X-RAY APPARATUS AND METHOD OF ACQUIRING MEDICAL IMAGE THEREOF

• US 20180146935A1
• Filed: 11/27/2017
• Published: 05/31/2018
• Est. Priority Date: 11/25/2016
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: SONG, Jeong Yong, LEE, Byeong Won
• Granted Patent: US 11,083,421 B2
• Time in Patent Office: Days
• CPC Class Codes: A61B 6/03 Computed tomography [CT] echo-tomography A61B8/14
• CPC Class Codes: A61B 6/04 Positioning of patients; Tiltable beds or the like operating tables A61G13/00; operating chairs A61G15/00
• CPC Class Codes: A61B 6/4014 arranged in multiple source-detector units
• CPC Class Codes: A61B 6/4405 the apparatus being movable or portable, e.g. handheld or mounted on a trolley
• CPC Class Codes: A61B 6/462 characterised by constructional features of the display
• CPC Class Codes: A61B 6/465 adapted to display user selection data, e.g. graphical user interface, icons or menus
• CPC Class Codes: A61B 6/5205 involving processing of raw data to produce diagnostic data
• CPC Class Codes: A61B 6/5282 due to scatter
• CPC Class Codes: A61B 6/5294 involving using additional data, e.g. patient information, image labeling, acquisition parameters
• CPC Class Codes: A61B 6/544 dependent on patient size
• CPC Class Codes: A61B 6/563 involving image data transmission via a network
• CPC Class Codes: A61B 6/584 determining position of components of the apparatus or device using images of the phantom
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/20084 Artificial neural networks [ANN]
• CPC Class Codes: G06T 5/60 using machine learning, e.g. neural networks
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06T 5/73 Deblurring; Sharpening

Abstract

Disclosed herein is a method of acquiring a medical image of an X-ray apparatus, including: acquiring an original radiation image of a target object and capturing condition information of the object; acquiring a scatter radiation image related to the original radiation image by inputting the original radiation image and the capturing condition information to a learning network model configured to estimate scatter radiation; and acquiring a scatter radiation-processed medical image from the original radiation image on the basis of the original radiation image and the scatter radiation image, wherein the learning network model configured to estimate scatter radiation is a learning network model taught using a plurality of scatter radiation images and a plurality of pieces of capturing condition information related to each of the plurality of scatter radiation images.

Claims

1. A method of acquiring a medical image of an X-ray apparatus performed by one or more computers, the method comprising:

acquiring an original radiation image of an object and capturing condition information of the object;

acquiring a scatter radiation image related to the original radiation image by inputting the original radiation image and the capturing condition information to a learning network model configured to estimate scatter radiation; and

outputting a scatter radiation-processed medical image from the original radiation image based on the original radiation image and the scatter radiation image, the scatter radiation-processed medical image having less scatter radiation information than the original radiation image,

wherein the learning network model configured to estimate scatter radiation comprises a learning network model taught based on a plurality of scatter radiation images and a plurality of pieces of capturing condition information related to a plurality of scatter radiation images.

2. The method of claim 1, wherein the acquiring of the scatter radiation image comprises acquiring the scatter radiation image based on a relationship between a plurality of network nodes of the learning network model and weights of the plurality of network nodes.

3. The method of claim 1, wherein the original radiation image comprises an original radiation image of the object captured when an anti-scatter grid is not used.

4. The method of claim 1, wherein the acquiring of the scatter radiation image comprises receiving a user input to set a degree of removal of the scatter radiation, and acquiring the scatter radiation image having an intensity of scatter radiation corresponding to the set degree of removal of the scatter radiation.

5. The method of claim 1, wherein the outputting of the scatter radiation-processed medical image comprises acquiring a scatter radiation-removed radiation image from the original radiation image.

6. The method of claim 1, wherein the learning network model configured to estimate scatter radiation comprises a model taught based on at least one of a characteristic of a region of the object and a thickness of the object.

7. The method of claim 1, wherein the learning network model configured to estimate scatter radiation comprises a model taught based on a degree of removal of scatter radiation for the original radiation image.

8. The method of claim 1, wherein the capturing condition information comprises at least one of a voltage applied to generate X-rays, a current applied to generate the X-rays, a distance from an X-ray emitter to the object, and an energy band of emitted X-rays.

