METHOD OF CALIBRATING X-RAY PROJECTION GEOMETRY IN X-RAY CONE BEAM COMPUTED TOMOGRAPHY

Abstract

The resent invention relates to a method of x-ray projection geometry calibration in x-ray cone beam computed tomography, the method comprising: at least one step (S1) of obtaining two-dimensional x-ray images (1) or a sinogram (2) of at least a part of an object (3), generated through relatively rotating around the object (3) a detector and an x-ray source projecting x-rays towards the detector; characterized by further comprising: at least one step (S4) of detecting in the two dimensional x-ray images (1) or the sinogram (2) at least one feature (3a) of the object (3) by using a trained artificial intelligence algorithm; and at least one step (S5) of creating, based on the detection, calibration information which defines the geometry of the x-ray projection.

Claims

1. A method of x-ray projection geometry calibration in x-ray cone beam computed tomography, the method comprising: at least one step (S1) of obtaining two-dimensional x-ray images (1) or a sinogram (2) of at least a part of an object (3), generated through relatively rotating around the object (3) a detector and an x-ray source projecting x-rays towards the detector; characterized by further comprising: at least one step (S4) of detecting in the two dimensional x-ray images (1) or the sinogram (2) at least one feature (3a) of the object (3) by using a trained artificial intelligence algorithm; and at least one step (S5) of creating, based on the detection, calibration information which defines the geometry of the x-ray projection.

2. The method according to claim 1, characterized in that in the detecting step (S4) the trained artificial intelligence algorithm generates 2D masks which represent the 2D location and/or 2D shape (3b) of the feature (3a) of the object (3) in the two-dimensional x-ray images (1) or a 3D mask which represents the 3D location and/or 3D shape of the feature (3a) of the object (3) in the sinogram (2).

3. The method according to claim 1 or 2, characterized in that in at least one obtaining step (S1) the object (3) is a calibration body, and the calibration information created corresponds to an x-ray unit-specific calibration information.

4. The method according to any one of claims 1 to 3, characterized in that in at least one obtaining step (S1) the object (3) is a patient, and the corresponding feature (3a) comprises an anatomical part or a prosthetic part of the patient body or the patient head, and the calibration information created corresponds to a patient-specific calibration information.

5. The method according to claim 4, characterized in that the anatomical part comprises at least part of a tooth or a bone, and/or the prosthetic part comprises at least part of an implant.

6. The method according to any one of claims 3 to 5, the method further comprising: a step (S6a) of storing a recently created x-ray unit-specific calibration information and/or a recently created patient-specific calibration information, or a step (S6b) updating a previously stored x-ray unit-specific calibration information and/or a previously stored patient-specific calibration information with a recently created x-ray unit-specific calibration information and/or a recently created patient-specific calibration information respectively.

7. The method according to any one of claims 3 to 6, characterized by further comprising: a step (S7) of reconstructing a three-dimensional tomographic image based on the two-dimensional x-ray images (1) or a sinogram (2) of at least a part of the body of a patient and the x-ray unit-specific calibration.

8. The method according to any one of claims 3 to 6, characterized by further comprising: a step (S7) of reconstructing a three-dimensional tomographic image based on the two-dimensional x-ray images (1) or the sinogram (2) of at least a part of the body of the patient and the corresponding patient-specific calibration information.

9. The method according to any one of claims 1 to 8, characterized by further comprising: a step (S2) of pre-processing the two-dimensional x-ray images (1) or the sinogram (2) prior to the detection step (S4).

10. The method according to any one of claims 1 to 9, characterized by further comprising: a step (S3) of selecting one or more a features (3a) to be detected in the detection step (S4).

11. The method according to claim 9, characterized in that the pre-processing step (S2) comprises at least one of a filtering process, a contrast enhancement process, an edge enhancement process, and a noise suppression process.

