System and method for hierarchical multi-level feature image synthesis and representation

Patent metadata

Field	Value
Publication number	US-12446842-B2
Application number	US-202418590033-A
Country	US
Kind code	B2
Filing date	Feb 28, 2024
Priority date	Mar 30, 2017
Publication date	Oct 21, 2025
Grant date	Oct 21, 2025

Abstract

A method for processing breast tissue image data includes processing the image data to generate a set of image slices collectively depicting the patient's breast; for each image slice, applying one or more filters associated with a plurality of multi-level feature modules, each configured to represent and recognize an assigned characteristic or feature of a high-dimensional object; generating at each multi-level feature module a feature map depicting regions of the image slice having the assigned feature; combining the feature maps generated from the plurality of multi-level feature modules into a combined image object map indicating a probability that the high-dimensional object is present at a particular location of the image slice; and creating a 2D synthesized image identifying one or more high-dimensional objects based at least in part on object maps generated for a plurality of image slices.

First claim

What is claimed is:

1. A method for processing breast tissue image data, comprising:
providing a set of image slices that collectively depict at least a portion of a patient's breast tissue, wherein the set of image slices are generated by one of a tomosynthesis acquisition system and a combination tomosynthesis/mammography system;
processing the set of image slices using a first-level feature module to detect at least one first assigned feature of a high-dimensional object present in the patient's breast tissue;
generating a first-level feature map based on the at least one first assigned feature;
processing the set of image slices using a second-level feature module to detect at least one second assigned feature of the high-dimensional object present in the patient's breast tissue,
wherein the at least one first assigned feature is a different level feature than the at least one second assigned feature;
generating a second-level feature map based on the at least one second assigned feature;
and
combining the first-level feature map and the second-level feature map into an object map that indicates a probability region of the high-dimensional object in each image slice.

2. The method of claim 1 , wherein the first-level feature module is configured to recognize the at least one first assigned feature by applying one or more first-level recognition models, and wherein the second-level feature module is configured to recognize the at least one second assigned feature by applying one or more second-level recognition models.

3. The method of claim 1 , wherein the first-level feature module is configured to recognize the at least one first assigned feature by applying one or more first-level recognition templates, and wherein the second-level feature module is configured to recognize the at least one second assigned feature by applying one or more second-level recognition templates.

4. The method of claim 1 , wherein the first-level feature module is configured to recognize the at least one first assigned feature by applying one or more first-level recognition filters, and wherein the second-level feature module is configured to recognize the at least one second assigned feature by applying one or more second-level recognition filters.

5. The method of claim 1 , wherein the first-level feature module is configured to recognize the at least one first assigned feature by applying one or more first-level recognition filters, and wherein the second-level feature module is configured to recognize the at least one second assigned feature by applying one or more second-level recognition models.

6. The method of claim 1 , further comprising creating a two-dimensional synthesized image of the patient's breast tissue based at least in part on the object map.

7. The method of claim 1 , further comprising identifying the high-dimensional object based at least in part on the object maps generated for each of the image slices.

8. The method of claim 1 , wherein combining the first-level feature map and the second-level feature map into the object map comprises combining, by a learning library-based combiner, the first-level feature map and the second-level feature map into the object map.

9. The method of claim 8 , further comprising assigning a first weight to the first-level feature map and a second weight to the second-level feature map.

10. The method of claim 9 , further comprising adjusting at least one of the first weight and the second weight.

11. The method of claim 1 , wherein the at least one first assigned feature is a high-level feature or a mid-level feature.

12. The method of claim 1 , wherein the at least one second assigned feature is a mid-level feature or a low-level feature.

13. The method of claim 1 , further comprising:
processing the set of image slices using a third-level feature module to detect at least one third assigned feature of the high-dimensional object present in the patient's breast tissue, wherein the at least one third assigned features is a different level feature than the at least one first and second assigned features;
generating a third-level feature map based on the at least one third assigned feature; and
combining the third-level feature map into the object map.

14. The method of claim 13 , wherein the at least one third assigned feature is a mid-level feature.

15. The method of claim 1 , wherein the probability region indicates one or more of a location, a size, and a scope of the high-dimensional object.

16. The method of claim 1 , wherein the probability region comprises a probability gradient.

17. The method of claim 1 , wherein the high-dimensional object comprises a three-dimensional image object.

18. The method of claim 1 , further comprising generating a three-dimensional volumetric object map based upon respective first-, second- and third-level object maps.

19. A system comprising:
a non-transitory 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:
providing a set of image slices that collectively depict at least a portion of a patient's breast tissue, wherein the set of image slices are generated by one of a tomosynthesis acquisition system and a combination tomosynthesis/mammography system;
processing the set of image slices using a first-level feature module to detect at least one first assigned feature of a high-dimensional object present in the patient's breast tissue;
generating a first-level feature map based on the at least one first assigned feature;
processing the set of image slices using a second-level feature module to detect at least one second assigned feature of the high-dimensional object present in the patient's breast tissue, wherein the at least one first assigned feature is a different level feature than the at least one second assigned feature;
generating a second-level feature map based on the at least one second assigned feature;
and
combining the first-level feature map and the second-level feature map into an object map that indicates a probability region of the high-dimensional object in each image slice.

20. A non-transitory computer readable medium having stored thereon one or more sequences of instructions for causing one or more processors to perform:
providing a set of image slices that collectively depict at least a portion of a patient's breast tissue, wherein the set of image slices are generated by one of a tomosynthesis acquisition system and a combination tomosynthesis/mammography system;
processing the set of image slices using a first-level feature module to detect at least one first assigned feature of a high-dimensional object present in the patient's breast tissue;
generating a first-level feature map based on the at least one first assigned feature;
processing the set of image slices using a second-level feature module to detect at least one second assigned feature of the high-dimensional object present in the patient's breast tissue,
wherein the at least one first assigned feature is a different level feature than the at least one second assigned feature;
generating a second-level feature map based on the at least one second assigned feature;
and
combining the first-level feature map and the second-level feature map into an object map that indicates a probability region of the high-dimensional object in each im

Assignees

• Hologic Inc

Inventors

• Chui Haili
• Wei Liyang
• Ge Jun
• Zhang Xiangwei
• Gkanatsios Nikolaos

Classifications

• G06V10/809

  of classification results, e.g. where the classifiers operate on the same input data · CPC title

• G06V10/806

  of extracted features · CPC title

• G06V30/2504

  Coarse or fine approaches, e.g. resolution of ambiguities or multiscale approaches · CPC title

• G06F18/254

  of classification results, e.g. of results related to same input data · CPC title

• G06T2207/30068

  Mammography; Breast · CPC title