IP Library › Granted Patent US 11,361,432
Granted Patent B2
US 11,361,432 · App. 16/632,420 · Granted Jun 14, 2022

Inflammation estimation from x-ray image data

Inventors: Mordechay Pinchas Freiman (Zichron-Yaakov, IL); Liran Goshen (Zichron-Yaakov, IL)
Assignee: KONINKLIJKE PHILIPS N.V.
G06T7/0012A61B6/032A61B6/504A61B6/5217G06T15/08G06T2207/30048G06T2211/40
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 11,361,432
App. No.
16/632,420
Granted
Jun 14, 2022
Kind
B2
Abstract

The present invention relates to X-ray image data analysis of a part of a cardiovascular system of a patient in order to estimate a level of inflammation in the part of the cardiovascular system. X-ray image data is received, a segmented model of the part of the cardiovascular system is generated and predetermined features related to inflammation are extracted from the segmented model. The extracted features are used as input to an inflammation function for calculating inflammation values of which each represents a level of inflammation in the part of the cardiovascular system. The image data analysis can improve the estimation of inflammation. Furthermore, the inflammation values can be presented to a user together with suggestions for performing actions. This can for example enable a prediction of plaque development as well as future acute coronary syndrome events.

Claims (32)

1. An image data analysis device for analyzing X-ray image data of a part of a cardiovascular system of a patient in order to estimate a level of inflammation in the part of the cardiovascular system, comprising:

a non-transitory memory configured to store instructions; and

a processor configured to execute the instructions that cause the image data analysis device to:

receive the X-ray image data comprising the part of the cardiovascular system of the patient;

generate a segmented model of the part of the cardiovascular system from the X-ray image data as an anatomical model, wherein the segmented model comprises segments that have different elements, density and/or thickness;

design predetermined features;

extract the predetermined features related to inflammation from the segmented model, wherein the predetermined features are extracted based on pattern-recognition performed on the segmented model;

combine the extracted and designed predetermined features into a vector; and

calculate inflammation values of an inflammation function depending on the extracted and designed features, wherein the vector is an input to the inflammation function, and wherein each of the inflammation values represents a level of inflammation in the part of the cardiovascular system.

2. The image data analysis device according to claim 1 , wherein the inflammation function is optimized by machine learning methods.

3. The image data analysis device according to claim 2 , wherein the inflammation function is optimized in dependence of training data comprising histology analysis data, disease outcome data, and/or data received from medical imaging techniques allowing to estimate the level of inflammation.

4. The image data analysis device according to claim 1 , wherein the processor is further configured to visualize the inflammation values or the inflammation values together with the segmented model, and generate different views based on the inflammation values.

5. The image data analysis device according to claim 1 , wherein the image data is spectral computed tomography data.

6. The image data analysis device according to claim 1 , wherein the processor is further configured to estimate a probability for development of plaque in the part of the cardiovascular system and/or a probability for rupturing of plaque in the part of the cardiovascular system based on the inflammation values.

7. The image data analysis device according to claim 1 , comprising a user interface configured to provide an interaction between a user and the image data analysis device, wherein the user interface is configured to provide suggestions for actions in dependence of the inflammation values.

8. A method for analyzing X-ray image data of a part of a cardiovascular system of a patient in order to estimate a level of inflammation in the part of the cardiovascular system, the method comprising:

receiving X-ray image data comprising the part of the cardiovascular system of the patient;

generating a segmented model of the part of the cardiovascular system from the image data as an anatomical model, wherein the segmented model comprises segments that have different elements, density and/or thickness;

designing predetermined features;

extracting the predetermined features related to inflammation from the segmented model by performing pattern-recognition on the segmented model;

combining the extracted and designed predetermined features into a vector; and

calculating inflammation values of an inflammation function depending on the extracted and designed features, wherein the vector is an input to the inflammation function, and wherein each of the inflammation values represents a level of inflammation in the part of the cardiovascular system.

9. The method according to claim 8 , further comprising visualizing the inflammation values or the inflammation values together with the segmented model, wherein different views based on the inflammation values can be generated.

10. A non-transitory computer-readable medium having one or more executable instructions stored thereon which, when executed by at least one processor, cause the at least one processor to perform a method for analyzing X-ray image data of a part of a cardiovascular system of a patient in order to estimate a level of inflammation in the part of the cardiovascular system, the method comprising:

receiving X-ray image data comprising the part of the cardiovascular system of the patient;

generating a segmented model of the part of the cardiovascular system from the image data as an anatomical model, wherein the segmented model comprises segments that have different elements, density and/or thickness;

designing the predetermined features;

extracting the predetermined features related to inflammation from the segmented model by performing pattern-recognition on the segmented model;

combining the extracted and designed predetermined features into a vector; and

calculating inflammation values of an inflammation function depending on the extracted and designed features, wherein the vector is an input to the inflammation function, and wherein each of the inflammation values represents a level of inflammation in the part of the cardiovascular system.

11. The image data anaylysis system according to claim 10 , comprising a training device configured to optimize the inflammation function of the image data analysis device.

12. The image data analysis system according to claim 11 , wherein the training device is configured to optimize the inflammation function in dependence of training data, and wherein the training data comprises histology analysis data, disease outcome data, and/or data received from medical imaging techniques allowing to estimate the level of inflammation.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 20, 2020
From: FREIMAN, MORDECHAY PINCHAS; GOSHEN, LIRAN
To: KONINKLIJKE PHILIPS N.V.
Reel/Frame 051554/0044 →
Priority Claims (1)
EP 17182117 · Jul 19, 2017 · regional
Continuity (1)
Related Publication 20200226749A1 · Jul 16, 2020