12. The method according to any one of claims 1 to 11, characterized by further comprising: a step of training the artificial intelligence algorithm by using data pairs, wherein each data pair includes a two-dimensional x-ray image (1′) and an associated 2D mask which represents the 2D location and/or 2D shape (3b′) of a feature (3a′) in the associated two-dimensional x-ray image (1), or wherein each data pair includes a sinogram (2) and an associated 3D mask which represents the 3D location and/or 3D shape (3b′) of a feature (3a′) in the sinogram (2).

13. An x-ray cone beam computed tomography system comprising: an x-ray unit comprising an acquisition means adapted to acquire two-dimensional x-ray images (1) or a sinogram (2) of at least part of an object (3) through relatively rotating around the object (3) an x-ray source and a detector; characterized by further comprising: a tomographic reconstruction unit comprising an image processing means adapted to detect in the two dimensional x-ray images (1) or the sinogram (2) at least one feature (3a) of the object (3) by using a trained artificial intelligence algorithm; and to create, based on the detection, calibration information which defines the geometry of the x-ray projection.

14. A computer-readable program comprising codes for causing a computer-based x-ray volume tomography system to perform the method steps according to any one of claims 1 to 12.

15. A computer-readable storage which stores the computer-readable program according to claim 14.

1. A method of x-ray projection geometry calibration in x-ray cone beam computed tomography, the method comprising: at least one step (S1) of obtaining two-dimensional x-ray images (1) or a sinogram (2) of at least a part of an object (3), generated through relatively rotating around the object (3) a detector and an x-ray source projecting x-rays towards the detector; characterized by further comprising: at least one step (S4) of detecting in the two dimensional x-ray images (1) or the sinogram (2) at least one feature (3a) of the object (3) by using a trained artificial intelligence algorithm; and at least one step (S5) of creating, based on the detection, calibration information which defines the geometry of the x-ray projection.

2. The method according to claim 1, characterized in that in the detecting step (S4) the trained artificial intelligence algorithm generates 2D masks which represent the 2D location and or 2D shape (3b) of the feature (3a) of the object (3) in the two-dimensional x-ray images (1) or a 3D mask which represents the 3D location and/or 3D shape of the feature (3a) of the object (3) in the sinogram (2).

3. The method according to claim 1 or 2 characterized in that in at least one obtaining step (S1) the object (3) is a calibration body, and the calibration information created corresponds to an x-ray unit-specific calibration information.

4. The method according to claim 1, characterized in that in at least one obtaining step (S1) the object (3) is a patient, and the corresponding feature (3a) comprises an anatomical part or a prosthetic part of the patient body or the patient head, and the calibration information created corresponds to a patient-specific calibration information.

5. The method according to claim 4, characterized in that the anatomical part comprises at least part of a tooth or a bone, and/or the prosthetic part comprises at least part of an implant.

6. The method according to claim 3, the method further comprising: a step (S6a) of storing a recently created x-ray unit-specific calibration information and/or a recently created patient-specific calibration information, or a step (S6b) updating a previously stored x-ray unit-specific calibration information and/or a previously stored patient-specific calibration information with a recently created x-ray unit-specific calibration information and/or a recently, created patient-specific calibration information respectively.

7. The method according to claim 3, characterized by further comprising: a step (S7) of reconstructing a three-dimensional tomographic image based on the two-dimensional x-ray images (1) or a sinogram (2) of at least a part of the body of a patient and the x-ray unit-specific calibration.

8. The method according to any 6 claim 3, characterized by further comprising: a step (S7) of reconstructing a three-dimensional tomographic image based on the two-dimensional x-ray images (1) or the sinogram (2) of at least a part of the body of the patient and the corresponding patient-specific calibration information.

9. The method according to claim 1, characterized by further comprising: a step (S2) of pre-processing the two-dimensional x-ray images (1) or the sinogram (2) prior to the detection step (S4).

10. The method according to claim 1, characterized by further comprising: a step (S3) of selecting one or more a features (3a) to be detected in the detection step (S4).

