Image registration method, device and equipment for radiotherapy, medium and product

Abstract

The invention discloses an image registration method, device and equipment for radiotherapy, a medium and a product. The method comprises the following steps: acquiring a three-dimensional medical image of a target object, a surface image under a predetermined body position and a ray image combination for positioning, wherein the ray image combination comprises ray images acquired at a first visual angle and a second visual angle respectively; determining a surface contour image corresponding to the three-dimensional medical image, and determining a registration matrix for registering the surface contour image to the surface image and a floating registration result of the three-dimensional medical image under the action of the registration matrix; under a pixel set corresponding to the ray image combination, projection images of the floating registration result under the first view angle and the second view angle are determined, and a projection image combination is obtained; and outputting a registration matrix under the condition that the similarity measure between the projection image combination and the ray image combination meets a predetermined screening condition. According to the embodiment of the invention, the accuracy of the image registration result between the three-dimensional medical image and the ray image combination can be improved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an image registration method, device, equipment, medium and product for radiotherapy. Background Art

[0002] In order to perform radiotherapy, it is usually necessary to obtain a three-dimensional medical image of the target object (patient) in a predetermined position during the simulation positioning stage, and then use the three-dimensional medical image to formulate a radiotherapy plan for the target object; during the radiotherapy execution stage, an optical guidance system is used to obtain a surface image of the target object in a predetermined position, and then the three-dimensional medical image and the surface image are registered to obtain a registration result, so as to map the three-dimensional medical image to the coordinate system where the surface image is located, and then based on the adaptability of the registration result and the radiotherapy plan, the radiotherapy equipment is controlled to perform radiotherapy operations on the target object in the predetermined position.

[0003] In summary, the effectiveness of radiotherapy depends on the accuracy of the above registration results, but the existing image registration methods cannot guarantee the accuracy of the above registration results. Therefore, radiotherapy performed based on the existing image registration methods is difficult to ensure a good radiotherapy effect. Summary of the invention

[0004] The present invention provides an image registration method, device, equipment, medium and product for radiotherapy, so as to solve the problem that the existing image registration methods are difficult to ensure that the image registration results between the three-dimensional medical images collected in the simulation positioning stage and the combination of the X-ray images used for radiotherapy positioning have high accuracy.

[0005] According to one aspect of the present invention, there is provided an image registration method for radiotherapy, comprising:

[0006] Acquire a three-dimensional medical image for formulating a radiotherapy plan for a target object, a surface image of the target object in a predetermined position during the radiotherapy execution phase, and a combination of radiographic images for positioning, wherein the combination of radiographic images includes radiographic images acquired at a first viewing angle and a second viewing angle, respectively, and the first viewing angle is orthogonal to the second viewing angle;

[0007] Determine a surface contour image corresponding to the three-dimensional medical image, determine a registration matrix for registering the surface contour image to the surface image, and a floating registration result of the three-dimensional medical image under the action of the registration matrix;

[0008] Under the pixel set corresponding to the radiation image combination, determining the projection images of the floating registration result under the first viewing angle and the second viewing angle respectively, to obtain a projection image combination;

[0009] A similarity measure between the projection image combination and the radiation image combination is determined, and the registration matrix is ​​output if the similarity measure meets a predetermined screening condition.

[0010] According to another aspect of the present invention, there is provided an image registration device for radiotherapy, comprising:

[0011] an acquisition module, configured to acquire a three-dimensional medical image for formulating a radiotherapy plan for a target object, a surface image of the target object in a predetermined position during the radiotherapy execution phase, and a combination of radiographic images for positioning, wherein the combination of radiographic images comprises radiographic images acquired at a first viewing angle and a second viewing angle, respectively, and the first viewing angle is orthogonal to the second viewing angle;

[0012] A registration module, used for determining a surface contour image corresponding to the three-dimensional medical image, determining a registration matrix for registering the surface contour image to the surface image, and a floating registration result of the three-dimensional medical image under the action of the registration matrix;

[0013] A projection module, configured to determine, under a pixel set corresponding to the ray image combination, projection images of the floating registration result under the first viewing angle and the second viewing angle, respectively, to obtain a projection image combination;

[0014] The decision module is used to determine a similarity measure between the projection image combination and the radiation image combination, and output the registration matrix when the similarity measure meets a predetermined screening condition.

