Granted Patent B2

US 12,211,124 · App. 18/631,216 · Granted Jan 28, 2025

Inventors: Haili Chui (Fremont, CA); Xiaomin Liu (Sunnyvale, CA); Xiangwei Zhang (Fremont, CA)

Assignee: Hologic, Inc.

G06T11/005A61B6/502G06N20/00G06T7/0012G06T15/205G06T2207/10072G06T2207/10116G06T2207/30068

Abstract

Claims (55)

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

obtaining a set of image slices that collectively depict a patient's breast tissue;

identifying a plurality of image patterns among slices of the set of image slices;

generating a high-dimensional object grid depicting the plurality of image patterns as two or more high-dimensional objects, each of the two or more high-dimensional objects having one or more features;

assigning a default weight to each of the two or more high-dimensional objects;

generating an interactive display of the high-dimensional object grid;

receiving, from the interactive display, a weight adjustment input associated with at least one of the two or more high-dimensional objects;

generating, based on the high-dimensional object grid and the weight adjustment input, a lower-dimensional format image of the two or more high-dimensional objects; and

modifying, based on the weight adjustment input, at least one feature of at least one of the two or more high-dimensional objects.

2. The method of claim 1 , wherein receiving the weight adjustment input associated with at least one of the two or more high-dimensional objects comprises:

receiving a selection of a first object of the two or more high-dimensional objects; and

associating, automatically, based on the selection of the first object, the weight adjustment input with the first object.

3. The method of claim 2 , wherein the weight adjustment input causes the first object to have a weight higher than the default weight.

4. The method of claim 2 , wherein modifying, based on the weight adjustment input, at least one feature of at least one or the two or more high-dimensional objects comprises:

emphasizing the first object over other objects of the two or more high-dimensional objects in the lower-dimensional format image.

5. The method of claim 2 , further comprising receiving an indication that the weight adjustment input causes the first object to have a weight lower than the default weight.

6. The method of claim 5 , wherein the indication is a characterization of the first object as a background object.

7. The method of claim 5 , wherein the indication is a characterization of the first object as an object that is not included in the lower-dimensional format image.

8. The method of claim 1 , further comprising displaying the lower-dimensional format image.

9. A system comprising:

a computer-readable memory storing executable instructions; and

one or more processors in communication with the computer-readable memory, wherein, when the one or more processors execute the executable instructions, the one or more processors perform:

obtaining a set of image slices that collectively depict a patient's breast tissue;

identifying a plurality of image patterns among slices of the set of image slices;

generating a high-dimensional object grid depicting the plurality of image patterns as two or more high-dimensional objects, each of the two or more high-dimensional objects having one or more features;

assigning a default weight to each of the two or more high-dimensional objects;

generating an interactive display of the high-dimensional object grid;

receiving, from the interactive display, a weight adjustment input associated with at least one of the two or more high-dimensional objects;

generating, based on the high-dimensional object grid and the weight adjustment input, a lower-dimensional format image of the two or more high-dimensional objects; and

modifying, based on the weight adjustment input, at least one feature of at least one of the two or more high-dimensional objects.

10. The system of claim 9 , wherein the one or more processors further perform receiving the weight adjustment input associated with at least one of the two or more high-dimensional objects comprising:

receiving a selection of a first object of the two or more high-dimensional objects; and

associating, automatically, based on the selection of the first object, the weight adjustment input with the first object.

11. The system of claim 10 , wherein the one or more processors further perform that the weight adjustment input causes the first object to have a weight higher than the default weight.

12. The system of claim 10 , wherein the one or more processors further perform modifying, based on the weight adjustment input, at least one feature of at least one or the two or more high-dimensional objects comprising:

emphasizing the first object over other objects of the two or more high-dimensional objects in the lower-dimensional format image.

13. The system of claim 10 , wherein the one or more processors further perform receiving an indication that the weight adjustment input causes the first object to have a weight lower than the default weight.

14. The system of claim 13 , wherein the one or more processors further perform that the indication is a characterization of the first object as a background object.

15. A non-transitory computer readable medium having stored thereon one or more sequences of instructions for causing one or more processor to perform:

obtaining a set of image slices that collectively depict a patient's breast tissue;

identifying a plurality of image patterns among slices of the set of image slices;

generating a high-dimensional object grid depicting the plurality of image patterns as two or more high-dimensional objects, each of the two or more high-dimensional objects having one or more features;

assigning a default weight to each of the two or more high-dimensional objects;

generating an interactive display of the high-dimensional object grid;

receiving, from the interactive display, a weight adjustment input associated with at least one of the two or more high-dimensional objects;

generating, based on the high-dimensional object grid and the weight adjustment input, a lower-dimensional format image of the two or more high-dimensional objects; and

modifying, based on the weight adjustment input, at least one feature of at least one of the two or more high-dimensional objects.

16. The non-transitory computer readable medium of claim 15 , wherein the one or more processors further perform receiving the weight adjustment input associated with at least one of the two or more high-dimensional objects comprising:

receiving a selection of a first object of the two or more high-dimensional objects; and

associating, automatically, based on the selection of the first object, the weight adjustment input with the first object.

17. The non-transitory computer readable medium of claim 16 , wherein the one or more processors further perform that the weight adjustment input causes the first object to have a weight higher than the default weight.

18. The non-transitory computer readable medium of claim 16 , wherein the one or more processors further perform modifying, based on the weight adjustment input, at least one feature of at least one or the two or more high-dimensional objects comprising:

emphasizing the first object over other objects of the two or more high-dimensional objects in the lower-dimensional format image.

19. The non-transitory computer readable medium of claim 16 , wherein the one or more processors further perform receiving an indication that the weight adjustment input causes the first object to have a weight lower than the default weight.

20. The non-transitory computer readable medium of claim 19 , wherein the one or more processors further perform that the indication is a characterization of the first object as a background object.

Assignments (4)

Continuity (4)

References Cited (400)