Method and X-ray system for computer aided detection of structures in X-ray images
The present invention relates to X-ray imaging technology as well as image post-processing. Particularly, the present invention relates to a method for computer aided detection of structures in X-ray images as well as an X-ray system. A computer aided detection algorithm visibly determines tissue structures in X-ray image information and subsequently matches the shape of a determined tissue structure with a library of known tissue structures for characterizing the type of determined tissue structure. The determination of a tissue structure and thus the characterization of the type of the tissue structure may be enhanced when employing also spectral information, in particular energy information of the acquired X-ray image. Accordingly, a method ( 70,80,90 ) for computer aided detection of structures and X-ray images is provided, comprising the steps of obtaining ( 72 ) spectral X-ray image information of an object, wherein the spectral X-ray image information constitutes at least one X-ray image, detecting ( 74 ) a tissue structure of interest in the X-ray image by employing a computer aided detection algorithm, wherein detecting a tissue structure of interest in the X-ray image comprises the computer aided detection algorithm being adapted to evaluate the X-ray image for tissue structure shape and compare the tissue structure shape with a plurality of pre-determined tissue structure shapes and wherein the computer aided detection algorithm is adapted to evaluate spectral information of the X-ray image for detecting the tissue structure of interest.
1. A method for computer aided detection of a tissue structure in X-ray images, the method comprising:
obtaining spectral X-ray image information of an object;
wherein the spectral X-ray image information constitutes at least one X-ray image; and
detecting a tissue structure of interest in the X-ray image by employing a computer aided detection algorithm;
wherein detecting a tissue structure of interest in the X-ray image comprises the computer aided detection algorithm being adapted to evaluate the X-ray image for tissue structure shape and compare the tissue structure shape with a plurality of pre-determined tissue structure shapes; and
wherein the computer aided detection algorithm is adapted to evaluate spectral information of the X-ray image for detecting the tissue structure of interest;
wherein the method further comprises: obtaining at least two X-ray images corresponding to at least two different X-ray energies;
determining from the at least two X-ray images at least one further X-ray image, which corresponds to the X-ray image of the spectral X-ray information;
wherein the at least one further X-ray image is an X-ray image having a defined energy-dependent weighting, wherein the energy-dependent weighting causes the further X-ray image to correspond to photon energies which are combined into an energy spectrum; and
wherein the method further comprises evaluating the at least one further X-ray image for detecting the tissue structure shape;
wherein the determining of the at least one further X-ray image employs equation
I syn =∫ 0 ∞ w ( E ) I 0 ( E ) e −μ a (E)t a −μ g (E)t g dE;
wherein w(E) represent energy-dependent weights of the energy-dependent weighting, μ A (E), μ G (E) represent attenuation functions of two materials, t a and t b represent a material separation of the two materials and l 0 (E) represents an X-ray spectrum.
2. The method according to claim 1 , further comprising
determining a plurality of further X-ray images, each further X-ray image having an individual defined energy-dependent weighting; and
evaluating the plurality of further X-ray images for detecting the tissue structure shape; and
determining from the plurality of further X-ray images at least one X-ray image by optimizing or minimizing visibility for a certain tissue structure shape.
3. The method according to claim 2 , wherein determining from the plurality of further X-ray images at least one X-ray image by optimizing or minimizing visibility for a certain tissue structure shape comprises determining an associated energy-dependent weighting applied to the at least one X-ray image.
4. The method according to claim 3 , wherein the determined associated energy-dependent weighting is employed for detecting the tissue structure of interest, in particular by employing an energy-dependent visibility of a certain tissue structure of interest.
5. The method according to claim 1 , wherein the computer aided detection comprises one of performing first a computer aided detection algorithm and second a spectral evaluation on an X-ray image, performing first a spectral evaluation and second a computer aided detection algorithm on an X-ray image, and performing a combined spectral computer aided detection algorithm on an X-ray image.
6. An X-ray system for detecting a tissue structure, comprising:
at least one electronic processor programmed for:
obtaining spectral X-ray image information of an object;
wherein the spectral X-ray image information constitutes at least one X-ray image; and
detecting a tissue structure of interest in the X-ray image by employing a computer aided detection algorithm;
wherein detecting a tissue structure of interest in the X-ray image comprises the computer aided detection algorithm being adapted to evaluate the X-ray image for tissue structure shape and compare the tissue structure shape with a plurality of pre-determined tissue structure shapes; and
wherein the computer aided detection algorithm is adapted to evaluate spectral information of the X-ray image for detecting the tissue structure of interest;
wherein the method further comprises: obtaining at least two X-ray images corresponding to at least two different X-ray energies;
determining from the at least two X-ray images at least one further X-ray image, which corresponds to the X-ray image of the spectral X-ray information;
wherein the at least one further X-ray image is an X-ray image having a defined energy-dependent weighting, wherein the energy-dependent weighting causes the further X-ray image to correspond to photon energies which are combined into an energy spectrum; and
wherein the method further comprises evaluating the at least one further X-ray image for detecting the tissue structure shape;
wherein the determining of the at least one further X-ray image employs equation
I syn =∫ 0 ∞ w ( E ) I 0 ( E ) e −μ a (E) a −μ g (E)t g dE;
wherein w(E) represent energy-dependent weights of the energy-dependent weighting, μ A (E), μ G (E) represent attenuation functions of two materials, t a and t b represent a material separation of the two materials and l 0 (E) represents an X-ray spectrum.
