of both. The best results were obtained using features from the time series, which outperformed the classification using only morphological features, showing higher correct classification rates with differences of 5.15, 3.75, 5.33% for epilepsy and Alzheimer’s disease (long and local projections) respectively. The morphological features were better for the ischemia set with a difference of 3.05%. Features like variance, Spearman auto-correlation, partial auto-correlation, mutual information, local minima and maxima, all related to the time series, exhibited the best performance. Also we compared different evaluators, among which ReliefF was the best ranked.

Keywords

Neuron classification Reconstructed neuron tree Neuron features 

Notes

Acknowledgments

The authors wish to thank the NeuroMorpho.Org project and Dr. Giorgio Ascoli for providing the information on traced neurons as well as statistical data used in this research for comparison purposes. We also acknowledge Drs. Carlos Morell-Pérez and María M. García-Lorenzo and BSc. José D. López-Cabrera for their useful comments and having providing useful references, as well as to the anonymous reviewers for their criticism and valuable comments that allowed us to introduce many improvements in the article.

Compliance with Ethical Standards

Conflict of Interest

All the authors declare no conflicts of interest.

Supplementary material

12021_2018_9374_MOESM1_ESM.avi (58.6 mb)
Online Resource 1 (AVI 59962 kb)
12021_2018_9374_MOESM2_ESM.xlsx (17 kb)
Online Resource 2 (XLSX 16 kb)
12021_2018_9374_MOESM3_ESM.xlsx (11 kb)
Online Resource 3 (XLSX 10 kb)
12021_2018_9374_MOESM4_ESM.pdf (180 kb)
Online Resource 4 (PDF 180 kb)
12021_2018_9374_MOESM5_ESM.pdf (439 kb)
Online Resource 5 (PDF 438 kb)
12021_2018_9374_MOESM6_ESM.xlsx (41 kb)
Online Resource 6 (XLSX 41 kb)
12021_2018_9374_MOESM7_ESM.pdf (775 kb)
Online Resource 7 (PDF 775 kb)
12021_2018_9374_MOESM8_ESM.pdf (177 kb)
Online Resource 8 (PDF 177 kb)

