Skip to Main content Skip to Navigation
Conference papers

Classification de types de neurones à partir de signaux calciques

Guillaume Becq 1, 2 Nagham Badreddine 3 Nicolas Tremblay 2 Florence Appaix 3 Gisela Zalcman 3 Elodie Fino 3 Sophie Achard 4
1 GIPSA-Services - GIPSA-Services
GIPSA-lab - Grenoble Images Parole Signal Automatique
4 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology, LJK - Laboratoire Jean Kuntzmann
Abstract : Videos of calcium activities of mice striatum slices are recorded under stimulations by two-photon fluorescence microscopy. Neurons are selected by regions of interests (ROI) on the images and labelled into two classes: medium spiny neuron (MSN); interneurons (IN). Each ROI enables to obtain a neural signal. Features are extracted on these ROI and signals. A subset feature selection is performed with a quadratic discriminant analysis, to solve the supervised learning of the two classes of neuron of the striatum. It is shown, that a realistic evaluation of the database leads to a classification with an accuracy of 75 % for IN and 90% for MSN.
Document type :
Conference papers
Complete list of metadata

Cited literature [15 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02528364
Contributor : Guillaume Becq <>
Submitted on : Tuesday, September 15, 2020 - 1:53:30 PM
Last modification on : Wednesday, March 24, 2021 - 4:50:54 PM

File

gretsi_2019.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02528364, version 2

Citation

Guillaume Becq, Nagham Badreddine, Nicolas Tremblay, Florence Appaix, Gisela Zalcman, et al.. Classification de types de neurones à partir de signaux calciques. GRETSI 2019 - XXVIIème Colloque francophone de traitement du signal et des images, Aug 2019, Lille, France. ⟨hal-02528364v2⟩

Share

Metrics

Record views

121

Files downloads

100