CN112863641A - Radiation therapy system and offset determination method and device of radiation source thereof - Google Patents

Radiation therapy system and offset determination method and device of radiation source thereof Download PDF

Info

Publication number
CN112863641A
CN112863641A CN201911102201.1A CN201911102201A CN112863641A CN 112863641 A CN112863641 A CN 112863641A CN 201911102201 A CN201911102201 A CN 201911102201A CN 112863641 A CN112863641 A CN 112863641A
Authority
CN
China
Prior art keywords
projection
radiation source
value
radiation
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201911102201.1A
Other languages
Chinese (zh)
Inventor
苟天昌
闫浩
李金升
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
SHENZHEN AOWO MEDICAL NEW TECHNOLOGY DEVELOPMENT CO LTD
Our United Corp
Shenzhen Our New Medical Technologies Development Co Ltd
Original Assignee
SHENZHEN AOWO MEDICAL NEW TECHNOLOGY DEVELOPMENT CO LTD
Our United Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by SHENZHEN AOWO MEDICAL NEW TECHNOLOGY DEVELOPMENT CO LTD, Our United Corp filed Critical SHENZHEN AOWO MEDICAL NEW TECHNOLOGY DEVELOPMENT CO LTD
Priority to CN201911102201.1A priority Critical patent/CN112863641A/en
Publication of CN112863641A publication Critical patent/CN112863641A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/40—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture

Landscapes

  • Health & Medical Sciences (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Surgery (AREA)
  • Urology & Nephrology (AREA)
  • Engineering & Computer Science (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Radiation-Therapy Devices (AREA)

Abstract

The application discloses a radiation therapy system and a method and a device for determining offset of a radiation source of the radiation therapy system, and relates to the field of radiation therapy. According to the method, a projection image can be acquired firstly, a projection position in projection parameters corresponding to at least one radioactive source in the projection image is acquired, then, the offset corresponding to at least one radioactive source can be determined according to the projection position corresponding to at least one radioactive source and a reference position, the offset of the whole radioactive sources is not only determined, and the accuracy of the determined offset of the radioactive sources is good.

