Methods and systems for automated assessment of antibiotic sensitivity

Patent metadata

Field	Value
Publication number	US-11319575-B2
Application number	US-201816650087-A
Country	US
Kind code	B2
Filing date	Sep 27, 2018
Priority date	Sep 28, 2017
Publication date	May 3, 2022
Grant date	May 3, 2022

Abstract

An imaging system and method provides automated microbial growth detection for antibiotic sensitivity testing. A processing system having an image sensor for capturing images of an inoculated culture plate having antibiotic disks disposed on the culture media captures images of the plate at separate times (e.g., first and second images). The system generates pixel characteristic data for pixels of the second image from a comparison of the first image and second image. The pixel characteristic data may be indicative of plate growth. The system may access growth modeling data concerning the antibiotic disk(s) and generate simulated image data with a growth model function. The growth model function uses the growth modeling data. The simulated image data simulates growth on the plate relative to the disk(s). The system compares the simulated image and the pixel characteristic data to identify pixel region(s) of the second image that differ from the simulated image.

First claim

What is claimed is:

1. A method in a processor for antibiotic susceptibility testing comprising:
providing a culture plate inoculated with a biological sample, the culture plate having culture media and at least one antibiotic disk disposed thereon;
receiving first and second image data of the culture plate generated with an image sensor and wherein the first image data serves as a pre-growth reference, the first image data and second image data respectively representing first and second captured images of the culture plate having a plurality of antibiotic disks thereon, the first and second captured images taken at separate times,
generating pixel characteristic data for pixels of the second image data from a comparison of the first image data and the second image data, the pixel characteristic data indicative of microbial growth on the culture plate over time;
accessing growth modeling data for microbial growth, wherein the growth modeling data models microbial growth for combinations of culture media, microorganisms, antibiotic, antibiotic concentration on at least one antibiotic disk of the plurality of antibiotic disks and in the culture media wherein the antibiotic concentration in the culture media is a function of antibiotic concentration on the antibiotic disk, time and a distance from the antibiotic disk;
generating simulated image data with a growth model function, the growth model function using the growth modeling data, the simulated image data simulating microbial growth on the inoculated culture plate based on the at least one antibiotic disk of the plurality of antibiotic disks disposed on the culture media, the antibiotic concentration on the at least one antibiotic disk; the culture media and the antibiotic concentration in the culture media as a function of time and distance from the antibiotic disk; and
comparing the simulated image data and the pixel characteristic data and identifying one or more pixel regions of the second image data that differ from one or more pixel regions of the simulated image data.

2. The method of claim 1 , wherein the generated pixel characteristic data comprises contrast data.

3. The method of claim 2 , wherein the contrast data comprises pixel intensity values.

4. The method of claim 3 , wherein the contrast data further comprises one or more of opacity data, color data and blurring data.

5. The method of claim 1 , wherein the pixel characteristic data comprises distance data, the distance data representing distance to the at least one of the plurality of antibiotic disks.

6. The method of claim 5 , wherein the distance data comprises a distance to center of the at least one of the plurality of antibiotic disks.

7. The method of claim 1 , wherein the growth model function comprises a maximum growth model, a minimum growth model, an average growth model, a median growth model or a percentile growth model.

8. The method of claim 1 , wherein the growth model function characterizes contrast data as a function of radial distance from the at least one antibiotic disk of the plurality of antibiotic disks.

9. The method of claim 1 , wherein the growth model function comprises a diffusion map.

10. The method of claim 1 , further comprising:
detecting in the first image data or second image data, antibiotic disk image data of the at least one antibiotic disk of the plurality of antibiotic disks,
analyzing the antibiotic disk image data to detect indicia data; and
wherein the step of accessing growth modeling data comprises locating the growth modelling data using the indicia data.

11. The method of claim 1 , wherein the growth modelling data comprises concentration information for an antibiotic load of the at least one antibiotic disk of the plurality of antibiotic disks.

12. The method of claim 1 , wherein the growth model function uses a growth time parameter representing elapsed time for microbial growth on the culture plate at a time of capture of the second image data.

13. The method of claim 1 , wherein the growth model function uses a diffusion coefficient parameter.

14. The method of claim 1 , wherein the growth model function uses a dimensionality parameter.

15. The method of claim 1 , wherein the generated simulated image data comprises an image mask having first image pixels representing a no-growth zone corresponding with a location of the at least one antibiotic disk of the plurality of antibiotic disks on the culture plate and second image pixels representing a growth zone radiating from the no-growth zone and beginning at a radial distance from the location, the radial distance determined from the growth model function, the radial distance representing an estimated inhibition zone limit for the at least one antibiotic disk.

16. The method of claim 15 , wherein the comparing the simulated image data and the pixel characteristic data comprises contrasting the image mask and the pixel characteristic data to generate difference image data.

17. The method of claim 16 , further comprising evaluating a region of the second image data based on the difference image data.

18. The method of claim 1 , wherein the first image data serves as a pre-growth reference.

19. The method of claim 1 , further comprising controlling the image sensor to capture the first and second captured images of the culture plate.

20. The method of claim 2 , wherein the contrast data comprises temporal contrast data and spatial contrast data.

21. The method of claim 20 , further comprising:
setting a threshold temporal contrast value as an indication of modulation of microbial growth caused by the antibiotic disk; and
when a measured temporal contrast between one or more pixels in the first image data and one or more pixels in the second image data exceeds the threshold temporal contrast value, providing an indication to a user that the second captured image can be used evaluate microbial growth; or
when the measured temporal contrast between one or more pixels in the first image data and one or more pixels in the second image data does not exceed the threshold temporal contrast value, providing an indication to a user that the second captured image cannot be used to evaluate microbial growth.

22. The method of claim 21 , further comprising:
in response to the indication that the second image data cannot be used to evaluate microbial growth, either: i) further incubating the culture plate for an additional period of time after the second captured image was obtained;
when the additional period of time has elapsed, receiving third image data of the culture plate generated with the image sensor, the third image data representing a third captured image of the culture plate including the plurality of antibiotic disks;
generating pixel characteristic data for pixels of the third image data from a comparison of the second image data and the third image data, the pixel characteristic data indicative of microbial growth on the culture plate over time;
accessing growth modeling data for microbial growth, wherein the growth modeling data models microbial growth for combinations of culture media, microorganisms, antibiotic, antibiotic concentration on the at least one of the plurality of antibiotic disks and in the culture media;
generating simulated image data with the growth model function; and
comparing the simulated image data and the pixel characteristic data and identifying one or more pixel regions in the third image data that differ from one or more p

Assignees

• Bd Kiestra Bv

Inventors

• Marcelpoil Raphael Rodolphe

Classifications

• G06T7/11

  Region-based segmentation · CPC title

• C12Q1/18 Primary

  Testing for antimicrobial activity of a material · CPC title

• G06V20/69

  Microscopic objects, e.g. biological cells or cellular parts · CPC title

• C12Q1/20

  using multifield media · CPC title

• G06T7/90

  Determination of colour characteristics · CPC title