IP Library Granted Patent US 12,482,282
Granted Patent B2
US 12,482,282 · App. 17/615,502 · Granted Nov 25, 2025

System for determining the effect of active ingredients on acariformes, insects and other organisms in an assay plate containing wells

Inventors: Johannes Linzbach (Cologne, DE); Barthel Bach-Zelewski (Remscheid, DE); Klaus Ochmann (Leverkusen, DE); Franco Fois (Monheim, DE); Kerstin Ilg (Cologne, DE); Angelika Köllen (Cologne, DE)
Assignee: Bayer Aktiengesellschaft
G06V20/698G06F18/24143G06V10/82
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 12,482,282
App. No.
17/615,502
Granted
Nov 25, 2025
Kind
B2
Abstract

The invention relates to an automated system and a method for determining the effect of active ingredients on organisms such as insects, Acariformes and nematodes in an assay plate containing wells with the aid of image-acquisition and image-analysis technology. The invention allows the characterization of the population of the organisms at multiple time points.

Claims (35)

1 . A system for determining the effect of active ingredients on living organisms accommodated on a support comprising a leaf in at least one well, comprising:

an assay plate with the at least one well, wherein the at least one well contains the living organisms accommodated on the support comprising the leaf and an active ingredient applied to the living organisms;

an apparatus for acquiring images of the at least one well comprising the living organisms and the active ingredient accommodated on the support, the apparatus comprising:

a camera having an optical system, wherein the camera is arranged over the at least one well and is configured to acquire multiple images of a scene in which the at least one well is present, said multiple images being acquired at different focal planes, wherein the camera comprises a sensor which allows a 1:1 imaging scale or greater of the at least one well;

a device for changing the focal plane;

a device for illuminating the at least one well with at least one light source, wherein the device for illumination illuminates the at least one well homogeneously from above; and

a control device configured to:

control the apparatus for acquiring images such that a series of images for each well having a differing focal plane is acquired according to a predefined sequence;

adjust and operate the device for changing the focal plane;

operate the camera; and

store one or more of the images or the series of images,

wherein the control device is connected to the camera via interfaces; and

wherein the system is configured for:

object recognition with respect to the living organisms on the image and automatic classification of the living organisms based on the object recognized with the aid of a neural network trained with annotated images comprising classified living organisms, wherein the classified living organisms of the annotated images are assigned a stage comprising adult, larvae, or egg;

processing the images at different focal planes using a focus stacking method into an image of the at least one well of increased depth of field; and

conducting the object recognition and classification with respect to the living organisms on the image of the at least one well of increased depth of field to determine the effect of the active ingredient applied to the living organisms, wherein the classification is configured to selectively determine the stage of the living organisms as adults, to selectively determine the stage of the living organisms as larvae, and to selectively determine the stage of the living organisms as eggs.

2 . The system of claim 1 , wherein classification in at least one of the following class lists is effected:

living or dead.

3 . The system of claim 2 , wherein the device for illuminating the well is a device for coaxial illumination.

4 . The system of claim 2 , wherein the optical system consists of a fixed-focus lens and one or more intermediate rings.

5 . The system of claim 4 , wherein the device for changing the focal plane is a device for moving the camera along the vertical axis (z).

6 . The system of claim 2 , wherein the system is further configured for processing of the series of images using the focus stacking method into an image that is in focus everywhere.

7 . The system of claim 2 , wherein the apparatus for acquiring macroscopic images comprises a device for positioning the wells that is movable horizontally in two directions (x, y).

8 . The system of claim 7 , wherein the system is further configured to carry out the following steps:

place a well in a predefined position in relation to the optical system by horizontally moving the cell culture plate with the aid of the device for positioning the wells; and

repeat placement for each well until all wells have been recorded.

9 . A method for determining an effect of active ingredients on living organisms accommodated on a support comprising a leaf in at least one well in an assay plate, comprising:

a) placing the assay plate comprising the living organisms and an active ingredient applied to the living organisms accommodated on the support comprising the leaf, and positioning the at least one well in a predefined position in relation to a camera by horizontal movement of the assay plate with the aid of the device for positioning the at least one well, so that multiple images of a scene in which the at least one well comprising the living organisms and the active ingredient accommodated on the support are acquired;

b) setting a focal plane by operation of the device for changing the focal plane;

c) acquiring an image of the at least one well by the camera;

d) storing the image;

e) changing the focal plane by operation of the device for changing the focal plane,

f) repeating steps c) to e) for acquisition of a predefined number of images at different focal planes; and