Description

Radiation therapy system and offset determination method and device of radiation source thereof
Technical Field
The application relates to the technical field of radiation therapy, in particular to a radiation therapy system and a method and a device for determining offset of a radiation source of the radiation therapy system.
Background
Radiation therapy systems generally include a gantry and a treatment head mounted on the gantry that can emit a treatment beam to deliver radiation treatment to an affected part of a patient.
In the related art, a radiation source box is usually disposed in the treatment head, and a radiation source hole is disposed on the radiation source box, and a radiation source can be disposed in the radiation source hole, and the radiation source can emit high-energy gamma rays (i.e., treatment beams) which can be focused and perform radiation treatment on an affected part of a patient. Treatment errors may result from deviations in the position of the radiation source within the radiation source bore. In the related art, the radiation source may be projected by using an imaging device to obtain an image, where the image includes a projection corresponding to the radiation source, and the offset of the radiation source in the aperture of the radiation source is determined by the projection of the radiation source in the image.
However, when the projections of the plurality of radiation sources in the image overlap, only the offset of the entire plurality of radiation sources can be determined, it is difficult to determine the offset of each radiation source, and the accuracy of determining the offset of the radiation source is poor.
Disclosure of Invention
The application provides a radiation therapy system and a method and a device for determining the offset of a radioactive source of the radiation therapy system, which can solve the problem of poor accuracy of the offset of the radioactive source determined in the related technology. The technical scheme is as follows:
in one aspect, a method for determining an offset of a radiation source is provided, the method including:
acquiring a projection image, wherein the projection image comprises a projection corresponding to at least one radioactive source;
acquiring projection parameters corresponding to at least one radioactive source in the projection images, wherein the projection parameters at least comprise a projection position;
and determining the offset corresponding to at least one radioactive source according to the projection position corresponding to at least one radioactive source and the reference position.
Optionally, the projection parameters further include: the maximum gray value corresponding to the radiation source, and/or the pixel gray distribution parameter set corresponding to the radiation source.
Optionally, the acquiring projection parameters corresponding to at least one of the radiation sources in the projection image includes:
and determining projection parameters corresponding to at least one radioactive source according to the gray level distribution in the projection image.
Optionally, the determining a projection parameter corresponding to at least one of the radiation sources according to the gray scale distribution in the projection image includes:
constructing a target projection image so that the gray value of each position in the target projection image is consistent with the gray value of the corresponding position in the projection image;
constructing a projection objective function of projection parameters corresponding to at least one radioactive source according to the relation between the gray value of each position in the target projection image and the gray value of the corresponding position in the projection image;
and outputting the value of the projection parameter corresponding to at least one radioactive source when the projection objective function takes the minimum value.
Optionally, the projection objective function satisfies:
Figure BDA0002270196770000021
f1 is an expression of the projection objective function, x1 is the abscissa of the pixel in the projection image, y1 is the ordinate of the pixel in the projection image, F1(x1, y1) is the gray-scale value at coordinates (x1, y1) in the projection image, P1(x1, y1) is the gray-scale value at coordinates (x1, y1) in the target projection image.
Optionally, before outputting the value of the projection parameter corresponding to at least one of the radiation sources when the projection objective function takes the minimum value, the method further includes:
and according to a gradient descent algorithm, iteratively solving a minimum value of the projection objective function, and iteratively solving a value of a projection parameter corresponding to at least one radioactive source.
Optionally, the iteratively solving the minimum value of the projection objective function according to a gradient descent algorithm, and iteratively solving the value of the projection parameter corresponding to at least one of the radiation sources, includes:
deriving the projection parameters in the projection objective function;
acquiring an initial value, a learning rate and a convergence condition of the projection parameter;
performing iterative calculation according to the initial values of the projection parameters, the learning rate and the calculation formula of gradient reduction;
and when the convergence condition is met, obtaining the minimum value of the projection target function and the value of the projection parameter corresponding to the minimum value of the projection target function.
Optionally, when the number of the projection parameters is at least two, in the iterative computation process of the gradient descent algorithm, the number of the projection parameters updated in each iteration is smaller than the total number of the projection parameters.
Optionally, before the determining the offset corresponding to the at least one radiation source according to the projection position corresponding to the at least one radiation source and the reference position, the method further includes:
and acquiring reference parameters corresponding to at least one radioactive source in a reference image, wherein the reference parameters at least comprise a reference position.
Optionally, the acquiring a reference parameter corresponding to at least one of the radiation sources in the reference image includes:
and determining a reference parameter corresponding to at least one radioactive source according to the gray level distribution in the reference image.
Optionally, the determining a reference parameter corresponding to at least one of the radiation sources according to the gray scale distribution in the reference image includes:
constructing a target reference image so that the gray value of each position in the target reference image is consistent with the gray value of the corresponding position in the reference image;
constructing a reference target function of a reference parameter corresponding to at least one radioactive source according to the relation between the gray value of each position in the target reference image and the gray value of the corresponding position in the reference image;
and when the reference objective function takes the minimum value, outputting the value of the reference parameter corresponding to at least one radioactive source.
Optionally, the reference objective function satisfies:
Figure BDA0002270196770000031
f2 is an expression of the reference objective function, x2 is the abscissa of the pixel in the reference image, y2 is the ordinate of the pixel in the reference image, F2(x2, y2) is the grayscale value at the coordinates (x2, y2) in the reference image, P2(x2, y2) is the grayscale value at the coordinates (x2, y2) in the target reference image.
Optionally, before outputting the value of the reference parameter corresponding to at least one of the radiation sources when the reference objective function takes the minimum value, the method further includes:
and according to a gradient descent algorithm, iteratively solving a minimum value for the reference objective function, and iteratively solving a value of a reference parameter corresponding to at least one of the radiation sources.
Optionally, the iteratively solving the minimum value of the reference objective function according to a gradient descent algorithm and the iteratively solving the value of the reference parameter corresponding to at least one of the radiation sources includes:
deriving the reference parameter in the reference objective function;
acquiring an initial value, a learning rate and a convergence condition of the reference parameter;
performing iterative calculation according to the initial value of the reference parameter, the learning rate and the calculation formula of gradient descent;
and when the convergence condition is met, obtaining the minimum value of the reference objective function and the value of the reference parameter corresponding to the minimum value of the reference objective function.
Optionally, when the number of the reference parameters is at least two, in the iterative computation process of the gradient descent algorithm, the number of the reference parameters updated in each iteration is smaller than the total number of the reference parameters.
Optionally, after the determining an offset corresponding to at least one of the radiation sources according to the projection position corresponding to at least one of the radiation sources and a reference position, the method further includes:
adjusting a position of at least one of the radiation sources in the radiation therapy system based on the offset, or adjusting a position of a treatment couch in the radiation therapy system based on the offset.
In another aspect, there is provided an apparatus for determining an offset of a radiation source, the apparatus comprising:
the first acquisition module is used for acquiring a projection image, and the projection image comprises a projection corresponding to at least one radioactive source;
the second acquisition module is used for acquiring projection parameters corresponding to at least one radioactive source in the projection image, and the projection parameters at least comprise a projection position;
and the determining module is used for determining the offset corresponding to at least one radioactive source according to the projection position corresponding to at least one radioactive source and the reference position.
Optionally, the second obtaining module is further configured to determine a projection parameter corresponding to at least one of the radiation sources according to a gray scale distribution in the projection image.
Optionally, the second obtaining module includes:
the first construction submodule is used for constructing a target projection image so that the gray value of each position in the target projection image is consistent with the gray value of the corresponding position in the projection image;
the second construction submodule is used for constructing a projection objective function of projection parameters corresponding to at least one radioactive source according to the relation between the gray value of each position in the target projection image and the gray value of the corresponding position in the projection image;
and the output submodule is used for outputting the value of the projection parameter corresponding to at least one radioactive source when the projection objective function takes the minimum value.
Optionally, the second obtaining module further includes:
and the iteration submodule is also used for solving the minimum value of the projection objective function in an iteration mode according to a gradient descent algorithm and solving the value of the projection parameter corresponding to at least one radioactive source in an iteration mode.
Optionally, the iteration sub-module includes:
a derivation unit, configured to derive the projection parameters in the projection objective function;
an acquisition unit configured to acquire an initial value, a learning rate, and a convergence condition of the projection parameter;
the iteration unit is used for carrying out iterative computation according to the initial values of the projection parameters, the learning rate and the gradient descending computation formula;
and the determining unit is used for obtaining the minimum value of the projection target function and the value of the projection parameter corresponding to the minimum value of the projection target function when the convergence condition is met.
Optionally, when the number of the projection parameters is at least two, in the iterative computation process of the gradient descent algorithm, the number of the projection parameters updated in each iteration is smaller than the total number of the projection parameters.
Optionally, the apparatus further comprises:
and the third acquisition module is used for acquiring reference parameters corresponding to at least one radioactive source in a reference image, and the reference parameters at least comprise a reference position.
Optionally, the third obtaining module is further configured to determine a reference parameter corresponding to at least one of the radiation sources according to the gray scale distribution in the reference image.
Optionally, the apparatus further comprises:
and the adjusting module is used for adjusting the position of at least one radioactive source in the radiation therapy system according to the offset, or adjusting the position of a treatment couch in the radiation therapy system according to the offset.
In yet another aspect, there is provided an offset determination apparatus for a radiation source, the apparatus comprising: a memory and a processor;
the memory is used for storing instructions executed by the processor, and the processor implements the offset determination method of the radiation source in the aspect by executing the instructions stored in the memory.
In yet another aspect, a radiation therapy system is provided, the radiation therapy system comprising: a radiation therapy apparatus and an offset determining device for a radiation source according to the above aspects;
the radiotherapy apparatus comprises: the treatment head comprises at least one radioactive source, and the imaging device is used for imaging the at least one radioactive source.
In yet another aspect, a computer-readable storage medium is provided, having instructions stored therein, which when run on a computer, cause the computer to perform the method for determining an offset of a radiation source according to the above aspect.
The beneficial effect that technical scheme that this application provided brought includes at least:
the method can acquire a projection image firstly, and acquire a projection position in projection parameters corresponding to at least one radioactive source in the projection image, and then can determine the offset corresponding to at least one radioactive source according to the projection position corresponding to at least one radioactive source and a reference position instead of only determining the integral offset of a plurality of radioactive sources, so that the accuracy of the determined offset of the radioactive source is better.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of an image acquired by an imaging device under a collimating aperture according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of an image acquired by an imaging device under another collimation aperture according to an embodiment of the present disclosure;
FIG. 3 is a flow chart of a method for determining an offset of a radiation source according to an embodiment of the present disclosure;
FIG. 4 is a flow chart of another method for determining an offset of a radiation source provided by an embodiment of the present application;
FIG. 5 is a flowchart of a method for determining projection parameters corresponding to at least one radiation source according to an embodiment of the present disclosure;
FIG. 6 is a graph illustrating a gray scale distribution of a radiation source according to an embodiment of the present disclosure;
