Granted Patent B2

US 11,664,128 · App. 16/647,799 · Granted May 30, 2023

Inventors: Christian Haase (Hamburg, DE); Holger Schmitt (Luetjensee, DE); Michael Grass (Buchholz in der Nordheide, DE); Arjen Van Der Horst (Tilburg, NL)

Assignee: KONINKLIJKE PHILIPS N.V.

G16H50/30G06F30/28G06T7/0012G16H30/40G06T2207/10081

Abstract

Claims (56)

1. An apparatus for assessing a patient's vasculature, the apparatus comprising:

at least one processor coupled to memory, the at least one processor configured to:

receive at least one diagnostic image of the vasculature;

generate, based on the at least one diagnostic image, a physiological model comprising a geometric model of a first vessel in the vasculature;

extract, based on the geometric model, a plurality of geometric parameter values for a geometric parameter of the first vessel at a plurality of positions along a longitudinal axis of the first vessel;

based on the extracted plurality of geometric parameter values, identify one or more candidate positions, of the plurality of positions, having a local change of the geometric parameter;

predict, based on the local change, a presence of a vessel branching from the first vessel at a candidate position of the one or more candidate positions; and

output an indicator identifying the vessel branching in the geometric model of the first vessel.

2. The apparatus according to claim 1 , wherein

the at least one diagnostic image is obtained using X-ray angiography.

3. The apparatus according to claim 1 , wherein:

the physiological model further comprises a lumped parameter fluid dynamics model; and

the at least one processor is further configured to adapt the lumped parameter fluid dynamics model based on the predicting of the vessel branching from the first vessel at the one or more candidate positions.

4. The apparatus according to claim 1 , wherein the at least one processor is further configured to:

segment the first vessel into one or more segments;

determine, for each segment, at least one segmented geometric parameter value;

apply a regression model on the at least one segmented geometric parameter value to calculate, for each segment, an averaged geometric parameter value; and

predict the vessel branching from the first vessel by predicting at least one hemodynamic parameter at the one or more candidate positions on the basis of an averaged geometric parameter value of each segment.

5. The apparatus according to claim 4 , wherein the predicting the at least one hemodynamic parameter comprises a predicting of a fluid outflow rate.

6. The apparatus according to claim 1 ,

wherein the at least one processor is further configured to define a region of interest in the at least one diagnostic image based on the one or more candidate positions; and

wherein the indicator that is output includes the region of interest.

7. The apparatus according to claim 6 , wherein:

the at least one processor is further configured to adapt the physiological model using the indicator of the region of interest.

8. The apparatus according to claim 6 , further comprising:

a display configured to,

generate a first graphical representation of the at least one diagnostic image and a second graphical representation of the indicator of the region of interest; and

jointly display the first graphical representation and the second graphical representation.

9. The apparatus according to claim 1 , wherein the at least one processor is further configured to:

receive intravascular measurement data; and

predict, based on the physiological model and the intravascular measurement data, one or more hemodynamic index values at the plurality of positions along the longitudinal axis of the first vessel.

10. The apparatus according to claim 9 , wherein the intravascular measurement data comprises at least one pressure gradient acquired in-situ for the first vessel.

11. The apparatus according to claim 9 , wherein the one or more hemodynamic index values predicted at the plurality of positions along the longitudinal axis of the first vessel comprises at least one of a volumetric flow rate or a blood flow velocity.

12. The apparatus of claim 1 , wherein a first geometric parameter value of the plurality of geometric parameter values comprises at least one of:

a value for a vessel diameter,

a local average vessel diameter, or

an estimated healthy vessel diameter that virtually removes an effect of a disease on the vessel diameter at the plurality of positions.

13. A method for assessing a patient's vasculature, the method comprising the steps of:

receiving at least one diagnostic image of the vasculature;

generating, based on the at least one diagnostic image, a physiological model comprising a geometric model of a first vessel in the vasculature;

extracting, based on the geometric model, a plurality of geometric parameter values for a geometric parameter of the first vessel at a plurality of positions along a longitudinal axis of the first vessel;

based on the extracted plurality of geometric parameter values, identifying one or more candidate positions, of the plurality of positions, having a local change of the geometric parameter;

predicting, based on the local change, a presence of a vessel branching from the first vessel at a candidate position of the one or more candidate positions; and

outputting an indicator identifying the vessel branching in the geometric model of the first vessel.

14. The method according to claim 13 , further comprising:

segmenting the first vessel into one or more segments;

determining, for each segment, at least one segmented geometric parameter value;

applying a regression model on the at least one segmented geometric parameter value to calculate, for each segment, an averaged geometric parameter value; and

predicting the vessel branching from the first vessel by predicting at least one hemodynamic parameter at the one or more candidate positions on the basis of the averaged geometric parameter value of each segment.

15. A non-transitory computer-readable medium having stored thereon instructions which, when executed by a processor cause the processor to:

receive at least one diagnostic image of the vasculature;

generate, based on the at least one diagnostic image, a physiological model comprising a geometric model of a first vessel in the vasculature;

extract, based on the geometric model, a plurality of geometric parameter values for a geometric parameter of the first vessel at a plurality of positions along a longitudinal axis of the first vessel; and

based on the extracted plurality of geometric parameter values, identify one or more candidate positions, of the plurality of positions, having a local change of the geometric parameter;

predict, based on the local change, a presence of a vessel branching from the first vessel at a candidate position of the one or more candidate positions; and

output an indicator identifying the vessel branching in the geometric model of the first vessel.

Assignments (1)

Priority Claims (1)

Continuity (1)

Cited By (9)

US 12,315,076 US 12,354,755 US 12,387,325 US 12,423,813 US 12,446,965 US 12,499,646 US 12,512,196 US 12,531,159 US 12,567,489