Method and apparatus for automated image analysis of biological specimens

• US 20050185832A1
• Filed: 04/26/2005
• Published: 08/25/2005
• Est. Priority Date: 11/30/1995
• Status: Active Grant

• Current Assignee: Carl Zeiss Microimaging Ais, Inc. (Carl-Zeiss-Stiftung)
• Original Assignee: Clariant GmbH (Clariant AG)
• Inventors: Riding, Thomas J., Ring, James E., Douglass, James W.
• Granted Patent: US 7,133,545 B2
• Time in Patent Office: Days
• US Class Current: 382/133
• CPC Class Codes: G01N 1/312 for samples mounted on planar substrates
• CPC Class Codes: G01N 15/1433 using image recognition
• CPC Class Codes: G01N 15/1468 with spatial resolution of the texture or inner structure of the particle
• CPC Class Codes: G01N 15/1475 using image analysis for extracting features of the particle
• CPC Class Codes: G01N 2015/1472 with colour
• CPC Class Codes: G01N 2015/1488 Methods for deciding
• CPC Class Codes: G01N 2015/1497 Particle shape
• CPC Class Codes: G02B 21/244 using image analysis techniques
• CPC Class Codes: G02B 21/367 providing an output produced by processing a plurality of individual source images, e.g. image tiling, montage, composite images, depth sectioning, image comparison
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes
• CPC Class Codes: G06V 20/69 Microscopic objects, e.g. biological cells or cellular parts
• CPC Class Codes: G06V 20/693 Acquisition

Abstract

A method and apparatus for automated cell analysis of biological specimens automatically scans at a low magnification to acquire images which are analyzed to determine candidate cell objects of interest. The low magnification images are converted from a first color space to a second color space. The color space converted image is then low pass filtered and compared to a threshold to remove artifacts and background objects from the candidate object of interest pixels of the color converted image. The candidate object of interest pixels are morphologically processed to group candidate object of interest pixels together into groups which are compared to blob parameters to identify candidate objects of interest which correspond to cells or other structures relevant to medical diagnosis of the biological specimen. The location coordinates of the objects of interest are stored and additional images of the candidate cell objects are acquired at high magnification. The high magnification images are analyzed in the same manner as the low magnification images to confirm the candidate objects of interest which are objects of interest. A high magnification image of each confirmed object of interest is stored for later review and evaluation by a pathologist.

Claims

1. A method, comprising:

identifying a sample area of a sample holder, the sample area including a biological sample;

receiving image data indicative of a first portion of the sample area, the image data including first color pixel data and second color pixel data for each of a plurality of pixels;

transforming the image data to generate transformed pixel data for each of the plurality of pixels which is in a different format than said image data, and which transformed pixel data includes information indicative of both a value of the first color pixel data and a value of the second color pixel data for the associated pixel.

2. The method of claim 1, wherein the transformed pixel data includes a value indicative of a ratio of the value of the first color pixel data to the value of the second color pixel data.

3. The method of claim 1, wherein the transformed pixel data for each of the plurality of pixels includes a value indicative of at least one of a hue value, a saturation value, and an intensity value.

4. The method of claim 1, wherein the biological sample includes an object of interest and further comprising:

processing the transformed pixel data to identify data indicative of the object of interest.

5. The method of claim 1, wherein identifying the sample area of a sample holder comprises:

acquiring a first image of at least a portion of the sample holder;

receiving data indicative of texture information of the first image;

analyzing the data indicative of the texture information to determine information indicative of a location of at least a portion of an edge of the biological sample; and

storing the information indicative of the location of the at least a portion of the edge of the biological sample.

6. The method of claim 1, wherein identifying the sample area of the sample holder comprises:

obtaining image information of the sample holder, the image information including texture information;

determining imaging parameters indicative of a location of an outer edge of the biological sample using the texture information; and

identifying the sample area of the sample area using the location of the outer edge of the biological sample.

7. The method of claim 6, further comprising:

acquiring image information corresponding to the first portion of the sample area.

8. The method of claim 7, further comprising:

digitizing the image information corresponding to the first portion of the sample area to obtain the image data indicative of the first portion of the sample area.

9. The method of claim 7, further comprising:

acquiring image information corresponding to a plurality of portions of the sample area using an imaging system, the plurality of portions of the sample area spanning the sample area, wherein acquiring image information corresponding to a plurality of portions of the sample area comprises;

acquiring image information corresponding to the first portion of the sample area;

moving the sample holder relative to the imaging system; and

acquiring image information corresponding to a different portion of the plurality of portions of the sample area.

10. The method of claim 9, wherein the first portion of the sample area partially overlaps the different portion of the sample area.

11. The method of claim 1, wherein the first color pixel data comprises data indicative of a value of one of a red pixel channel, a blue pixel channel, and a green pixel channel of an image detector of an imaging system.

12. The method of claim 11, wherein the image detector comprises a charge coupled device.

13. The method of claim 11, wherein the second color pixel data comprises data indicative of a value of a different one of the red pixel channel, the blue pixel channel, and the green pixel channel of the image detector of the imaging system.

14. The method of claim 13, wherein the biological sample is a pre-processed biological sample including one or more pre-processed objects of interest, and wherein the transformed pixel data comprises data indicative of a ratio of the first color pixel data and the second color pixel data.

15. The method of claim 14, wherein the pre-processed object of interest comprises one or more cells stained to increase the value of the first color pixel data.

16. The method of claim 1, where said transforming comprises transforming in color space.

17. An article comprising a machine-readable medium embodying information indicative of instructions that when performed by one or more machines result in operations comprising:

automatically identifying a sample area of a sample holder, the sample area including a biological sample;

receiving image data indicative of a first portion of the sample area, the image data including first color pixel data and second color pixel data for each of a plurality of pixels;

transforming the image data to generate transformed pixel data for each of the plurality of pixels which is in a different format than said image data, and which transformed pixel data includes information indicative of both a value of the first color pixel data and a value of the second color pixel data for the associated pixel.

18. The article of claim 17, wherein the transformed pixel data for each of the plurality of pixels includes a value indicative of a ratio of the value of the first color pixel data to the value of the second color pixel data.

19. The article of claim 17, wherein the transformed pixel data for each of the plurality of pixels includes a value indicative of at least one of a hue value, a saturation value, and an intensity value.

20. The article of claim 17, wherein the biological sample includes an object of interest and further comprising:

processing the transformed pixel data to identify data indicative of the object of interest.

21. The article of claim 17, wherein automatically identifying the sample area of a sample holder comprises:

receiving image data indicative of a first image of at least a portion of the sample holder;

analyzing the image data to determine data indicative of texture information;

determining information indicative of a location of at least a portion of an edge of the biological sample using the data indicative of texture information; and

storing the information indicative of the location of the at least a portion of the edge of the biological sample.

22. The article of claim 17, wherein automatically identifying the sample area of the sample holder comprises:

obtaining image information of the sample holder, the image information including texture information;

determining imaging parameters indicative of a location of an outer edge of the biological sample using the texture information; and

identifying the sample area of the sample area using the location of the outer edge of the biological sample.

23. The article of claim 22, the operations further comprising:

acquiring image information corresponding to the first portion of the sample area.

24. The article of claim 23, the operations further comprising:

digitizing the image information corresponding to the first portion of the sample area to obtain the image data indicative of the first portion of the sample area.

25. The article of claim 23, the operations further comprising:

acquiring image information corresponding to a plurality of portions of the sample area using an imaging system, the plurality of portions of the sample area spanning the sample area, wherein acquiring image information corresponding to a plurality of portions of the sample area comprises;

acquiring image information corresponding to the first portion of the sample area;

moving the sample holder relative to the imaging system; and

acquiring image information corresponding to a different portion of the plurality of portions of the sample area.

26. The article of claim 25, wherein the first portion of the sample area partially overlaps the different portion of the sample area.

27. The article of claim 17, wherein the first color pixel data comprises data indicative of a value of one of a red pixel channel, a blue pixel channel, and a green pixel channel of an image detector of an imaging system.

28. The article of claim 27, wherein the image detector comprises a charge coupled device.

29. The article of claim 27, wherein the second color pixel data comprises data indicative of a value of a different one of the red pixel channel, the blue pixel channel, and the green pixel channel of the image detector of the imaging system.

30. The article of claim 29, wherein the biological sample is a pre-processed biological sample including one or more pre-processed objects of interest, and wherein the transformed pixel data comprises data indicative of a ratio of the first color pixel data and the second color pixel data.

31. The article of claim 30, wherein the pre-processed object of interest comprises one or more cells stained to increase the value of the first color pixel data.

32. The article of claim 17, wherein said transforming comprises transforming in color space.