Methods and system for simulated radiology studies based on prior imaging data

Patent metadata

Field	Value
Publication number	US-11955228-B2
Application number	US-202117643738-A
Country	US
Kind code	B2
Filing date	Dec 10, 2021
Priority date	Dec 10, 2021
Publication date	Apr 9, 2024
Grant date	Apr 9, 2024

Abstract

Systems and methods are provided for simulating medical images based on previously acquired data and a defined imaging protocol. In an example, a method includes generating a simulated medical image of a patient via virtual imaging based on previously obtained medical images and a scan intent of the virtual imaging, and outputting an imaging protocol based on a virtual protocol of the virtual imaging.

First claim

The invention claimed is:

1. A method, comprising:
generating a simulated medical image of a patient via virtual imaging based on previously obtained medical images and a scan intent of the virtual imaging, wherein the scan intent comprises one or more of an interventional intent, a regulatory clearance intent, and a parameter optimization intent; and
outputting an imaging protocol based on a virtual protocol of the virtual imaging.

2. The method of claim 1 , wherein the previously obtained medical images comprise one or more of previously obtained medical images of the patient and previously obtained medical images of different patients selected to match demographics of the patient.

3. The method of claim 1 , wherein the previously obtained medical images are obtained via a first type of imaging and the scan intent of the virtual imaging includes using a second type of imaging, and the method further comprises performing style transfer on the previously obtained medical images to simulate obtaining the previously obtained medical images using the second type of imaging.

4. The method of claim 3 , wherein the first type of imaging and the second type of imaging include different imaging modalities.

5. The method of claim 3 , wherein the first type of imaging and the second type of imaging include different imaging protocols.

6. The method of claim 3 , wherein performing the style transfer comprises processing the previously obtained medical images via one or more of a generative adversarial network and a physiological simulation.

7. The method of claim 1 , wherein generating the simulated medical image of the patient via the virtual imaging based on the previously obtained medical images and the scan intent of the virtual imaging comprises:
building a digital model of the patient based on the previously obtained medical images;
generating the virtual protocol for the virtual imaging based on the scan intent of the virtual imaging; and
virtually imaging the digital model of the patient using the virtual protocol.

8. The method of claim 7 , wherein the virtual imaging uses a Monte Carlo method.

9. The method of claim 7 , wherein generating the virtual protocol for the virtual imaging is further based on a user selection, the user selection comprising one or more of a desired imaging system model, a type of contrast agent, and a type of radionuclide.

10. The method of claim 1 , wherein the parameter optimization intent comprises one or more of optimization of a dose of a contrast agent, optimization of a radiation dose, optimization of an image smoothness, optimization of an image contrast, optimization of organ fill states, and optimization of implant imaging.

11. A method, comprising:
selecting one or more previously obtained medical images based on demographics of a patient;
building a three-dimensional (3D) anatomical representation of the patient using the one or more previously obtained medical images; and
generating an expected medical image of the patient by processing the 3D anatomical representation of the patient using physics of an image acquisition process and a protocol generated based on an imaging intent and user selections, wherein the imaging intent comprises one or more of an interventional intent, a regulatory clearance intent, and a parameter optimization intent.

12. The method of claim 11 , wherein the one or more previously obtained medical images comprise medical images of digital phantoms.

13. The method of claim 11 , wherein selecting the one or more previously obtained medical images comprises:
outputting a plurality of potential medical images to a display, the plurality of potential medical images selected from an image database according to the demographics of the patient; and
selecting the one or more previously obtained medical images from the plurality of potential medical images based on user input.

14. The method of claim 11 , wherein the imaging intent and the user selections provide constraints for the image acquisition process, including at least one of a type of contrast agent for the image acquisition process, a type of radionuclide for the image acquisition process, contrast optimization for the image acquisition process, dose optimization for the image acquisition process, and timing optimization for the image acquisition process.

15. The method of claim 11 , further comprising:
generating an imaging protocol for imaging the patient via an imaging system based on the protocol used for generating the expected medical image;
acquire imaging data of the patient via the imaging system according to the generated imaging protocol;
reconstruct one or more images of the patient based on the acquired imaging data; and
output the one or more reconstructed images.

16. A system, comprising:
a display; and
an image processing device operably coupled to the display and storing instructions executable to:
retrieve one or more medical images from an image database based on demographic information of a patient;
build a three-dimensional (3D) anatomical representation of the patient from the one or more medical images;
generate predicted medical images of the patient by processing the 3D anatomical representation of the patient based on physics of an image acquisition process and a protocol generated based on an imaging intent and user selections, wherein the imaging intent comprises one or more of an interventional intent, a regulatory clearance intent, and a parameter optimization intent; and
output the predicted medical images of the patient to the display.

17. The system of claim 16 , further comprising a user interface operatively coupled to the image processing device, and wherein the image processing device stores further instructions executable to:
generate a protocol for processing the 3D anatomical representation based on input received via the user interface.

18. The system of claim 17 , wherein the image processing device stores further instructions executable to:
generate an imaging protocol for imaging the patient with an imaging system based on the protocol for processing the 3D anatomical representation; and
output the imaging protocol to the imaging system.

19. The system of claim 16 , wherein the image database comprises a plurality of medical images acquired over a plurality of different image acquisitions using a plurality of different imaging modalities.

Assignees

• Ge Prec Healthcare Llc

Inventors

• Thibault Jean-Baptiste
• Maltz Jonathan S

Classifications

• G06T12/20

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

• G06T12/30

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

• G16H30/40 Primary

  for processing medical images, e.g. editing · CPC title

• A61B6/465

  adapted to display user selection data, e.g. graphical user interface, icons or menus · CPC title

• A61B6/466

  adapted to display 3D data · CPC title