A METHOD AND SYSTEM FOR AUTOMATED MICROBIAL COLONY COUNTING FROM STREAKED SAPLE ON PLATED MEDIA

• US 20180112173A1
• Filed: 04/22/2016
• Published: 04/26/2018
• Est. Priority Date: 04/23/2015
• Status: Active Grant

• Current Assignee: BD Kiestra B.V. (Becton, Dickinson & Co)
• Original Assignee: BD Kiestra B.V. (Becton, Dickinson & Co)
• Inventors: WILES, TIMOTHY M, Marcelpoil, Raphael R.
• Granted Patent: US 10,696,938 B2
• Time in Patent Office: Days
• CPC Class Codes: C12M 41/36 of biomass, e.g. colony counters or by turbidity measurements electrooptical investigation of individual particles G01N15/14, flow cytometers G01N15/1404
• CPC Class Codes: C12Q 1/02 involving viable microorganisms
• CPC Class Codes: G06T 2207/10056 Microscopic image
• CPC Class Codes: G06T 2207/30024 Cell structures in vitro; Tissue sections in vitro
• CPC Class Codes: G06T 7/0016 involving temporal comparison
• CPC Class Codes: G06V 20/695 Preprocessing, e.g. image segmentation
• CPC Class Codes: G06V 20/698 Matching; Classification

Abstract

An imaging system and method for microbial growth detection, counting or identification. One colony may be contrasted in an image that is not optimal for another type of colony. The system and method provides contrast from all available material through space (spatial differences), time (differences appearing over time for a given capture condition) and color space transformation using image input information over time to assess whether microbial growth has occurred for a given sample.

Claims

1. An automated method for evaluating microbial growth on plated media, the method comprising:

providing a culture media inoculated with a biological sample;

incubating the inoculated culture media;

following incubation, obtaining a first image of the inoculated media at a first time (t₁);

after further incubation, obtaining a second image of the inoculated media at a second time (t₂);

aligning the first image with the second image, such that the coordinates of a pixel in the second image are about the same as the coordinates of a corresponding pixel in the first image;

comparing image features of the second image with image features of the first image;

classifying image features of the second image as colony candidates based on image feature changes from time t₁ to time t₂;

for colony candidates determined to be from a common microorganism in the biological sample inoculated on the culture media, counting said colony candidates; and

determining whether the number of counted colonies meets or exceeds a threshold count value stored in memory and indicative of significant growth.

2. The method of claim 1 wherein if the number of counted colonies meets or exceeds the threshold value, the method further comprises:

identifying at least one of the colonies using matrix-assisted laser desorption ionization (MALDI); and

testing said at least one colony for antibacterial susceptibility; and

outputting a report containing the MALDI and antibacterial susceptibility test results.

3. The method of either one of claim 2 wherein a plurality of threshold count values are stored in memory, each threshold count value associated with a different microorganism.

4. The method of claim 3 wherein classifying image features of the second image as colony candidates comprises:

determining contrast information of the second image, the contrast information including at least one of;

spatial contrast information indicating differences between pixels of the second image; and

temporal contrast information indicating differences between pixels of the second image and corresponding pixels of a previous image;

identifying an object in the second image based on the contrast information; and

obtaining one or more object features of the identified object from pixel information associated in the first and second images, wherein the object is classified as a colony candidate based on the object features.

5. The method of claim 4 further comprising, for each colony candidate, determining whether the colony candidate is a colony or an artifact based on pixel information associated with the colony candidate, wherein colony candidates that are determined to be artifacts are not counted.

6. The method of claim 5 wherein determining whether a colony candidate is a colony or an artifact further comprises determining whether the colony candidate is present in each of the first and second images and larger in the second image than the first image by a threshold growth factor, wherein a colony candidate that is present in both images and is larger in the second image by at least the threshold growth factor is classified as a colony.

7. The method of claim 6 wherein determining whether a colony candidate is a colony or an artifact further comprises, for a colony candidate that is present in the second image and not the first image:

obtaining one or more object features of the identified object from the pixel information associated with the object in the second image;

determining a probability that the colony candidate is a colony based on the one or more object features; and

comparing the determined probability to a predefined threshold probability value, wherein, if the determined probability is greater than the predefined threshold probability value, then the colony candidate is classified as a colony.

8. The method of claim 7 further comprising:

classifying (i) colony candidates that are present in both images and not larger in the second image, and (ii) colony candidates that are present in first image and not in the second image, as definite artifacts;

classifying colony candidates that are present in each of the first and second images and larger in the second image by the threshold growth factor as definite colonies; and

calculating an artifact probability value based on a combination of the definite artifacts and the definite colonies, wherein the determined probability that a colony candidate is a colony is further based on artifact probability.

9. The method of claim 8 wherein the object features comprise at least one of object shape, object size, object edge and object color.

10. The method of claim 9 wherein the object features comprise at least one of color, hue, luminance and chrominance of the pixels of the object.

11. The method of claim 10 further comprising obtaining background feature information, wherein background feature information comprises media type and media color, and wherein the object is classified as a colony candidate based further on the background feature information.

12. The method of claim 11 wherein aligning the first image with the second image involves assigning polar coordinates to pixels of each of the first and second images such that the polar coordinates of a pixel in the second image are the same as the polar coordinates of a corresponding pixel in the first image.

13. An automated method for estimating a number of colony forming units on plated media that has been inoculated with a culture according to a predefined pattern and incubated, the method comprising:

after incubation of the culture, obtaining a digital image of the plated media;

from the digital image, identifying colony candidates in the image;

linearizing the digital image according to the predefined pattern;

plotting the colony candidates according to pixels of the linearized coordinates of the digital image; and

estimating the number of colony forming units on the plated media based on pixels of the colony candidates in the linearized digital image.

