Robotic microtool control in an intelligent automated in vitro fertilization and intracytoplasmic sperm injection platform
Disclosed is a method of artificial intelligence-based robotic pipetting for cell preparation. The method includes training an artificial intelligence/machine learning system (AI/ML system) to classify images of biological specimens. The method includes storing the classified images. The method includes receiving an image object from an imaging system that includes a microscopy system, a camera system configured to receive imaging from the microscopy system, and a lighting system configured to illuminate a biological material. The method includes processing the image object, using the AJ/ML system to determine a presence of a retrievable target cell. The method includes positioning a robotic pipettor at a target physical orientation relative to the retrievable target cell. The method includes confirming the robotic pipettor's location at the target physical orientation, using AI/ML system. The method includes instructing the robotic pipettor to obtain the retrievable target cell from the target physical orientation.
1. A method of artificial intelligence-based robotic pipetting for spermatozoa preparation, comprising:
positioning a vessel containing a semen sample;
receiving by an artificial intelligence/machine learning system (AI/ML system) an image object from an imaging system that includes a microscopy system, a camera system, and a lighting system;
determining a semen liquefaction state of the semen sample based at least in part on the image object, by comparing the determined semen liquefaction state to a stored liquefaction state criterion using the AI/ML system to confirm the adequacy of the determined liquefaction state for spermatozoa collection;
determining, using the AI/ML system, a sperm characteristic within the semen sample based at least in part on the image object;
comparing the determined sperm characteristic and motility fraction to a stored sperm criterion using the AI/ML system to confirm the adequacy of the determined sperm characteristic and motility fraction for spermatozoa collection;
determining, using the AI/ML system, a rate of spermatozoa movement based at least in part on the image object;
comparing the determined rate of spermatozoa movement to a stored movement criterion using the AI/ML system to confirm the adequacy of the determined rate of spermatozoa movement for spermatozoa separation;
using the AI/ML system to instruct a robotic pipettor to collect a sperm within the semen sample upon confirmation of adequacy of the determined liquefaction state, determined sperm characteristic and motility fraction, and determined spermatozoa movement; and
collecting at least one sperm within the robotic pipettor.
2. The method of claim 1 wherein the positioning of the vessel is made at least in part by rotating the vessel using a staging system controlled by the AI/ML system.
3. The method of claim 1 wherein the rate of spermatozoa movement is at least one of a measure of vertical movement, a measure of horizontal movement, or a measure of angular movement.
4. The method of claim 1 wherein the sperm characteristic is at least one of a sperm count, a motility parameter, or a morphology measure.
5. The method of claim 1 wherein the AI/ML system uses at least one neural network.
6. The method of claim 1 wherein the sperm collected by the robotic pipettor is a plurality of sperm.