US 12,259,308 B2
Medical analysis device with impedance signal processing
Pierre Taraconat, Montpellier (FR); Damien Isebe, Montpellier (FR); Simon Mendez, Montpellier (FR); and Franck Nicoud, Montpellier (FR)
Assigned to HORIBA ABX SAS, Montpellier (FR); UNIVERSITE DE MONTPELLIER, Montpellier (FR); and CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE (CNRS), Paris (FR)
Appl. No. 17/793,208
Filed by HORIBA ABX SAS, Montpellier (FR); UNIVERSITE DE MONTPELLIER, Montpellier (FR); and CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE (CNRS), Paris (FR)
PCT Filed Jan. 15, 2021, PCT No. PCT/FR2021/050078
§ 371(c)(1), (2) Date Jul. 15, 2022,
PCT Pub. No. WO2021/144546, PCT Pub. Date Jul. 22, 2021.
Claims priority of application No. 2000439 (FR), filed on Jan. 17, 2020.
Prior Publication US 2023/0066255 A1, Mar. 2, 2023
Int. Cl. G01N 15/12 (2024.01); G01N 15/01 (2024.01); G01N 33/487 (2006.01)
CPC G01N 15/12 (2013.01) [G01N 33/48728 (2013.01); G01N 2015/012 (2024.01)] 10 Claims
OG exemplary drawing
 
1. A medical analysis device with cellular impedance signal processing comprising:
a memory arranged to receive pulse data sets, each pulse data set comprising impedance value data that are associated each time with a time marker, each pulse data set representing a curve of cellular impedance values that are measured when a cell passes through a polarized opening, the device further comprising:
a classifier, the classifier being an element directly or indirectly accessing the memory and comprising a convolutional neural network receiving the pulse data sets as input, the convolutional neural network comprising:
at least one convolutional layer having a depth greater than or equal to 3,
at least two fully connected layers, and
an output layer rendering a classification of a cell from which one of the pulse data sets received as input is derived.