Systems and methods for processing x-ray images

Patent metadata

Field	Value
Publication number	US-2025166205-A1
Application number	US-202519031405-A
Country	US
Kind code	A1
Filing date	Jan 18, 2025
Priority date	May 24, 2019
Publication date	May 22, 2025
Grant date	—

Abstract

The present disclosure is related to systems and methods for processing X-ray images. A method for processing an X-ray image may include obtaining an X-ray image; and determining a metal image based on the X-ray image by using a trained metal detection model. The metal image includes information of a metal object in the X-ray image.

First claim

What is claimed is:

1 . A system for processing an image, comprising:
at least one storage device including a set of instructions for processing an image; and at least one processor in communication with the at least one storage device, wherein when executing the set of instructions, the at least one processor is directed to cause the system to perform operations including: determining an initial human body region in an image; determining a threshold image based on pixel values of the initial human body region, wherein a threshold pixel in the threshold image corresponds to one or more pixels in the initial human body region; and determining whether pixels in the initial human body region are target pixels in a target human body region based on the threshold image.

2 . The system of claim 1 , wherein the determining the initial human body region in the image includes:
determining a non-beam limiter region in the image; determining a direct exposure region in the non-beam limiter region; and determining the initial human body region based on the non-beam limiter region and the direct exposure region, wherein the initial human body region is a region by excluding the direct exposure region from the non-beam limiter region.

3 . The system of claim 2 , wherein the determining the non-beam limiter region in the image includes:
obtaining a position of a beam limiter from an imaging device; and determining the non-beam limiter region based on the position of the beam limiter.

4 . The system of claim 3 , wherein the determining the non-beam limiter region based on the position of the beam limiter includes:
determining a curve equation of a boundary of the beam limiter in the image based on the position of the beam limiter; and determining the non-beam limiter region based on the curve equation of the boundary of the beam limiter in the image.

5 . The system of claim 2 , wherein the determining the direct exposure region in the non-beam limiter region includes:
determining the direct exposure region based on gray values with respect to the non-beam limiter region according to a maximum between-cluster variance segmentation algorithm.

6 . The system of claim 1 , wherein the determining the threshold image based on pixel values of the initial human body region includes:
segmenting the initial human body region into a plurality of sub-regions; determining segment thresholds of the plurality of sub-regions; and determining the threshold image by fitting the segment thresholds.

7 . The system of claim 6 , wherein each sub-region of the plurality of sub-regions includes at least one pixel in the initial human body region.

8 . The system of claim 6 , wherein at least two sub-regions of the plurality of sub-regions are different from each other.

9 . The system of claim 6 , wherein shapes of the plurality of sub-regions are regular.

10 . The system of claim 6 , wherein the threshold image is a curve or a surface.

11 . The system of claim 6 , wherein the determining the threshold image by fitting the segment thresholds includes:
obtaining an initial surface equation; determining a target surface equation of the threshold image by solving the initial surface equation based on the segment thresholds of the plurality of sub-regions and positions of the plurality of sub-regions in the image; and determining pixel values of pixels in the threshold image based on the target surface equation.

12 . The system of claim 6 , wherein the segment thresholds of the plurality of sub-regions are determined according to a maximum between-cluster variance segmentation algorithm.

13 . The system of claim 1 , wherein the determining whether pixels in the initial human body region are target pixels in the target human body region based on the threshold image includes:
determining a compare result by comparing a pixel value of a pixel or a pixel operation value of a plurality of pixels in the initial human body region with a threshold pixel value of a corresponding threshold pixel in the threshold image; and determining whether the pixels in the initial human body region are target pixels in the target human body region based on the compare result.

14 . The system of claim 1 , wherein the image is an X-ray image.

15 . A method for processing an image, comprising:
determining an initial human body region in an image; determining a threshold image based on pixel values of the initial human body region, wherein a threshold pixel in the threshold image corresponds to one or more pixels in the initial human body region; and determining whether pixels in the initial human body region are target pixels in a target human body region based on the threshold image.

16 . The method of claim 15 , wherein the determining the initial human body region in the image includes:
determining a non-beam limiter region in the image; determining a direct exposure region in the non-beam limiter region; and determining the initial human body region based on the non-beam limiter region and the direct exposure region, wherein the initial human body region is a region by excluding the direct exposure region from the non-beam limiter region.

17 . The method of claim 15 , wherein the determining the non-beam limiter region in the image includes:
obtaining a position of a beam limiter from an imaging device; and determining the non-beam limiter region based on the position of the beam limiter.

18 . The method of claim 17 , wherein the determining the non-beam limiter region based on the position of the beam limiter includes:
determining a curve equation of a boundary of the beam limiter in the image based on the position of the beam limiter; and determining the non-beam limiter region based on the curve equation of the boundary of the beam limiter in the image.

19 . The method of claim 16 , wherein the determining the direct exposure region in the non-beam limiter region includes:
determining the direct exposure region based on gray values with respect to the non-beam limiter region according to a maximum between-cluster variance segmentation algorithm.

20 . A non-transitory readable medium, comprising at least one set of instructions for processing an image, wherein when executed by at least one processor of an electrical device, the at least one set of instructions directs the at least one processor to perform a method, the method comprising:
determining an initial human body region in an image; determining a threshold image based on pixel values of the initial human body region, wherein a threshold pixel in the threshold image corresponds to one or more pixels in the initial human body region; and determining whether pixels in the initial human body region are target pixels in a target human body region based on the threshold image.

Assignees

• Shanghai United Imaging Healthcare Co Ltd

Inventors

• Cui Kai
• Jiang Chunhua
• Xu Liang
• Zhao Shurui
• Zhong Jian
• Niu Jie
• Ma Yan'Ge
• Teng Wanli
• Zhang Na
• Feng Juan

Classifications

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/10116

  X-ray image · CPC title

• G06T7/0012

  Biomedical image inspection · CPC title

• A61B6/505

  for diagnosis of bone · CPC title