11. The method according to claim 9, characterized in that the pre-processing step (S2) comprises at least one of a filtering process, a contrast enhancement process, an edge enhancement process, and a noise suppression process.

12. The method according to claim 1, by further comprising: a step of training the artificial intelligence algorithm by using, data pairs, wherein each data pair includes a two-dimensional x-ray image (1′) and an associated 2D mask which represents the 2D location and/or 2D shape (3b′) of a feature (3a′) in the associated two-dimensional x-ray image (1), or wherein each data pair includes a sinogram (2) and an associated 3D mask which represents the 3D location and/or 3D shape (3b′) of a feature (3a′) in the sinogram (2).

13. An x-ray cone beam computed tomography system comprising: an x-ray unit comprising an acquisition means adapted to acquire two-dimensional x-ray images (1) or a sinogram (2) of at least part of an object (3) through relatively rotating around the object (3) an x-ray source and a detector; characterized by further comprising: a tomographic reconstruction unit comprising an image processing means adapted to detect in the two dimensional x-ray images (1) or the sinogram (2) at least one feature (3a) of the object (3) by using a trained artificial intelligence algorithm; and to create, based on the detection, calibration information which defines the geometry of the x-ray projection.

14. A computer-readable program comprising codes for causing a computer-based x-ray volume tomography system to perform the method steps according to claim 1.

15. A computer-readable storage which stores the computer-readable program according to claim 14.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In the subsequent description, the present invention will be described in more detail by using exemplary embodiments and by referring to the drawings, wherein

[0019] FIG. 1—is a flowchart showing the steps of a method of x-ray projection geometry calibration in x-ray cone beam computed tomography according to the present invention;

[0020] FIG. 2—is a two-dimensional x-ray image generated through an x-ray unit according to the present invention;

[0021] FIG. 3—is a cross sectional view of a sinogram, along the line A-A in FIG. 2, of the two-dimensional x-ray images generated through the x-ray unit according to the present invention.

[0022] The reference numbers shown in the drawings denote the elements as listed below and will be referred to in the subsequent description of the exemplary embodiments. [0023] 1. 2D x-ray image [0024] 2. Sinogram [0025] 3. Object (e.g. Patient or calibration body) [0026] 3a. Feature (e.g. Anatomical/Prosthetic Part) [0027] 3b. Location/Shape

[0028] FIG. 1 shows the steps (S1-S7) of the x-ray projection geometry calibration method for x-ray cone beam computed tomography according to an embodiment of the present invention.

[0029] In a first step (S1), a plurality two-dimensional x-ray images (1) or a sinogram (2) of at least a part of an object (3) is obtained from an x-ray cone beam computed tomography system of the present invention. The object (3) may be a patient or a calibration body such as a dummy. The three-dimensional x-ray images (1) and the sinogram (2) are generated by the x-ray cone beam computed tomography system through relatively rotating around the object (3) a detector and an x-ray source projecting x-rays towards the detector.

[0030] In an optional second step (S2), the two-dimensional x-ray images (1) or the sinogram (2) is pre-processed. The pre-processing step (S2) comprises at least one of a filtering process, a contrast enhancement process, an edge enhancement process, and a noise suppression process.

[0031] In another optional third step (S3), one or more features (3a) of the object (3) are selected in the 2D x-ray images (1) or the sinogram (2) as originally obtained or as pre-processed. The selection can be performed manually on a display. Alternatively, the selection is performed automatically.

