Method and device for monitoring a flow of a fluid in a vessel
A method is provided for monitoring a flow of a fluid in a vessel of a body of a living being is provided. The method comprises obtaining a first image data set representing the vessel filled with a first fluid, the first image data set comprising at least one first image frame and the first fluid contrasting with matter surrounding the vessel and obtaining a second image data set representing the vessel substantially void of the first fluid, the second image data set comprising at least one second image frame. Based on the first image data set and the second image set, an estimated location of the vessel in the second image set is estimated; and monitoring presence in the second data set of contrasting image data at the estimated location of the vessel is monitored.
1. A method of monitoring a flow of a fluid in a vessel of a body of a living being, the method comprising:
obtaining a first image data set representing the vessel filled with a first fluid, the first image data set comprising at least one first image frame and the first fluid contrasting with matter surrounding the vessel;
obtaining a second image data set representing the vessel substantially void of the first fluid, the second image data set comprising at least one second image frame;
based on the first image data set and the second image set, estimating an estimated location of the vessel in the second image set; and
monitoring presence in the second image data set of contrasting image data at the estimated location of the vessel,
wherein:
the first image data set comprises a multitude of first image frames, the first image frames having been acquired consecutively in time; and
the second image data set comprises a multitude of second image frames, the second image frames having been acquired consecutively in time;
the method further comprising, over time;
tracking, in the first image data set, the vessel;
estimating, based on the tracking, a location of the vessel in the second frames of the second image data set, and
reconstructing the vessel geometry.
2. The method according to claim 1 , wherein:
the first image data set is acquired over a first time interval relative to a heartbeat sequence;
the second image data set is acquired over a second time interval relative to the heartbeat sequence; and
the first time interval and the second time interval cover at least one equivalent part of the heartbeat sequence.
3. The method according to claim 1 , wherein the first timer interval and the second timer interval cover at least one heartbeat sequence.
4. The method of claim 2 , further comprising:
aligning the first image data set and the second image data set based on heartbeat sequence data associated with the first image data set and the second image data set;
associating frames in the first image data set and the second image data set with a particular phase in the heartbeat sequence;
estimating, over time, estimated locations of the vessel in the second frames of the second image data set based on locations of the vessel in the first frames of the first image data set having substantially the same phase in the heartbeat sequence associated therewith as with the second frames.
5. The method of claim 4 , wherein the first image data set and the second image data set have electrocardiogram data as heartbeat sequence data associated therewith.
6. The method of claim 4 , wherein heartbeat sequence data is derived from image frame data in at least one of the first image data set and the second image data set.
7. The method according to claim 1 , wherein the tracking of the vessel over time comprises:
identifying a multitude of points of interest distributed on a representation of the vessel in the first image frames; and
tracking locations of the points of interest in the applicable image over time.
8. The method according to claim 1 , wherein the reconstructing comprises determining a centreline of the vessel in the image data.
9. The method according to claim 1 , wherein the first image data set comprises:
a first image subset comprises at least a first image acquired under a first angle relative to the living being; and
a second image subset comprises at least a second image acquired under a second angle relative to the living being;
wherein the reconstructed vessel geometry is a three-dimensional geometry.
10. The method of claim 9 , further wherein the second image data set comprises:
a first image subset comprises at least a first image acquired under the first angle relative to the living being; and
a second image subset comprises at least a second image acquired under the second angle relative to the living being;
wherein the estimated location of the vessel in the second image set is a three-dimensional location.
11. The method of claim 9 , further comprising:
determining a first length of the vessel as depicted by the first image subset;
determining a second length of the vessel as depicted by the second image subset;
determining a natural length of the reconstructed vessel;
selecting the first image subset if the first length is closer to the natural length or selecting the second image subset if the second length is closer to the natural length;
estimating the location of the vessel in the second image data set based on the subset of the first dataset of which the length is closest to the natural length.
12. The method of claim 11 , wherein the second image data set comprises:
a first image subset comprises at least a first image acquired under the first angle relative to the living being; and
a second image subset comprises at least a second image acquired under the second angle relative to the living being;
wherein the estimated location of the vessel in the second image set is a three-dimensional location, and
wherein the location in the second image data set is determined based on the image subset corresponding to the image subset of the first image data set depicting a length closest to the natural length.
13. The method according to claim 1 , wherein the vessel is filling with the first fluid while the second dataset is acquired.
14. The method according to claim 1 , further comprising estimating the location of the vessel in the second image data set by providing the first image data set to a trained neural network.
15. The method according to claim 1 , wherein the second image data set is acquired prior in time relative to the acquiring the first image data set.
16. A computer programme product comprising computer executable code for causing a processor to execute the method according to claim 1 .
17. A non-transitory computer readable medium having stored thereon the computer programme product according to claim 16 .
18. A method of monitoring a flow of a fluid in a vessel of body of a living being, the method comprising:
obtaining a first image data set representing the vessel filled with a first fluid, the first image data set comprising at least one first image frame and the first fluid contrasting with matter surrounding the vessel;
obtaining a second image data set representing the vessel substantially void of the first fluid, the second image data set comprising at least one second image frame;
based on the first image data set and the second image set, estimating an estimated location of the vessel in the second image set,
monitoring presence in the second image data set of contrasting image data at the estimated location of the vessel;
reconstructing a vessel geometry based on the first image data set; and
estimating a location of the vessel in the second image set based on the first image data set and the reconstructed vessel geometry.
19. A method of determining vessel fluid flow velocity of a fluid in a vessel segment of a body of a human or another mammal, the method comprising:
obtaining a natural length model of the vessel representing a length of the vessel in accordance with the method according to claim 9 ;
obtaining a two-dimensional model of the vessel segment based on the first image dataset;
dividing the two-dimensional model in vessel sections;
receiving the second dataset comprising a multitude of second image frames, the second image frames having been acquired consecutively in time;
based on the images of the second dataset, assigning, for each image of the set, at least one intensity value to each vessel section;
identifying, in a first image related to a first moment in time, a first vessel section, based on an intensity criterion;
identifying, in a second image related to a second moment in time, a second vessel section, based on the intensity criterion, the second moment in time being later than the first moment in time and the second vessel section being distal to the first vessel section;
obtaining a propagation length by relating the first vessel section and the second vessel section to the natural length; and
determining a vessel fluid flow velocity based on the propagation length, and a difference between the first moment in time and the second moment in time.