Determining a complexity value of a stenosis or a section of a vessel

Patent metadata

Field	Value
Publication number	US-10664985-B2
Application number	US-201815881187-A
Country	US
Kind code	B2
Filing date	Jan 26, 2018
Priority date	Jan 27, 2017
Publication date	May 26, 2020
Grant date	May 26, 2020

Abstract

Systems and methods are provided for evaluating the complexity of a stenosis or a section of a vessel. At least one image of the stenosis or the section of the vessel is provided. A geometrical feature value of the stenosis and/or or the section of the vessel is identified from the at least one image. At least one intensity feature value is determined based on a grey level intensity of the stenosis or the section of the vessel from the at least one image. A complexity value relating to the geometrical complexity of the stenosis or the section of the vessel is calculated as a function of the at least one geometrical feature value and the at least one intensity feature value of the stenosis or the section of the vessel.

First claim

The invention claimed is:

1. A method of evaluating a geometrical complexity of a stenosis or a section of a vessel, the method comprising:
providing at least one image of the stenosis or the section of the vessel;
identifying at least one geometrical feature value of the stenosis, the section of the vessel, or the stenosis and the section of the vessel from the at least one image;
determining at least one intensity feature value based on a grey level intensity of the stenosis or the section of the vessel from the at least one image; and
automatically calculating a complexity value related to the geometrical complexity of the stenosis or the section of the vessel in dependency on the at least one geometrical feature value and the at least one intensity feature value of the stenosis or the section of the vessel.

2. The method of claim 1 , wherein the at least one image is provided by angiography.

3. The method of claim 1 , wherein the at least one geometrical feature value relates to a 2D-contour, a centerline of a blood vessel, or a curvature of the blood vessel.

4. The method of claim 1 , wherein the at least one intensity feature value results from an attenuation or excitation of radiation and relates to a sum, a distribution, or an energy of grey values within one or more regions of a blood vessel.

5. The method of claim 1 , wherein the complexity value is calculated by regression or classification of the at least one geometrical feature value and the at least one intensity feature value.

6. The method of claim 1 , further comprising determining at least three feature values of one or more geometrical features and one or more intensity features,
wherein automatically calculating the complexity value comprises weighting the at least three feature values.

7. The method of claim 1 , wherein a ratio of the at least one geometrical feature value and the at least one intensity feature value is used for calculating the complexity value.

8. The method of claim 1 , wherein calculating the complexity value comprises using machine learning.

9. The method of claim 1 , wherein the stenosis is an eccentric stenosis.

10. The method of claim 1 , further comprising:
determining whether a 3D-reconstruction of the stenosis or the section of the vessel is possible as a function of the complexity value.

11. The method of claim 1 , further comprising:
determining whether to provide a further image of the stenosis or the section of the vessel as a function of the complexity value.

12. The method of claim 2 , wherein the at least one geometrical feature value relates to a 2D-contour, a centerline of a blood vessel, or a curvature of the blood vessel.

13. The method of claim 2 , wherein the at least one intensity feature value results from an attenuation or excitation of radiation and relates to a sum, a distribution, or an energy of grey values within one or more regions of a blood vessel.

14. The method of claim 2 , wherein the complexity value is calculated by regression or classification of the at least one geometrical feature value and the at least one intensity feature value.

15. The method of claim 2 , further comprising determining at least three feature values of one or more geometrical features and one or more intensity features,
wherein calculating the complexity value comprises weighting the feature values.

16. The method of claim 2 , wherein a ratio of the at least one geometrical feature value and the at least one intensity feature value is used for calculating the complexity value.

17. The method of claim 2 , wherein calculating the complexity value comprises using machine learning.

18. The method of claim 2 , wherein the stenosis is an eccentric stenosis.

19. A device for evaluating a geometrical complexity of a stenosis or a section of the vessel, the device comprising:
a memory configured to store at least one image of the stenosis or the section of the vessel;
an analyzer configured to identify at least one geometrical feature value of the stenosis, the section of the vessel, or the stenosis and the section of the vessel from the at least one image, the analyzer further configured to determine at least one intensity feature value based on a grey level intensity of the stenosis or the section of the vessel from the at least one image; and
a processor configured to automatically calculate a complexity value related to the geometrical complexity of the stenosis or the section of the vessel in dependency on the at least one geometrical feature value and the at least one intensity feature value of the stenosis or the section of the vessel.

20. The device of claim 19 wherein the device is used in an angiography system.

Assignees

• Berger Martin
• Redel Thomas
• Siemens Healthcare Gmbh

Inventors

• Berger Martin
• Redel Thomas

Classifications

• A61B5/026

  Measuring blood flow {(A61B3/1233, A61B3/1241 take precedence)} · CPC title

• A61B2576/00

  Medical imaging apparatus involving image processing or analysis (A61B1/00009, A61B6/52 and A61B8/52 take precedence) · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G16H30/40

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

• G06T2207/20224

  Image subtraction · CPC title