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

Patent metadata

Field	Value
Publication number	US-10978026-B2
Application number	US-202016792182-A
Country	US
Kind code	B2
Filing date	Feb 14, 2020
Priority date	Nov 27, 2011
Publication date	Apr 13, 2021
Grant date	Apr 13, 2021

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 method comprising:
obtaining a plurality of images of a breast, each of the images in the plurality having a corresponding region;
identifying features within the respective corresponding region of each of the images;
assigning a weight to the respective corresponding region of each image based on the identified features;
generating a synthesized 2D mammography image of the breast, the synthesized 2D mammography image also having the corresponding region, wherein the synthesized 2D mammography image is generated by selecting a source image from the plurality of images to source image data for the corresponding region in the synthesized 2D mammography image by comparing the assigned weights of the respective corresponding region of the plurality of images; and
displaying at least one of the synthesized 2D mammography image and the source image data for the at least one corresponding region.

2. The method of claim 1 , further comprising generating a map for the synthesized 2D mammography image, wherein the map identifies the source image of the corresponding region in the synthesized 2D mammography image.

3. The method of claim 1 , wherein the identified features include at least one of speculated lesions, masses, and calcifications.

4. The method of claim 1 , wherein the source image for the corresponding region in the synthesized 2D mammography image is selected based on having a comparatively highest assigned weight for the corresponding region of all images of the plurality.

5. The method of claim 1 , wherein the corresponding region in the synthesized 2D mammography image includes at least one pixel from the source image.

6. The method of claim 1 , wherein a size of the corresponding region in the synthesized 2D mammography image is statically pre-defined.

7. The method of claim 1 , wherein a size of the corresponding region in the synthesized 2D mammography image varies in accordance with a varying threshold of the source image.

8. A method for processing breast image data, the method comprising:
obtaining a plurality of images of a breast, wherein each image of the plurality has a plurality of corresponding regions with the other images of the plurality;
identifying features within the respective corresponding regions of each of the images;
assigning a respective weight to the corresponding regions of each image based on the identified features;
generating a synthesized 2D mammography image of the breast, the synthesized 2D mammography image also having the plurality of corresponding regions, wherein the synthesized 2D mammography image is generated by selecting a respective source image from the plurality of images to source image data for each of the corresponding regions in the synthesized 2D mammography image by comparing the assigned weights of the respective corresponding regions of the plurality of images; and
displaying at least one of the synthesized 2D mammography image and the source image data for at least one of the corresponding regions.

9. The method of claim 8 , further comprising generating a map for the synthesized 2D mammography image, wherein the map identifies the respective source image for each of the corresponding regions in the synthesized 2D mammography image.

10. The method of claim 8 , wherein the identified features include at least one of speculated lesions, masses, and calcifications.

11. The method of claim 8 , wherein the respective source image for each of the corresponding regions in the synthesized 2D mammography image is selected based on having a comparatively highest assigned weight for the respective corresponding region of all images of the plurality.

12. The method of claim 8 , wherein the corresponding regions in the synthesized 2D mammography image include at least one pixel from the respective source images of the corresponding regions.

13. The method of claim 8 , wherein a size of each corresponding region in the synthesized 2D mammography image is statically pre-defined.

14. The method of claim 8 , wherein a size of each corresponding region in the synthesized 2D mammography image varies in accordance with a varying threshold of the respective source image of the corresponding region.

15. A workstation for reviewing breast image data, the workstation comprising:
a processor;
a display operatively coupled with the processor; and
an interface operatively coupled with the processor, wherein the respective processor and interface are configured to allow a user to selectively cause the processor to
obtain a plurality of images of a breast, each of the images in the plurality having a corresponding region;
identify features within the respective corresponding region of each of the images;
assign a weight to the respective corresponding region of each image based on the identified features;
generate a synthesized 2D mammography image of the breast, the synthesized 2D mammography image also having the corresponding region, wherein the synthesized 2D mammography image is generated by selecting a source image from the plurality of images to source image data for the corresponding region in the synthesized 2D mammography image by comparing the assigned weights of the respective corresponding region of the plurality of images; and
display at least one of the synthesized 2D mammography image and the source image data for the at least one corresponding region.

16. The workstation of claim 15 , wherein the respective processor and interface are configured to allow a user to selectively cause the processor to generate a map for the synthesized 2D mammography image, wherein the map identifies the source image of the corresponding region in the synthesized 2D mammography image.

17. The workstation of claim 15 , wherein the identified features include at least one of speculated lesions, masses, and calcifications.

18. The workstation of claim 15 , wherein the source image for the corresponding region in the synthesized 2D mammography image is selected based on having a comparatively highest assigned weight for the corresponding region of all images of the plurality.

Assignees

• Hologic Inc

Inventors

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