Methods and systems for imaging cells

• US 7,711,174 B2
• Filed: 05/13/2005
• Issued: 05/04/2010
• Est. Priority Date: 05/13/2004
• Status: Active Grant

• Current Assignee: Charles Stark Draper Laboratory Incorporated, University Of Pittsburgh (University of Pittsburgh of The Commonwealth System of Higher Education)
• Original Assignee: Charles Stark Draper Laboratory Incorporated, University of Pittsburgh of The Commonwealth System of Higher Education
• Inventors: Desai, Mukund, Mangoubi, Rami, Sammak, Paul, Jeffreys, Christopher
• Primary Examiner(s): AZARIAN, SEYED H
• Application Number:
  US11/128,612
• Publication Number:
  US 20060039593A1
• Time in Patent Office: 1,817 Days
• Field of Search: 382/100, 382/106, 382/107, 382/128, 382/129, 382/130, 382131-133, 382/168, 382/181, 382/191, 382/203, 382/232, 382/255, 382/260, 382/274, 382/276, 382/291, 382317-321, 250/208.1, 703/2, 600/544, 119/421, 424/278.1, 702/19
• US Class Current: 382/133
• CPC Class Codes: G06F 18/2411 based on the proximity to a decision surface, e.g. support vector machines
• CPC Class Codes: G06T 2207/20084 Artificial neural networks [ANN]
• CPC Class Codes: G06T 2207/30024 Cell structures in vitro; Tissue sections in vitro
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/41 based on statistical description of texture
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 20/69 Microscopic objects, e.g. biological cells or cellular parts

Abstract

The invention generally provides methods and systems for determining characteristics of cellular structures. The methods include non-invasive, non-perturbing, automatable, and quantitative methods and may be applied to the examination of cells such as stem cells, embryos, and egg cells.

Claims

1. A non-invasive, automatable method for determining one or more characteristics of a cell, comprising:

a) capturing an image of a cellular structure of one or more viable cells;

b) using a processor to derive a plurality of image features in a tiered, hierarchical cellular structure paradigm, comprising

i) deriving a plurality of image features from said image at the pixel level in a first tier;

ii) deriving a plurality of image features from said image at the cellular structure level in a second tier; and

c) classifying the cellular structure according to a statistical classification model based on the derived image features;

thereby determining the characteristics of said cell.

2. The method of claim 1, wherein said characteristic is one or more of:

the viability of the cell, the stemness or plasticity of the cell, the suitability for implantation of the cell and the suitability for fertilization of the cell.

3. The method of claim 1, wherein the period between capturing an image is in the range of about 0.001 seconds and about 10,000 seconds.

4. The method of claim 1, wherein said cell is a viable cell.

5. The method of claim 1, wherein said cell is a eukaryotic cell.

6. The method of claim 1, wherein said cell is a mammalian cell.

7. The method of claim 1, wherein said cell is at least one of an egg cell, an embryo, a stem cell, a tumor cell, a differentiated cell, a colon cell, a breast cell, a lung cell, a prostate cell, a pancreatic cell, a kidney cell, an endometrial cell, a cervical cell, an ovarian cell, and a thyroid cell.

8. The method of claim 1, wherein said cellular structure is at least one of a cell colony, a nucleus, cell membrane, cell wall, mitochondria, golgi, chromatin, DNA, cytoskeleton, ribosome, and endoplasmic reticulum.

9. The method of claim 1, wherein the numerical value of image features is derived from the physiological features of the image cells.

10. The method of claim 9, wherein said physiological features include at least one of a cellular border, a colony border, a cell membrane, cell texture, and colony texture.

11. The method of claim 10, wherein a plurality of image features may be captured over a period of time.

12. The method of claim 10, wherein the changes in the image features over a period of time may be correlated to changes in the characteristics of the cell over a period of time.

13. The method of claim 1, wherein external cellular structure data is combined with the derived image features to classify the cellular structure according to a statistical classification model.

14. The method of claim 1, wherein said image features are derived by at least one of wavelet decomposition, multiresolution analysis, time-space frequency analysis, dilate and erode, co-occurrence matrices, Fourier spectral analysis, Gabor methods, wavelet packet decomposition, statistical analysis of wavelet coefficients, Markov Random fields, autoregression models, spatial domain filters, Fourier and Wavelet domain filters, and texture segmentation.

15. The method of claim 1, wherein said image features are derived in a multi-tiered hierarchical cellular structure paradigm, comprising:

a) deriving a plurality of image features at the pixel level in tier 1;

b) deriving a plurality of image features in increasing image resolutions in progressive tiers; and

c) deriving a plurality of image features at the cellular structure level in the final tier.

