System and method for generating a 2D image using mammography and/or tomosynthesis image data

Patent metadata

Field	Value
Publication number	US-12183309-B2
Application number	US-202318493433-A
Country	US
Kind code	B2
Filing date	Oct 24, 2023
Priority date	Nov 27, 2011
Publication date	Dec 31, 2024
Grant date	Dec 31, 2024

Abstract

The invention includes a method including the steps of obtaining a plurality of images, each of the images in the plurality having at least one corresponding region, generating a merged image, the merged image also having the corresponding region. The step of generating includes selecting an image source from the plurality of images to source image data for the corresponding region in the merged image by comparing attributes of the corresponding regions of the plurality of images to identify the image source having preferred attributes.

First claim

What is claimed is:

1. A method for processing breast image data, the breast image data comprising one or more reconstruction images Tr generated from a plurality of projection images Tp of a breast, the method comprising:
comparing the reconstruction images Tr in the one or more reconstruction images Tr to one another at pixel or multi-pixel granularities;
defining, in each of the reconstruction images Tr in the one or more reconstruction images Tr, boundaries for one or more corresponding regions using the comparing;
generating, from the reconstruction images Tr, a synthesized 2D mammography image of an entire thickness of the breast, wherein the synthesized 2D mammography image contains the one or more corresponding regions and is generated by selecting a source image from the plurality of reconstruction images Tr to source image data for each corresponding region in the synthesized 2D mammography image using the comparing and the boundaries;
displaying the synthesized 2D mammography image of the entire thickness of the breast;
receiving, in the displayed synthesized 2D mammography image of the entire thickness of the breast, a selection of the corresponding region; and
displaying the reconstruction images Tr used to source the image data of the selection.

2. The method of claim 1 , wherein the boundaries define arbitrary shapes.

3. The method of claim 1 , wherein the boundaries for the one or more corresponding regions are identified according to detection of a feature within the reconstruction images Tr.

4. The method of claim 3 , wherein the boundaries define a contour of the feature.

5. The method of claim 3 , further comprising applying a computer assisted detection (CAD) algorithm to the reconstruction images Tr to detect the feature.

6. The method of claim 5 , further comprising assigning a weight to each pixel or each region based on the detected feature.

7. The method of claim 6 , wherein a highest weight is assigned to a most relevant feature in each corresponding region.

8. The method of claim 1 , wherein comparing the reconstruction images Tr in the one or more reconstruction images Tr to one another at pixel or multi-pixel granularities comprises identifying for each pixel or multi-pixel the projection image with one of a highest pixel value, a lowest pixel value, or a pixel or multi-pixel which has been assigned a threshold value or weight based on application of a CAD algorithm.

9. The method of claim 1 , further comprising comparing each of the one or more corresponding regions, wherein generating the synthesized 2D mammography image by selecting the source image from the one or more reconstruction images Tr to source image data for the corresponding region in the synthesized 2D mammography image uses the comparing of the each of the one or more corresponding regions.

10. The method of claim 9 , further comprising assigning a weight to each of the corresponding regions using the boundaries and the comparing of the each of the one or more corresponding regions.

11. The method of claim 1 , further comprising identifying features within the respective corresponding region of each of the reconstruction images Tr.

12. The method of claim 11 , wherein identifying features within the respective corresponding region of each of the reconstruction images Tr comprises comparing attributes of the corresponding regions of the plurality of images to identify the image source having preferred attributes.

13. The method of claim 11 , further comprising assigning a weight to the respective corresponding region of each reconstruction images Tr based on the identified features.

14. The method of claim 1 , further comprising generating a synthesized 2D reconstructed image slab of the breast, the synthesized 2D reconstructed image slab also having the corresponding region.

15. The method of claim 14 , further comprising displaying the synthesized 2D reconstructed image slab based on the selection.

16. The method of claim 14 , wherein the synthesized 2D reconstructed image slab is generated by selecting a source image from the one or more reconstruction images Tr to source image data for the corresponding region in the synthesized 2D mammography image using the comparing.

17. A workstation for reviewing breast image data, the breast image data comprising one or more reconstruction images Tr generated from a plurality of projection images Tp of a breast, the workstation comprising:
a processor;
a display operatively coupled with the processor; and
an interface operatively coupled with the processor, wherein the processor and interface are configured to selectively cause the processor to:
compare the reconstruction images Tr in the one or more reconstruction images Tr to one another at pixel or multi-pixel granularities;
define, in each of the reconstruction images Tr in the one or more reconstruction images Tr, boundaries for one or more corresponding regions using the comparing;
generate, from the reconstruction images Tr, a synthesized 2D mammography image of an entire thickness of the breast, wherein the synthesized 2D mammography image of the entire thickness of the breast contains the one or more corresponding regions and is generated by selecting a source image from the one or more reconstruction images Tr to source image data for each corresponding region in the synthesized 2D mammography image using the comparing;
display the synthesized 2D mammography image of the entire thickness of the breast;
receive, in the displayed synthesized 2D mammography image of the entire thickness of the breast, a selection of the corresponding region; and
display the reconstruction images Tr used to source the image data of the selection.

18. The workstation of claim 17 , wherein the boundaries for the one or more corresponding regions are identified according to the detection of a feature within the reconstruction images Tr.

19. The workstation of claim 18 , wherein the boundaries define a contour of the feature.

20. The workstation of claim 18 , further comprising assigning a weight to each pixel or each region based on the detected feature.

Assignees

• Hologic Inc

Inventors

• Kreeger Kevin
• Smith Andrew P
• Kshirsagar Ashwini
• Ge Jun
• Zhang Xiangwei
• Chui Haili
• Ruth Christopher
• Zhang Yiheng
• Wei Liyang
• Stein Jay

Classifications

• G06T12/30

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

• G06T12/20

  Inverse problem, i.e. transformations from projection space into object space · CPC title

• G06T2211/436

  Limited angle · CPC title

• A61B6/025 Primary

  Tomosynthesis · CPC title

• A61B6/5205

  involving processing of raw data to produce diagnostic data · CPC title