FIG. 7 is a graph of a two-dimensional gray scale distribution of a radiation source according to an embodiment of the present disclosure;
FIG. 8 is a two-dimensional gray scale distribution graph of another radiation source provided in accordance with an embodiment of the present disclosure;
FIG. 9 is a graph illustrating a two-dimensional gray scale distribution of another radiation source according to an embodiment of the present disclosure;
FIG. 10 is a graph illustrating a two-dimensional gray scale distribution of another radiation source according to an embodiment of the present disclosure;
FIG. 11 is a flow chart of an iterative solution according to a gradient descent algorithm provided by an embodiment of the present application;
FIG. 12 is a schematic diagram of a region of interest of a projection image provided by an embodiment of the present application;
FIG. 13 is a schematic diagram of a binary image of a projection image according to an embodiment of the present disclosure;
FIG. 14 is a schematic diagram of a diamond-shaped light spot provided by an embodiment of the present application;
FIG. 15 is a schematic diagram of a light spot having an elliptical shape according to an embodiment of the present disclosure;
fig. 16 is a schematic diagram of a light spot having a rectangular shape according to an embodiment of the present application;
FIG. 17 is a schematic diagram of an apparatus for determining an offset of a radiation source according to an embodiment of the present disclosure;
fig. 18 is a schematic structural diagram of a second obtaining module according to an embodiment of the present disclosure;
fig. 19 is a schematic structural diagram of an iteration sub-module provided in an embodiment of the present application;
FIG. 20 is a schematic diagram illustrating an alternative radiation source offset determination apparatus in accordance with embodiments of the present disclosure;
fig. 21 is a schematic structural diagram of another device for determining an offset of a radiation source according to an embodiment of the present disclosure.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
Fig. 1 is a schematic diagram of an image acquired under a collimation aperture of an imaging device according to an embodiment of the present disclosure. Fig. 2 is a schematic diagram of an image acquired under another collimation aperture of an imaging device according to an embodiment of the present disclosure. Referring to fig. 1, it can be seen that the image acquired by the imaging device includes projections corresponding to 13 radiation sources, and there is no overlapping area in the projections corresponding to the 13 radiation sources. Referring to fig. 2, it can be seen that the image acquired by the imaging device includes projections corresponding to 13 radiation sources, and there is an overlapping region in the projections corresponding to the 13 radiation sources. That is, 13 radiation sources may be included in the radiation therapy system.
In the related art, the projections corresponding to the 13 radiation sources shown in fig. 1 are independent from each other, so that the offset of each radiation source can be determined according to the image, and between the projections corresponding to the 13 radiation sources shown in fig. 2, there is an overlapping area between the projections corresponding to the left 5 radiation sources, and there is an overlapping area between the projections corresponding to the right 8 radiation sources, so that only the offset of the overlapping area formed by the projections corresponding to the left 5 radiation sources and the offset of the overlapping area formed by the projections corresponding to the right 8 radiation sources can be determined according to the image. That is, only the global offset of the left 5 sources and the global offset of the right 8 sources can be determined.
That is, in the case where there is an overlapping area in the projections corresponding to a plurality of radiation sources, it is difficult to determine the offset of each radiation source itself. Therefore, the embodiment of the application provides a method for determining the offset of a radioactive source, which can solve the problem that the offset of each radioactive source is difficult to determine in the related art. The method may be applied in an offset determination device for a radiation source of a radiation therapy system, which may comprise a plurality of (i.e. at least two) radiation sources. Referring to fig. 3, the method may include:
step 101, acquiring a projection image.
The projection images may include projections corresponding to at least one radiation source, which may be images acquired by an imaging device in a radiation therapy system. After the imaging device acquires the image, the imaging device can send the acquired image to an offset determining device of a radioactive source of the radiation therapy system, and the offset determining device of the radioactive source can acquire the projection image. The imaging device may be an Electronic Portal Imaging Device (EPID) or a film, which is not limited in this embodiment of the present invention.
And 102, acquiring projection parameters corresponding to at least one radioactive source in the projection image.
In this embodiment, the projection parameters at least include a projection position, and the offset determining device of the radiation source may obtain the projection position corresponding to at least one radiation source according to the obtained projection image. The projection position corresponding to the at least one radiation source can be represented by coordinates of the projection corresponding to the at least one radiation source in the projection image.
Alternatively, the origin of coordinates may be pre-configured by the offset determination apparatus of the radiation source, or the origin of coordinates may be selected by the operator according to actual conditions. For example, the origin of coordinates may be located at the position of the first row and the first column of pixels in the projection image.
Step 103, determining the offset corresponding to at least one radioactive source according to the projection position corresponding to at least one radioactive source and the reference position.
In an embodiment of the present application, the reference position corresponding to the at least one radiation source may refer to a standard position of the at least one radiation source. The offset determining device of the radioactive sources can determine the offset of each radioactive source according to the standard position of each radioactive source in the reference image and the projection position in the projection image.
For example, the offset determining device of the radiation source may determine the offset of each radiation source according to a difference between an abscissa corresponding to each radiation source in the reference image and an abscissa corresponding to each radiation source in the projection image, and a difference between an ordinate corresponding to each radiation source in the reference image and an ordinate corresponding to each radiation source in the projection image.
To sum up, the embodiment of the present application provides a method for determining offset of a radiation source, which may first acquire a projection image and acquire a projection position in projection parameters corresponding to at least one radiation source in the projection image, and then may determine the offset corresponding to at least one radiation source according to the projection position corresponding to at least one radiation source and a reference position, instead of determining only the offset of the whole plurality of radiation sources, so that the accuracy of the determined offset of the radiation source is better.
FIG. 4 is a flow chart of another method for determining an offset of a radiation source according to an embodiment of the present disclosure. As can be seen with reference to fig. 4, the method may include:
step 201, acquiring a projection image.
In an embodiment of the application, the projection image may comprise a projection corresponding to the at least one radiation source. By way of example, the projection images may be images acquired by an imaging device in a radiation therapy system. After the imaging device acquires the image, the imaging device can send the acquired image to an offset determining device of a radioactive source of the radiation therapy system, and the offset determining device of the radioactive source can acquire the projection image.
It should be noted that the projection images may be images acquired by an imaging device in the radiation therapy system in real time when the offset of the radiation source needs to be determined. Alternatively, the projection images may be images acquired by an imaging device in the radiation therapy system every predetermined period of time. The predetermined time period may be pre-stored in the offset determination device of the radiation source of the radiation therapy system according to actual conditions, or the predetermined time period may be determined empirically by the operator, which is not limited in the embodiment of the present application.
Step 202, determining projection parameters corresponding to at least one radioactive source according to the gray level distribution in the projection image.
In this embodiment, the projection parameters may be parameters of a projection corresponding to the radiation source, and the projection parameters may include: the projection position, the maximum gray value corresponding to each radioactive source and the pixel gray distribution parameter group corresponding to at least one radioactive source.
Alternatively, the projection position of at least one radiation source in the projection image may refer to the coordinates of the corresponding center pixel of the radiation source.
Step 203, determining a reference parameter corresponding to at least one radioactive source according to the gray level distribution in the reference image.
In embodiments of the present application, the reference parameter may include at least a reference position. The offset determining device of the radioactive source can determine the reference position corresponding to at least one radioactive source according to the reference image. The reference position corresponding to the at least one radiation source may be a standard position corresponding to the at least one radiation source. The standard position corresponding to each radiation source can be represented by the coordinates of the projection corresponding to the radiation source in the reference image.
Alternatively, the origin of coordinates may be pre-configured by the offset determination apparatus of the radiation source, or the origin of coordinates may be selected by the operator according to actual conditions. For example, the origin of coordinates may be located at the position of the first row and the first column of pixels in the upper left corner of the reference image.
The offset determining device of the radioactive source can store a plurality of reference images, and each reference image is an image acquired by the imaging device when the projection corresponding to the radioactive source is located at the standard position. In the multiple reference images, the standard positions corresponding to the radioactive sources may be different, and the number of the radioactive sources corresponding to the radioactive sources may also be different. When the offset determining device of the radioactive source needs to acquire the standard positions of the projections corresponding to the plurality of radioactive sources in the reference image, a projection image corresponding to the projection image can be determined from the plurality of reference images stored in the offset determining device of the radioactive source according to the acquired projection image, and then the offset determining device of the radioactive source acquires the standard position of each radioactive source in the plurality of radioactive sources in the reference image according to the determined reference image.
It should be noted that the number of the standard positions of the plurality of radiation sources in the reference image, which are acquired by the radiation source offset determination device, may be the same as the number of the projection positions of the plurality of acquired radiation sources in the projection image, and the standard positions of the plurality of radiation sources may correspond to the projection positions of the plurality of radiation sources one to one. That is, the number of corresponding radiation sources in the reference image may be the same as the number of corresponding radiation sources in the projection image.
And step 204, determining the offset corresponding to at least one radioactive source according to the projection position corresponding to at least one radioactive source and the reference position.
In this embodiment, for at least one radiation source, the offset determining device of the radiation source can determine the offset of the radiation source according to the reference position in the reference parameters determined in step 203 and the projection position in the projection parameters determined in step 202.
The position of each radiation source in the radiation therapy system is adjusted according to the offset, or the position of the treatment couch in the radiation therapy system is adjusted according to the offset, step 205.
In the embodiment of the application, when the offset determining device of the radioactive source determines that a certain radioactive source in the radiation therapy system has offset, the offset determining device of the radioactive source can automatically adjust the position of the radioactive source in the radiation therapy system according to the offset of the radioactive source with offset, so that the radioactive source can accurately irradiate the affected part of a patient, and the treatment effect of the radiation therapy system is improved.
When the offset determining device of the radioactive source determines that all radioactive sources in the radiotherapy system have overall offset, the offset determining device of the radioactive source can automatically adjust the position of the radioactive source in the radiotherapy system according to the offset of the radioactive source, or an operator can adjust the position of a treatment couch in the radiotherapy system according to the offset of the radioactive source, so that the radioactive source can accurately irradiate the affected part of a patient, and the treatment effect of the radiotherapy system is improved.
Optionally, the offset determining device of the radiation source may adjust the position of each radiation source in real time according to the offset of each radiation source. Or, the offset determining device of the radioactive source can adjust the position of each radioactive source according to the offset of each radioactive source at preset time intervals. The embodiment of the present application does not limit this.
It should be noted that the order of the steps of the offset determination method of the radiation source provided by the embodiment of the present application may be adjusted appropriately, for example, step 203 may be performed before step 202. Any method that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application is covered by the protection scope of the present application, and thus the detailed description thereof is omitted.
In the embodiment of the present application, referring to fig. 5, step 202 may include:
step 2021, constructing the target projection image so that the gray value of each position in the target projection image is consistent with the gray value of the corresponding position in the projection image.
In the embodiment of the present application, the gray-scale value of each position in the target projection image may be determined according to the gray-scale distribution in the projection image, and the gray-scale value of each position in the projection image may be the actual gray-scale value of each position in the projection image.
