IP Library Granted Patent US 12,437,396
Granted Patent B2
US 12,437,396 · App. 17/957,042 · Granted Oct 7, 2025

Machine-learned cell counting or cell confluence for a plurality of cell types

Inventors: Manuel Amthor (Jena, DE); Daniel Haase (Zöllnitz, DE); Michael Gögler (Wolfratshausen, DE)
Assignee: Carl Zeiss Microscopy GmbH
G06T7/0012G06T2207/10061G06T2207/20081G06T2207/30024
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,437,396
App. No.
17/957,042
Granted
Oct 7, 2025
Kind
B2
Abstract

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.

Claims (6)

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.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 6, 2023
From: AMTHOR, MANUEL; HAASE, DANIEL; GÖGLER, MICHAEL
To: CARL ZEISS MICROSCOPY GMBH
Reel/Frame 062296/0855 →
Priority Claims (1)
DE 102021125538.4 · Oct 1, 2021 · national
Continuity (1)
Related Publication 20230108453A1 · Apr 6, 2023
References Cited (9)
US 20140286562A1 · Chen · 2014 [cited by examiner]
US 20180312803A1 · Banju · 2018 [cited by examiner]
DE 102020126554A1 · 2022 [cited by applicant]
DE 102021114351A1 · 2022 [cited by applicant]
Cohen, Joseph, et al. “Count-ception: Counting by fully convolutional redundant counting.” Proceedings of the IEEE International conference on computer vision workshops. 2017. [cited by applicant]
Xie, Weidi, J. Alison Noble, and Andrew Zisserman. “Microscopy cell counting and detection with fully convolutional regression networks.” Computer methods in biomechanics and biomedical engineering: Imaging & Visualizat… [cited by applicant]
Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. “U-net: Convolutional networks for biomedical image segmentation.” International Conference on Medical image computing and computer-assisted intervention. Springer, C… [cited by applicant]
He, Shenghua et al, “Deeply-supervised density regression for automatic cell counting in microscopy images”, Medical Image Analysis, Feb. 2021; 68:101892, pp. 1-12. [cited by applicant]
German Search Report (with English translation) dated Jun. 6, 2022 from related/corresponding German Patent Appl. No. DE102021125538.4. [cited by applicant]