Automatic Identification of Neurons in Complex Cultures Using Image Processing Algorithms

  1. Gerard Villarroya-Pique 1
  2. Víctor M. González 1
  3. Esther Serrano-Pertierra 1
  4. Antonello Novelli 1
  5. M. Teresa Fernández-Sánchez 1
  6. Angel Rio-Alvarez 1
  1. 1 Universidad de Oviedo
    info

    Universidad de Oviedo

    Oviedo, España

    ROR https://ror.org/006gksa02

Proceedings:
Actas XLII Congreso Anual de la Sociedad Española de Ingeniería Biomédica (CASEIB 2024)

Publisher: SEIB

ISBN: 978-84-09-67332-2

Year of publication: 2024

Pages: 9-12

Congress: Congreso Anual de la Sociedad Española de Ingeniería Biomédica. CASEIB (42. 2024. Sevilla)

Type: Conference paper

GOOGLE SCHOLAR

Abstract

In the study of neurodegenerative diseases, and, more generally, inneuroscience, cell culture viability tests are a very common technique.These tests are based on chemical staining means designedto target only the living cells, but at the expense of killing the neuronsin the mid term. Then, the researchers have to manually countthe number of living neurons identified in the microscope imagesobtained using fluorescence techniques. This manual task is verytedious and prone to errors. Computer Vision may help to solvethese two issues. Many Deep Learning (DL) based algorithms havebeen developed to identify neurons in a culture. When the culturesare particularly complex due to their variability, as well as the presenceof other types of elements, the use of Supervised DL modelsis a requirement. This kind of techniques require a big data setof images manually labeled by experts for the models to performaccurately. The manual labelling of the neurons can introduce researcherbias, hence optimizing the models for a single type of culture.This work addresses the automatic identification of neurons influorescence images of neuronal cultures using classical algorithms,thus avoiding the need for manual labeling of images. The methodemploys a peak extraction algorithm to locate the centroids of theneurons in the image. Results indicate that the method can countneurons with a reliability similar to that achieved by experts.

Bibliographic References

  • Z. Nozhat, M. S. Khalaji, M. Hedayati, and S. K. Kia, “Different methods for cell viability and proliferation assay: Essential tools in pharmaceutical studies,” Anti-Cancer Agents in Medicinal Chemistry, vol. 22, pp. 703–712, Feb 2022.
  • K. H. Jones and J. A. Senft, “An improved method to determine cell viability by simultaneous staining with fluorescein diacetate-propidium iodide,” Journal of Histochemistry & Cytochemistry, vol. 33, pp. 77–79, Jan 1985.
  • D. Reis, J. Kupec, J. Hong, and A. Daoudi, “Real-time flying object detection with yolov8,” arXiv, 2024.
  • S. Chen, Y. Zou, and P. X. Liu, “Iba-u-net: Attentive bconvlstm u-net with redisigned inception for medical image segmentation,” Computers in Biology and Medicine, vol. 135, p. 104551, Aug 2021.
  • P. Hirapara and A. Sikander, “An approach for neuronal cell segmentation based on mask-rcnn,” Energy Systems, Drives and Automations (ESDA 2021), pp. 411–418, 2023.
  • A. Moen, H. Eriksen, J. de Knegt, A. Myklebost, K. Brurberg, and O. Langørgen, “Quality assessment of cell image segmentation methods: A review,” Journal of Microscopy, vol. 269, no. 3, pp. 247–256, 2018.
  • M. Oberlaender, V. J. Dercksen, R. Egger, M. Gensel, B. Sakmann, and H.-C. Hege, “Automated three-dimensional detection and counting of neuron somata,” J. Neurosci. Methods, vol. 180, pp. 147–160, May 2009.
  • T. Liu, G. Li, J. Nie, A. Tarokh, X. Zhou, L. Guo, J. Malicki, W. Xia, and S. T. C.Wong, “An automated method for cell detection in zebrafish,” Neuroinformatics, vol. 6, pp. 5–21, Mar 2008.
  • “Pyclesperanto-prototype.” [Disponible en: https://github.com/clesperanto/pyclesperanto_ prototype/].
  • “Clij project.” [Disponible en: https://clij.github.io/].
  • R. Haase, L. A. Royer, P. Steinbach, D. Schmidt, A. Dibrov, U. Schmidt, M. Weigert, N. Maghelli, P. Tomancak, F. Jug, and E. W. Myers, “Clij: Gpu-accelerated image processing for everyone,” Nature Methods, vol. 17, pp. 5–6, Jan 2020.
  • N. Otsu, “A threshold selection method from gray-level histograms,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62–66, 1979.
  • S. Shabanipour, A. Dalvand, X. Jiao, M. R. Balaei, S. H. Chung, J. Kong, M. R. D. Bigio, and H. Marzban, “Primary culture of neurons isolated from embryonic mouse cerebellum,” Journal of Visualized Experiments, vol. 152, p. e60168, Oct 2019.