Quantitative measurement of human blastocyst and morula morphology developmental kinetics
Methods, compositions and kits for determining the developmental potential of one or more embryos are provided. These methods, compositions and kits find use in identifying embryos in vitro that are most useful in treating infertility in humans.
1. A method for treating infertility, comprising:
a) providing a computer system comprising:
i) a time-lapse microscope comprising a camera and software for automatically acquiring a series of time-sequential images of one or more human embryos contained in a multi-well culture dish comprising a plurality of microwells with a camera of at least one time-lapse microscope, wherein said one or more human embryos are between about three (3)-five (5) days following fertilization; and
ii) a computer in communication with said microscope, said computer comprising image analysis software;
b) extracting one or more image features from said series of time-sequential images with said image analysis software, wherein said one or more image features comprise a plurality of cell parameters wherein at least one of said plurality of cell parameters is selected from the group consisting of a time from first cleavage to cavitation (tCav) parameter and an average size after initial expansion (Pexp-area) parameter;
c) classifying said one or more human embryos as: i) euploid when said Pexp-area parameter is within 21.25-20.75 k pixels or when said tCav parameter is within 72.65-71.95 hours; or ii) aneuploid when said Pexp-area parameter is within 19.67-16.33 k pixels or when said tCav parameter is within 74.97-73.83 hours;
d) selecting a euploid human embryo based on said classifying; and
e) treating a recipient with in vitro fertilization by single embryo transfer of said selected human embryo.
2. The method of claim 1 wherein said image features include at least one of: cell boundary segment distribution, average intensity at embryo center, or standard deviation of intensity at embryo center.
3. The method of claim 1 further comprising determining a parameter from said image features, wherein said parameter identifies one of:
duration of expansion, duration of collapse, frequency of collapse, degree of expansion, degree of collapse, rate of expansion, rate of collapse, average embryo size after initial expansion and the time interval between expansion and collapse.
4. The method of claim 1 wherein said one or more human embryos have not been frozen.
5. The method of claim 1 wherein said one or more human embryos have been frozen.
6. The method of claim 1 , wherein said image feature is selected from the group consisting of embryo shape, texture in the region defined around the embryo edge, and texture at embryo center.
7. The method of claim 6 , wherein said extracting of said image features is selected from the group consisting of a shape based method, a low level method, a curvature based method and a combination thereof.
8. The method of claim 7 , wherein said shape based method is at least one of template matching, Hough transforms or a combination thereof.
9. The method of claim 1 , wherein said classifying uses a classifier selected from the group consisting of a nave Bayesian classifier, a SVM classifier, a Random Forest classifier and a Boosting Tree classifier.
10. The method of claim 1 , wherein said selected human embryo is euploid and viable.
11. The method of claim 1 , wherein said selecting comprises physically moving said selected human embryo from one location to another.