Template-less method for arbitrary radiopaque object tracking in dynamic imaging
First Claim
Patent Images
1. A method for localizing a fiducial marker in a medical image comprising:
- obtaining the medical image;
determining a search window for the medical image; and
performing an analysis, using an analysis unit, to localize the fiducial marker in the medical image;
wherein the fiducial marker is localized by the analysis unit without use of a marker template; and
wherein the act of performing the analysis comprises determining a cost function, the cost function having a component representing a rescaled grayscale intensity at a minima in the search window.
2 Assignments
0 Petitions
Accused Products
Abstract
A method for localizing a fiducial marker in a medical image includes: obtaining the medical image; and performing an analysis, using an analysis unit, to localize the fiducial marker in the medical image; wherein the fiducial marker is localized by the analysis unit without use of a marker template.
-
Citations
35 Claims
-
1. A method for localizing a fiducial marker in a medical image comprising:
-
obtaining the medical image; determining a search window for the medical image; and performing an analysis, using an analysis unit, to localize the fiducial marker in the medical image; wherein the fiducial marker is localized by the analysis unit without use of a marker template; and wherein the act of performing the analysis comprises determining a cost function, the cost function having a component representing a rescaled grayscale intensity at a minima in the search window. - View Dependent Claims (2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
4. A method for localizing a fiducial marker in a medical image comprising:
-
obtaining the medical image; determining a search window for the medical image, wherein the search window is determined based on a geometry formed by a combination of an object, a source, and an imager; and performing an analysis, using an analysis unit, to localize the fiducial marker in the medical image; wherein the fiducial marker is localized by the analysis unit without use of a marker template. - View Dependent Claims (14)
-
-
15. A method for localizing a fiducial marker in a medical image comprising:
-
obtaining the medical image; determining a search window for the medical image; and performing an analysis, using an analysis unit, to localize the fiducial marker in the medical image; wherein the fiducial marker is localized by the analysis unit without use of a marker template; and wherein the act of performing the analysis comprises determining a cost function, wherein the cost function includes a component representing a distance from a reference location in the search window to a minima in the search window.
-
-
16. A method for localizing a fiducial marker in a medical image comprising:
-
obtaining the medical image; determining a search window for the medical image; and performing an analysis, using an analysis unit, to localize the fiducial marker in the medical image; wherein the fiducial marker is localized by the analysis unit without use of a marker template; and wherein the act of performing the analysis comprises determining a cost function, wherein the cost function includes a component representing a distance between a minima in the search window of the medical image and a minima in another search window of a successive medical image.
-
-
17. A method for localizing a fiducial marker in a medical image comprising:
-
obtaining the medical image; determining a search window for the medical image; and performing an analysis, using an analysis unit, to localize the fiducial marker in the medical image; wherein the fiducial marker is localized by the analysis unit without use of a marker template; and wherein the act of performing the analysis comprises determining a cost function, wherein the cost function includes a first component representing a rescaled grayscale intensity at a minima in the search window, a second component representing a distance from a reference location in the search window to the minima in the search window, and a third component representing a distance between the minima in the search window of the medical image and a minima in another search window of a successive medical image.
-
-
18. An apparatus for localizing a fiducial marker in a medical image comprising:
-
a processing unit configured to obtain the medical image, and performing an analysis to localize the fiducial marker in the medical image, wherein the processing unit is configured to localize the fiducial marker without use of a marker template; and a medium for storing a position of the fiducial marker; wherein the processing unit is configured to perform the analysis by determining a cost function, the cost function having a component representing a rescaled grayscale intensity at a minima in a search window.
-
-
19. An apparatus for localizing a fiducial marker in a medical image comprising:
-
a processing unit configured to obtain the medical image, and performing an analysis to localize the fiducial marker in the medical image, wherein the processing unit is configured to localize the fiducial marker without use of a marker template; and a medium for storing a position of the fiducial marker; wherein the processing unit is further configured to determine a search window of for the medical image based on a geometry formed by a combination of an object, a source, and an imager. - View Dependent Claims (20, 21, 22, 23, 24, 25, 26, 27, 28, 29)
-
-
30. An apparatus for localizing a fiducial marker in a medical image comprising:
-
a processing unit configured to obtain the medical image, and performing an analysis to localize the fiducial marker in the medical image, wherein the processing unit is configured to localize the fiducial marker without use of a marker template; and a medium for storing a position of the fiducial marker; wherein the processing unit is configured to perform the analysis by determining a cost function, wherein the cost function includes a component representing a distance from a reference location in a search window to a minima in the search window.