g) repeating steps a) to f) for another well until images at different focal planes are acquired for all wells, wherein the images at different focal planes are processed using a focus stacking method into an image of the at least one well of increased depth of field; and

h) conducting object recognition with respect to the living organisms on the image and automatic classification of the living organisms based on the object recognized with the aid of a neural network trained with annotated images comprising classified living organisms, wherein the classified living organisms of the annotated images are assigned a stage comprising adult, larvae, or egg, conducting the object recognition and classification with respect to the living organisms on the image of the at least one well of increased depth of field determines the effect of the active ingredient applied to the living organisms, and the classification is configured to selectively determine the stage of the living organisms as adults, to selectively determine the stage of the living organisms as larvae, and to selectively determine the stage of the living organisms as eggs.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 1, 2021
From: LINZBACH, JOHANNES; BACH-ZELEWSKI, BARTHEL; OCHMANN, KLAUS; FOIS, FRANCO; ILG, KERSTIN; KÖLLEN, ANGELIKA
To: BAYER AKTIENGESELLSCHAFT
Reel/Frame 058254/0166 →
Priority Claims (1)
EP 19177911 · Jun 3, 2019 · regional
Continuity (1)
Related Publication 20220318575A1 · Oct 6, 2022
References Cited (20)
US 11900600B2 · Stamatoyannopoulos · 2024 [cited by examiner]
US 20110169985A1 · Cooper · 2011 [cited by examiner]
US 20110181622A1 · Bacus · 2011 [cited by examiner]
US 20190384051A1 · Gaiduk · 2019 [cited by examiner]
WO 2016172532A2 · 2016 [cited by applicant]
Gopakumar, Gopalakrishna Pillai, et al. “Convolutional neural network-based malaria diagnosis from focus stack of blood smear images acquired using custom-built slide scanner.” Journal of biophotonics 11.3 (2018): e2017… [cited by examiner]
Naro, Yuta, et al. “Small molecule inhibition of MicroRNA miR-21 rescues chemosensitivity of renal-cell carcinoma to topotecan.” Journal of medicinal chemistry 61.14 (2018): 5900-5909. (Year: 2018). [cited by examiner]
Patten, Tom,etal.“Automatic [cited by examiner]
Vincent, Thomas R., et al. “Real-time in vivo recording of [cited by examiner]
De Souza, M.R.Q., et al. (2018). “A Framework 1-16 for Automatic Recognition of Cell Damage on Microscopic Images using Artificial Neural Networks”, 40th Annual International Conference of the IEEE Engineering in Medici… [cited by applicant]
Gopakumar, G.P. et al. (2018). “Convolutional neural network-based malaria diagnosis from focus stack of blood smear images acquired using custom-built slide scanner”, Journal of Biophotonics, DOI: 10.1002/ibio.20170000… [cited by applicant]
He, K. et al. (2016). “Deep Residual Learning for Image Recognition,” CVFR paper, http://openaccess.thecvf.com/content_cvpr_2016/papers/He_Deep_Residual_Learning_CVPR_2016_paper.pdf; 770-778. [cited by applicant]
International Search Report mailed Aug. 12, 2020 for PCT Application No. PCT/EP2020/064682, filed May 7, 2020, 6 pages. [cited by applicant]
Kurtulmus, F. et al. (2013) “Detection of 1-16 dead entomopathogenic nematodes in microscope images using computer vision”, Biosystems Engineering, 118: 29-38. [cited by applicant]
Lin, T-Y et al (Feb. 7, 2018). “Focal Loss for Detection,” Facebook AI Research, arXiv:1708.02002v2 [cs.CV], pp. 1-10. [cited by applicant]
Mallard, F. et al.. (2013). “An Automated 1-16 Image Analysis System to Measure and Count Organisms in Laboratory Microcosms”, PLOS One, 8(5): e64387. [cited by applicant]
Patten, T. et al. (2004). “Automatic [cited by applicant]
Ren, S. et al. (2015). “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” Advances in Neural Information Processing Systems (NIPS), Curran Associates, Inc., (arXiv:1506.01497v2 [cs.CV] Sep… [cited by applicant]
Ren, S. et al. (2016). “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE International Conference on Computer Vision (ICCV) (arXiv:1506.01497v3 [cs.CV] Jan. 6, 2016): 1-14. [cited by applicant]
Effilux, (2024). “High power LED Lighting for machine vision,” available on-line at <www.effilux.com>, 2 pages. [cited by applicant]