14. The method of claim 13 wherein the plated media from which the image was obtained was inoculated using a magnetically controlled bead streaked along a continuous zig-zag pattern, wherein the digital image is linearized according to the zig-zag streaking pattern with the zig-zag streaking pattern being a main axis of the linearized image.

15. The method of claim 14 wherein the initial bead load of the magnetically controlled bead is estimated from the plot of colony candidates.

16. The method of claim 15 wherein estimating the initial bead load comprises:

selecting a distance from origin along the main axis of the linearized image;

determining a probability that a colony forming unit is released by the bead at the selected distance; and

counting the number of colony forming units present in the digital image that are farther from origin along the main axis than the selected distance,

wherein the estimated initial bead load is equal to the ratio between said determined probability and said counted number of colony forming units.

17. The method of claim 16 wherein the distance is selected such that no confluent regions of microbial growth are present in the image at a distance farther from an origin of the linearized image than the selected distance.

18. The method of claim 16 further comprising:

selecting a plurality of distances along the main axis of the linearized image;

for each of the selected distances, counting the number of colony forming units present in the digital image that are farther from an origin of the linearized image along the main axis than the selected distance; and

based on the counted number of colony forming units for each distance, calculating a probability that a colony forming unit is released onto the media by the bead when a point of the bead containing the colony forming unit makes contact with the media,

wherein determining a probability that a colony forming unit is released by the bead at a given distance is based on said calculated probability that a colony forming unit is released onto the media by the bead when a point of the bead containing the colony forming unit makes contact with the media.

19. The method of claim 18 further comprising:

comparing the digital image to a plurality of distribution models stored in memory, each distribution model showing an expected distribution of colony forming units across an imaged plate for a given initial bead load, and a given probability that a colony forming unit is released onto the media when contact is made with the media; and

determining the initial bead load based at least in part on the compared distribution models.

20. The method of claim 18 further comprising:

selecting a distance from the origin along the main axis of the linearized image;

determining a fraction of pixels at the selected distance that are associated with a colony candidate; and

estimating the initial bead load based on said determined fraction.

21. The method of claim 18, further comprising:

after incubation of the culture, obtaining a plurality of digital images of the plated media, each digital image containing one or more colony candidates;

identifying one digital image in which at least some of the colony candidates form a confluent region;

identifying an earlier digital image in which said colony candidates that form the confluent region in the digital image have not combined to form a confluent region; and

estimating the number of colony forming units in the confluent region based on the earlier digital image.

22. A computer-readable memory storage medium having program instructions encoded thereon configured to cause a processor to perform a method of evaluating microbial growth on plated media, the method comprising:

following incubation of a culture media inoculated with a biological sample for first predetermined time, instructing an image acquisition device to obtain a first image of the inoculated media at a first time (t₁);

after further incubation a culture media inoculated with a biological sample for a second predetermined time, obtaining a second image of the inoculated media at a second time (t₂);

aligning the first image with the second image, such that the coordinates of a pixel in the second image are about the same as the coordinates of a corresponding pixel in the first image;

comparing image features of the second image with image features of the first image;

classifying image features of the second image as colony candidates based on image feature changes from time t₁ to time t₂;

for colony candidates determined to be from a common microorganism in the biological sample inoculated on the culture media, counting said colony candidates; and

determining whether the number of counted colonies meets or exceeds a threshold count value stored in memory and indicative of significant growth.

23. A computer-readable memory storage medium having program instructions encoded thereon configured to cause a processor to perform a method of estimating a number of colony forming units on plated media, the method comprising:

at a predetermined incubation time of a culture media inoculated with a biological sample, instructing the image acquisition device to obtain a digital image of the plated media;

from the digital image, identifying colony candidates in the image;

linearizing the digital image according to the predefined pattern;

plotting the colony candidates according to pixels of the linearized coordinates of the digital image; and

estimating the number of colony forming units on the plated media based on pixels of the colony candidates in the linearized digital image.

24. A system for evaluating growth in a culture media inoculated with a biological sample, the system comprising:

an image acquisition device for capturing digital images of the culture media;

memory storing information regarding predicted amounts of microbial growth for one or more different organisms in one or more different culture media; and

one or more processors operable to execute instructions to perform a method comprising;

following incubation of a culture media inoculated with a biological sample for first predetermined time, instructing an image acquisition device to obtain a first image of the inoculated media at a first time (t₁);

after further incubation a culture media inoculated with a biological sample for a second predetermined time, obtaining a second image of the inoculated media at a second time (t₂);

aligning the first image with the second image, such that the coordinates of a pixel in the second image are about the same as the coordinates of a corresponding pixel in the first image;

comparing image features of the second image with image features of the first image;

classifying image features of the second image as colony candidates based on image feature changes from time t₁ to time t₂;

for colony candidates determined to be from a common microorganism in the biological sample inoculated on the culture media, counting said colony candidates; and

determining whether the number of counted colonies meets or exceeds a threshold count value stored in memory and indicative of significant growth.

25. A system for evaluating growth in a culture media inoculated with a biological sample, the system comprising:

an image acquisition device for capturing digital images of the culture media;

memory storing information regarding a pattern for inoculating the culture media with the biological sample; and

one or more processors operable to execute instructions to perform a method comprising;

at a predetermined incubation time of a culture media inoculated with a biological sample, instructing the image acquisition device to obtain a digital image of the plated media;

from the digital image, identifying colony candidates in the image;

linearizing the digital image according to the predefined pattern;

plotting the colony candidates according to pixels of the linearized coordinates of the digital image; and

estimating the number of colony forming units on the plated media based on pixels of the colony candidates in the linearized digital image.