[0015] According to another aspect of the present invention, a computer device is provided, the computer device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the image registration method for radiotherapy described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the image registration method for radiotherapy described in any embodiment of the present invention when executed.

[0020] According to another aspect of the present invention, a computer program product is provided. The computer program product comprises a computer program. When the computer program is executed by a processor, the computer program implements the image registration method for radiotherapy described in any one of the embodiments.

[0021] The technical solution of the embodiment of the present invention is that since the radiation image combination can reflect the current body position information of the target object, after determining the registration matrix for registering the surface contour image to the surface image and the floating registration result of the three-dimensional medical image under the action of the registration matrix, under the pixel set corresponding to the radiation image combination, the projection images of the floating registration result under the first perspective and the second perspective are determined to obtain the projection image combination, and then the similarity measure between the projection image combination and the radiation image combination is calculated; the introduction of the voxel set helps to improve the similarity measure between the two image combinations, thereby increasing the probability that the similarity measure between the projection image combination and the radiation image combination meets the predetermined filtering conditions, and only when the similarity measure between the projection image combination and the radiation image combination meets the predetermined filtering conditions, the registration matrix is ​​output, which can ensure the accuracy of the registration result and the effect of the radiotherapy performed based on the registration result and the radiotherapy plan information corresponding to the three-dimensional medical image.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A flow chart of an image registration method for radiotherapy provided by an embodiment of the present invention;

[0025] Figure 2A A first ray image and a first projection image provided by an embodiment of the present invention;

[0026] Figure 2B A second ray image and a second projection image provided by an embodiment of the present invention;

[0027] Figure 2C A schematic diagram of a superposition result of a first ray image and a first projection image provided by an embodiment of the present invention;

[0028] Figure 2DA schematic diagram of a superposition result of a second ray image and a second projection image provided by an embodiment of the present invention;

[0029] Figure 2E A schematic diagram of an image registration result between a first ray image and a first projection image provided by an embodiment of the present invention;

[0030] Figure 2F A schematic diagram of an image registration result between a second ray image and a second projection image provided by an embodiment of the present invention;

[0031] Figure 3 is another flow chart of an image registration method for radiotherapy provided according to an embodiment of the present invention;

[0032] Figure 4 is a schematic structural diagram of an image registration device for radiotherapy provided according to an embodiment of the present invention;

[0033] Figure 5 It is a structural schematic diagram of a computer device for implementing the image registration method for radiotherapy according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] Figure 1The flowchart of the image registration method for radiotherapy provided by the embodiment of the present invention is applicable to the case where the similarity measure between the projection image combination and the radiation image combination is determined under the pixel set corresponding to the radiation image combination, and whether to output the registration matrix is ​​determined based on whether the similarity measure meets the predetermined screening condition. The method can be executed by the image registration device for radiotherapy, which can be implemented in the form of hardware and / or software, and can be configured in the processor of the computer device. Figure 1 As shown, the method includes:

[0037] S110, obtaining a three-dimensional medical image for formulating a radiotherapy plan for the target object, a surface image of the target object in a predetermined position during the radiotherapy execution phase, and a combination of radiographic images for positioning, wherein the combination of radiographic images includes radiographic images captured at a first viewing angle and a second viewing angle, respectively, and the first viewing angle is orthogonal to the second viewing angle.

[0038] The three-dimensional medical image used to formulate the radiotherapy plan can be obtained during the simulation positioning stage. After the three-dimensional medical image is obtained, it will be uploaded to the server. The doctor uses the radiotherapy planning system to query the three-dimensional medical image and outline the target area in the three-dimensional medical image based on the patient's condition. The physicist formulates a radiotherapy plan for the three-dimensional medical image and the target area corresponding to the three-dimensional medical image based on the target area outlined by the doctor in the three-dimensional medical image and the radiotherapy order issued by the doctor for the target object. After the radiotherapy plan is generated, it is submitted to the server.