9. The method of claim 1, wherein the learning network model is stored in a memory of the X-ray apparatus or a memory of an external server, wherein, when the learning network model is stored in the memory of the external server, the acquiring of the scatter radiation image comprises acquiring the scatter radiation image by inputting the original radiation image and the capturing condition information to the learning network model stored in the external server.

10. A method of acquiring a medical image of an X-ray apparatus performed by one or more computers, the method comprising:

acquiring an original radiation image of a target object and capturing condition information of the target object; and

acquiring a scatter radiation-processed medical image from the original radiation image by inputting the original radiation image and the capturing condition information to a learning network model configured to estimate a scatter radiation-processed medical image,

wherein the learning network model configured to estimate a scatter radiation-processed medical image comprises a learning network model taught based on a plurality of original radiation images and a plurality of pieces of capturing condition information related to the plurality of original radiation images.

11. An X-ray apparatus comprising:

an X-ray emitter configured to emit X-rays toward an object;

an X-ray detector configured to detect the X-rays that have passed through the object;

a controller communicatively connected to the X-ray emitter and the X-ray detector to control the X-ray apparatus; and

a memory communicatively connected to the controller,

wherein the memory is configured to store instructions for the controller to perform a control operation to;

acquire a scatter radiation image related to an original radiation image of the object acquired from the X-ray detector, by inputting the original radiation image and capturing condition information of the object to a learning network model configured to estimate scatter radiation, and

acquire a scatter radiation-processed medical image from the original radiation image based on the original radiation image and the scatter radiation image, and

wherein the learning network model configured to estimate scatter radiation comprises learning network model taught based on a plurality of scatter radiation images and a plurality of pieces of capturing condition information related to the plurality of scatter radiation images.

12. The X-ray apparatus of claim 11, wherein the instructions for the controller to perform the control operation to acquire the scatter radiation image related to the original radiation image is based on a relationship between a plurality of network nodes constituting the learning network model and weights of the plurality of network nodes.

13. The X-ray apparatus of claim 11, wherein the original radiation image comprises an original radiation image of the object captured when an anti-scatter grid is not used.

14. The X-ray apparatus of claim 11, wherein the instructions for the controller further perform a control operation to receive a user input to set a degree of removal of the scatter radiation and performs the control operation to acquire the scatter radiation image having an intensity of scatter radiation corresponding to the set degree of removal of the scatter radiation.

15. The X-ray apparatus of claim 11, wherein the scatter radiation-processed medical image has less scatter radiation information than the original radiation image.

16. The X-ray apparatus of claim 11, wherein the learning network model configured to estimate scatter radiation comprises a model taught based on the at least one of a characteristic of a region of the object and a thickness of the object.

17. The X-ray apparatus of claim 11, wherein the learning network model configured to estimate scatter radiation comprises a model taught based on a degree of removal of the scatter radiation for the original radiation image.

18. The X-ray apparatus of claim 11, wherein the capturing condition information comprises at least one of a voltage applied to generate X-rays, a current applied to generate the X-rays, a distance from an X-ray emitter to the object, and an energy band of emitted X-rays.

19. An X-ray apparatus comprising:

an X-ray emitter configured to emit X-rays toward an object;

an X-ray detector configured to detect the X-rays that have passed through the object;

a controller communicatively connected to the X-ray emitter and the X-ray detector to control the X-ray apparatus; and

a memory communicatively connected to the controller,

wherein the memory is configured to store instructions for the controller to perform a control operation to acquire a scatter radiation-processed medical image from an original radiation image of the object acquired from the X-ray detector, the scatter radiation-processed medical image being acquired by inputting the original radiation image and capturing condition information of the object to a learning network model configured to estimate a scatter radiation-processed medical image, and

wherein the learning network model configured to estimate the scatter radiation-processed medical image comprises a learning network model taught based on a plurality of original radiation images and a plurality of pieces of capturing condition information related to the plurality of original radiation images.

20. A computer program product comprising computer-readable recording media, the computer program product comprising instructions enabling an X-ray apparatus to:

acquire an original radiation image of an object and capturing condition information of the object,

acquire a scatter radiation image related to the original radiation image by inputting the original radiation image and the capturing condition information to a learning network model configured to estimate scatter radiation, and

acquire a scatter radiation-processed medical image from the original radiation image based on the original radiation image and the scatter radiation image,

wherein the learning network model configured to estimate scatter radiation comprises a learning network model taught based on a plurality of scatter radiation images and a plurality of pieces of capturing condition information related to the plurality of scatter radiation images.