Neuron cell classification using machine learning algorithms: Methodological considerations

Slade Matthews, Ian Spence, Herbert F. Jelinek, Craig S. McLachlan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Retinal ganglion cells of different species have been categorised using different paradigms and resulting in different number of suggested classes/types based on traditional morphological parameters such as cell body size or dendritic diameter. The inherent nature of the neuron's branching pattern has also been shown to play a role in signal processing and therefore additional features such as fractal dimension and lacunarity were added. Machine learning algorithms (MLA) provide a basis for classification tasks based on large numbers of features. However there are numerous ways of presenting data, different algorithms, validation methods and determination of performance. No studies have been undertaken that investigate the influence of model validation on small datasets with diverse feature parameters. This paper outlines the differences when balanced and imbalanced data is used in combination with six supervised MLAs and two different validation algorithms (LOO and 10-fold) as well as interpreting the results using two performance measures (AUC or accuracy). Our results indicate that that the largest effect on MLA outcomes is whether data is balanced or imbalanced. AUC is a more robust decision rule compared to accuracy. The best classifiers for our data were neural networks and logistic regression with an AUC of greater than 0.9.

Original languageEnglish
Title of host publicationProceedings of the 9th IASTED International Conference on Biomedical Engineering, BioMed 2012
Pages599-604
Number of pages6
DOIs
Publication statusPublished - 16 Jul 2012
Externally publishedYes
Event9th IASTED International Conference on Biomedical Engineering, BioMed 2012 - Innsbruck, Austria
Duration: 15 Feb 201217 Feb 2012

Publication series

NameProceedings of the 9th IASTED International Conference on Biomedical Engineering, BioMed 2012

Conference

Conference9th IASTED International Conference on Biomedical Engineering, BioMed 2012
CountryAustria
CityInnsbruck
Period15/02/1217/02/12

Keywords

  • Balanced datasets
  • Machine learning algorithms
  • Neurons
  • Performance
  • Verification

Fingerprint Dive into the research topics of 'Neuron cell classification using machine learning algorithms: Methodological considerations'. Together they form a unique fingerprint.

  • Cite this

    Matthews, S., Spence, I., Jelinek, H. F., & McLachlan, C. S. (2012). Neuron cell classification using machine learning algorithms: Methodological considerations. In Proceedings of the 9th IASTED International Conference on Biomedical Engineering, BioMed 2012 (pp. 599-604). (Proceedings of the 9th IASTED International Conference on Biomedical Engineering, BioMed 2012). https://doi.org/10.2316/P.2012.764-083