16. The method of claim 1, wherein said image features are derived in a two-tiered hierarchical cellular structure paradigm, wherein the first tier derives a plurality of image features at the pixel level, and wherein the second tier derives a plurality of image features at the cellular structure level.

17. The method of claim 1, wherein said statistical classification model utilizes a non-parametric class algorithm.

18. The method of claim 1, wherein said statistical classification model includes the application of at least one of Bayes classifiers, discriminant analysis, Parzen windows, multiple hypothesis testing, neural networks, k-nearest neighbors, decision trees, hierarchical clustering, fuzzy methods, component analysis, and support vector machines.

19. The method of claim 1, wherein said statistical classification model includes the application of support vector machines.

20. The method of claim 1, wherein said statistical classification model utilizes a parametric class algorithm.

21. The method of claim 1, wherein said statistical classification model includes the application of Kullback-Leibler Distances.

22. A computer readable medium having computer readable program codes embodied therein for determining one or more characteristics of a cell, the computer readable program codes performing the functions of the methods of claim 1.

23. The method of claim 1, for determining a developmental state of a cell, wherein said classification determines a developmental state of a cell.

24. The method of claim 23, wherein said cell is a stem cell, and wherein said biological state is a state of differentiation.

25. The method of claim 23, wherein said cell is an egg cell, and wherein said biological state is a suitability state for fertilization.

26. The method of claim 23, wherein said cell an embryo, and wherein said biological state is a suitability state for implantation in the uterus.

27. The method of claim 23, wherein said cell is a tumor cell, and wherein said biological state is the tumorigenic state of said tumor cell.

28. The method of claim 1, further comprising deriving a plurality of image features in increasing resolutions in progressive tiers.

29. The method of claim 1, wherein said cell is a stem cell, and wherein said one or more characteristics of the stem cell is stemness or plasticity.

30. The method of claim 1, wherein classifying the cellular structure comprises classifying the cellular structure based on image features derived at the pixel level and at the cellular structure level.

31. A non-invasive system for determining one or more characteristics of a cell, comprising:

a) an image capturing device for capturing at least one image of the cell;

b) a device comprising a processor for deriving a plurality of numerical image features from an image of said cell at the pixel level and at the cellular structure level using a tiered hierarchical cellular structure paradigm; and

c)a device for classifying a cellular structure according to a statistical classification model based on image features derived at the pixel level and at the cellular structure level.

32. The system of claim 31, for determining a developmental state of a cell wherein said classification determines a developmental state of a cell.

33. The system of claim 32, wherein said system further comprises a biological status module for associating said classification with external biological data, to determine the developmental state of a cellular structure.

34. A system for monitoring one or more characteristics of a cell in an environment, comprising:

a) an image input for generating images of a cellular structure;

b) an image analysis module for deriving a plurality of numerical image features from said images at the pixel level and at the cellular structure level using a tiered hierarchical cellular structure paradigm; and

c) a statistical classification module for classifying the cellular structure based on image features derived at the pixel level and at the cellular structure level.

35. The system of claim 34, further comprising one or more sensors for monitoring a plurality of environmental conditions.

36. The system of claim 35, wherein the plurality of sensors include at least one of a temperature sensor, a humidity sensor, a pH sensor, an oxygen sensor, a carbon dioxide sensor, and a nutrient sensor.

37. The system of claim 34, further comprising a classification tracking module maintaining data reflecting environmental conditions detected by the plurality of sensors and the classification of the cellular structure.

38. A system for managing the development of a cell in an environment, comprising

a) an image capture device for generating images of a cellular structure;

b) an image analysis module for deriving a plurality of numerical image features from said images at the pixel level and at the cellular structure level using a tiered hierarchical cellular structure paradigm; and

c) a statistical classification module for classifying the cellular structure based on image features derived at the pixel level and at the cellular structure level; and

d) an environmental control module for altering a condition of the environment based on the classification assigned by the statistical classification module.

39. The system of claim 38, further comprising a plurality of sensors for monitoring a plurality of environmental conditions.

40. The system of claim 39, wherein the plurality of sensors include at least one of a temperature sensor, a humidity sensor, a pH sensor, an oxygen sensor, a carbon dioxide sensor, and a nutrient sensor.

41. The system of claim 38, further comprising a classification tracking module maintaining data reflecting environmental conditions detected by the plurality of sensors and the classification of the cellular structure.

42. The system of claim 38, further comprising a sensor control module for recognizing abnormalities in the plurality of sensors and altering the conditions of the plurality of sensors.