System and method for synthetic breast tissue image generation by high density element suppression

Patent metadata

Field	Value
Publication number	US-11857358-B2
Application number	US-201917280866-A
Country	US
Kind code	B2
Filing date	Sep 24, 2019
Priority date	Sep 28, 2018
Publication date	Jan 2, 2024
Grant date	Jan 2, 2024

Abstract

A method and breast imaging system for processing breast tissue image data includes feeding image data of breast images to an image processor, identifying image portions depicting breast tissue and high density elements and executing different processing methods on input images. A first image processing method involves breast tissue enhancement and high density element suppression, whereas the second image processing method involves enhancing high density elements. Respective three-dimensional sets of image slices may be generated by respective image processing methods, and respective two-dimensional synthesized images are generated and combined to form a two-dimensional composite synthesized image which is presented through a display of the breast imaging system. First and second image processing may be executed on generated three-dimensional image sets or two-dimensional projection images acquired by an image acquisition component at respective angles relative to the patient's breast.

First claim

What is claimed is:

1. A computer-implemented for processing images of breast tissue, the computer-implemented method comprising:
feeding image data of a plurality of images of a breast as an input into an image processor of an image generation and display system;
identifying, by the image processor, image portions depicting breast tissue and image portions depicting a high density element generated by imaging the high density object together with breast tissue;
executing, by the image processor, a first image processing method comprising: enhancing identified image portions depicting breast tissue, suppressing identified image portions depicting the high density element, and generating, a first two-dimensional (2D) synthesized image based at least in part upon enhanced breast tissue image portions and suppressed high density element image portions;
executing, by the image processor, a second image processing method comprising: enhancing identified image portions depicting the high density element, and generating a second 2D synthesized image based at least in part upon enhanced high density element portions;
combining, by the image processor, the first 2D synthesized image generated by the first image processing method and the second 2D synthesized image generated by the second image processing method to generate a 2D composite synthesized image; and
presenting the 2D composite synthesized image through a display of the image generation and display system.

2. The computer-implemented method of claim 1 , further comprising, before generating the first 2D synthesized image and generating the second 2D synthesized image:
generating, by the image processor, a first three-dimensional (3D) set of image slices based at least in part upon enhanced breast tissue images and suppressed high density element image portions, and generating a second 3D set of images slices based at least in part upon enhanced high density element image portions,
wherein the first 2D synthesized image is generated based at least in part upon the first 3D set of image slices, and the second 2D synthesized image is generated based at least in part upon the second 3D set of image slices.

3. The computer-implemented method of claim 1 , the input to the image processor comprising image data of a plurality of 2D projection images acquired by an x-ray acquisition component of the image generation and display system at respective angles between the breast and the x-ray image acquisition component, wherein the first image processing method and the second image processing method are executed on image data of the 2D projection images.

4. The computer-implemented method of claim 1 , further comprising:
the image generation and display system activating an x-ray image acquisition component and acquiring, by the x-ray image acquisition component a plurality of 2D projection images acquired at respective angles between the breast and an x-ray image acquisition component;
generating an input 3D stack of image slices based on the plurality of 2D projection images, the input 3D stack of image slices collectively depicting the breast, wherein the input to the image processor is the input 3D stack of image slices.

5. The computer-implemented method of claim 4 , wherein high density element suppression of the first image processing method and high density element enhancement of the second image processing method are not executed on the plurality of 2D projection images acquired by the x-ray image acquisition component.

6. The computer-implemented of claim 5 , wherein
the first image processing method is executed on the input stack of 3D image slices to generate a first 3D stack of image slices, and the second image processing method is executed on the input stack of 3D image slices to generate a second 3D stack of image slices, and
the first 2D synthesized image is generated based at least in part upon the first 3D set of image slices, and the second 2D synthesized image is generated based at least in part upon the second 3D set of image slices.

7. The computer-implemented method of claim 6 , wherein the high density element is depicted as extending across multiple slices of the input stack of 3D image slices.

8. The computer-implemented method of claim 7 , wherein metal suppression of the first image processing method and metal enhancement of the second image processing method are not executed on the plurality of 2D projection images.

9. The computer-implemented method of claim 6 , wherein the first imaging processing method suppresses the identified image portions depicting the high density element such that the high density element is not visible in the first 3D stack of image slices.

10. The computer-implemented method of claim 1 , identifying image portions depicting the high density element comprising identifying image portions depicting a metallic object in breast tissue, wherein image portions depicting the metallic object are suppressed by the first image processing method and enhanced by the second image processing method.

11. The computer-implemented method of claim 1 , identifying image portions depicting the high density element comprising identifying image portions depicting a shadow cast by a metallic object as a result of imaging of the metallic object, wherein image portions depicting the shadow are suppressed by the first image processing method and enhanced by the second image processing method.

12. The computer-implemented method of claim 1 , identifying image portions depicting the high density element comprising identifying image portions depicting a calcification in the breast tissue, wherein image portions depicting the calcification are suppressed by the first image processing method and enhanced by the second image processing method.

13. The computer-implemented method of claim 1 , identifying image portions identifying the high density element comprising identifying image portions identifying a radiopaque object in breast tissue.

14. The computer-implemented method of claim 1 , wherein the first image processing method and the second image processing method are executed simultaneously in parallel.

15. The computer-implemented method of claim 1 , wherein the second image processing method enhances image portions depicting the high density element without enhancing image portions depicting breast tissue or lesions within the breast tissue.

16. The computer-implemented method of claim 1 , wherein image portions depicting the high density element are suppressed by replacing image portions depicting the high density element with background image data that is not enhanced.

17. The computer-implemented method of claim 1 , wherein the first 2D synthesized image is free of image portions depicting the high density element.

18. The computer-implemented method of claim 17 , wherein the first 2D synthesized image is free of image portions depicting the high density element and free of image portions depicting a shadow generated by imaging the high density element with the breast tissue.

19. The computer-implemented method of claim 1 , wherein the second 2D synthesized image is free of image portions depicting breast tissue.

20. The computer-implemented method of claim 1 , the first image processing method and the second image processing method being executed by a tomosynthesis system.

Assignees

• Hologic Inc

Inventors

• Liu Xiaomin
• Chui Haili
• Zhang Xiangwei
• Gkanatsios Nikolaos

Classifications

• G06T12/30

  Image post-processing, e.g. metal artefact correction · CPC title

• A61B6/5258 Primary

  involving detection or reduction of artifacts or noise · CPC title

• A61B6/461

  Displaying means of special interest · CPC title

• A61B6/502

  for diagnosis of breast, i.e. mammography · CPC title

• G06T11/008

  Physics · mapped topic