In order to determine the gray value for each position in the target projection image from the gray distribution in the projection image, a gray distribution curve of the projection of the at least one radiation source in the projection image may first be determined. Then, a gray value for each position in the projection image of the object is determined based on the gray profile of the projection of the at least one radiation source.
Fig. 6 is a graph of a gray scale distribution corresponding to a radiation source according to an embodiment of the present disclosure. For example, the graph of the AA-direction gray scale distribution shown in fig. 2 may be used. Wherein, X may refer to the coordinate of the projection corresponding to the radiation source in the X direction (i.e. the horizontal axis direction of the projection image), Y may refer to the coordinate of the projection corresponding to the radiation source in the Y direction (i.e. the vertical axis direction of the projection image), and Z may refer to the gray value corresponding to the radiation source. Wherein the gray scale values in fig. 6 range from 0 to 1.
Referring to fig. 6, it can be seen that the gray distribution curve of the projection of the at least one radiation source is a curve that is open downward, and the gray distribution curves of the projections corresponding to the radiation source along any direction passing through the central pixel in the radiation source may be the same, that is, the gray value at the central pixel corresponding to the radiation source may be larger, and the gray value along the direction away from the central pixel may gradually decrease.
For example, the gray value at the center pixel corresponding to the radiation source may be 255, and the gray value in the direction away from the center pixel may gradually decrease to 0.
In this embodiment, the geometric meaning of the gray-scale distribution curve corresponding to a radiation source when only one radiation source is provided in the radiation therapy system can be determined, and then the gray-scale distribution curve corresponding to at least one radiation source can be determined according to the gray-scale distribution curve corresponding to the one radiation source.
Alternatively, only the gray-scale distribution of the radiation source in the X-axis (the horizontal axis of the projection image) direction may be considered, and a basis function may be constructed first according to the gray-scale distribution, and the basis function may satisfy:
Figure BDA0002270196770000121
wherein, B may be used to represent a gray-scale distribution curve of the projection corresponding to the radiation source along the X-axis direction, X1 may represent pixel coordinates along the X-axis direction, r11 may represent a radius of a pixel area of a gray-scale value of a pixel corresponding to the radiation source within a gray-scale threshold range, r12 may represent a width of the pixel area of the projection corresponding to the radiation source in a direction away from a central pixel and within a gray-scale drop threshold range, and m1 and n1 may be pixel gray-scale distribution parameters corresponding to the radiation source in the projection image.
In order to express the meaning of each parameter, when the values of r11, r12, m1, and n1 are different, a gray scale distribution curve corresponding to the above formula (1) is plotted.
In the gray distribution graph shown in fig. 7, r11 may be equal to 100, r12 may be equal to 200, m1 may be equal to 10, and n1 may be equal to 5. Alternatively, in the gradation distribution curve shown in fig. 8, r11 may be equal to 100, r12 may be equal to 300, m1 may be equal to 10, and n1 may be equal to 5. Still alternatively, in the gradation distribution curve shown in fig. 9, r11 may be equal to 100, r12 may be equal to 300, m1 may be equal to 8, and n1 may be equal to 5. Still alternatively, in the gradation distribution curve shown in fig. 10, r11 may be equal to 100, r12 may be equal to 300, m1 may be equal to 8, and N may be equal to 2.
As can be seen from fig. 8 and 9, when m1 is smaller, the change of the gray level value corresponding to the radiation source in the r12 region can be slower, and when m1 is larger, the change of the gray level value corresponding to the radiation source in the r12 region can be steeper.
As can be seen from fig. 9 and 10, when n1 becomes small, the range of the r11 region may become small, and when n1 becomes large, the range of the r11 region may become large.
In fig. 7 to 10, the maximum value of the ordinate is 1, and may be used to represent the maximum grayscale value 255.
Referring to fig. 7 to 10, the gray scale values of the pixels corresponding to each radiation source in the projection image can be relatively close to each other in the r11 area, that is, the gray scale values corresponding to the radiation sources in the r11 area can be within the gray threshold range. Alternatively, the grayscale threshold may range from 245 to 255.
It can also be seen with reference to fig. 7-10 that the variation of the gray scale value of the corresponding pixel of each radiation source in the projection image within the region r12 can be large, and the gray scale value of the portion of the region near r11 can be large, and the gray scale value of the portion in the direction away from the region r11 can be small. That is, in the r12 region, the gray scale value corresponding to the radiation source may gradually decrease in a direction away from the central pixel, and the gray scale decrease threshold may range from 245 to 0.
According to the analysis, the gray value of each position in the target projection image determined by the embodiment of the application can satisfy the following conditions:
Figure BDA0002270196770000131
wherein N1 may be the number of corresponding radiation sources in the projection image, SX1iMay be the abscissa of the central pixel corresponding to the ith radiation source in the projection image, SY1iMay be an ordinate of a central pixel corresponding to an i-th radiation source in the projection image, r11 may be a radius of a pixel area within a threshold range of gray scale for a gray scale value of a pixel corresponding to each radiation source in the projection image, r12 may be a width of a pixel area within a threshold range of gray scale decrease in a direction away from the central pixel in the projection corresponding to each radiation source in the projection image, m1 and n1 may be gray scale distribution parameters of pixels corresponding to radiation sources in the projection image, g1iThe maximum gray value corresponding to the ith radiation source in the projection image.
In the above formula (2), SX1i，SY1iR11, r12, m1, n1, and g1iAre all unknown numbers, SX1iAnd SY1iThe coordinates of the central pixel corresponding to at least one radioactive source to be acquired.
Step 2022, constructing a projection objective function related to the projection parameters corresponding to the at least one radiation source according to the relationship between the gray value of each position in the target projection image and the gray value of the corresponding position in the projection image.
In the embodiment of the present application, the constructed projection objective function may satisfy:
Figure BDA0002270196770000132
where F1 may be an expression of a projection objective function, x1 may be an abscissa of a pixel in the projection image, y1 may be an ordinate of a pixel in the projection image, F1(x1, y1) may be a gray scale value at coordinates (x1, y1) in the projection image, height may be a number of pixels included per column of pixels in the projection image, weight may be a number of pixels included per row of pixels in the projection image, and P1(x1, y1) may be a gray scale value at coordinates (x1, y1) in the target projection image.
The above formula (3) can represent the sum of the gray value of the position corresponding to the projection of the at least one radiation source in the target projection image and the square difference of the gray value of the corresponding position in the projection image.
Step 2023, outputting the projection parameter value corresponding to the at least one radiation source when the projection objective function takes the minimum value.
In an embodiment of the present application, when the projection objective function takes the minimum value, the offset determining device of the radiation source may output a value of the projection parameter corresponding to at least one radiation source.
Because the number of unknowns in the constructed projection objective function is large, and when the number of radiation sources included in the radiation therapy system is large, the pixel gray level distribution parameter set (including the first radius, the first width, and 2 pixel gray level distribution parameters) corresponding to all the radiation sources, the coordinates of the center pixel corresponding to each radiation source, and the maximum gray level value corresponding to each radiation source need to be calculated. More parameters need to be determined, so that the minimum value of the projection objective function can be iteratively solved according to a gradient descent algorithm, and the value of the projection parameter corresponding to at least one radioactive source is iteratively solved. That is, the various unknowns in the projection objective function may be determined according to a gradient descent algorithm.
Referring to fig. 2, the projection image includes projections corresponding to 13 radiation sources, that is, the unknowns include pixel gray scale fraction parameter sets corresponding to the 13 radiation sources, and the abscissa, ordinate and maximum gray scale value corresponding to each of the 13 radiation sources. That is, it may include: the first radius, the first width and the 2-pixel gray scale distribution parameters in the pixel gray scale fraction parameter set corresponding to the 13 radiation sources, as well as 13 abscissas, 13 ordinates, 13 maximum gray values, are 43 unknowns in total, that is, the parameters to be determined are 43.
Fig. 11 is a flowchart for iterative solution according to a gradient descent algorithm according to an embodiment of the present application. As can be seen with reference to fig. 11, the method may include:
step 20231, derivation of the projection parameters in the projection objective function.
In the embodiment of the present application, in order to use a gradient descent algorithm to iteratively solve the values of the projection parameters, a derivative may be first obtained for each projection parameter in the projection objective function.
From equations (2) and (3), the projection objective function can be determined as:
Figure BDA0002270196770000141
order to
Figure BDA0002270196770000142
Then
Figure BDA0002270196770000143
Order to
Figure BDA0002270196770000144
Then
Figure BDA0002270196770000145
Figure BDA0002270196770000146
Figure BDA0002270196770000147
Figure BDA0002270196770000148
Figure BDA0002270196770000149
Figure BDA00022701967700001410
From the derivative chain rule, it can be determined that:
Figure BDA0002270196770000151
Figure BDA0002270196770000152
；
Figure BDA0002270196770000153
Figure BDA0002270196770000154
Figure BDA0002270196770000155
Figure BDA0002270196770000156
Figure BDA0002270196770000157
step 20232, obtain initial values of projection parameters, learning rate and convergence conditions.
Referring to the above-mentioned partial derivatives of the projection parameters, the maximum gray value corresponding to at least one radiation source in the projection image can be directly obtained by making the partial derivative equal to zero.
For the projection position corresponding to at least one radioactive source in the projection image and the pixel gray level distribution parameter group corresponding to all the radioactive sources, the initial value, the learning rate and the convergence condition corresponding to each projection parameter can be determined.
In an embodiment of the present application, the set of pixel gray scale distribution parameters corresponding to the radiation source may include: a first radius of the radiation source, a first width, and 2 pixel intensity distribution parameters of the radiation source. The first radii of the plurality of radiation sources may be the same and the first widths may be the same, and thus the initial values of the first radii of the plurality of radiation sources determined may be the same and the initial values of the first widths of each radiation source determined may be the same. And the 2 pixel gray level distribution parameters of the radioactive source are determined according to the pixel gray level distribution curve, so the pixel gray level distribution parameters of a plurality of radioactive sources can be the same.
The initial value of the first radius r11 and the initial value of the first width r12 corresponding to each radiation source can be roughly determined according to an image processing algorithm, and are generally empirical values.
Furthermore, the parameters m1 and n1 of the gray-scale distribution of pixels corresponding to the radiation source in the projection image are acquired, and m1 and n1 may be empirical values.
For example, the initial value of the pixel distribution parameter m1 corresponding to a plurality of radiation sources may be equal to 10, and the initial value of n1 may be equal to 5.
Optionally, referring to fig. 12, when the initial value of the maximum gray value corresponding to each radioactive source in the projection image is obtained, an image processing algorithm may be first used to determine a region of interest (ROI) of the projection image, determine a median (mean) of gray values of all pixels in the ROI region, and determine the initial value of the maximum gray value corresponding to each radioactive source region as the median.
For example, if the median of the gray values of all pixels in the ROI area is determined to be 155, the initial value of the maximum gray value corresponding to each radiation source may be determined to be 155.
In the embodiment of the present application, when the initial coordinates of the center pixel corresponding to each radiation source in the projection image are obtained, a threshold segmentation method may be first used to obtain a binary image of the projection image, and obtain a connected domain of the binary image, and the initial coordinates of the center pixel corresponding to each radiation source are determined according to the connected domain of the binary image.
Referring to fig. 2, the projection image acquired by the imaging device includes projections corresponding to 13 radiation sources (the radiation therapy system includes 13 radiation sources), and when the initial coordinates of the central pixel corresponding to each radiation source are determined, referring to fig. 13, a binary image of the projection image may be acquired by using a threshold segmentation method, two connected domains of the binary image may be acquired, the minimum bounding rectangles of the two connected domains may be determined, and the boundary values of the minimum bounding rectangles of the two connected domains may be respectively obtained.
The upper boundary value of the minimum circumscribed rectangle of the first connected domain a is taken as top1, the lower boundary value of the minimum circumscribed rectangle of the first connected domain a is taken as bottom1, the left boundary value of the minimum circumscribed rectangle of the first connected domain a is taken as left1, and the right boundary value of the minimum circumscribed rectangle of the first connected domain a is taken as right 1. The upper boundary of the minimum bounding rectangle of the second connected domain b is taken as top2, the lower boundary value of the minimum bounding rectangle of the second connected domain b is taken as bottom2, the left boundary value of the minimum bounding rectangle of the second connected domain b is taken as left11, and the right boundary value of the minimum bounding rectangle of the second connected domain b is taken as right 2.
