Digital pathology color calibration and validation

Patent metadata

Field	Value
Publication number	US-10845245-B2
Application number	US-201716095267-A
Country	US
Kind code	B2
Filing date	Apr 20, 2017
Priority date	Apr 20, 2016
Publication date	Nov 24, 2020
Grant date	Nov 24, 2020

Abstract

Color calibration for digital pathology is provided. A standard glass slide is prepared with a specimen having zero or more stains. The specimen is scanned a first time using a hyperspectral imaging system to produce a first digital image having XYZ color values. The specimen is scanned a second time using a digital pathology imaging system to produce a second digital image having RGB color values. The first and second digital images are then registered against each other to align the digital image data. Individual pixels of the first and second images may be combined in the registration process so that the first and second digital images have substantially similar pixel sizes. A lookup table is generated to associate XYZ color values to RGB color values. Once the lookup table has been generated, it can be used to present RGB color on a display using the corresponding XYZ color.

First claim

What is claimed is:

1. A system comprising:
a non-transitory computer readable medium configured to store data and executable programmed modules;
at least one processor communicatively coupled with the non-transitory computer readable medium and configured to execute instructions stored thereon; and
one or more software modules stored in the non-transitory computer readable medium and configured to, when executed by the at least one processor
capture a first digital image of a specimen in XYZ color via a first imaging system, the first digital image having a plurality of image pixels having a first image pixel size,
capture a second digital image of the specimen in RGB color via a second imaging system, the second digital image having a plurality of image pixels having a second image pixel size,
align image data of the first digital image with corresponding image data of the second digital image,
convert the first digital image and the second digital image to a common image pixel size, wherein the converted image pixels of the first digital image are aligned with corresponding converted image pixels of the second digital image,
group image pixels in the first digital image into a plurality of first groups, wherein each image pixel in each one of the plurality of first groups has a substantially same XYZ color value,
for each of the plurality of first groups of image pixels in the first digital image,
determine an average XYZ color value for the first set of image pixels in the first group,
identify a second group of image pixels in the second digital image that corresponds to the first group, wherein each image pixel in the second group of image pixels corresponds to an image pixel in the first group, and
determine an average RGB color value for the image pixels in the second group, and

generate a look up table to associate the average XYZ color value of each first group of image pixels in the first digital image with the average RGB color value of the corresponding second group of image pixels in the second digital image.

2. The system of claim 1 , wherein each of the image pixels in each first group of image pixels in the first digital image is contiguous with at least one other image pixel in the first group of image pixels in the first digital image.

3. The system of claim 1 , wherein at least some of the image pixels in one or more of the first groups of image pixels in the first digital image are not contiguous.

4. The system of claim 3 , wherein each corresponding first group and second group represents one of a plurality of color indices in the look up table, wherein each image pixel in each of the plurality of first groups is assigned the average XYZ color value determined for that first group, and wherein each image pixel in each second group is assigned the average RGB color value determined for that second group.

5. A method comprising:
capturing a first digital image of a specimen in XYZ color, via a first imaging system, the first digital image having a plurality of image pixels having a first image pixel size;
capturing a second digital image of the specimen in RGB color, via a second imaging system, the second digital image having a plurality of image pixels having a second image pixel size;
grouping image pixels in the first digital image into a plurality of first groups, wherein each image pixel in each one of the plurality of first groups has a substantially same XYZ color value;
for each of the plurality of first groups of image pixels in the first digital image,
determining an average XYZ color value for the image pixels in the first group,
identifying a second group of image pixels in the second digital image that corresponds to the first group, wherein each image pixel in the second group of image pixels corresponds to an image pixel in the first group, and
determining an average RGB color value for the image pixels in the second group; and

generating a lookup table to associate the average XYZ color value of each first group of image pixels in the first digital image with the average RGB color value of the corresponding second group of image pixels in the second digital image.

6. The method of claim 5 , further comprising aligning image data in the first digital image with image data in the second digital image, wherein identifying a second group of image pixels in the second digital image that corresponds to the first group is performed in accordance with said alignment.

7. The method of claim 6 , wherein aligning image data of the first digital image with corresponding image data of the second digital image comprises converting the image pixels of the first digital image having the first image pixel size and the image pixels of the second digital image having the second image pixel size to a common image pixel size.

8. A a non-transitory computer readable medium that stores instructions that, when executed by a processor, cause the processor to:
capture a first digital image of a specimen in XYZ color via a first imaging system;
capture a second digital image of the specimen in RGB color via a second imaging system;
register the first digital image to the second digital image to align image data in the first digital image and the second digital image;
group image pixels in the first digital image into a plurality of first groups, wherein each image pixel in each one of the plurality of first groups has a substantially same XYZ color value;
for each of the plurality of first groups of image pixels in the first digital image,
determine an average XYZ color value for the image pixels in the first group,
identify a second group of image pixels in the second digital image that corresponds to the first group, wherein each image pixel in the second group of image pixels corresponds to an image pixel in the first group, and
determine an average RGB color value for the image pixels in the second group; and

generate a lookup table that associates the average XYZ color value of each first group of image pixels in the first digital image with the average RGB color value of the corresponding second group of image pixels in the second digital image.

9. The non-transitory computer readable medium of claim 8 , wherein the instructions further cause the processor to provide XYZ color data for presentation of the second digital image on a display.

10. The non-transitory computer readable medium of claim 8 , wherein the instructions further cause the processor to embed the look up table in a file comprising the second digital image.

11. The non-transitory computer readable medium of claim 8 , wherein registering the first digital image to the second digital image comprises matching patterns in the first digital image to patterns in the second digital image.

12. The non-transitory computer readable medium of claim 8 , wherein registering the first digital image to the second digital image comprises overlaying a grid on the specimen prior to creating the first and second digital images and using the grid to align the first and second digital images.

13. The non-transitory computer readable medium of claim 8 , wherein the instructions further cause the processor to:
for each of the plurality of first groups, combine the image pixels in that first group into a first superpixel, and assign the average XYZ color value for that first group to the first superpixel; and,
for each of the plurality of second groups, combine the image pixels in that second group into a second superpixel, and assign the average RGB color value to the second superpixel;
wherein the look up table associates the average XYZ color value assigned

Assignees

• Leica Biosystems Imaging Inc

Inventors

• Olson Allen

Classifications

• G06T11/10

  Texturing; Colouring; Generation of textures or colours (retouching, inpainting or scratch removal G06T5/77) · CPC title

• G16H70/60

  relating to pathologies · CPC title

• G16H30/40

  for processing medical images, e.g. editing · CPC title

• G16H30/20

  for handling medical images, e.g. DICOM, HL7 or PACS · CPC title

• G06T2207/30024

  Cell structures in vitro; Tissue sections in vitro · CPC title