Methods and systems for automated counting and classifying colonies of microorganisms

A colony-counting system comprising:

• a colony-counting device, wherein the colony-counting device comprises:
• a processor;
• a non-transitory storage medium storing instructions;
• a memory;
• and
• at least one media acquisition device;
• wherein the processor is operably coupled to the memory and the at least one media acquisition device;
• and
• wherein the processor is configured to execute the instructions stored in the non-transitory storage medium to:
• receive at least one input media of an incubated dish from the at least one media acquisition device;
• perform automated quality analysis of the received at least one input media using at least one of reference-based methods and non-reference-based methods, wherein a quality type of the received at least one input media is classified as one of a good quality media or a low quality media;
• if the received at least one input media is classified as good quality media, detect, through a colony detection and separation module using one or more neural network processing methods, at least one colony of the at least one microorganism in a growth medium disposed on the incubated dish by:
• separating foreground regions including the at least one colony from background regions of the at least one input media, wherein the background regions include the incubated dish;
• extracting features from the foreground regions to form a features map, wherein the features include at least one of color, texture, edges, and corners;
• detecting the at least one colony of the at least one microorganism in the growth medium, if the extracted features map with labelled training data, wherein the labelled training data includes a plurality of original media including at least one specific colony of the at least one microorganism and associated label feature data;
• count, through a counting module using at least one learning method, wherein the processor is configured to:
• segregate, using a distance transform and a watershed segmentation method, at least one grouped colony into a first individual colony and a second individual colony;
• classify each of the first and the second individual colonies into at least one species of the at least one microorganism;
• generate at least one output pixel overlay including information about at least one of the at least one bounding box and the at least one free form contour of the at least one colony;
• provide the at least one output pixel overlay to at least one user for validating the classification of the at least one colony of the at least one microorganism into the at least one species;
• and
• re-classify the classified first and the second individual colonies into the at least one species of the at least one microorganism based on inputs received from the at least one user.