Machine-learned cell counting or cell confluence for a plurality of cell types
Various examples of the disclosure relate to techniques to count cells in a microscopy image and/or to determine a degree of confluence of the cells in the microscopy image. To that end, machine-learned algorithms are used.
1. A computer-implemented method, comprising:
acquiring a light-microscope image, which images a multiplicity of cells of a plurality of cell types,
determining a plurality of density maps for the light-microscope image using a plurality of machine-learned processing paths of at least one machine-learned algorithm, wherein the plurality of processing paths are assigned to the plurality of cell types, wherein the plurality of density maps each encodes a probability for the presence or absence of cells of a corresponding cell type, and
on the basis of the plurality of density maps and for each of the plurality of cell types: determining at least one of an estimation of a number or of a degree of confluence of the respective cells.
2. The computer-implemented method as claimed in claim 1 , further comprising: plausiblising the plurality of density maps by a spatially resolved comparison.
3. The computer-implemented method as claimed in claim 1 , wherein the plurality of machine-learned processing paths have a common encoding branch and separate decoding branches.