Identifying individual sub-regions of the cardiovascular system for calcium scoring

• US 9,317,919 B2
• Filed: 11/09/2011
• Issued: 04/19/2016
• Est. Priority Date: 11/12/2010
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Waechter-Stehle, Irina, Kneser, Reinhard, Weese, Juergen
• Primary Examiner(s): Park, Chan
• Assistant Examiner(s): Thomas, Mia M
• Application Number:
  US13/884,617
• Publication Number:
  US 20130230225A1
• Time in Patent Office: 1,623 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: A61B 6/032 Transmission computed tomography [CT]
• CPC Class Codes: A61B 6/463 characterised by displaying multiple images or images and diagnostic data on one display
• CPC Class Codes: A61B 6/466 adapted to display 3D data
• 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 6/5217 extracting a diagnostic or physiological parameter from medical diagnostic data
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• CPC Class Codes: G06T 2207/30048 Heart; Cardiac
• CPC Class Codes: G06T 2207/30101 Blood vessel; Artery; Vein; Vascular
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/0014 using an image reference approach
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06V 2201/03 Recognition of patterns in medical or anatomical images
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment

Abstract

A method includes identifying a plurality of different anatomical sub-regions of the cardiovascular system of a subject in image data of the subject based on a subject specific cardiovascular anatomical model, wherein the plurality of different regions corresponds to regions where calcifications occur, searching for and identifying calcifications in the sub-regions based on voxel grey value intensity values of the image data, and generating a signal indicative of one or more regions of voxels of the image data respectively corresponding to sub-regions including identified calcifications. A computing system (118) includes a processor that automatically determines a plurality of different groups of voxels of image data of a subject, wherein each group of voxels corresponds to a different sub-region of the cardiovascular system of the subject and each group of voxels corresponds to a region that includes a calcification identified in the image data.

Claims

1. A method, comprising:

identifying a plurality of different anatomical sub-regions of a cardiovascular system of a subject in image data of the subject based on a subject specific cardiovascular anatomical model, wherein the plurality of different anatomical sub-regions corresponds to regions where calcifications occur;

searching for calcifications in the sub-regions based on voxel grey value intensity values of the image data,

identifying calcifications in a sub-region using a pre-determined threshold, wherein a first threshold is used for a first sub-region of the plurality of different anatomical sub-regions, a second threshold is used for a second sub-region of the plurality of different anatomical sub-regions, and the first and second thresholds are different;

generating a signal indicative of one or more regions of voxels of the image data respectively corresponding to sub-regions including identified calcifications;

determining calcium scores for at least one of the sub-regions

determining relative severities for the calcium scores;

assigning a different color to the different severities;

generating a mapping between the relative severities and a surface of the subject specific cardiovascular anatomical model; and

visually presenting the subject specific cardiovascular anatomical model, using the different colors assigned to the severities to identify the relative severities in corresponding sub-regions.

2. The method of claim 1, further comprising:

obtaining a generic anatomical model of the cardiovascular system; and

generating the subject specific cardiovascular anatomical model based on the image data and the generic anatomical model of the cardiovascular system.

3. The method of claim 1, wherein the threshold is based on intensity values of a blood pool near the region.

4. The method of claim 3, wherein the threshold is based on an average value of the intensity values plus a margin.

5. The method of claim 1, wherein the threshold is based on a mean intensity and standard deviation in structures neighboring the sub-region in the subject specific cardiovascular model.

6. The method of claim 1, further comprising:

growing at least one of the regions of voxels outside of a corresponding search sub-region into an expanded region; and

determining a calcium score based on the expanded region.

7. The method of claim 1, further comprising:

visually presenting the calcium scores along with indicia indicating respective sub-regions of the anatomical sub-regions.

8. The method of claim 7, further comprising:

associating a different color with each of the sub-regions;

visually presenting the calcium scores along and with the indicia, using the respective colors for the sub-regions; and

visually presenting the subject specific cardiovascular anatomical model, using the respective colors of the sub-regions to identify the sub-regions in the subject specific cardiovascular anatomical model.

