Most relevant x-ray image selection for hemodynamic simulation
A method and apparatus for selecting one or more diagnostic images to generate a physiological model are provided in which a set of candidate images is determined for review by a user, in particular by a physician. The candidate images are hereby determined using one or more target measures, such as a density measure, a motion measure, a deviation measure or the like, that have been derived for each diagnostic image of an X-ray angiography series and by analyzing said target measure. Subsequently, a suitability score that is based on the requirements of the physiological model that shall be generated from the selected candidate images is assigned to each candidate image.
1. A computer-implemented method of selecting one or more diagnostic images for generating a physiological model of a target structure, the method comprising:
obtaining a plurality of diagnostic images of the target structure,
deriving a plurality of target measures indicating one or more properties of the target structure in the plurality of diagnostic images, wherein at least one target measure is derived for each of the plurality of diagnostic images,
analyzing the plurality of target measures to select, from the plurality of diagnostic images, a set of candidate images, and
assigning a suitability score to each candidate image in the set of candidate images, the suitability score indicating a suitability of the respective candidate image for generating the physiological model of the target structure, wherein the suitability score is assigned based on the one or more properties of the target structure indicated in the respective candidate image being suitable to model a physiological aspect of the target structure.
2. The method according to claim 1 , wherein the deriving of the plurality of target measures comprises:
generating, for each of the plurality of diagnostic images, a respective processed image, the generating comprising assigning a plurality of quantitative values to a plurality of pixels of the respective processed image, a quantitative value indicating a probability that a pixel represents the target structure, and
deriving a target structure density measure for each of the plurality of diagnostic images based on the plurality of quantitative values.
3. The method according to claim 2 , wherein the target structure density measure for each of the plurality of images is derived based on a sum of the plurality of quantitative values.
4. The method according to claim 2 , wherein the selecting the set of candidate images comprises:
analyzing the derived target structure density measure as a function of measurement time, and
obtaining, based on the analyzing of the derived target structure density measure:
a first subset of candidate images representing a contrast agent inflow phase;
a second subset of candidate images representing a contrast agent full filling phase; and
a third subset of candidate images representing a contrast agent outflow phase.
5. The method according to claim 4 , further comprising:
analyzing at least one of the first subset of candidate images or the third subset of candidate images, and
determining, for each one of the at least one of the first subset of candidate images or the third subset of candidate images, a visibility measure indicating a visibility of the target structure.
6. The method according to claim 2 , wherein the deriving of the plurality of target measures comprises:
identifying, for each of the plurality of diagnostic images, a motion measure indicative of a motion of the target structure.
7. The method according to claim 6 , wherein the motion measure is identified by:
determining, for each of the plurality of diagnostic images, the respective processed image, and
analyzing the respective processed image as a function of measurement time, wherein the analyzing of the respective processed image comprises subtracting two consecutive processed images from one another to determine the motion measure.
8. The method according to claim 1 , wherein the deriving of the plurality of target measures comprises:
identifying, for each of the plurality of diagnostic images, an overlap measure indicative of an overlap in the target structure.
9. The method according to claim 1 , wherein the deriving of the plurality of target measures comprises:
identifying, for each of the plurality of diagnostic images, a deviation measure indicative of a deviation from a desired target acquisition time.
10. The method according to claim 1 , wherein the suitability score is based on a weighted sum of the plurality of derived target measures.
11. The method according to claim 10 , whereby respective weighting factors are adjusted based on one or more hemodynamic parameters to be modelled using the physiological model to be generated based on one or more images to be selected from the set of candidate images.
12. An apparatus for selecting one or more diagnostic images for generating a physiological model of a target structure, the apparatus comprising:
a processor in communication with memory, the processor configured to:
obtain a plurality of diagnostic images of the target structure,
derive a plurality of target measures indicating one or more properties of the target structure in the plurality of diagnostic images, wherein at least one respective target measure is derived for each of the plurality of diagnostic images,
analyze the plurality of target measures to select a set of candidate images, and
assign a suitability score to each candidate image in the set of candidate images, the suitability store indicating a suitability of the respective candidate image for generating the physiological model of the target structure, wherein the suitability score is assigned based on the one or more properties of the target structure indicated in the respective candidate image being suitable to model a physiological aspect of the target structure.
13. The apparatus according to claim 12 , wherein the processor is further configured to:
apply a model that has been trained using a training data set correlating one or more diagnostic images with correspondingly measured hemodynamic parameter data.
14. A non-transitory computer-readable storage medium having stored a computer program comprising instructions, which, when executed by a processor, cause the processor to:
obtain a plurality of diagnostic images of a target structure,
derive a plurality of target measures indicating one or more properties of the target structure in the plurality of diagnostic images, wherein at least one respective target measure is derived for each of the plurality of diagnostic images,
analyze the plurality of target measures to select a set of candidate images, and
assign a suitability score to each candidate image in the set of candidate images, the suitability score indicating a suitability of the respective candidate image for generating a physiological model of the target structure, wherein the suitability score is assigned based on the one or more properties of the target structure indicated in the respective candidate image being suitable to model a physiological aspect of the target structure.
15. The apparatus according to claim 12 , wherein the processor is further configured to:
generate, for each of the plurality of diagnostic images, a respective processed image, the generating comprising assigning a plurality of quantitative values to a plurality of pixels of the respective processed image, a quantitative value indicating a probability that a pixel represents the target structure, and
derive a target structure density measure for each of the plurality of diagnostic images based on the plurality of quantitative values.
16. The apparatus according to claim 15 , wherein the processor is further configured to:
derive the target structure density measure for each of the plurality of diagnostic images based on a sum of the plurality of quantitative values.
17. The apparatus according to claim 15 , wherein the processor is further configured to:
analyze the derived target structure density measure as a function of measurement time, and
obtain, based on the analysis of the derived target structure density measure:
a first subset of candidate images representing a contrast agent inflow phase;
a second subset of candidate images representing a contrast agent full filling phase; and
a third subset of candidate images representing a contrast agent outflow phase.
18. The non-transitory computer-readable storage medium of claim 14 , wherein the instruction, when executed by the processor, further cause the processor to:
generate, for each of the plurality of diagnostic images, a respective processed image, the generating comprising assigning a plurality of quantitative values to a plurality of pixels of the respective processed image, a quantitative value indicating a probability that a pixel represents the target structure, and
derive a target structure density measure for each of the plurality of diagnostic images based on the plurality of quantitative values.
19. The non-transitory computer-readable storage medium of claim 18 , wherein the instruction, when executed by the processor, further cause the processor to:
derive the target structure density measure for each of the plurality of diagnostic images based on a sum of the plurality of quantitative values.
20. The non-transitory computer-readable storage medium of claim 18 , wherein the instruction, when executed by the processor, further cause the processor to:
analyze the derived target structure density measure as a function of measurement time, and
obtain, based on the analysis of the derived target structure density measure:
a first subset of candidate images representing a contrast agent inflow phase;
a second subset of candidate images representing a contrast agent full filling phase; and
a third subset of candidate images representing a contrast agent outflow phase.