Model-based heart reconstruction and navigation

• US 7,773,719 B2
• Filed: 03/25/2008
• Issued: 08/10/2010
• Est. Priority Date: 03/26/2007
• Status: Active Grant

• Current Assignee: Siemens Healthineers AG (Siemens AG)
• Original Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Inventors: Comaniciu, Dorin, Galant, Adam K.
• Primary Examiner(s): Glick; Edward J
• Assistant Examiner(s): Taningco; Alexander H
• Application Number:
  US12/054,622
• Publication Number:
  US 20080240337A1
• Time in Patent Office: 868 Days
• Field of Search: 378/8, 378/42, 378/4, 378/20
• US Class Current: 378/4
• CPC Class Codes: A61B 2017/00703 correcting for movement of heart, e.g. ECG-triggered
• CPC Class Codes: A61B 2090/367 creating a 3D dataset from 2D images using position information
• CPC Class Codes: A61B 6/032 Transmission computed tomography [CT]
• CPC Class Codes: A61B 6/503 for diagnosis of the heart
• CPC Class Codes: A61B 6/504 for diagnosis of blood vessels, e.g. by angiography
• CPC Class Codes: A61B 6/5235 combining images from the same or different ionising radiation imaging techniques, e.g. PET and CT
• CPC Class Codes: A61B 90/36 Image-producing devices or illumination devices not otherwise provided for
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• CPC Class Codes: G06T 2207/30048 Heart; Cardiac
• CPC Class Codes: G06T 7/0012 Biomedical image inspection

Abstract

A method to obtain a patient based organ model from patient data, having steps of obtaining a computerized organ model based upon at least one data set of patients, the computerized organ model having a set of classifiers that are used to determine physical parameters of the patients heart, placing the patient in a diagnostic scanner device, taking representative data images of a patients organ while changing position of the image scan, the data images taken with ECG synchronization; and preparing the patient based organ model by evaluating the representative data images of the patients organ with the set of classifiers in the computerized organ model.

Claims

1. A method to obtain a patient based organ model from patient data, comprising:

storing a computerized organ model based upon at least one data set of patients, the computerized organ model having a set of classifiers derived based upon organ structure information in a database and that are used to determine physical parameters of a patients organ;

in response to a patient being placed in a diagnostic scanner device, taking representative data images of the patients organ while changing position of the image scan, the data images taken with ECG synchronization; and

preparing the patient based organ model by generating a patient specific reconstructed organ model using the representative data images of the patients organ and the set of classifiers in the computerized organ model.

2. The method according to claim 1, wherein a maximum of representative data images of the patient'"'"'s organ taken is a smaller number of images compared with a full acquisition and comprise a reduced number of images insufficient for generation of an artifact free full 3D organ model.

3. The method according to claim 1, further comprising:

visually depicting the patient'"'"'s organ based upon the representative data images and

iteratively acquiring additional representative data images of the patient'"'"'s organ to supplement the patient specific reconstructed organ model in response to user command.

4. The method according to claim 1, further comprising:

identifying artifacts in the model based upon the representative data images taken.

5. The method according to claim 4, further comprising:

obtaining a second set of representative data images of the patient'"'"'s organ while changing position of the image scan, the data images taken with ECG synchronization to eliminate artifacts; and

preparing a revised patient based organ model by evaluating the second set of representative data images of the patients organ with the set of classifiers in the computerized organ model.

6. The method according to claim 5, further comprising:

identifying a second set of artifacts in the model based upon the representative data images taken.

7. The method according to claim 5, further comprising:

obtaining a third set of taking representative data images of the patient'"'"'s organ while changing position of the image scan, the third set of data images taken with ECG synchronization to eliminate artifacts; and

preparing a second revised patient based organ model by evaluating the representative data images of the patients organ with the set of classifiers in the computerized organ model.

8. The method according to claim 1, further comprising:

obtaining a first organ position based upon a first set of representative data images at a specific time;

obtaining a second organ position based upon a second set of representative data images at a second specific time; and

obtaining a third organ position at a third specific time between the specific time and the second specific time based upon an interpolation between the first set of representative data images and the second set of representative data images.

9. The method according to claim 1, wherein the representative data images are limited to two dimensions.

10. The method according to claim 9, further comprising:

projecting a two dimensional position of the organ from the patient based organ model.

11. A method to obtain a temporal patient based organ model from patient data, comprising:

obtaining a computerized organ model based upon at least one data set of patients comprising temporal information, the computerized organ model having a set of classifiers derived based upon organ structure information in a database and that are used to determine physical parameters of a patients organ;

including motion information;

in response to a patient being placed in a diagnostic scanner device, taking representative temporal data images of a patients organ while changing position of the image scan; and

preparing a temporal patient based organ model by generating a patient specific reconstructed organ model using the representative data images of the patients organ and the set of classifiers in the computerized organ model.

12. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps comprising:

acquiring data of a computerized organ model based upon at least one data set of patients, the computerized organ model having a set of classifiers derived based upon organ structure information in a database and that are used to determine physical parameters of the patients organ;

in response to a patient being placed in a diagnostic scanner device, acquiring representative data images of a patients organ while changing position of the image scan, the data images taken with ECG synchronization; and

preparing the patient based organ model by generating a patient specific reconstructed organ model using the representative data images of the patients organ and the set of classifiers in the computerized organ model.

13. The device according to claim 12, wherein a maximum of representative data images of the patient'"'"'s organ taken is 30 images.

14. The device according to claim 13, wherein the method accomplished further comprises:

visually depicting the patient'"'"'s organ based upon the data images.

15. The device according to claim 13, wherein the method accomplished further comprises:

identifying artifacts in the model based upon the representative data images taken.

16. The device according to claim 15, wherein the method accomplished further comprises:

obtaining a second set of representative data images of the patient'"'"'s organ while changing position of the image scan, the data images taken with ECG synchronization to eliminate artifacts; and

preparing a revised patient based organ model by evaluating the representative data images of the patients organ with the set of classifiers in the computerized organ model.

17. The device according to claim 13, wherein a maximum of representative data images of the patients organ taken is dependent upon a number of degrees of freedom of the model.