References

  1. 0 - 1 test for chaos - File Exchange - MATLAB Central. (2018). https://www.mathworks.com/matlabcentral/fileexchange/25050-0-1-test-for-chaos.
  2. Absoud, M., Parr, J. R., Halliday, D., Pretorius, P., Zaiwalla, Z., & Jayawant, S. (2010). A novel ARX phenotype: rapid neurodegeneration with Ohtahara syndrome and a dyskinetic movement disorder. Dev Med Child Neurol, 52(3), 305–307.  https://doi.org/10.1111/j.1469-8749.2009.03470.x.CrossRefPubMedGoogle Scholar
  3. Alligood, K. T., Sauer, T. D., & Yorke, J. A. (2009). Chaos: An introduction to dynamical systems (Corrected edition.). New York: Springer.Google Scholar
  4. Armañanzas, R., & Ascoli, G. A. (2015). Towards automatic classification of neurons. Trends Neurosci, 38(5), 307–318.  https://doi.org/10.1016/j.tins.2015.02.004.CrossRefPubMedPubMedCentralGoogle Scholar
  5. Ascoli, G. A., Donohue, D. E., & Halavi, M. (2007). NeuroMorpho.Org: a central resource for neuronal morphologies. J Neurosci, 27(35), 9247–9251.  https://doi.org/10.1523/JNEUROSCI.2055-07.2007.CrossRefPubMedGoogle Scholar
  6. Backes, A. R., & Bruno, O. M. (2012). Fractal and Multi-Scale Fractal Dimension analysis: a comparative study of Bouligand-Minkowski method. arXiv:1201.3153 [cs]. http://arxiv.org/abs/1201.3153. Accessed May 23, 2014.
  7. Beguin, S., Crépel, V., Aniksztejn, L., Becq, H., Pelosi, B., Pallesi-Pocachard, E., Bouamrane, L., Pasqualetti, M., Kitamura, K., Cardoso, C., & Represa, A. (2013). An epilepsy-related ARX polyalanine expansion modifies glutamatergic neurons excitability and morphology without affecting GABAergic neurons development. Cerebral Cortex (New York, NY: 1991), 23(6), 1484–1494.  https://doi.org/10.1093/cercor/bhs138.Google Scholar
  8. BenSaïda, A. (2015). A practical test for noisy chaotic dynamics. SoftwareX, 3-4, 1–5.  https://doi.org/10.1016/j.softx.2015.08.002.CrossRefGoogle Scholar
  9. Bianchi, S., Stimpson, D. C., Bauernfeind, A., Schapiro, S., Baze, W., Mcarthur, M., et al. (2012). Dendritic morphology of pyramidal neurons in the chimpanzee neocortex: regional specializations and comparison to humans. Cerebral Cortex (New York, NY : 1991), 23, 2429–2436.  https://doi.org/10.1093/cercor/bhs239.Google Scholar
  10. Bouckaert, R., Frank, E., Hall, M., Kirkby, R., Reutemann, P., Seewald, A., & Scuse, D. (2015). WEKA manual for version 3–6-13. CreateSpace Independent Publishing Platform.Google Scholar
  11. Calvo, B., & Santafe, G. (2015). scmamp: Statistical comparison of multiple algorithms in multiple problems. https://cran.r-project.org/web/packages/scmamp/index.html. Accessed October 17, 2016.
  12. Chaos and Time-Series Analysis. (2018, enero 17). http://sprott.physics.wisc.edu/chaostsa/. Accessed January 17, 2018.
  13. Cross, S. S. (1994). The application of fractal geometric analysis to microscopic images. Micron, 25(1), 101–113.  https://doi.org/10.1016/0968-4328(94)90057-4.CrossRefPubMedGoogle Scholar
  14. Cuntz, H., Forstner, F., Borst, A., & Häusser, M. (2011). The TREES toolbox--probing the basis of axonal and dendritic branching. Neuroinformatics, 9(1), 91–96.  https://doi.org/10.1007/s12021-010-9093-7.CrossRefPubMedGoogle Scholar
  15. Dean, J. M., McClendon, E., Hansen, K., Azimi-Zonooz, A., Chen, K., Riddle, A., Gong, X., Sharifnia, E., Hagen, M., Ahmad, T., Leigland, L. A., Hohimer, A. R., Kroenke, C. D., & Back, S. A. (2013). Prenatal cerebral ischemia disrupts MRI-defined cortical microstructure through disturbances in neuronal arborization. Sci Transl Med, 5(168), 168ra7.  https://doi.org/10.1126/scitranslmed.3004669.CrossRefPubMedGoogle Scholar
  16. Delgado Castillo, D., Martín Pérez, R., Hernández Pérez, L., Orozco Morález, R., & Lorenzo Ginori, J. (2016). Algoritmos de aprendizaje automático para la clasificación de neuronas piramidales afectadas por el envejecimiento. Revista Cubana de Informática Médica, 8, 559–571.Google Scholar
  17. Demšar, J. (2006). Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res, 7(Jan), 1–30.Google Scholar
  18. Di Ieva, A., Grizzi, F., Jelinek, H., Pellionisz, A. J., & Losa, G. A. (2013). Fractals in the neurosciences, part I: general principles and basic neurosciences. The Neuroscientist: A Review Journal Bringing Neurobiology, Neurology and Psychiatry, 20(4), 403–417.  https://doi.org/10.1177/1073858413513927.CrossRefGoogle Scholar