-
-
31. An apparatus for localizing a fiducial marker in a medical image comprising:
-
a processing unit configured to obtain the medical image, and performing an analysis to localize the fiducial marker in the medical image, wherein the processing unit is configured to localize the fiducial marker without use of a marker template; and a medium for storing a position of the fiducial marker; wherein the processing unit is configured to perform the analysis by determining a cost function, wherein the cost function includes a component representing a distance between a minima in a search window of the medical image and a minima in another search window of a successive medical image.
-
-
32. An apparatus for localizing a fiducial marker in a medical image comprising:
-
a processing unit configured to obtain the medical image, and performing an analysis to localize the fiducial marker in the medical image, wherein the processing unit is configured to localize the fiducial marker without use of a marker template; and a medium for storing a position of the fiducial marker; wherein the processing unit is configured to perform the analysis by determining a cost function, wherein the cost function includes a first component representing a rescaled grayscale intensity at a minima in a search window, a second component representing a distance from a reference location in the search window to the minima in the search window, and a third component representing a distance between the minima in the search window of the medical image and a minima in another search window of a successive medical image.
-
-
33. A method for image analysis comprising:
-
I) manipulating a set of images to generate at least one approximated search window in each image such that the at least one approximated search window is located in the vicinity of a point of interest in the images; II) performing a first dynamic analysis, relative to the approximated search windows by;
A) identifying within the at least one approximated search window generated in each image one or more contrast points, a contrast point being a local point having an imaging intensity presenting a peak contrast relative to the imaging intensities of points surrounding the local point;
B) performing a contrast point characteristic identification step of determining, for each contrast point identified in an individual approximated search window in an individual image of the set of images, at least one of the following contrast point characteristics;
i) a distance value between the contrast point and a reference point of the individual approximated search window;
ii) an imaging intensity value of the contrast point; and
iii) a plurality of distance values measuring the distance from the location of the contrast point in the individual approximated search window to the location of each contrast point in the at least one approximated search window in another image of the set of images;
C) repeating the contrast point characteristic identification step for the at least one approximated search window in each image of the image set;
D) executing a dynamic programming algorithm to calculate a first resultant point for an individual approximated search window in an individual image of the image set, wherein the dynamic programming algorithm is executed based, at least in part, on input values corresponding to at least one contrast point characteristic value determined during the contrast point characteristic identification step, with an input value being provided for each contrast point identified in the individual approximated search window;
E) repeating execution of the dynamic programming algorithm for the at least one approximated search window in each image of the image set; and
F) storing the calculated first resultant point of each approximate search window in a data storage unit;III) manipulating the set of images to generate at least one refined search window in each image such that the at least one refined search window is positioned based on the first resultant point calculated relative to the individual approximated search window for that respective image during the first dynamic analysis; IV) performing a second dynamic analysis, relative to the refined search windows by repeating the steps of the first dynamic analysis (II), though performing the repeated steps in the second dynamic analysis relative to the refined search windows to calculate and store a second resultant point for each refined search window; and V) performing a convergence judgment step to judge if a convergence has occurred in the image analysis by;
G) performing a comparison step of comparing the first resultant point calculated for the at least one approximate search window generated an individual image of the image set with the second resultant point calculated for the at least one refined search window generated in the same individual image to determine if the first resultant point and the second result point are identical;
H) repeating the comparison step for the first resultant point and the second resultant point calculated for each image of the image set;
I) calculating a convergence percentage by calculating the percent of images of the image set that have a first resultant point and a second resultant point that are identical; and
J) judging whether the calculated convergence percentage satisfies a predetermined convergence threshold, with a convergence being deemed to have occurred if the calculated convergence percentage is equal to or above the predetermined convergence threshold, and a convergence being deemed to not have occurred if the calculated convergence percentage is below the predetermined convergence threshold, wherein, if it is deemed in the convergence judgment step (J) that a convergence has occurred, then the identical point identified by the first resultant point and the second resultant point in each image of the image set is deemed to be the point of interest, and wherein, if it is deemed in the convergence judgment step (J) that a convergence has not occurred, then steps (Ill), (IV) and (V) are repeated to calculate and store a third resultant point for each further refined search window, and to judge convergence in the image analysis by comparing the third resultant points to the second resultant points. - View Dependent Claims (34, 35)
-
Specification