[0039] During the radiotherapy execution phase, the technician guides the target object to complete the positioning according to the predetermined body position of the target object in the simulation positioning phase, and obtains the surface image of the target object under the current positioning result based on the body surface optical guidance system, and then controls the radiographic imaging device to obtain a combination of radiographic images of the target object under the current positioning result, and the combination of radiographic images includes a first radiographic image acquired at a first viewing angle based on the radiographic imaging device and a second radiographic image acquired at a second viewing angle, and the first viewing angle is orthogonal to the second viewing angle. In one embodiment, the first viewing angle is the AP viewing angle (front-to-back direction), and the second viewing angle is the LAT viewing angle (left-to-right direction). It can be understood that the combination of radiographic images is most consistent with the current positioning result and physical condition of the target object.

[0040] The predetermined body position is a body position that is compatible with the radiotherapy site of the target object. The predetermined body position in this embodiment can be the predetermined body position specified in the industry, and is not specifically limited here.

[0041] Positioning can be understood as reproducing the predetermined position so that the target object can complete the current radiotherapy in the same predetermined position used in the simulation positioning stage.

[0042] S120, determining a surface contour image corresponding to the three-dimensional medical image, determining a registration matrix for registering the surface contour image to the surface image, and a floating registration result of the three-dimensional medical image under the action of the registration matrix.

[0043] After the surface image and the radiographic image are combined and acquired, the processor automatically pulls the three-dimensional medical image corresponding to the target object identifier and the radiotherapy plan information corresponding to the three-dimensional medical image, or in response to the pull operation for the three-dimensional medical image and the radiotherapy plan information, pulls the three-dimensional medical image corresponding to the target object identifier and the radiotherapy plan information corresponding to the three-dimensional medical image; then determines the surface contour image corresponding to the three-dimensional medical image. The surface contour image only includes the body surface information of the target object in the three-dimensional medical image, and does not include the internal structure information, such as the internal organ tissue information.

[0044] In this embodiment, the surface contour image corresponding to the three-dimensional medical image can be determined by using existing methods, or by using the following method:

[0045] Step a1, determine the energy function for the three-dimensional medical image, the energy function includes a length constraint term, an area constraint term, a first intensity constraint term and a second intensity constraint term, the first intensity constraint term is used to determine the intensity constraint information corresponding to all pixels in the three-dimensional medical image whose pixel values ​​are greater than zero, and the second intensity constraint term is used to determine the intensity constraint information corresponding to all pixels in the three-dimensional medical image whose pixel values ​​are less than 1 and greater than zero.

[0046] The energy function is Where C is the surface contour curve of the target object in the 3D medical image, Length(C) is the length constraint, Area(C) is the area constraint, E1(C) and E2(C) are the intensity constraints, μ, λ1 and λ2 are constant coefficients. Each constraint can be specifically expressed as:

[0047]

[0048] in, is the constraint curve expression; C1 is the mean pixel value of all pixels inside the curve, and C2 is the mean pixel value of all pixels outside the curve.

[0049] Step a2: determining the partial differential equation of the energy function by solving the extreme value of the energy function.

[0050] Based on the variational method and gradient descent flow to solve the extreme value of the energy function, the partial differential equation of the energy function can be obtained Where t is the time step of the evolution curve.

[0051] Step a3: determining an evolution curve based on the partial differential equation, and using the evolution curve as a surface contour image corresponding to the three-dimensional medical image.

[0052] Solve the partial differential equation, and use the evolution curve determined by the iteration round corresponding to the iteration termination condition as the surface contour image corresponding to the three-dimensional medical image. The existing iteration termination condition can be used, and this embodiment does not make any specific limitation here.

[0053] After the surface contour image is determined, the surface contour image and the surface image are image-registered to obtain a registration matrix for registering the surface contour image to the surface image. It can be understood that the registration matrix used to register the surface contour image to the surface image is the conversion relationship between the coordinate system of the imaging device in the simulation positioning stage and the coordinate system of the radiotherapy setting. The registration matrix can also more accurately register the three-dimensional medical image to the surface image, and the floating registration result generated by the registration operation has a high accuracy. Since the amount of data of the surface contour image is much smaller than that of the three-dimensional medical image, compared with directly registering the three-dimensional medical image with the surface image to determine the registration matrix, registering the surface contour image with the surface image to determine the registration matrix can significantly reduce the amount of data calculation in the process of determining the registration matrix and improve the speed of determining the registration matrix.