9. The method of claim 1, further comprising:

generating a mapping between the calcium scores and the subject specific cardiovascular anatomical model;

visually presenting the subject specific cardiovascular anatomical model; and

visually presenting a calcium score for a sub-region in response to receiving a signal indicative of a user input selecting the sub-region.

10. The method of claim 1, further comprising:

assigning a transparency value to the surface; and

visually presenting the subject specific cardiovascular anatomical model, using the different colors to identify the relative severities in corresponding sub-regions behind the surface.

11. A computing system, comprising:

a processor that automatically determines a plurality of different groups of voxels of image data of a subject, wherein each group of voxels corresponds to a different sub-region of a cardiovascular system of the subject and each group of voxels corresponds to a region that includes a calcification identified in the image data, wherein the processor determines calcium score values for the plurality of different groups, determines relative severities for the calcium scores, assigns a different color to the different severities, generates a mapping between the relative severities and a surface of a subject specific cardiovascular anatomical model, and visually presents the subject specific cardiovascular anatomical model, using the different colors to identify the relative severities in corresponding sub-regions, wherein the processor is programmed to recommend at least one of an access point for an implant or a size of the implant based on a calcium score for a given sub-region.

12. The system of claim 11, wherein the processor determines the plurality of different sub-regions based on a subject specific cardiovascular anatomical model.

13. The system of claim 12, wherein the processor determines the subject specific cardiovascular anatomical model based on the image data and a generic anatomical model of the cardiovascular system, using a model-based segmentation.

14. The system of claim 11, wherein the processor identifies calcifications based on a pre-determined voxel intensity value threshold.

15. The system of claim 14, wherein the threshold is based on at least one of a blood pool near the sub-region or tissue surrounding the sub-region.

16. The system of claim 11, wherein the processor identifies the sub-regions by growing a region around a landmark starting from a surface of the subject specific cardiovascular model.

17. The system of claim 11, wherein the processor visually presents the calcium scores along with indicia indicating respective sub-regions of the anatomical sub-regions.

18. The system of claim 17, wherein the processor associates a different color with each of the sub-regions, visually presents the calcium scores along and with the indicia, using the respective colors of the sub-regions, and visually presents the subject specific cardiovascular anatomical model, using the respective colors of the sub-regions to identify the sub-regions in the subject specific cardiovascular anatomical model.

19. The system of claim 17, wherein the processor generates a mapping between the calcium scores and the subject specific cardiovascular anatomical model, visually presents the subject specific cardiovascular anatomical model, and visually presents a calcium score for a sub-region in response to receiving a signal indicative of a user selected sub-region.

20. The system of claim 11, wherein the processor is programmed to recommend a course of action based on a calcium score for a given sub-region.

21. The system of claim 11, wherein the processor is programmed to recommend a course of action based on a compilation of calcium scores for multiple sub-regions.

22. A non-transitory computer readable medium encoded with computer executable instructions, which, when executed by a computer processor, causes the computer processor to:

identify a plurality of different anatomical sub-regions of a cardiovascular system of a subject in image data of the subject based on a subject specific cardiovascular anatomical model, wherein the plurality of different regions corresponds to regions where calcifications occur;

search for and identify calcifications in the sub-regions based on voxel grey value intensity values of the image data;

generate a signal indicative of one or more regions of voxels of the image data respectively corresponding to sub-regions including identified calcifications;

determine calcium scores for at least one of the sub-regions

determine relative seventies for the calcium scores;

assign a different color to the different seventies;

generate a mapping between the relative seventies and a surface of the subject specific cardiovascular anatomical model;

assign a transparency value to the surface; and

visually present the subject specific cardiovascular anatomical model, using the different colors assigned to the seventies to identify the relative seventies in corresponding sub-regions behind the surface.