For the area where the minimum circumscribed rectangle of the first connected domain a is located, the projections corresponding to the 5 radioactive sources (the projections corresponding to the radioactive sources can also be called as light spots) are distributed in two rows, and according to the geometric characteristics of the 5 light spots shown in fig. 12, the longitudinal coordinate SY1 of the central pixel of the two light spots in the first row can be determined1＝SY12Top1+ r11+ r12, ordinate SY1 of the central pixel of the second row of two spots3＝SY14＝SY15Bottom1-r11-r 12. The abscissa SX1 of the central pixel of the first spot of the second row3Left1+ r11+ r12, the abscissa SX1 of the central pixel of the third spot of the second row5Right1-r11-r12, the abscissa of the center pixel of the second row of second spots may be equal to the mean of the abscissa of the center pixel of the second row of first spots and the abscissa of the center pixel of the second row of third spots, SX14＝(left1+ right 1)/2. The abscissa of the central pixel of the first spot of the first row may be equal to the mean of the abscissa of the central pixel of the first spot of the second row and the abscissa of the central pixel of the second spot of the second row, i.e. SX11＝(SX13+SX14) Where 2 is left1 × 3/4+ right1/4+ (r11+ r12)/2, the abscissa of the center pixel of the first row of second spots may be equal to the mean of the abscissa of the center pixel of the second row of second spots and the abscissa of the center pixel of the second row of third spots, i.e. SX12＝(SX14+SX15)/2＝right1×3/4+left1/4-(r11+r12)/2。
According to the above analysis, the initial coordinates of the central pixels of the 5 light spots in the area where the minimum bounding rectangle of the first connected domain a of the two connected domains is determined are (left1 × 3/4+ right1/4+ (r11+ r12)/2, top1+ r11+ r12), (right1 × 3/4+ left1/4- (r11+ r12)/2, top1+ r11+ r12), (left1+ r11+ r12, bottom1-r11-r12), (left1+ right1)/2, bottom1-r11-r12), (right1-r11-r12, and bottom1-r11-r 12).
For the area where the minimum circumscribed rectangle of the second connected domain b is located, the 8 light spots are distributed in two rows, and according to the geometrical characteristics of the 8 light spots shown in fig. 12, the ordinate SY1 of the central pixel of the first row of four light spots can be determined6＝SY17＝SY18＝SY19Top2+ r11+ r12, ordinate SY1 of the central pixel of the second row of three spots10＝SY111＝SY112The abscissa SX1 of the central pixel of the first spot of the first row, from bottom2-r11-r126Left2+ r11+ r 12. Since the difference of the abscissa of the central pixel of each two adjacent light spots in the second connected component b may be equal to the difference of the abscissa of the central pixel of each two adjacent light spots in the first connected component a, in order to calculate the abscissas of the central pixels of the remaining light spots in the second connected component b, the difference gap of the abscissas of the central pixels of each two adjacent light spots in the first connected component a may be calculated first, that is, the gap is SX12-SX11＝SX15-SX14＝SX14-SX13(right1-left1) x 1/2-r11-r12, the second of the second connected domain bThe abscissa of the central pixel of the row of second spots is SX17＝SX16+ gap (right1-left1) x 1/2+ left2, and the abscissa of the central pixel of the first row and the third spot is SX18＝SX17+ gap 1-left1+ left2-r11-r12, and the abscissa of the central pixel of the fourth spot in the first row is SX19＝SX18+ gap (right1-left1) × 3/2+ left2- (r11+ r12) × 2, and the abscissa of the central pixel of the first spot of the second row may be equal to the mean of the abscissa of the central pixel of the first spot of the first row and the abscissa of the central pixel of the second spot of the first row, i.e. SX110＝(SX16+SX17) (right1-left1)/4+ (r11+ r12)/2+ left 2. the abscissa of the center pixel of the second row of second spots may be equal to the mean of the abscissa of the center pixel of the first row of first spots and the abscissa of the center pixel of the first row of second spots, or the abscissa of the center pixel of the second row of second spots may be equal to the sum of the differences gap between the abscissa of the center pixel of the second row of first spots and the abscissa of the center pixel of each two adjacent spots in the first connected domain a, that is, SX111＝SX110+ gap ═ x 3/4+ left2- (r11+ r12)/2, (right1-left1) ×, 3/4+ left2- (r11+ r12)/2, the abscissa of the central pixel of the second row of the third spot may be equal to the mean of the abscissa of the central pixel of the first row of the third spot and the abscissa of the central pixel of the first row of the fourth spot, or the abscissa of the central pixel of the second row of the third spot may be equal to the sum of the differences gap between the abscissa of the central pixel of the second row of the second spot and the abscissa of the central pixel of each two adjacent spots in the first connected domain a, namely SX112＝SX111+ gap ═ x 5/4+ left2- (r11+ r12) x 3/2 (right1-left 1). The abscissa of the central pixel of the fourth light spot in the second row can be equal to the sum of the differences gap between the abscissa of the central pixel of the third light spot in the second row and the abscissas of the central pixels of every two adjacent light spots in the first connected component a, namely SX113＝SX112+gap＝(right1-left1)×7/4+left2-(r11+r12)×5/2。
According to the above analysis, the initial coordinates of the center pixels of the 8 light spots in the area where the minimum bounding rectangle of the second connected domain b of the two connected domains are determined are (left + r + r, top + r + r), ((right-left) x + left, top + r), (right-left + left-r, top + r), ((right-left) x + left- (r + r) x2, top + r), ((right-left)/4 + (r + r)/2 + left, bottom-r), ((right-left) x + left- (r + r)/2, bottom-m-r), ((right-left) x + left- (r + r)/2, bottom-r-r), and (right-left) x + left- (r + r) x + r), bottom2-r11-r12), ((right1-left1) X7/4 + left2- (r11+ r12) X5/2, bottom2-r11-r 12).
The first radius r11 and the first width r12 in the initial coordinate of the central pixel of each spot may be empirically determined initial values, such as r11 being 100 and r12 being 150. And (3) substituting the determined boundary values of the minimum bounding rectangles of the two connected domains, and the determined initial values of the first radius r11 and the first width r12 into the coordinate formula, so as to determine the initial value of the central pixel corresponding to each radioactive source in the projection image.
In the embodiment of the present application, in addition to determining the initial values of the projection parameters (including the abscissa, the ordinate, the first radius, the first width, and the pixel gray-scale distribution parameters of the central pixel corresponding to each radiation source), the learning rate and the convergence condition of the projection parameters corresponding to each radiation source need to be determined.
In one aspect, a first learning rate, lean _ rate _ SX1, for a center pixel corresponding to each radiation source in the projection imagei＝0.00005，learn_rate_SY1i0.00005. The first convergence condition may be: the iteration number C1 is less than the first iteration number threshold, and the iteration error currs 1 is greater than the first error threshold. The first iteration number threshold may be 100, the first error threshold may be 1, and the iteration error may be
Figure BDA0002270196770000191
pre_SX1iPre _ SY1, the abscissa of the central pixel corresponding to the ith radiation source at the kth iterationiSX1, the ordinate of the central pixel corresponding to the ith radiation source in the kth iterationiIs the k +1 th iterationAbscissa of central pixel corresponding to i radioactive sources, SY1iThe ordinate of the central pixel corresponding to the ith radiation source in the (k + 1) th iteration is shown.
The iteration continues when the number of iterations C1 is less than the first iteration number threshold, and when the iteration error currs 1 is greater than the first error threshold, and the iteration ends when the number of iterations is greater than or equal to the first iteration number threshold, or when the iteration error currs 1 is less than or equal to the first error threshold.
On the other hand, for the projection corresponding to each radiation source, the first radius, the first width, the pixel gray scale distribution parameter m1 and the pixel gray scale distribution parameter n1 are all equal to the first radius, the first width, the pixel gray scale distribution parameter m1 and the pixel gray scale distribution parameter n1 corresponding to the rest radiation sources. Thus, for the first radius, the first width, the pixel intensity distribution parameter m1 and the pixel intensity distribution parameter n1 may determine only one convergence condition and be calculated in one iteration.
The second learning rate learn _ rate _ r11 of the first radius r11 corresponding to each radiation source in the projection image is 0.5, the third learning rate learn _ rate _ r12 of the first width r12 is 2, the fourth learning rate learn _ rate _ m1 of the pixel gray scale distribution parameter m1 is 0.0075, and the fifth learning rate learn _ rate _ m1 of the pixel gray scale distribution parameter n1 is 0.0025. The second convergence condition may be: the iteration number C2 is less than a second iteration number threshold, the iteration error crups2 is greater than a second error threshold, the second iteration number threshold may be 50, the second error threshold may be 2.5, and the iteration error satisfies:
Figure BDA0002270196770000192
where pre _ r11 is the first radius at the jth iteration, pre _ r12 is the first width at the jth iteration, pre _ m1 is the pixel gray distribution parameter m1 at the jth iteration, pre _ n1 is the pixel gray distribution parameter n1 at the jth iteration, r11 is the first radius at the jth +1 iteration, r12 is the first width at the jth +1 iteration, m1 is the pixel gray distribution parameter m1 at the jth +1 iteration, and n1 is the pixel gray distribution parameter m1 at the jth +1 iterationDistribution parameter n 1.
The iteration continues when the number of iterations C2 is less than the first iteration number threshold, and when the iteration error currs 2 is greater than the second error threshold, and the iteration ends when the number of iterations is greater than or equal to the second iteration number threshold, or when the iteration error currs 2 is less than or equal to the second error threshold.
Step 20233, performing iterative computation according to the initial values of the projection parameters, the learning rate, and the calculation formula of gradient descent.
When the number of the projection parameters is at least two, in the iterative calculation process of the gradient descent algorithm, the number of the projection parameters updated in each iteration is smaller than the total number of the projection parameters.
In the embodiment of the present application, the first radius r11, the first width r12, the pixel gray distribution parameter m1, and the pixel gray distribution parameter n1 in the pixel gray distribution parameter set may be obtained by using the same gradient descent algorithm. In the calculation process, the coordinates of the central pixel corresponding to each radiation source in the projection image and the maximum gray value can be set as fixed values.
For example, when the iteration number C2 is less than the second iteration number threshold, and when the iteration error currs 2 is greater than the second error threshold, the first radius r11 obtained by the j +1 th iteration may be assigned to the first radius pre _ r11 obtained by the j th iteration, the first width r12 obtained by the j +1 th iteration may be assigned to the first width pre _ r11 obtained by the j th iteration, the pixel gray distribution parameter m1 obtained by the j +1 th iteration may be assigned to the pixel gray distribution parameter pre _ m1 obtained by the j th iteration, and the pixel gray distribution parameter n1 obtained by the j +1 th iteration may be assigned to the pixel gray distribution parameter pre _ n1 obtained by the j th iteration. That is, pre _ r11 ═ r 11; pre _ r 12; pre _ m1 ═ m 1; pre _ n1 ═ n 1.
The calculation formulas for the gradient descent of the first radius r11, the first width r12, the pixel gray-scale distribution parameter m1, and the pixel gray-scale distribution parameter n1 are as follows:
Figure BDA0002270196770000201
Figure BDA0002270196770000202
the coordinates of the central pixel corresponding to each radioactive source in the projection image can be obtained by adopting the same gradient descent algorithm. In the calculation process, the maximum gray value corresponding to each radiation source in the projection image, and the first radius, the first width, and the pixel gray distribution parameter in the pixel gray distribution parameter set may be set as fixed values.
For example, the coordinates of the central pixel corresponding to the ith radiation source in the projection image can be obtained by a gradient descent algorithm. When the iteration number C1 is less than the first iteration number threshold and when the iteration error currs 1 is greater than the first error threshold, the abscissa SX1 of the center pixel obtained in the (k + 1) th iteration can be compared with the abscissaiAssign to the abscissa pre _ SX1 of the central pixel obtained in the kth iterationiThe ordinate SY1 of the central pixel obtained in the (k + 1) th iterationiAssign the ordinate pre _ SY1 to the central pixel obtained in the k-th iterationi. That is, pre _ SX1i＝SX1i；pre_SY1i＝SY1i。
Abscissa SX1 of center pixel corresponding to ith radiation sourceiAnd ordinate SY1iThe calculation formula of the gradient descent of (a) is as follows:
Figure BDA0002270196770000211
Figure BDA0002270196770000212
step 20234, when the convergence condition is satisfied, obtaining the minimum value of the projection objective function and the value of the projection parameter corresponding to the minimum value of the projection objective function.
And iteratively calculating the value of the first radius r11, the value of the first width r12, the value of the pixel gray scale distribution parameter m1 and the value of the pixel gray scale distribution parameter n1 by adopting the calculation formula of gradient descent. The iteration ends when the number of iterations is greater than or equal to the second number of iterations threshold, or when the iteration error currs 2 is less than or equal to the second error threshold. The initial value of the iteration number C2 may be 0, and the initial value of the iteration error currps 2 may be 10.
And calculating the coordinates of the central pixel corresponding to the ith radiation source by using the gradient descending calculation formula, and ending the iteration when the iteration number is greater than or equal to a first iteration number threshold value or when the iteration error currs 1 is less than or equal to a first error threshold value. The initial value of the iteration number C1 may be 0, and the initial value of the iteration error currps 1 may be 10.
For example, referring to fig. 2, the image acquired by the imaging device includes projections corresponding to 13 radiation sources, and assuming that the coordinates of the first radiation source in the determined projection image are (368, 1163), the maximum gray value is 113, the coordinates of the second radiation source are (602, 1163), the maximum gray value is 99, the coordinates of the 13 th radiation source are (1979, 1171), the maximum gray value is 137, the first radius is 100, the first width is 200, the pixel gray distribution parameter m1 is 10, and the n1 is 5, then the coordinates of the first radiation source are (1979, 1171), the maximum gray value is 137, the first radius is 100
