Systems and methods for image-based object modeling using multiple image acquisitions or reconstructions

Patent metadata

Field	Value
Publication number	US-9058692-B1
Application number	US-201414254491-A
Country	US
Kind code	B1
Filing date	Apr 16, 2014
Priority date	Apr 16, 2014
Publication date	Jun 16, 2015
Grant date	Jun 16, 2015

Abstract

Systems and methods are disclosed for integrating imaging data from multiple sources to create a single, accurate model of a patient's anatomy. One method includes receiving a representation of a target object for modeling; determining one or more first anatomical parameters of the target anatomical object from at least one of one or more first images of the target anatomical object; determining one or more second anatomical parameters of the target anatomical object from at least one of one or more second images of the target anatomical object; updating the one or more first anatomical parameters based at least on the one or more second anatomical parameters; and generating a model of the target anatomical object based on the updated first anatomical parameters.

First claim

What is claimed is:

1. A computer-implemented method of modeling at least a portion of a patient's anatomy, using a computer system, the method comprising:
determining one or more first anatomical parameters of a target anatomical object associated with a first segmentation of image data;
determining one or more second anatomical parameters of the target anatomical object associated with a second segmentation of said image data;
calculating one or more updated first anatomical parameters based on the one or more second anatomical parameters; and
updating a model of the target anatomical object, based at least on the updated first anatomical parameters.

2. The method of claim 1 , wherein the image data includes one or more first images and one or more second images.

3. The method of claim 2 , wherein the one or more first images include one or more computed tomography (CT) scans obtained using a first reconstruction method, and the one or more second images include one or more CT scans obtained using a second reconstruction method.

4. The method of claim 2 , wherein the one or more first images include one or more CT scans obtained at a first time, and the one or more second images include one or more CT scans obtained at a second time that is different from the first time.

5. The method of claim 4 , further comprising:
designating one of the first images or second images as a reference image;
using image registration to register each of the one or more first images and each of the one or more second images to the reference image; and
calculating the one or more updated first anatomical parameters by determining the average of a probability that a portion of each first image represents a portion of the target anatomical object and a probability that a portion of each second image represents the portion of the target anatomical object.

6. The method of claim 2 , wherein the one or more first images include one or more CT scans and the one or more second images include one or more magnetic resonance (MR) images.

7. The method of claim 6 , further comprising:
designating one of the first or second images having a maximum or optimum spatial resolution as a reference image;
using three-dimensional image registration to register each of the one or more first images and each of the one or more second images to the reference image; and
calculating the one or more updated first anatomical parameters by determining the average of a probability that a portion of each first image represents a portion of the target anatomical object with a probability that a portion of each second image represents the portion of the target anatomical object.

8. The method of claim 1 , further comprising:
receiving a representation of a target anatomical object for modeling, wherein the representation of the target anatomical object includes one or more of a boundary model, volume model, appearance model, and a shape model.

9. The method of claim 1 , further comprising:
receiving a representation of a target anatomical object for modeling, wherein the representation of the target anatomical object includes a model of a patient coronary vessel lumen, the model including a plurality of voxels representing a probability that each of the plurality of voxels belongs to the patient's coronary vessel lumen.

10. The method of claim 9 , wherein calculating the one or more updated first anatomical parameters includes determining the average of a probability that a voxel of a first image belongs to the patient's coronary vessel lumen and a probability that a voxel of a second image belongs to the patient's coronary vessel lumen.

11. The method of claim 1 , wherein calculating the one or more updated first anatomical parameters includes combining the one or more first anatomical parameters with the one or more second anatomical parameters.

12. The method of claim 1 , further comprising:
determining a probability that a portion of the image data represents a portion of the target anatomical object, based on the first segmentation or second segmentation.

13. The method of claim 12 , wherein calculating the one or more updated first anatomical parameters includes determining the average of a probability that a portion of a first image represents a portion of the target anatomical object and a probability that a portion of a second image represents the portion of the target anatomical object.

14. The method of claim 1 , further comprising:
receiving a representation of a target anatomical object for modeling, wherein the representation is determined from the one or more first anatomical parameters.

15. The method of claim 1 , further comprising:
assigning a probability or level set value to each pixel of the image data.

16. A system of modeling at least a portion of a patient's anatomy, the system comprising:
a data storage device storing instructions for modeling based on patient-specific anatomic image data; and
a processor configured to execute the instructions to perform a method including:
determining one or more first anatomical parameters of a target anatomical object associated with a first segmentation of image data;
determining one or more second anatomical parameters of the target anatomical object associated with a second segmentation of said image data;
calculating one or more updated first anatomical parameters based on the one or more second anatomical parameters; and
updating a model of the target anatomical object, based at least on the updated first anatomical parameters.

17. The system of claim 16 , wherein the image data includes one or more first images and one or more second images.

18. The system of claim 17 , wherein the one or more first images include one or more computed tomography (CT) scans obtained using a first reconstruction method, and the one or more second images include one or more CT scans obtained using a second reconstruction method.

19. The system of claim 17 , wherein the one or more first images include one or more CT scans obtained at a first time, and the one or more second images include one or more CT scans obtained at a second time that is different from the first time.

20. The system of claim 17 , wherein the one or more first images include one or more CT scans and the one or more second images include one or more magnetic resonance (MR) images.

21. A non-transitory computer readable medium for use on a computer system containing computer-executable programming instructions for modeling at least a portion of a patient's anatomy, the method comprising:
determining one or more first anatomical parameters of a target anatomical object associated with a first segmentation of image data;
determining one or more second anatomical parameters of the target anatomical object associated with a second segmentation of said image data;
calculating one or more updated first anatomical parameters based on the one or more second anatomical parameters; and
updating a model of the target anatomical object, based at least on the updated first anatomical parameters.

22. The method of claim 21 , wherein the image data includes one or more first images and one or more second images.

23. The method of claim 22 , wherein the one or more first images include one or more computed tomography (CT) scans obtained using a first reconstruction method, and the one or more second images include one or more CT scans obtained using a second reconstruction me

Assignees

• Heartflow Inc

Inventors

• Grady Leo
• Schaap Michiel

Classifications

• G06T7/0014 Primary

  using an image reference approach · CPC title

• G06T15/08 Primary

  Volume rendering · CPC title

• G06T2207/20128

  Atlas-based segmentation · CPC title

• G06T7/337

  involving reference images or patches · CPC title

• G06T7/174

  involving the use of two or more images · CPC title