Detecting a condition for a culture device using a machine learning model

1 . A method of processing, using a colony enumeration device, an input image of a culture device for a condition, comprising:

receiving, by the colony enumeration device, the input image;

classifying, on the colony enumeration device, the input image with a machine learning model, the machine learning model that is configured to be trained on a training set of images having the condition;

determining that the condition exists in the input image based on the classification;

performing at least one action in response to the determination that the condition exists;

wherein the condition is a too numerous to count condition or indication thereof;

further comprising training the machine learning model on the training set of images to classify a condition on the culture device;

wherein training the machine learning model further comprises:

receiving the training set of images comprising a plurality of training images related to a plurality of culture devices:

establishing a ground truth for a class label with a bounding box on at least some of the plurality of training images in the training set, the bounding box encompasses at least a majority of a growth compartment of a culture device on a training image, wherein the class label is associated with the condition;

providing the training set of images to the machine learning model; and

allowing the machine learning model to analyze the plurality of training images to train the machine learning model and form a trained machine learning model.

2 . The method of claim 1 , wherein the machine learning model is a deep learning model using a neural network circuitry, further comprising:

extracting, with the deep learning model, a proposed region of the input image, the input image being an input to the deep learning model; and

classifying, with a classifier, the input image based on the proposed region, the proposed region being an input to the classifier.

3 . The method of claim 1 , wherein the determining that the condition exists comprises:

applying the machine learning model to the image to determine a probability that the condition exists in the proposed region and an extent of the proposed region;

determining if the probability and the extent are within a threshold; and

determining that the condition exists if the threshold is satisfied by the probability and the extent.

4 . The method of claim 1 , wherein performing at least one action comprises communicating to a user interface on a display device that the condition exists for the image.

5 . The method of claim 1 , wherein performing at least one action comprises ejecting, with a feed mechanism, the culture device.

6 . The method of claim 1 , wherein the bounding box is expanded past the condition on the training image to establish the ground truth.

7 . The method of claim 1 , further comprising pre-processing the plurality of training images from the training set.

8 . The method of claim 1 , wherein the plurality of training images are partially cropped.

9 . The method of claim 1 , the bounding box includes areas of the training image without the condition.

10 . The method of claim 1 , wherein the bounding box does not encompass a substrate of the culture device.

11 . The method of claim 10 , wherein the bounding box encompasses an entire growth compartment of the culture device.

12 . The method of claim 11 , wherein the bounding box encompasses at least a portion of a substrate.

13 . The method of claim 12 , wherein the bounding box encompasses an entire culture device in the training image.

14 . The method of claim 12 , wherein the bounding box encompasses a fiducial on the substrate.

15 . The method of claim 1 , further comprising providing the trained machine learning model to a colony enumeration device, the colony enumeration device configured to analyze a plurality of input images.

16 . A colony enumeration device comprising:

neural network circuitry configured to use the machine learning model;

a processor; and

a memory storing instructions that, when executed by the processor, configure the colony enumeration device to perform the method of claim 1 .