METHODS AND SYSTEMS FOR CLASSIFICATION OF EGGS AND EMBRYOS USING MORPHOLOGICAL AND MORPHO-KINETIC SIGNATURE
Methods and systems are described for classifying unfertilized eggs. For example, using control circuitry, first images of fertilized eggs can be received, and the first images can be labeled with known classifications. Using the control circuitry, an artificial neural network can be trained to detect the known classifications based on the first images of the fertilized eggs and a second image can be received of an unfertilized egg with an unknown classification. Using the control circuitry, the second image can be input into the trained artificial neural network and a prediction from the trained artificial neural network can be received that the second image corresponds to one or more of the known classifications.
1 - 9 . (canceled)
10 . A method of classifying unfertilized eggs, the method comprising:
receiving, using control circuitry, first images of fertilized eggs;
labeling, using the control circuitry, the first images with known classifications;
training, using the control circuitry, an artificial neural network to detect the known classifications based on the first images of the fertilized eggs;
receiving, using the control circuitry, a second image of an unfertilized egg with an unknown classification;
inputting, using the control circuitry, the second image into the trained artificial neural network; and
receiving, using the control circuitry, a prediction from the trained artificial neural network that the second image corresponds to one or more of the known classifications.
11 . The method of claim 10 , wherein the first images of the fertilized eggs are acquired prior to a first cell split.
12 . The method of claim 10 , wherein the known classifications include one or more of a predicted implantation quality, a predicted preimplantation genetic screening result, a likelihood of viability, a prediction of the future development of a morphological feature, a predicted birth weight, or a predicted gender.
13 . The method of claim 10 , wherein the second image is a portion of time-lapse imaging of the unfertilized egg and the known classifications include one or more aspects that occur after fertilization.
14 . The method of claim 13 , wherein the one or more aspects includes formation of a blastocyst.
15 . A system for classifying unfertilized eggs, the system comprising:
memory configured to store an artificial neural network; and
control circuitry configured to:
receive, using control circuitry, first images of fertilized eggs;
label, using the control circuitry, the first images with known classifications;
train, using the control circuitry, the artificial neural network to detect the known classifications based on the first images of the fertilized eggs;
receive, using the control circuitry, a second image of an unfertilized egg with an unknown classification;
input, using the control circuitry, the second image into the trained artificial neural network; and
receive, using the control circuitry, a prediction from the trained artificial neural network that the second image corresponds to one or more of the known classifications.
16 . The system of claim 15 , wherein the first images of the fertilized eggs are acquired prior to a first cell split.
17 . The system of claim 15 , wherein the known classifications include one or more of a predicted implantation quality, a predicted preimplantation genetic screening result, a likelihood of viability, a prediction of the future development of a morphological feature, a predicted birth weight, or a predicted gender.
18 . The system of claim 15 , wherein the second image is a portion of time-lapse imaging of the unfertilized egg and the known classifications include one or more aspects that occur after fertilization.
19 . The system of claim 18 , wherein the one or more aspects includes formation of a blastocyst.
20 . A non-transitory computer-readable medium for classifying unfertilized eggs comprising instructions that, when executed by one or more processors, cause operations comprising:
receiving, using control circuitry, first images of fertilized eggs;
labeling, using the control circuitry, the first images with known classifications;
training, using the control circuitry, an artificial neural network to detect the known classifications based on the first images of the fertilized eggs;
receiving, using the control circuitry, a second image of an unfertilized egg with an unknown classification;
inputting, using the control circuitry, the second image into the trained artificial neural network; and
receiving, using the control circuitry, a prediction from the trained artificial neural network that the second image corresponds to one or more of the known classifications.
21 . The computer-readable medium of claim 20 , wherein the first images of the fertilized eggs are acquired prior to a first cell split.
22 . The computer-readable medium of claim 20 , wherein the known classifications include one or more of a predicted implantation quality, a predicted preimplantation genetic screening result, a likelihood of viability, a prediction of the future development of a morphological feature, a predicted birth weight, or a predicted gender.
23 . The computer-readable medium of claim 20 , wherein the second image is a portion of time-lapse imaging of the unfertilized egg and the known classifications include one or more aspects that occur after fertilization.
24 . The computer-readable medium of claim 23 , wherein the one or more aspects includes formation of a blastocyst.