Figure BDA0002270196770000213
Note that, since the gradation value of each position in the constructed target projection image coincides with the gradation value of the corresponding position in the projection image, the minimum value of F1 may be 0. However, if it is necessary to iterate F1 to 0 and obtain the projection parameters when F1 is 0, the number of iterations required is large, so when a gradient descent algorithm is used to iteratively solve the minimum value for the projection objective function, F1 may be within a certain error range, and when F1 is within the error range, the projection parameters corresponding to at least one radiation source are already iteratively completed.
In this embodiment, the step 2021 to the step 2023 may be referred to in the process of determining the reference parameter corresponding to the at least one radiation source according to the gray scale distribution in the reference image in the step 203, and details of this embodiment are not repeated herein.
Wherein, the constructed reference objective function can satisfy:
Figure BDA0002270196770000221
f2 is an expression of the reference objective function, x2 is the abscissa of the pixel in the reference image, y2 is the ordinate of the pixel in the reference image, and F2(x2, y2) is the grayscale value at coordinates (x2, y2) in the reference image. Since the number of pixels included in each column of pixels in the reference image is the same as the number of pixels included in each column of pixels in the projection image, and the number of pixels included in each row of pixels in the reference image is the same as the number of pixels in each row of the pixel bank in the projection image, height can also be used to represent the number of pixels included in each column of pixels in the reference image, weight can also be used to represent the number of pixels included in each row of pixels in the reference image, and P2(x2, y2) can be a gray value at coordinates (x2, y2) in the target reference image.
P2(x2, y2) satisfies:
Figure BDA0002270196770000222
n2 is the number of radiation sources in the reference image, SX2iIs the abscissa of the central pixel corresponding to the ith radiation source in the reference image, SY2iR21 is the radius of the pixel area of the gray value of the pixel corresponding to each radioactive source in the reference image within the gray threshold range, r22 is the width of the pixel area of the projection corresponding to each radioactive source in the reference image in the direction away from the central pixel and within the gray reduction threshold range, m2 and n2 are the gray distribution parameters of the pixel corresponding to the radioactive source in the reference image, g2iThe maximum gray value corresponding to the ith radiation source in the reference image.
Optionally, the offset of the radiation source may satisfy:
Figure BDA0002270196770000223
that is, the offset corresponding to the i-th radiation source can be determined by using the coordinates of the center pixel corresponding to the i-th radiation source in the projection image and the coordinates of the center pixel corresponding to the i-th radiation source in the reference image.
It should also be noted that the corresponding size and shape of the radiation source may be determined by a collimating aperture in the collimator. Referring to fig. 1 and 2, the aperture of the collimation hole corresponding to the light spot (projection corresponding to the radiation source) shown in fig. 1 is smaller, and the aperture of the collimation hole corresponding to the light spot shown in fig. 2 is larger. Referring to fig. 1 and 2, each of the light spots is circular, but each of the light spots may have other shapes, for example, a diamond shape, an oval shape, or a rectangular shape, and the offset of the radiation source may be determined by the method provided in the embodiments of the present application regardless of the shape of the light spot. Also, in the present embodiment, the radiation source may be a cobalt source.
Alternatively, referring to fig. 14, when the shape of the light spot is a diamond shape, P1(x1, y1) in the projection objective function may satisfy:
Figure BDA0002270196770000231
in the above formula (6), N1 represents the number of radiation sources in the projection image, SX1iSY1, the abscissa of the central pixel corresponding to the i-th radiation source in the projection imageiR11x is the width of the pixel region within the gray scale threshold range of the gray scale value of the pixel corresponding to each radioactive source in the x-axis direction (i.e., the horizontal axis of the projection image) in the projection image, r12x is the width of the pixel region within the gray scale drop threshold range of the projection image corresponding to each radioactive source in the x-axis direction in the projection image, m1x and n1x are the pixel gray scale distribution parameters of the radioactive sources in the projection image corresponding to the radioactive sources in the x-axis direction, and r11y is the pixel gray scale distribution parameters of the projection image corresponding to each radioactive source in the y-axis direction (i.e., the vertical axis of the projection image)The width of a pixel area of a gray value of a pixel within a gray threshold range, r12y is the width of a pixel area of a projection image corresponding to each radiation source along the y-axis direction, in a direction away from a central pixel and within a gray drop threshold range, and m1y and n1y are pixel gray distribution parameters of the projection image corresponding to the radiation source along the y-axis direction.
Referring to fig. 15, when the corresponding shape of the radiation source is an ellipse, P1(x1, y1) in the projection objective function can satisfy:
Figure BDA0002270196770000232
in the above formula (7), N1 is the number of radiation sources in the projection image, SX1iSY1, the abscissa of the central pixel corresponding to the i-th radiation source in the projection imageiThe x-coordinate of the central pixel corresponding to the ith radiation source in the projection image, r11 is the width of the pixel area of the gray scale value of the pixel corresponding to each radiation source in the projection image within the gray scale threshold range, r12 is the width of the pixel area of the projection corresponding to each radiation source in the projection image in the direction away from the central pixel and within the gray scale drop threshold range, m1 and n1 are the gray scale distribution parameters of the pixels corresponding to the radiation sources in the projection image, and s is the ratio of the width of the projection corresponding to the radiation source along the x-axis (i.e., the horizontal axis of the projection image) to the width along the y-axis (i.e., the vertical axis of the projection image).
Referring to fig. 16, when the corresponding shape of the radiation source is rectangular, P1(x1, y1) in the projection objective function can satisfy:
Figure BDA0002270196770000241
in the above equation (8), N1 is the number of radiation sources in the projection image, SX1iSY1, the abscissa of the central pixel corresponding to the i-th radiation source in the projection imageiR11x is the x-axis of the projection image (i.e., projection view) as the ordinate of the center pixel corresponding to the ith radiation source in the projection imageHorizontal axis of image) of the projection image, r12x is the width of the pixel area within the gray threshold range of the gray value of the pixel corresponding to each radiation source in the x-axis direction of the projection image, the width of the pixel area in the direction away from the central pixel and within the threshold range of gray scale reduction, m1x and n1x are the pixel gray scale distribution parameters corresponding to the radiation source in the projection image along the x-axis direction, r11y is the width of the pixel area in the gray scale threshold range of the gray scale value of the pixel corresponding to each radiation source in the projection image along the y-axis direction (i.e. the longitudinal axis of the projection image), r12y is the width of the pixel area in the projection image corresponding to each radiation source in the y-axis direction, the width of the pixel area in the direction away from the center pixel and within the threshold range of the gray scale drop, m1y and n1y are the pixel gray scale distribution parameters corresponding to the radiation source in the y-axis direction in the projection image.
It should be noted that, when the shape of the light spot is a diamond, an ellipse, or a rectangle, P2(x2, y2) in the reference objective function may be similar to P1(x1, y1) in the projection objective function, and the description of the embodiment of the present application is omitted here.
To sum up, the embodiment of the present application provides a method for determining offset of a radiation source, which may first acquire a projection image and acquire a projection position in projection parameters corresponding to at least one radiation source in the projection image, and then may determine the offset corresponding to at least one radiation source according to the projection position corresponding to at least one radiation source and a reference position, instead of determining only the offset of the whole plurality of radiation sources, so that the accuracy of the determined offset of the radiation source is better.
Fig. 17 is a schematic structural diagram of a device for determining an offset of a radiation source according to an embodiment of the present application, which may be used in a radiation therapy system including a plurality of radiation sources, and which may include:
a first acquisition module 301 configured to acquire projection images, wherein the projection images include projections corresponding to at least one radiation source.
A second obtaining module 302, configured to obtain projection parameters corresponding to at least one radiation source in the projection image, where the projection parameters at least include a projection position.
The determining module 303 is configured to determine an offset corresponding to at least one radiation source according to the projection position corresponding to the at least one radiation source and the reference position.
Optionally, the projection parameters further include: the maximum gray value corresponding to each radioactive source and/or the pixel gray distribution parameter set corresponding to the radioactive source.
Optionally, the second obtaining module 302 is configured to determine a projection parameter corresponding to at least one radiation source according to a gray scale distribution in the projection image.
Alternatively, referring to fig. 18, the second obtaining module 302 may include:
a first construction sub-module 3021 configured to construct the target projection image such that the grayscale value of each position in the target projection image matches the grayscale value of the corresponding position in the projection image.
A second construction submodule 3022, configured to construct a projection objective function with respect to projection parameters corresponding to the at least one radiation source according to a relationship between the gray-level value of each position in the target projection image and the gray-level value of the corresponding position in the projection image.
And the output sub-module 3023 is configured to output a value of a projection parameter corresponding to the at least one radiation source when the projection objective function takes a minimum value.
Optionally, the second obtaining module 302 may further include:
the iteration submodule 3024 is configured to iteratively solve the minimum value for the projection objective function according to a gradient descent algorithm, and iteratively solve the value of the projection parameter corresponding to the at least one radiation source.
Alternatively, referring to fig. 19, the iteration sub-module 3024 may include:
a derivation unit 30241, configured to derive the projection parameters in the projection objective function.
An acquisition unit 30242 for acquiring initial values of the projection parameters, the learning rate, and the convergence condition.
An iteration unit 30243, configured to perform iterative computation according to the initial values of the projection parameters, the learning rate, and the calculation formula of gradient descent.
A determining unit 30244, configured to obtain a minimum value of the projection objective function and a value of the projection parameter corresponding to the minimum value of the projection objective function when the convergence condition is satisfied.
Optionally, when the number of projection parameters is at least two, in the iterative computation process of the gradient descent algorithm, the number of projection parameters updated in each iteration is smaller than the total number of projection parameters.
Alternatively, referring to fig. 20, the apparatus may further include:
a third obtaining module 304, configured to obtain reference parameters corresponding to at least one radiation source in the reference image, where the reference parameters at least include a reference position.
Optionally, the third obtaining module 304 is further configured to determine a reference parameter corresponding to at least one radiation source according to the gray scale distribution in the reference image.
Optionally, the apparatus may further include:
an adjustment module 305 for adjusting a position of at least one radiation source in the radiation therapy system based on the offset.
To sum up, the embodiment of the present application provides an offset determining apparatus for a radiation source, which may first obtain a projection image, and obtain a projection position in projection parameters corresponding to at least one radiation source in the projection image, and then determine an offset corresponding to at least one radiation source according to the projection position corresponding to at least one radiation source and a reference position, instead of determining only offsets of a plurality of radiation sources as a whole, where the accuracy of the determined offset of the radiation source is better.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses, modules, sub-modules and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
Fig. 21 is a schematic structural diagram of an offset determination apparatus for a radiation source according to an embodiment of the present application, and referring to fig. 21, the apparatus 40 may include: a processor 401 and a memory 402. The memory 402 may be used to store instructions executed by the processor 401, and the processor 401 may execute the instructions stored in the memory 402 to implement the offset determination method of the radiation source provided by the above-mentioned embodiments, such as the method shown in fig. 3, 4, 5 or 11.
Embodiments of the present application also provide a radiation therapy system, which may include: the radiation therapy equipment and the offset determining device of the radiation source provided by the embodiment are provided. The radiotherapy apparatus comprises: the treatment head comprises at least one radioactive source, and the imaging device is used for imaging the at least one radioactive source.
Embodiments of the present application also provide a computer-readable storage medium having instructions stored therein, which when run on a computer, cause the computer to perform the method shown in any one of fig. 2, fig. 3, fig. 4, fig. 5, and fig. 11.
It will be understood by those skilled in the art that all or part of the steps of implementing the above embodiments may be implemented by hardware, or may be implemented by operating the relevant hardware by a program, where the program is stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only exemplary of the present application and should not be taken as limiting, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims (14)

