Method and systems for anatomy/view classification in x-ray imaging

Patent metadata

Field	Value
Publication number	US-11564651-B2
Application number	US-202016742629-A
Country	US
Kind code	B2
Filing date	Jan 14, 2020
Priority date	Jan 14, 2020
Publication date	Jan 31, 2023
Grant date	Jan 31, 2023

Abstract

Various methods and systems are provided for x-ray imaging. In one embodiment, a method for an image pasting examination comprises acquiring, via an optical camera and/or depth camera, image data of a subject, controlling an x-ray source and an x-ray detector according to the image data to acquire a plurality of x-ray images of the subject, and stitching the plurality of x-ray images into a single x-ray image. In this way, optimal exposure techniques may be used for individual acquisitions in an image pasting examination such that the optimal dose is utilized, stitching quality is improved, and registration failures are avoided.

First claim

The invention claimed is:

1. A method, comprising:
controlling an x-ray source and an x-ray detector to acquire a plurality of images of a subject;
classifying, with a trained neural network, a respective anatomy/view depicted in each image of the plurality of images, where each respective anatomy/view includes a predicted anatomy and a predicted view depicted in that image;
performing post-processing of each image based on the respective anatomy/view, including selecting two or more images from the plurality of images that are classified as having the same predicted view and stitching the two or more images to form a stitched image; and
displaying the stitched image.

2. The method of claim 1 , further comprising determining parameters for adjusting one or more of edge details, contrast, and noise level in each image according to the respective anatomy/view, and performing the post-processing of the image according to the determined parameters.

3. The method of claim 1 , wherein the predicted view is a first predicted view, and further comprising:
determining, based on the respective anatomy/view depicted in each image of the plurality of images, that the plurality of images further includes two or more additional images classified as having a second predicted view, different than the first predicted view;
stitching together the two or more additional images to form a second stitched image; and
displaying the second stitched image.

4. The method of claim 1 , wherein the at least two images include a first image and a second image that depict adjacent and overlapping regions of the subject, and wherein classifying, with the trained neural network, the respective anatomy/view depicted in each image of the plurality of images includes classifying at least a first anatomy/view depicted in the first image and a second anatomy/view depicted in the second image.

5. The method of claim 4 , wherein performing the post-processing comprises registering the plurality of images according to the anatomy/views depicted in the plurality of images, including registering the first image to the second image according to the first anatomy/view and the second anatomy/view, and stitching the registered first image and second image to generate the stitched image.

6. The method of claim 5 , wherein stitching the first image and the second image comprises stitching the first image and the second image according to an image pasting protocol configured for the predicted view of the first image and the second image.

7. The method of claim 6 , further comprising controlling the x-ray source and the x-ray detector to acquire a second plurality of images including at least a third image and a fourth image of the subject, wherein the plurality of images including the first image and the second image depict adjacent and overlapping regions of the subject in a first view, and wherein the second plurality of images depict adjacent and overlapping regions of the subject in a second view different from the first view.

8. The method of claim 7 , further comprising classifying, with the trained neural network, a respective anatomy/view depicted in each image of the second plurality of images including a third anatomy/view depicted in the third image and a fourth anatomy/view depicted in the fourth image.

9. The method of claim 8 , further comprising determining that the respective anatomy/view depicted in each image of the second plurality of images includes the second view, registering the second plurality of images according to an image pasting protocol for the second view, stitching the registered second plurality of images to generate a second stitched image with the second view, and displaying the second stitched image.

10. The method of claim 9 , further comprising receiving, from the trained neural network, probabilities for corresponding anatomy/views classified for the plurality of images and the second plurality of images, determining whether the corresponding anatomy/views are correct based on an occurrence of anatomy/views and the probabilities, and adjusting a classification of an anatomy/view for a given image if one of the occurrence of anatomy/views and the probabilities indicate that the classification of the anatomy/view for the given image is incorrect.

11. An x-ray imaging system, comprising:
an x-ray source for generating x-rays;
an x-ray detector configured to detect the x-rays;
a display device; and
a processor configured with instructions in non-transitory memory that when executed cause the processor to:
control the x-ray source and the x-ray detector to acquire a plurality of images of a subject;
classify, with a trained neural network, a respective anatomy/view depicted in each image of the plurality of images;
receiving, from the trained neural network, a respective probability for each anatomy/view classified for the plurality of images, determining whether each anatomy/view is correct based on an occurrence of anatomy/views and each probability, and adjusting a classification of an anatomy/view for a given image if one of the occurrence of anatomy/views and the probabilities indicate that the classification of the anatomy/view for the given image is incorrect;
perform post-processing of each image based on each anatomy/view; and
display, via the display device, the post-processed image.

12. The system of claim 11 , wherein the processor is further configured with instructions in the non-transitory memory that when executed cause the processor to determine parameters for adjusting one or more of edge details, contrast, and noise level in each image according to the respective anatomy/view, and perform the post-processing of each image according to the determined parameters.

13. The system of claim 11 , wherein the processor is further configured with instructions in the non-transitory memory that when executed cause the processor to determine a first plurality of images in the plurality of images corresponding to a first view, determine a second plurality of images in the plurality of images corresponding to a second view, register and stitch the first plurality of images into a first stitched image according to the first view, and register and stitch the second plurality of images into a second stitched image according to the second view.

14. The system of claim 11 , further comprising an optical camera positioned adjacent to the x-ray source and co-aligned with the x-ray source, wherein the processor is further configured with instructions in the non-transitory memory that when executed cause the processor to:
acquire camera data via the optical camera;
classify, with the trained neural network, an anatomy/view of the subject depicted in the camera data;
select one or more acquisition parameters based on the anatomy/view of the subject depicted in the camera data; and
control the x-ray source and the x-ray detector with the one or more acquisition parameters to acquire the plurality of images of the subject.

Assignees

• Ge Prec Healthcare Llc

Inventors

• Wang Dejun
• Yang Jingyi
• Ge Yaan
• Zhou Aizhen
• Nye Katelyn
• Rao Gireesha
• Qi Buer
• Akram Najib

Classifications

• G06T2207/20221

  Image fusion; Image merging · CPC title

• A61B6/5217 Primary

  extracting a diagnostic or physiological parameter from medical diagnostic data · CPC title

• G06K9/6267

  Physics · mapped topic

• G06T7/30 Primary

  Determination of transform parameters for the alignment of images, i.e. image registration · CPC title

• G06T2207/10116

  X-ray image · CPC title