  19. Di Ieva, A., Esteban, F. J., Grizzi, F., Klonowski, W., & Martín-Landrove, M. (2015). Fractals in the neurosciences, part II: clinical applications and future perspectives. The Neuroscientist: A Review Journal Bringing Neurobiology, Neurology and Psychiatry, 21(1), 30–43.  https://doi.org/10.1177/1073858413513928.CrossRefGoogle Scholar
  20. Dokukin, M. E., Guz, N. V., Gaikwad, R. M., Woodworth, C. D., & Sokolov, I. (2011). Cell surface as a fractal: normal and cancerous cervical cells demonstrate different fractal behavior of surface adhesion maps at the nanoscale. Phys Rev Lett, 107(2), 028101.  https://doi.org/10.1103/PhysRevLett.107.028101.CrossRefPubMedPubMedCentralGoogle Scholar
  21. Duan, H., Wearne, S. L., Morrison, J. H., & Hof, P. R. (2002). Quantitative analysis of the dendritic morphology of corticocortical projection neurons in the macaque monkey association cortex. Neuroscience, 114(2), 349–359.CrossRefPubMedGoogle Scholar
  22. Duan, H., Wearne, S. L., Rocher, A. B., Macedo, A., Morrison, J. H., & Hof, P. R. (2003). Age-related dendritic and spine changes in corticocortically projecting neurons in macaque monkeys. Cerebral Cortex (New York, N.Y.: 1991), 13(9), 950–961.CrossRefGoogle Scholar
  23. Fernández, E., & Jelinek, H. F. (2001). Use of fractal theory in neuroscience: methods, advantages, and potential problems. Methods (San Diego, Calif.), 24(4), 309–321.  https://doi.org/10.1006/meth.2001.1201.CrossRefGoogle Scholar
  24. Foster, K. R., Koprowski, R., & Skufca, J. D. (2014). Machine learning, medical diagnosis, and biomedical engineering research - commentary. Biomed Eng Online, 13, 94.  https://doi.org/10.1186/1475-925X-13-94.CrossRefPubMedPubMedCentralGoogle Scholar
  25. Gottwald, G. A., & Melbourne, I. (2009). On the implementation of the 0-1 test for chaos. SIAM J Appl Dyn Syst, 8(1), 129–145.  https://doi.org/10.1137/080718851.CrossRefGoogle Scholar
  26. Gottwald, G. A., & Melbourne, I. (2016). The 0-1 test for Chaos: a review. SpringerLink, 221–247.  https://doi.org/10.1007/978-3-662-48410-4_7.
  27. Guerra, L., McGarry, L. M., Robles, V., Bielza, C., Larrañaga, P., & Yuste, R. (2011). Comparison between supervised and unsupervised classifications of neuronal cell types: a case study. Developmental Neurobiology, 71(1), 71–82.  https://doi.org/10.1002/dneu.20809.CrossRefPubMedGoogle Scholar
  28. Halavi, M., Hamilton, K. A., Parekh, R., & Ascoli, G. A. (2012). Digital reconstructions of neuronal morphology: three decades of research trends. Front Neurosci, 6.  https://doi.org/10.3389/fnins.2012.00049.
  29. Hamilton, P., & West, B. (2000). Software review chaos data analyzer, professional version. by J. Sprott and G. Rowlands. Nonlinear Dynamics, Psychology, and Life Sciences, 4, 195–199.  https://doi.org/10.1023/A:1009580513427.CrossRefGoogle Scholar
  30. Kabaso, D., Coskren, P.J., Henry, B.I., Hof, P.R., & Wearne, S.L. (2009). The electrotonic structure of pyramidal neurons contributing to prefrontal cortical circuits in macaque monkeys is significantly altered in aging. Oxford University Press, 19, 2248–2268.  https://doi.org/10.1093/cercor/bhn242.
  31. Kugiumtzis, D., & Tsimpiris, A. (2010). Measures of analysis of time series (MATS): a MATLAB toolkit for computation of multiple measures on time series data bases. arXiv:1002.1940 [stat]. http://arxiv.org/abs/1002.1940. Accessed February 27, 2018.
  32. Leite-Morris, K. A., Kobrin, K. L., Guy, M. D., Young, A. J., Heinrichs, S. C., & Kaplan, G. B. (2014). Extinction of opiate reward reduces dendritic arborization and c-Fos expression in the nucleus accumbens core. Behav Brain Res, 263, 51–59.  https://doi.org/10.1016/j.bbr.2013.12.041.CrossRefPubMedGoogle Scholar
  33. Mavroudis, I. A., Manani, M. G., Petrides, F., Petsoglou, C., Njau, S. N., Costa, V. G., & Baloyannis, S. J. (2014). Dendritic and spinal alterations of neurons from Edinger-Westphal nucleus in Alzheimer’s disease. Folia Neuropathol, 52(2), 197–204.CrossRefPubMedGoogle Scholar
  34. NeuroMorpho_Linkout. (2018, febrero 28). http://neuromorpho.org/NeuroMorpho_Linkout.jsp?PMID=12902394. Accessed February 28, 2018.
  35. Papana, A., & Kugiumtzis, D. (2009). Evaluation of mutual information estimators for time series. International Journal of Bifurcation and Chaos, 19(12), 4197–4215.  https://doi.org/10.1142/S0218127409025298.CrossRefGoogle Scholar
