IP Library › Granted Patent US 10,699,392
Granted Patent B2
US 10,699,392 · App. 15/924,470 · Granted Jun 30, 2020

Contrast-enhanced reproduction of spectral CT image data

Inventors: Matthias Lichy (Nuremberg, DE); Sebastian Schmidt (Weisendorf, DE)
Assignee: Siemens Healthcare GmbH
G06T5/009A61B6/032A61B6/5217G06T5/007G06T5/50G06T7/0012G06T2207/10081G06T2207/20081G06T2207/20208G06T2207/30096
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,699,392
App. No.
15/924,470
Granted
Jun 30, 2020
Kind
B2
Abstract

A method is for setting a contrast of a multi-energy CT image representation. In an embodiment of the method, a plurality of multispectral image datasets of an examination region of a patient are received. Furthermore, an automated identification of a structure to be examined is achieved based upon the multispectral image datasets and an automated combining of the differently weighted multispectral image datasets is accomplished such that the contrast between the structure to be examined and its environment is improved compared to a uniform weighting. Further, a multi-energy CT imaging method is described. An image setting device is also described. In addition, a computed tomography system is described.

Claims (40)

1. A method for setting a contrast of a multi-energy CT image representation, the method comprising:

receiving a plurality of multispectral image datasets of an examination region of a patient, the plurality of multispectral image datasets obtained by reconstruction based on multispectral projection measurement datasets;

automatically identifying a structure to be examined based on the plurality of multispectral image datasets; and

automatically combining differently weighted ones of the plurality of multispectral image datasets such that contrast between the structure to be examined and an environment of the structure to be examined is increased as compared to a uniform weighting.

2. The method of claim 1 , wherein the structure to be examined includes a lesion.

3. The method of claim 2 , wherein the structure to be examined is identified using a method based on machine learning.

4. The method of claim 2 , wherein the structure to be examined is identified using a method based on computer-assisted detection.

5. The method of claim 2 , wherein the plurality of multispectral image datasets are additionally combined with calculated image data.

6. The method of claim 1 , wherein the structure to be examined is identified using a method based on machine learning.

7. The method of claim 1 , wherein the structure to be examined is identified using a method based on computer-assisted detection.

8. The method of claim 1 , wherein

the automatically combining differently weighted ones of the plurality of multispectral image datasets is determined based on a learning system, and

the learning system is trained by corrections by a user.

9. The method of claim 1 , wherein the automatically combining differently weighted ones of the plurality of multispectral image datasets is determined using a rule-based approach.

10. The method of claim 1 , wherein the automatically combining differently weighted ones of the plurality of multispectral image datasets includes a weighted addition of the plurality of multispectral image datasets.

11. The method of claim 1 , wherein the automatically combining differently weighted ones of the plurality of multispectral image datasets includes a weighted subtraction of the plurality of multispectral image datasets.

12. The method of claim 1 , wherein the automatically combining differently weighted ones of the plurality of multispectral image datasets includes a nonlinear transformation.

13. The method of claim 1 , wherein the automatically combining differently weighted ones of the plurality of multispectral image datasets is accomplished such that the contrast between the structure to be examined and the environment of the structure to be examined is optimized.

14. The method of claim 1 , wherein the plurality of multispectral image datasets are additionally combined with calculated image data.

15. A multi-energy CT imaging method, the method comprising:

acquiring a plurality of multispectral projection measurement datasets of an examination region of a patient;

reconstructing a plurality of multispectral image datasets based upon the plurality of multispectral projection measurement datasets; and

generating an image representation using the method of claim 1 .

16. An image setting device, comprising:

at least one processor configured to execute computer-readable instructions to cause the image setting device to

receive a plurality of multispectral image datasets of an examination region of a patient, the plurality of multispectral image datasets obtained by reconstruction based on multispectral projection measurement datasets,

automatically identify a structure to be examined based on the plurality of multispectral image datasets, and

automatically combine differently weighted ones of the plurality of multispectral image datasets such that contrast between the structure to be examined and an environment of the structure to be examined is increased as compared to a uniform weighting.

17. A computed tomography system, comprising:

a scanner to acquire a plurality of multispectral projection measurement datasets of an examination region of a patient;

a control device to control the scanner and to generate a plurality of multispectral image datasets based on the plurality of multispectral projection measurement datasets; and

the image setting device of claim 16 .

18. A non-transitory computer program product including a computer program, which is directly loadable into a memory of a computed tomography system, the computer program including program sections that cause the computed tomography system to perform the method of claim 1 when the computer program is executed on the computed tomography system.

19. A non-transitory computer-readable medium storing program sections that cause a computer to perform the method of claim 1 when the program sections are executed by the computer.

20. A method for setting a contrast of a multi-energy CT image representation, the method comprising:

receiving a plurality of multispectral image datasets of an examination region of a patient;

automatically identifying a structure to be examined based on the plurality of multispectral image datasets; and

automatically combining differently weighted ones of the plurality of multispectral image datasets such that contrast between the structure to be examined and an environment of the structure to be examined is increased as compared to a uniform weighting, wherein

the automatically combining of the differently weighted ones of the plurality of multispectral image datasets is determined based on a learning system, and

the learning system is trained by corrections by a user.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 20, 2023
From: SIEMENS HEALTHCARE GMBH
To: SIEMENS HEALTHINEERS AG
Reel/Frame 066267/0346 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 30, 2018
From: LICHY, MATTHIAS; SCHMIDT, SEBASTIAN
To: SIEMENS HEALTHCARE GMBH
Reel/Frame 045665/0194 →
Priority Claims (1)
EP 17162007 · Mar 21, 2017 · regional
Continuity (1)
Related Publication 20180276802A1 · Sep 27, 2018