Granted Patent B2

US 12,307,604 · App. 18/298,663 · Granted May 20, 2025

Inventors: Jin-Long Chen (Santa Clara, CA); Haili Chui (Fremont, CA); Nikolaos Gkanatsios (Danbury, CT); Kevin Kreeger (Sunnyvale, CA); Julian Marshall (Los Altos, CA); David Mislan (Lexington, MA); Mark A. Prazer (San Jose, CA); Xiangwei Zhang (Fremont, CA)

Assignee: Hologic, Inc.

G06T19/003A61B6/025A61B6/466A61B6/502G06F3/04815G06F3/04842G06T7/0012G06T2207/30068

Abstract

Claims (41)

1. A method for processing breast tissue image data, comprising:

obtaining a plurality of images of a patient's breast tissue, the plurality of images distributed along a z-axis of the patient's breast tissue;

generating a synthesized 2D image of the patient's breast tissue by:

identifying a first region in a first image of the plurality of images having a first set of attributes;

identifying a second region in a second image of the plurality of images having a second set of attributes;

determining the first region and second region overlap along the z-axis;

comparing the first set of attributes and the second set of attributes;

prioritizing the first region over the second region based on a priority scheme, wherein the first set of attributes is more similar to a set of attributes associated with a prioritized tissue structure in the priority scheme than the second set of attributes; and

importing the first region into the synthesized 2D image.

2. The method of claim 1 , wherein the priority scheme ranks a number of tissue structures based on relative clinical importance.

3. The method of claim 1 , wherein the priority scheme comprises the set of attributes associated with the prioritized tissue structure prioritized based on the prioritized tissue structure being associated with a possible disease state and being prioritized over tissue structures associated with anatomy of the patient's breast tissue.

4. The method of claim 1 , further comprising generating an index map of the synthesized 2D image, wherein the index map associates one or more regions of the synthesized 2D image with a source image from the plurality of images.

5. The method of claim 4 , further comprising importing the second region into the synthesized 2D image such that the second region is obscured by the first region; and

adding a visual indicator of features distributed along the z-axis.

6. The method of claim 5 , further comprising mapping the first region and the region separately on the index map.

7. The method of claim 4 , wherein generating the index map comprises generating a pixel-based index map and an object-based index map.

8. The method of claim 7 , wherein generating the object-based index map comprises generating an individual object map for each object type detected and combining the individual object maps.

9. The method of claim 8 , wherein object types include one or more of blob density, spiculated masses, and micro-calcifications.

10. The method of claim 7 , wherein the object-based index map is prioritized over the pixel-based index map.

11. The method of claim 7 , wherein generating the pixel-based index map comprises searching, for each region of the synthesized 2D image, the plurality of images to identify an image including a best-fit match of the region of the synthesized 2D image.

12. The method of claim 4 , wherein the source image is a group of images.

13. The method of claim 4 , wherein the source image is selected from two or more candidate source images based on one or more of: the source image is a central image in a group of candidate images; the source image is a highest weighted image in a group of candidate images; the source image is a least noisy image in a group of candidate images.

14. The method of claim 1 , further comprising comparing the first region and the second region; and

determining a first boundary for the first region and a second boundary for the second region.

15. The method of claim 14 , further comprising importing the second feature into the synthesized 2D image; and

presenting the first region in portions of the second boundary overlapped by the first boundary.

16. The method of claim 1 , wherein attributes include one or more of indicators of disease states, indicators of location and orientation, and indicators of image quality.

17. The method of claim 16 , wherein indicators of location and orientation include one or more of a breast tissue border or anatomical feature, or presence of a contrast agent.

18. The method of claim 1 , further comprising receiving a selection of the first region in the 2D image and, in response, returning the first image.

19. The method of claim 18 , further comprising associating the first region with an object type based the first set of attributes and filtering the first image based on the object type.

20. A system comprising:

a processor; and

memory coupled to the processor, the memory comprising computer executable instructions that, when executed by the processor, performs a method comprising:

obtaining a plurality of images of a patient's breast tissue, the plurality of images distributed along a z-axis of the patient's breast tissue;

generating a synthesized 2D image of the patient's breast tissue by:

identifying a first region in a first image of the plurality of images having a first set of attributes;

identifying a second region in a second image of the plurality of images having a second set of attributes;

determining the first region and second region overlap along the z-axis;

comparing the first set of attributes and the second set of attributes;

prioritizing the first region over the second region based on a priority scheme, wherein the first set of attributes relates more closely to a prioritized tissue structure in the priority scheme than the second set of attributes; and

importing the first region into the synthesized 2D image.

Assignments (4)

Continuity (6)

References Cited (400)