Automatic image analysis and quantification for fluorescence in situ hybridization

• US 20080137937A1
• Filed: 11/30/2006
• Published: 06/12/2008
• Est. Priority Date: 11/16/2006
• Status: Active Grant

• Current Assignee: Definiens AG (Astrazeneca PLC)
• Original Assignee: Definiens AG (Astrazeneca PLC)
• Inventors: Schmidt, Guenter, Binnig, Gerd, Manuelian, Tamara, Athelogou, Maria, Diebold, Joachim
• Granted Patent: US 8,019,134 B2
• Time in Patent Office: Days
• US Class Current: 382/133
• 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 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 20/695 Preprocessing, e.g. image segmentation

Abstract

An analysis system automatically analyzes and counts fluorescence signals present in biopsy tissue marked using Fluorescence in situ Hybridization (FISH). The user of the system specifies classes of a class network and process steps of a process hierarchy. Then pixel values in image slices of biopsy tissue are acquired in three dimensions. A computer-implemented network structure is generated by linking pixel values to objects of a data network according to the class network and process hierarchy. Objects associated with pixel values at different depths of the biopsy tissue are used to determine the number, volume and distance between cell components. In one application, fluorescence signals that mark Her2/neural genes and centromeres of chromosome seventeen are counted to diagnose breast cancer. Her2/neural genes that overlap one another or that are covered by centromeres can be accurately counted. Signal artifacts that do not mark genes can be identified by their excessive volume.

Claims

1. A method comprising:

specifying a class network;

specifying a process hierarchy;

acquiring pixel values of an image that includes cell components, wherein certain of the cell components are marked using fluorescence in situ hybridization;

generating a data network based on the class network and the process hierarchy; and

counting the marked cell components using the data network.

2. The method of claim 1, wherein the data network includes an object that is linked to some of the pixel values, and wherein the object corresponds to a marked cell component.

3. The method of claim 2, wherein the marked cell component is an Her-2/neural gene.

4. The method of claim 2, wherein the marked cell component is a centromere of a chromosome.

5. The method of claim 2, wherein the marked cell component is a nucleus of a cell.

6. The method of claim 1, wherein one of the cell components has a volume, further comprising:

determining the volume of the cell component using the data network.

7. A computer-readable medium comprising program instructions for performing the steps of:

receiving a specification of a class network;

receiving a specification of a process hierarchy, wherein the process hierarchy includes process steps;

acquiring pixel values of an image that includes cell components, wherein certain of the cell components are marked using fluorescence in situ hybridization;

performing the process steps of the process hierarchy to generate a data network that includes an object, wherein the data network is generated by linking selected pixel values to the object based on the class network; and

counting the marked cell components using the data network.

8. The computer-readable medium of claim 7, wherein the object corresponds to a marked cell component.

9. The computer-readable medium of claim 8, wherein the marked cell component is an Her-2/neural gene.

10. The computer-readable medium of claim 8, wherein the marked cell component is a centromere of a chromosome.

11. The computer-readable medium of claim 8, wherein the marked cell component is a nucleus of a cell.

12. The computer-readable medium of claim 7, wherein one of the cell components has an area, having further program instructions for performing the step of:

determining the area of the cell component using the data network.

13. A method comprising:

specifying a class network having a class, wherein a membership function defines a likelihood that an object of a data network belongs to the class;

specifying a process step that is part of a process hierarchy;

acquiring table data values that include pixel values of an image of cell components;

generating the data network by generating the object of the data network and by selectively linking selected table data values to the object according to the class network and the process hierarchy; and

quantifying the cell components.

14. The method of claim 13, wherein the cell components are genes marked with a fluorescent marker, and wherein the quantifying includes counting the genes.

15. The method of claim 13, wherein the image depicts a slice from a z-stack on a slide taken from a biopsy tissue, wherein the table data values include pixel values of a second image of cell components, and wherein the second image depicts a second slice from the z-stack on the slide taken from the biopsy tissue.

16. The method of claim 15, wherein a first cell component in the image is a distance in the biopsy tissue apart from a second cell component in the second image, and wherein the quantifying includes determining the distance in the biopsy tissue between the first cell component and the second cell component.

17. The method of claim 13, wherein each of the cell components has a volume, and wherein the quantifying includes determining the volume of each cell component.

18. The method of claim 13, wherein the image is obtained using a confocal microscope.

19. The method of claim 13, wherein the image is one of a plurality of parallel planar scans of human tissue, wherein the generating the data network includes generating sub-objects by linking selected pixel values of the scans to the sub-objects, and wherein the generating the data network includes linking the sub-objects of adjacent scans.

20. The method of claim 19, wherein the linked sub-objects of adjacent scans represent the cell components.

21. The method of claim 13, wherein the table data values include items of metadata relating to the image.

22. The method of claim 13, wherein the table data values comprise values associated with a plurality of scans taken at different time intervals, wherein the generating the data network includes generating sub-objects by linking selected values in each of the scans to the sub-objects, and wherein the generating the data network includes linking the sub-objects of scans taken in adjacent time intervals.

23. The method of claim 22, wherein the linked sub-objects of scans taken in adjacent time intervals depict a movement of a cell component.

24. The method of claim 13, wherein the table data values comprise values from a first group of parallel planar slices of a three-dimensional data set of a cell taken at one time and from a second group of parallel planar slices of the three-dimensional data set of the cell taken at a different time, and wherein the values from the first group and the second group of parallel planar slices depict movement of the cell components.

25. The method of claim 13, wherein the table data values include patient data of a patient, wherein the patient has a gender, an age, a weight, a height, blood values, prescribed medications, a number of children, a family history of ailments, a history of breastfeeding, a history of smoking and a history of drug use, and wherein the patient data is taken from the group consisting of:

the gender, the age, the weight, the height, the blood values, the prescribed medications, the number of children, the family history of ailments, the history of breastfeeding, the history of smoking, the history of drug use, and tissue analysis results of the patient.

26. A computer-implemented network structure, comprising:

a data network including a first pixel value, a second pixel value, a first link, a second link, a first object and a second object, wherein the first pixel value is part of a first data table and the second pixel value is part of a second data table, wherein the first data table includes pixel values from a first image slice of a biopsy tissue, wherein the second data table includes pixel values from a second image slice of the biopsy tissue, wherein the first link links the first pixel value to the first object, and wherein the second link links the second pixel value to the second object;

a class network including a class, wherein a membership function determines that both the first object and the second object belong to the class; and

a process hierarchy including a process step, wherein the process step includes a domain specification and an algorithm, wherein the domain specification designates the class, wherein the class corresponds to cell components of the biopsy tissue that have been marked using fluorescence in situ hybridization, and wherein the algorithm counts the cell components that belong to the class.

27. The network structure of claim 26, wherein the cell components are Her-2/neural genes.

28. The network structure of claim 26, wherein the first image slice and the second image slice are part of a z-stack on a slide taken from the biopsy tissue.

29. The network structure of claim 26, wherein each of the cell components has a volume, and wherein the algorithm determines the volume of each of the cell components.

30. The network structure of claim 26, wherein the first data table includes an item of metadata that relates to the biopsy tissue, and wherein the algorithm is performed based on the item of metadata.