1. A method for determining an offset of a radiation source, the method comprising:
acquiring a projection image, wherein the projection image comprises a projection corresponding to at least one radioactive source;
acquiring projection parameters corresponding to at least one radioactive source in the projection images, wherein the projection parameters at least comprise a projection position;
and determining the offset corresponding to at least one radioactive source according to the projection position corresponding to at least one radioactive source and the reference position.
2. The method of claim 1, wherein the projection parameters further comprise: the maximum gray value corresponding to the radiation source, and/or the pixel gray distribution parameter set corresponding to the radiation source.
3. The method of claim 1, wherein acquiring projection parameters corresponding to at least one of the radiation sources in the projection image comprises:
and determining projection parameters corresponding to at least one radioactive source according to the gray level distribution in the projection image.
4. The method of claim 3, wherein determining projection parameters corresponding to at least one of the radiation sources according to a gray scale distribution in the projection image comprises:
constructing a target projection image so that the gray value of each position in the target projection image is consistent with the gray value of the corresponding position in the projection image;
constructing a projection objective function of projection parameters corresponding to at least one radioactive source according to the relation between the gray value of each position in the target projection image and the gray value of the corresponding position in the projection image;
and outputting the value of the projection parameter corresponding to at least one radioactive source when the projection objective function takes the minimum value.
5. The method of claim 4, wherein the projection objective function satisfies:
Figure FDA0002270196760000011
f1 is an expression of the projection objective function, x1 is the abscissa of the pixel in the projection image, y1 is the ordinate of the pixel in the projection image, F1(x1, y1) is the gray-scale value at coordinates (x1, y1) in the projection image, P1(x1, y1) is the gray-scale value at coordinates (x1, y1) in the target projection image.
6. The method of claim 4, wherein before outputting the value of the projection parameter corresponding to the at least one radiation source when the projection objective function takes the minimum value, the method further comprises:
and according to a gradient descent algorithm, iteratively solving a minimum value of the projection objective function, and iteratively solving a value of a projection parameter corresponding to at least one radioactive source.
7. The method of claim 6, wherein iteratively solving the minimum value for the projection objective function and the value of the projection parameter for the at least one radiation source according to a gradient descent algorithm comprises:
deriving the projection parameters in the projection objective function;
acquiring an initial value, a learning rate and a convergence condition of the projection parameter;
performing iterative calculation according to the initial values of the projection parameters, the learning rate and the calculation formula of gradient reduction;
and when the convergence condition is met, obtaining the minimum value of the projection target function and the value of the projection parameter corresponding to the minimum value of the projection target function.
8. The method of claim 6, wherein when the projection parameters are at least two, the number of projection parameters updated per iteration during the iterative calculation of the gradient descent algorithm is less than the total number of projection parameters.
9. The method of claim 1, wherein before determining the offset corresponding to the at least one radiation source according to the projection position corresponding to the at least one radiation source and a reference position, the method further comprises:
and acquiring reference parameters corresponding to at least one radioactive source in a reference image, wherein the reference parameters at least comprise a reference position.
10. The method of claim 9, wherein the acquiring of the reference parameter corresponding to the at least one radiation source in the reference image comprises:
and determining a reference parameter corresponding to at least one radioactive source according to the gray level distribution in the reference image.
11. The method of any one of claims 1 to 10, wherein after said determining an offset corresponding to at least one of the radiation sources from the projection position corresponding to at least one of the radiation sources and a reference position, the method further comprises:
adjusting a position of at least one of the radiation sources in the radiation therapy system based on the offset, or adjusting a position of a treatment couch in the radiation therapy system based on the offset.
12. An offset determination apparatus for a radiation source, the apparatus comprising: a memory and a processor;
the memory is used for storing instructions executed by the processor, and the processor implements the offset determination method of the radiation source according to any one of claims 1 to 11 by executing the instructions stored in the memory.
13. A radiation therapy system, characterized in that it comprises: an offset determination device for a radiation therapy apparatus and a radiation source according to claim 12;
the radiotherapy apparatus comprises: the treatment head comprises at least one radioactive source, and the imaging device is used for imaging the at least one radioactive source.
14. A computer-readable storage medium having stored therein instructions which, when run on a computer, cause the computer to execute the offset determination method of a radiation source according to any one of claims 1 to 11.
CN201911102201.1A 2019-11-12 2019-11-12 Radiation therapy system and offset determination method and device of radiation source thereof Pending CN112863641A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911102201.1A CN112863641A (en) 2019-11-12 2019-11-12 Radiation therapy system and offset determination method and device of radiation source thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911102201.1A CN112863641A (en) 2019-11-12 2019-11-12 Radiation therapy system and offset determination method and device of radiation source thereof

