Automatic Cell Migration and Proliferation Analysis

• US 20100080439A1
• Filed: 04/06/2009
• Published: 04/01/2010
• Est. Priority Date: 04/04/2008
• Status: Active Grant

• Current Assignee: Asaad Said, Lina Jamil Karam
• Original Assignee: Asaad Said, Lina Jamil Karam
• Inventors: Karam, Lina Jamil, Said, Asaad
• Granted Patent: US 9,082,164 B2
• Time in Patent Office: Days
• US Class Current: 382/133
• CPC Class Codes: G06T 2207/20104 Interactive definition of region of interest [ROI]
• CPC Class Codes: G06T 2207/20161 Level set
• 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 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/41 based on statistical description of texture
• CPC Class Codes: G06V 20/693 Acquisition
• CPC Class Codes: G06V 20/695 Preprocessing, e.g. image segmentation

Abstract

The disclosed methods and apparatus provide for the automatic segmentation and analysis of the overall migration rate and proliferation rate of cells that may be used with any resolution image and without the need to prepare the sample or the image before the image is analyzed. In particular embodiments, the method or apparatus of analyzing a cell image comprise performing a structure tensor analysis and/or regularization and/or a histogram-based analysis and/or a level-set analysis to classify pixels in the image into a region of interest (ROI), corresponding to cell clusters, and a non-significant region. Methods and apparatus for cell migration analysis comprise means for computing the areas of the segmented ROIs for a set of images. Methods and apparatus for cell proliferation analysis comprise means for counting the number of cells within the segmented ROIs for a set of images.

Claims

1. A method of analyzing and segmenting an image of cells, comprising:

a. means for detecting high-activity regions or textured regions in said image,

b. means for segmenting clusters of cells within said regions.

2. The method of claim 1, wherein said means for detecting and/or said means for segmenting comprise performing a structure tensor analysis.

3. The method of claim 2, wherein said structure tensor analysis comprises a structure tensor vector or a structure tensor vector amplitude.

4. The method of claim 1, further comprising means for regularizing the said regions.

5. The method of claim 4, wherein said means for regularizing comprises a morphological closing operation.

6. The method of claim 4, wherein said means for regularizing comprises a wavelet-based decomposition.

7. The method of claim 4, wherein said means for regularizing comprises a non-linear diffusion filter.

8. The method of claim 1, further comprising means for binarizing and/or means for labeling the said regions.

9. The method of claim 8, wherein said means for binarizing comprises a histogram-based thresholding.

10. The method of claim 1, wherein said means for segmenting comprises a level-set segmentation.

11. The method of claim 10, wherein said level-set segmentation comprises a one-function level-set segmentation or a statistical level-set segmentation.

12. The method of claim 1, wherein said means for detecting and/or said means for segmenting comprises a histogram-based thresholding.

13. The method of claim 1, wherein said means for detecting and/or said means for segmenting comprise a level-set based segmentation.

14. The method of claim 13, wherein said level-set segmentation comprises a weighted level-set segmentation or a two-step level-set segmentation.

15. The method of claim 1, further comprising means for computing areas of said clusters of cells.

16. The method of claim 1, further comprising means for counting cells in said clusters of cells.

17. A method of analyzing and segmenting an image of cells, comprising:

a. means for identifying, within said image, regions subsuming said cells,

b. means for segmenting clusters of said cells within said regions.

18. The method of claim 17, wherein said means for identifying and/or said means for segmenting comprise a level-set based segmentation.

19. The method of claim 18, wherein said level-set segmentation comprises a weighted level-set segmentation or a two-step level-set segmentation or a one-function level-set segmentation or a statistical level-set segmentation.

20. The method of claim 17, wherein said means for identifying and/or said means for segmenting comprise performing a structure tensor analysis.

21. The method of claim 20, wherein said structure tensor analysis comprises a structure tensor vector or a structure tensor vector amplitude.

22. The method of claim 17, further comprising means for regularizing the said regions.

23. The method of claim 22, wherein said means for regularizing comprises a morphological closing operation.

24. The method of claim 22, wherein said means for regularizing comprises a wavelet-based decomposition.

25. The method of claim 22, wherein said means for regularizing comprises a non-linear diffusion filter.

26. The method of claim 17, further comprising means for binarizing and/or means for labeling the said regions.

27. The method of claim 26, wherein said means for binarizing comprises a histogram-based thresholding.

28. The method of claim 17, wherein said means for identifying and/or said means for segmenting comprises a histogram-based thresholding.

29. The method of claim 17, further comprising means for computing areas of said clusters of cells.

30. The method of claim 17, further comprising means for counting cells in said clusters of cells.

31. An apparatus for analyzing and segmenting an image of cells, comprising:

a. an interface configured to receive said image,

b. a memory for storing, at least temporarily, some or all of said image,

c. one or more processors in communication with said memory and designed or configured to detect regions subsuming said cells and/or segment clusters of cells within said image and/or determine areas of said clusters of cells and/or count cells within said clusters of cells.

32. The apparatus of claim 31, wherein the one or more processors detect said regions and/or segment said clusters of cells by performing a level-set based segmentation.

33. The apparatus of claim 31, wherein the one or more processors detect said regions and/or segment said clusters of cells by performing a structure tensor analysis.

34. The apparatus of claim 33, wherein said structure tensor analysis comprises computing a structure tensor vector or a structure tensor vector amplitude.

35. The apparatus of claim 31, wherein the one or more processors perform a regularization of the said regions.

36. The apparatus of claim 35, wherein said regularization comprises a morphological closing operation.

37. The apparatus of claim 35, wherein said regularization comprises a wavelet-based decomposition.

38. The apparatus of claim 35, wherein said regularization comprises a non-linear diffusion filter.

39. The apparatus of claim 31, wherein the one or more processors perform a binarization and/or labeling of the said regions.

40. The apparatus of claim 39, wherein said binarizing comprises a histogram-based thresholding.

41. The apparatus of claim 31, wherein the one or more processors detect said regions and/or segment said clusters of cells by performing a histogram-based thresholding.