[0032] In a fourth step (S4), at least one feature (3a), optionally the selected feature (3a) of the object (3) is detected in the two-dimensional x-ray images (1) or the sinogram (2), or optionally in the pre-processed two-dimensional x-ray images (1) or the pre-processed sinogram (2) by using a trained artificial intelligence algorithm. Optionally additional information may be input into the trained artificial intelligence algorithm for detecting the feature (3a) in the fourth step (S4). The additional information may include an initial estimation about the 2D/3D position, shape and relative motion of the feature (3a). The additional information may include information to enhance detection of the at least one selected feature (3a) of step (S3). The feature (3a) may be detected simultaneously or one after the other. A further pre-processing step can be optionally performed after the selection step (S3). Thereby, for instance the pre-processing can be adapted to the spatial or image properties of the selected feature (3a) to optimize the feature detection. The feature (3a) to be detected may correspond to an anatomical part or a prosthetic part of the patient, particularly of the patient head, more particularly of the patient jaw. The anatomical part might be a tooth or a bone or the like. The prosthetic part might be an implant or the like. As shown in FIG. 2, the trained artificial intelligence algorithm generates 2D masks which represent the 2D location and/or 2D shape (3b) of the feature (3a) of the object (3) i.e., the tooth in the patient's jaw, in the two-dimensional x-ray images (1). FIG. 3 is a cross sectional view of the sinogram (2), along the line A-A in FIG. 2, that includes the two-dimensional x-ray image (1) of FIG. 2 at the projection index “100”. The projection index and the coordinates may vary depending on the details of the tomography. The projection index indicates the plurality of two-dimensional x-ray images (1) in the sinogram (2). As shown in FIG. 3, the trained artificial intelligence algorithm may alternatively generate a 3D mask which represents the 3D location and/or 3D shape (3b) of the feature (3a) of the object (3) i.e., the tooth in the patient's jaw, in the sinogram (2). In the subsequent description, the reference signs which have a prime denote elements that are used for training the artificial intelligence algorithm. The artificial intelligence algorithm is trained using data pairs. Each data pair includes a two-dimensional x-ray image (1′) and an associated 2D mask which represents the location and/or shape (3b′) of a feature (3a′) in the associated two-dimensional x-ray image (1). Alternatively, each data pair includes a sinogram (2′) and an associated 3D mask which represents the location and/or shape (3b′) of a feature (3a′) in the sinogram (2).

[0033] In a fifth step (S5), based on the detection, calibration information is created. The calibration information defines the geometry of the x-ray projection. When the irradiated object (3) is a calibration body, the created calibration information corresponds to an x-ray unit-specific calibration information. When the irradiated object (3) is a patient, the created calibration information corresponds to a patient-specific calibration information.

[0034] In an optional initial stage of the sixth step (S6a), the recently created x-ray unit-specific calibration information and the patient-specific calibration information are stored temporarily or permanently in the x-ray cone beam computed tomography system. Various patient-specific calibration information pertaining to different patients may be created and stored. In an optional subsequent stage of the sixth step (S6b) the previously stored x-ray unit-specific calibration information and the previously stored patient-specific calibration information are updated with the recently created x-ray unit-specific calibration information and the recently created patient-specific calibration information of the same patient respectively.

[0035] In a seventh step (S7), a three-dimensional tomographic image is reconstructed based on the two-dimensional x-ray images (1) or a sinogram (2) of at least a part of the body of a patient and the x-ray unit-specific calibration. Alternatively, the three-dimensional tomographic image may be reconstructed based on the two-dimensional x-ray images (1) or the sinogram (2) of at least a part of the body of the patient and the corresponding patient-specific calibration information.

[0036] The x-ray cone beam computed tomography system of the present invention has an x-ray unit and a tomographic reconstruction unit. The x-ray unit has an acquisition means adapted to acquire two-dimensional x-ray images (1) or the sinogram (2) of at least part of an object (3) through relatively rotating around the object (3) the x-ray source and the detector. The tomographic reconstruction unit has an image processing means adapted to perform the steps of the x-ray projection geometry calibration method.

[0037] The method may be provided in form of a computer-readable program having codes for causing the computer-based x-ray cone beam computed tomography system to execute the above described method steps (S1-S7). The computer-readable program may be stored in a computer-readable storage of the computer-based x-ray cone beam computed tomography system.