Publications (1)

Publication Number Publication Date
CN112863641A true CN112863641A (en) 2021-05-28

Family

ID=75984638

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911102201.1A Pending CN112863641A (en) 2019-11-12 2019-11-12 Radiation therapy system and offset determination method and device of radiation source thereof

Country Status (1)

Country Link
CN (1) CN112863641A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116092632A (en) * 2023-03-15 2023-05-09 南京谷睿生物科技有限公司 Nuclear medicine imaging data analysis method for radiopharmaceutical evaluation

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102169578A (en) * 2011-03-16 2011-08-31 内蒙古科技大学 Non-rigid medical image registration method based on finite element model
CN103955930A (en) * 2014-04-28 2014-07-30 中国人民解放军理工大学 Motion parameter estimation method based on gray integral projection cross-correlation function characteristics
CN105288869A (en) * 2015-10-26 2016-02-03 深圳市奥沃医学新技术发展有限公司 Device and method for controlling rotation of radiotherapy device
US20160284062A1 (en) * 2014-10-16 2016-09-29 Uniwersytet Slaski W Katowicach Method of determining distortion and/or distortion correction for projection image obtained during computer tomography routine
CN106408509A (en) * 2016-04-29 2017-02-15 上海联影医疗科技有限公司 Registration method and apparatus
CN106693215A (en) * 2016-12-30 2017-05-24 上海联影医疗科技有限公司 Locating method for cross wire in radiotherapy equipment
CN107041997A (en) * 2016-02-05 2017-08-15 瓦里安医疗系统国际股份公司 Beam of radiation is directed at the system measured with beam of radiation, method and apparatus
CN107567343A (en) * 2015-01-28 2018-01-09 医科达有限公司 three-dimensional localization and tracking for adaptive radiation therapy
CN108871588A (en) * 2018-08-09 2018-11-23 昆明物理研究所 A kind of infrared imaging system various dimensions joint asymmetric correction method
CN110075428A (en) * 2018-09-12 2019-08-02 上海联影医疗科技有限公司 A kind of beam examines, measurement method and device
CN110292723A (en) * 2019-06-25 2019-10-01 上海联影医疗科技有限公司 Dosage guidance pendulum position device, dosage monitoring device, radiotherapy system and medium

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102169578A (en) * 2011-03-16 2011-08-31 内蒙古科技大学 Non-rigid medical image registration method based on finite element model
CN103955930A (en) * 2014-04-28 2014-07-30 中国人民解放军理工大学 Motion parameter estimation method based on gray integral projection cross-correlation function characteristics
US20160284062A1 (en) * 2014-10-16 2016-09-29 Uniwersytet Slaski W Katowicach Method of determining distortion and/or distortion correction for projection image obtained during computer tomography routine
CN107567343A (en) * 2015-01-28 2018-01-09 医科达有限公司 three-dimensional localization and tracking for adaptive radiation therapy
CN105288869A (en) * 2015-10-26 2016-02-03 深圳市奥沃医学新技术发展有限公司 Device and method for controlling rotation of radiotherapy device
CN107041997A (en) * 2016-02-05 2017-08-15 瓦里安医疗系统国际股份公司 Beam of radiation is directed at the system measured with beam of radiation, method and apparatus
CN106408509A (en) * 2016-04-29 2017-02-15 上海联影医疗科技有限公司 Registration method and apparatus
CN106693215A (en) * 2016-12-30 2017-05-24 上海联影医疗科技有限公司 Locating method for cross wire in radiotherapy equipment
CN108871588A (en) * 2018-08-09 2018-11-23 昆明物理研究所 A kind of infrared imaging system various dimensions joint asymmetric correction method
CN110075428A (en) * 2018-09-12 2019-08-02 上海联影医疗科技有限公司 A kind of beam examines, measurement method and device
CN110292723A (en) * 2019-06-25 2019-10-01 上海联影医疗科技有限公司 Dosage guidance pendulum position device, dosage monitoring device, radiotherapy system and medium

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
BARBER J ET AL: "Comparison of automatic image registration uncertainty for three IGRT systems using a male pelvis phantom", JOURNAL OF APPLIED CLINICAL MEDICAL PHYSICS, vol. 17, no. 5, 31 December 2016 (2016-12-31), pages 283 - 292 *
王振江 等: "一种结合快速灰度投影与SSDA的图像匹配方法", 计算机工程与应用, vol. 47, no. 33, 31 December 2011 (2011-12-31), pages 195 - 197 *
郑莹 等: "下颌骨系统模型重建及受力分析的研究", 同济大学出版社, pages: 6 - 7 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116092632A (en) * 2023-03-15 2023-05-09 南京谷睿生物科技有限公司 Nuclear medicine imaging data analysis method for radiopharmaceutical evaluation

Similar Documents

Publication Publication Date Title
JP6996633B2 (en) Teacher label image correction method, trained model creation method and image analysis device
KR102070256B1 (en) Cephalo image processing method for orthodontic treatment planning, apparatus, and method thereof
US10716530B2 (en) Method and system of automated X-ray positioning and collimation control on hand and foot scan
JP6495441B2 (en) Radiotherapy plan optimization and visualization
JP6684205B2 (en) An interactive dose-gradient-based optimization method to control IMRT delivery complexity
US20190329073A1 (en) Ray tracing for the detection and avoidance of collisions between radiotherapy devices and patient
EP3003483B1 (en) Device for determining illumination distributions for imrt
CN113034382B (en) Brightness uniformity adjustment method, brightness uniformity adjustment device, computer device, and readable storage medium
CN107349531B (en) radiotherapy equipment, storage medium, and method and device for generating subfield shape
CN112863641A (en) Radiation therapy system and offset determination method and device of radiation source thereof
CN105389476B (en) The interpolation algorithm of IMRT intended dose data based on Gradient Features
US10373349B2 (en) Image generation apparatus
US11337669B2 (en) Automatic positioning of an X-ray source by way of segmentation
WO2022027545A1 (en) Image data processing method, and isocenter verification method and system for radiotherapy apparatus
EP2908176A1 (en) Method and apparatus for adjusting light intensity based on content to achieve a uniform exposure
US20230302298A1 (en) Method and system for robust radiotherapy treatment planning for dose mapping uncertainties
US10373350B2 (en) Apparatus and method for CT data reconstruction based on motion compensation
CN116209501A (en) Trajectory optimization using dose estimation and collision detection
CN101677873B (en) Method and apparatus for calculating a laser shot file for use in an excimer laser
JPWO2013129258A1 (en) Particle beam direction determination system, particle beam direction determination method, and particle beam direction determination computer program
US12017089B2 (en) Planning apparatus for planning a radiation therapy
US20220296921A1 (en) Path planning for radiation treatment
Kügler et al. How bad is good enough: Noisy annotations for instrument pose estimation
Liu et al. Study on star shot analysis for physics quality assurance in radiotherapy
Chaves-de-Plaza et al. Implementation of Delineation Error Detection Systems in Clinical Practice: Do AI-Supported Optimization and Human Preferences Meet?

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination