Biomarker evaluation through image analysis

• US 9,466,103 B2
• Filed: 04/27/2015
• Issued: 10/11/2016
• Est. Priority Date: 10/26/2011
• Status: Active Grant

• Current Assignee: Definiens AG (Astrazeneca PLC)
• Original Assignee: Definiens AG (Astrazeneca PLC)
• Inventors: Athelogou, Maria, Binnig, Gerd, Schmidt, Guenter
• Primary Examiner(s): Bitar, Nancy
• Application Number:
  US14/697,378
• Publication Number:
  US 20150228075A1
• Time in Patent Office: 533 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/10056 Microscopic image
• 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 7/155 involving morphological operators
• CPC Class Codes: G06T 7/187 involving region growing; involving region merging; involving connected component labelling
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 10/26 Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
• CPC Class Codes: G06V 20/695 Preprocessing, e.g. image segmentation

Abstract

A method for determining whether a test biomarker is a stain for a type of cell component, such as membrane or nucleus, involves performing various segmentation processes on an image of tissue stained with the test biomarker. One segmentation process searches for a first cell component type, and another segmentation process searches for a second cell component type by segmenting only stained pixels. The test biomarker is identified as a stain for each component type if the process identifies the component based only on stained pixels. Whether the test biomarker is a membrane stain or nucleus stain is displayed on a graphical user interface. In addition, the method identifies stained pixels corresponding to a second cell component using pixels determined to correspond to a first cell component. An expression profile for the test biomarker is then displayed that indicates the proportion of stained pixels in each type of cell component.

Claims

1. A method comprising:

performing a first segmentation process on a digital image that searches for a first cell component type having a predetermined color, wherein the digital image depicts tissue that is stained with a test biomarker to have the predetermined color, and wherein the first segmentation process includes;

identifying a starting pixel in the digital image;

expanding from the starting pixel into each successive neighboring pixel so long as the neighboring pixel has a color that is not more dissimilar to the predetermined color than is the previous neighboring pixel; and

halting the expanding into successive neighboring pixels at a boundary at which the neighboring pixel of each boundary pixel has a color that is more dissimilar to the predetermined color than is the boundary pixel;

performing a second segmentation process on the digital image that searches for a second cell component type that has the predetermined color;

identifying the test biomarker as a stain for the first cell component type if the first segmentation process identifies the first cell component type;

identifying the test biomarker as a stain for the second cell component type if the second segmentation process identifies the second cell component type, wherein both, neither or only one of the first and second cell component types can be identified; and

displaying on a graphical user interface whether the test biomarker is a stain for the first cell component type and whether the test biomarker is a stain for the second cell component type.

2. The method of claim 1, wherein the first cell component type is a membrane, and wherein the second cell component type is a nucleus.

3. The method of claim 2, wherein the test biomarker is a stain for the first cell component type, and wherein the first cell component type is a membrane.

4. The method of claim 1, wherein the first segmentation process identifies a plurality of cell components of the first cell component type, further comprising:

counting a total number of the plurality of cell components of the first cell component type in the digital image.

5. The method of claim 1, wherein the first segmentation process identifies a plurality of cell components of the first cell component type, further comprising:

determining that the plurality of cell components of the first cell component type are clumped together.

6. The method of claim 1, wherein the first segmentation process identifies a plurality of cell components of the first cell component type, further comprising:

determining that the plurality of cell components of the first cell component type are dispersed throughout the tissue.

7. The method of claim 1, wherein the predetermined color is a range of colors, wherein the first segmentation process searches for cell components of the first cell component type that have colors within the range of colors, and wherein the second segmentation process searches for cell components of the second cell component type that have colors within the range of colors.

8. The method of claim 1, wherein the first cell component is a nucleus, and wherein the second cell component is a membrane.

9. The method of claim 1, wherein the test biomarker includes a first stain and a second stain.

10. The method of claim 1, wherein both of the first and second cell component types are identified, further comprising:

determining a first stained proportion of the first cell component type;

determining a second stained proportion of the second cell component type; and

displaying on the graphical user interface an expression profile of the test biomarker, wherein the expression profile includes the first stained proportion of the first cell component type and the second stained proportion of the second cell component type.

11. The method of claim 4, further comprising:

calculating an expression parameter for the test biomarker using the total number; and

displaying the expression parameter on the graphical user interface.

12. A method comprising:

searching a digital image for a first type of cell components that have a predetermined color, wherein the digital image depicts tissue that is stained with a test biomarker to have the predetermined color, and wherein the searching for the first type of cell components includes;

identifying a starting pixel in the digital image;

expanding from the starting pixel into each successive neighboring pixel so long as the neighboring pixel has a color that is not more dissimilar to the predetermined color than is the previous neighboring pixel; and

halting the expanding into successive neighboring pixels at a boundary at which the neighboring pixel of each boundary pixel has a color that is more dissimilar to the predetermined color than is the boundary pixel;

searching the digital image for a second type of cell components that have the predetermined color;

identifying the test biomarker as a stain for the first type of cell components if the searching identifies the first type of cell components;

identifying the test biomarker as a stain for the second type of cell components if the searching identifies the second type of cell components, wherein both, neither or only one of the first and second types of cell components can be identified; and

displaying on a graphical user interface whether the test biomarker is a stain for the first type of cell components and whether the test biomarker is a stain for the second type of cell components.

13. The method of claim 12, wherein the searching for the first type of cell components is performed using a pixel-by-pixel segmentation process.

14. The method of claim 12, wherein the predetermined color is defined as a range of colors in a multi-dimensional color space.

15. The method of claim 12, wherein the first type of cell components is a membrane, and wherein the second type of cell components is a nucleus.

16. The method of claim 12, wherein the test biomarker is a stain for the first type of cell components, and wherein the first type of cell components is a membrane.

17. The method of claim 12, further comprising:

counting a total number of the first type of cell components in the digital image that have the predetermined color.

18. The method of claim 12, further comprising:

determining that the cell components of the first type are clumped together.

19. The method of claim 12, further comprising:

determining that the cell components of the first type are dispersed throughout the tissue.