Mathematical image analysis based cell reprogramming with applications for epigenetic and non-epigenetic base induced pluripotent stem cell derivation
View Patent ↗Mathematical and statistical image analysis methods and systems are applied to enhance and refine the process of reprogramming cells, for example, to modify cells from patients into custom-matched stem cells.
1. A method for identifying induced pluripotent stem cells, comprising:
(a) obtaining an image of one or more cells including a mix of at least feeder cells and induced pluripotent stem cells;
(b) representing the image as a multiplicity of pixels;
(c) using a processor to extract one or more image features from said multiplicity of pixels;
(d) comparing the one or more image features with image features derived from one or more pluripotent stem cells, wherein the processor applies one or more statistical comparison methods to compare the image features; whereby induced pluripotent stem cells are identified within the mix of cells.
2. The method of claim 1 , wherein the one or more cells is a colony of cells.
3. The method of claim 1 , wherein the image contains the nucleus of one cell.
4. The method of claim 1 , wherein the image feature is texture.
5. The method of claim 4 , wherein the texture corresponds to a morphological structure of the cell.
6. The method of claim 4 , wherein the texture is heterogeneous.
7. The method of claim 1 , further comprising:
(e) performing simultaneous smoothing and segmentation of said image;
(f) determining one or more boundaries of said cell;
(g) identifying a region or subregion near to said one or more boundaries;
(h) deriving one or more attributes of region or subregion;
(i) analyzing variation in said one or more attributes; wherein said one or more image features comprise components of said one or more attributes.
8. The method of claim 1 , wherein the one or more image features are extracted using a wavelet decomposition algorithm.
9. The method of claim 8 , wherein the wavelet algorithm is an n-level decomposition that yields three detail subbands per level.
10. The method of claim 9 , wherein one of each of the three detail subbands per level are orientated horizontally, vertically, and diagonally.
11. The method of claim 1 , wherein the one or more statistical methods is a comparison of probability density functions.
12. The method of claim 11 , wherein one or more areas of the one or more images are classified using a clustering algorithm.
13. The method of claim 12 , wherein dissimilarity between the one or more image features is calculated using a pdf estimator and quantified using information divergence.
14. The method of claim 13 , wherein dissimilarity is calculated using a Kullback-Leibler divergence (KLD).
15. The method of claim 13 , wherein the method used to estimate the pdf and KLD is selected from: a generalized Gaussian density model (GGD); a symmetric alpha-stable (S.alpha.S) Density Model; an Ahmad-Lin (A-L) KLD Estimation; and a Loftsgaarden-Quesenberry (L-Q) KLD Estimation.
16. The method of claim 13 , wherein the one or more windows are classified, subdivided, and re-classified.
17. The method of claim 11 , wherein the clustering algorithm is selected from the k-Nearest Neighbor (kNN) algorithm and the Support Vector Machine (SVM).
18. The method of claim 17 , further comprising subdividing the image of one or more cells into one or more windows.
19. The method of claim 1 , wherein the induced pluripotent stem cells are contained in a heterogeneous mixture of cells.