7. The X-ray system according to claim 6 , being adapted as a spectral photon counting system.
8. A non-transitory computer-readable medium comprising a stored computer program adapted to perform a method for computer aided detection of a tissue structure in X-ray images, the method comprising:
obtaining spectral X-ray image information of an object;
wherein the spectral X-ray image information constitutes at least one X-ray image; and
detecting a tissue structure of interest in the X-ray image by employing a computer aided detection algorithm;
wherein detecting a tissue structure of interest in the X-ray image comprises the computer aided detection algorithm being adapted to evaluate the X-ray image for tissue structure shape and compare the tissue structure shape with a plurality of pre-determined tissue structure shapes; and
wherein the computer aided detection algorithm is adapted to evaluate spectral information of the X-ray image for detecting the tissue structure of interest;
wherein the method further comprises; obtaining at least two X-ray images corresponding to at least two different X-ray energies;
determining from the at least two X-ray images at least one further X-ray image, which corresponds to the X-ray image of the spectral X-ray information;
wherein the at least one further X-ray image is an X-ray image having a defined energy-dependent weighting, wherein the energy-dependent weighting causes the further X-ray image to correspond to photon energies which are combined into an energy spectrum; and
wherein the method further comprises evaluating the at least one further X-ray image for detecting the tissue structure shape;
wherein the determining of the at least one further X-ray image employs equation
I syn =∫ 0 ∞ w ( E ) I 0 ( E ) e −μ a (E)t a 31 μ g (E)t g dE;
wherein w(E) represent energy-dependent weights of the energy-dependent weighting, μ A (E), μ G (E) represent attenuation functions of two materials, t a and t b represent a material separation of the two materials and l 0 (E) represents an X-ray spectrum.
9. The X-ray system according to claim 6 , wherein the at least one electronic processor is further programmed to:
determine a plurality of further X-ray images, each further X-ray image having an individual defined energy-dependent weighting;
evaluate the plurality of further X-ray images for detecting the tissue structure shape; and
determine from the plurality of further X-ray images at least one X-ray image by optimizing or minimizing visibility for a certain tissue structure shape.
10. The X-ray system according to claim 9 , wherein the at least one electronic processor is further programmed to:
determine an associated energy-dependent weighting applied to the at least one X-ray image.
11. The X-ray system according to claim 10 , wherein the determined associated energy-dependent weighting is employed for detecting the tissue structure of interest by employing an energy-dependent visibility of a certain tissue structure of interest.
12. The X-ray system according to claim 6 , wherein the at least one electronic processor is further programmed to one of:
perform first a computer aided detection algorithm and second a spectral evaluation on an X-ray image;
perform first a spectral evaluation and second a computer aided detection algorithm on an X-ray image; and
perform a combined spectral computer aided detection algorithm on an X-ray image.
13. The non-transitory computer-readable medium according to claim 8 , further comprising
determining a plurality of further X-ray images, each further X-ray image having an individual defined energy-dependent weighting; and
evaluating the plurality of further X-ray images for detecting the tissue structure shape; and
determining from the plurality of further X-ray images at least one X-ray image by optimizing or minimizing visibility for a certain tissue structure shape.
14. The non-transitory computer-readable medium according to claim 8 , wherein determining from the plurality of further X-ray images at least one X-ray image by optimizing or minimizing visibility for a certain tissue structure shape comprises determining an associated energy-dependent weighting applied to the at least one X-ray image.
15. The non-transitory computer-readable medium according to claim 14 , wherein the determined associated energy-dependent weighting is employed for detecting the tissue structure of interest, in particular by employing an energy-dependent visibility of a certain tissue structure of interest.
16. The non-transitory computer-readable medium according to claim 8 , wherein the computer aided detection comprises one of performing first a computer aided detection algorithm and second a spectral evaluation on an X-ray image, performing first a spectral evaluation and second a computer aided detection algorithm on an X-ray image, and performing a combined spectral computer aided detection algorithm on an X-ray image.
17. The method of claim 1 , wherein the energy-dependent weighting is one of a band pass weighting, a low pass weighting, a high pass weighting and a notch weighting.
18. The X-ray system of claim 6 , wherein the energy-dependent weighting is one of a band pass weighting, a low pass weighting, a high pass weighting and a notch weighting.
19. The non-transitory computer-readable medium of claim 8 , wherein the energy-dependent weighting is one of a band pass weighting, a low pass weighting, a high pass weighting and a notch weighting.