  36. Pawel, S., Frishman, D., & Kramer, S. (2009). Pitfalls of supervised feature selection. Bioinformatics (Oxford, England), 26, 440–443.  https://doi.org/10.1093/bioinformatics/btp621.Google Scholar
  37. Rand, D., & Young, L.-S. (Eds.). (1981). Dynamical systems and turbulence, Warwick 1980 (Vol. 898). Berlin, Heidelberg: Springer Berlin Heidelberg.  https://doi.org/10.1007/BFb0091903
  38. Riddle, A., Luo, N. L., Manese, M., Beardsley, D. J., Green, L., Rorvik, D. A., Kelly, K. A., Barlow, C. H., Kelly, J. J., Hohimer, A. R., & Back, S. A. (2006). Spatial heterogeneity in oligodendrocyte lineage maturation and not cerebral blood flow predicts fetal ovine periventricular white matter injury. J Neurosci, 26(11), 3045–3055.  https://doi.org/10.1523/JNEUROSCI.5200-05.2006.CrossRefPubMedGoogle Scholar
  39. Riddle, A., Dean, J., Buser, J. R., Gong, X., Maire, J., Chen, K., Ahmad, T., Cai, V., Nguyen, T., Kroenke, C. D., Hohimer, A. R., & Back, S. A. (2011). Histopathological correlates of magnetic resonance imaging-defined chronic perinatal white matter injury. Ann Neurol, 70(3), 493–507.  https://doi.org/10.1002/ana.22501.CrossRefPubMedPubMedCentralGoogle Scholar
  40. Rosenstein, M. T., Collins, J. J., & Luca, C. J. D. (1993). A practical method for calculating largest Lyapunov exponents from small data sets. Physica D, 65, 117–134.CrossRefGoogle Scholar
  41. Saeb, T., & Hövel, P. (2013). Dynamical systems in neuroscience. Institut für Theoretische Physik, Technische Universität Berlin. http://www.itp.tu-berlin.de/fileadmin/a3233_bccn-nachwuchsgruppe/dynamical_systems.pdf.
  42. Schierwagen, A., Costa, L. da F., Alpár, A., & Gärtner, U. (2007). Multiscale fractal analysis of cortical pyramidal neurons. En A. Horsch, T. M. Deserno, H. Handels, H.-P. Meinzer, & T. Tolxdorff (Eds.), Bildverarbeitung für die Medizin 2007 (pp. 424–428). Springer Berlin Heidelberg. http://link.springer.com/chapter/10.1007/978-3-540-71091-2_85. Accessed may 22, 2014.
  43. Schierwagen, A., Costa, L. da F., Alpar, A., Gärtner, U., & Arendt, T. (2008). Neuromorphological phenotyping in transgenic mice: a multiscale fractal analysis. En A. Deutsch, R. B. de la Parra, R. J. de Boer, O. Diekmann, P. Jagers, E. Kisdi, et al. (Eds.), Mathematical Modeling of Biological Systems, Volume II (pp. 185–192). Birkhäuser Boston. http://link.springer.com/chapter/10.1007/978-0-8176-4556-4_16. Accessed may 22, 2014.
  44. Scorcioni, R., Polavaram, S., & Ascoli, G. A. (2008). L-measure: a web-accessible tool for the analysis, comparison and search of digital reconstructions of neuronal morphologies. Nat Protoc, 3(5), 866–876.  https://doi.org/10.1038/nprot.2008.51.CrossRefPubMedPubMedCentralGoogle Scholar
  45. Sholl, D. A. (1953). Dendritic organization in the neurons of the visual and motor cortices of the cat. J Anat, 87(4), 387-406.Google Scholar
  46. Task Force of the European Society of Cardiology and the North American Society of Pacing and Electrophysiology. (1996). Heart rate variability: standards of measurement, physiological interpretation and clinical use. Circulation, 93(5), 1043–1065.Google Scholar
  47. TISEAN: Nonlinear Time Series Analysis. (2018, enero 17). https://www.pks.mpg.de/~tisean/. Accessed January 17, 2018.
  48. Vasilkoski, Z., & Stepanyants, A. (2009). Detection of the optimal neuron traces in confocal microscopy images. J Neurosci Methods, 178(1), 197–204.  https://doi.org/10.1016/j.jneumeth.2008.11.008.CrossRefPubMedGoogle Scholar
  49. Wallis, J. W., & Miller, T. R. (1991). Three-dimensional display in nuclear medicine and radiology. J Nucl Med, 32(3), 534–546.PubMedGoogle Scholar
  50. Zhou, Z., Liu, X., Long, B., & Peng, H. (2016). TReMAP: automatic 3D neuron reconstruction based on tracing, reverse mapping and assembling of 2D projections. Neuroinformatics, 14(1), 41–50.  https://doi.org/10.1007/s12021-015-9278-1.CrossRefPubMedGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  • Leonardo A. Hernández-Pérez
    • 1
  • Duniel Delgado-Castillo
    • 1
  • Rainer Martín-Pérez
    • 1
  • Rubén Orozco-Morales
    • 2
  • Juan V. Lorenzo-Ginori
    • 3
  1. 1.Empresa de Telecomunicaciones de Cuba S.ASanta ClaraCuba
  2. 2.Department of Automatics and Computational SystemsUniversidad Central “Marta Abreu” de Las VillasSanta ClaraCuba
  3. 3.Informatics Research CenterUniversidad Central “Marta Abreu” de Las VillasSanta ClaraCuba

Personalised recommendations