Method and apparatus for automated image analysis of biological specimens

• US 7,359,548 B2
• Filed: 11/07/2006
• Issued: 04/15/2008
• Est. Priority Date: 11/30/1995
• Status: Expired due to Fees

• Current Assignee: Carl Zeiss Microscopy GmbH (Carl-Zeiss-Stiftung)
• Original Assignee: Carl Zeiss Microimaging Ais, Inc. (Carl-Zeiss-Stiftung)
• Inventors: Riding, Thomas J., Ring, James E., Douglass, James W.
• Primary Examiner(s): PATEL, KANJIBHAI B
• Application Number:
  US11/594,374
• Publication Number:
  US 20070053569A1
• Time in Patent Office: 525 Days
• Field of Search: 382128-134, 382/162, 382/167, 382/203, 382/224, 382/274, 382/312, 345/604, 348/577, 348/655
• US Class Current: 382/162
• 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 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 system, comprising:

an electronic microscope that obtains an electronic signal indicative of pixels of a microscope image; and

a processor, that processes said electronic signal to determine relationships between different colors within the whole electronic signal;

wherein said processor receives color balance information for the image and said processor calculates ratios between a first channel of color of the image across the entire image, and a second channel of color of the image across the entire image.

2. A system as in claim 1, wherein said processor calculates ratios between different color pixels of the signal.

3. A system as in claim 1, wherein said processor determines a relationship between a first color channel and a second color channel.

4. A system as in claim 3, wherein said first and second color channels are each one of red, green and blue channels.

5. A system as in claim 3, wherein said relationship is a ratio.

6. A system as in claim 3, wherein said processor calculates at least one ratio from the group consisting of red/red;

red/green;

red/blue;

green/green;

green/blue;

green/red;

blue/blue;

blue/green;

blue/red.

7. A system as in claim 3 wherein said processor calculates ratios of each of red/red;

red/green;

red/blue;

green/green;

green/blue;

green/red;

blue/blue;

blue/green;

blue/red.

8. A method, comprising:

obtaining an electronic signal indicative of pixels of a microscope image;

processing said electronic signal to determine relationships between different colors within each of the pixels of the image;

calculating a color balance for the image; and

calculating ratios between a first channel of color of the image across the entire image, and a second channel of color of the image across the entire image.

9. A method as in claim 8, further comprising calculating ratios between different color pixels of the image.

10. A method as in claim 8, further comprising calculating a relationship between a first color channel and a second color channel.

11. A method as in claim 10, wherein said first and second color channels are each one of red, green and blue channels.

12. A method as in claim 8, wherein said relationship is a ratio.