[0054] In one embodiment, the surface contour image is used as a floating image, the surface image is used as a reference image, a similarity measure between the surface contour image and the surface image is calculated, and the similarity measure is used as a registration similarity measure; then, the least square method is used to solve the initial space transformation matrix according to the registration similarity measure to obtain a registration matrix. This embodiment can optionally use the sum of squared errors as the registration similarity measure.

[0055] The registration matrix can be expressed as M = [tx, ty, tz, rx, ry, rz], which can be decomposed into a translation transformation T and a rotation transformation R, where T = [tx, ty, tz], and the rotation transformation R can be decomposed into the product of the rotation transformations in the three orthogonal directions of x, y, and z R = R x ·R y ·R z .in,

[0056]

[0057] The registration matrix is ​​used to transform each voxel Pv in the three-dimensional medical image to determine the corresponding voxel P in the coordinate system of the radiotherapy device. C , specifically, P C =R·T·P VAfter determining the voxels corresponding to each voxel in the three-dimensional medical image in the coordinate system where the radiotherapy device is located, a floating registration image corresponding to the three-dimensional medical image in the space where the radiotherapy device is located can be obtained through interpolation, such as trilinear interpolation.

[0058] Determine the similarity measure (S) used to measure the similarity between the floating registration image and the reference image. When the transformation parameters of the similarity measure (S) on the six degrees of freedom (x, y, z translation and rotation) can be expressed as M = [x_trans, y_trans, z_trans, x_rot, y_rot, z_rot], perform Taylor expansion and obtain the following results:

[0059]

[0060] Denoted as:

[0061]

[0062] The optimal estimation of the above formula gives the iterative formula:

[0063] △t=(A T A) -1 A T b

[0064] When Δt is less than a preset threshold, the iteration is terminated, and M including the transformation parameters is the registration matrix.

[0065] In one embodiment, before / after / while the registration matrix is ​​determined, the three-dimensional medical image is smoothed using an existing image smoothing method to update the three-dimensional medical image, such as a Gaussian image smoothing method. The updated three-dimensional medical image is then processed using the registration matrix to obtain a floating registration result. This embodiment can improve the image quality of the three-dimensional medical image and the accuracy of the floating registration result by smoothing the three-dimensional medical image.

[0066] Specifically, the desired size is selected according to the size of the three-dimensional medical image. μ With standard deviation σ, calculate the one-dimensional Gaussian convolution kernel The three-dimensional medical image is convolved with the Gaussian convolution kernel in the x, y, and z axes in sequence to obtain an updated three-dimensional medical image.

[0067] S130 , determining the projection images of the floating registration result at the first viewing angle and the second viewing angle respectively under the pixel set corresponding to the radiation image combination, and obtaining a projection image combination.

[0068] All pixel points in the ray image combination are combined as a pixel set, the pixel with the largest x-coordinate value in the pixel set is determined, and the pixel is used as the first pixel; the pixel with the largest y-coordinate value in the pixel set is determined, and the pixel is used as the second pixel.

[0069] Specifically, the floating registration results are respectively determined as a first initial projection image at a first viewing angle and a second initial projection image at a second viewing angle, to obtain an initial projection image combination. Pixels whose x-coordinate values ​​are greater than the x-coordinate value of the first pixel are deleted from the initial projection image combination, and pixels whose y-coordinate values ​​are greater than the y-coordinate value of the second pixel are deleted to obtain a projection image combination. Alternatively, non-intersecting pixels in the initial projection image combination and the ray image combination are deleted from the initial projection image combination, and the intersection pixels of the two are retained to obtain a projection image combination.

[0070] Regarding the first initial projection image and the second initial projection image. In the coordinate system of the radiotherapy device, the spatial coordinates of the ray source are clarified, which is the focus of the perspective projection ray and the origin of all perspective projection rays. The above pixel set is taken as the end point of the perspective projection ray. Perform Siddon's projection on the three-dimensional medical image (or the smoothed three-dimensional medical image), determine the floating registration image voxels that each perspective projection ray passes through, and perform weighted averaging based on the intensity of each perspective projection ray and the length of the intersecting line segment. Specifically, according to Determine the first initial projection image, according to Determine the second initial projection image. Where, α k The AP perspective projection ray and I VolumeT The length of the k-th voxel intersection line segment, β k Projection ray for LAT view and I VolumeT The length of the line segment where the k-th voxel intersects.

[0071] In one embodiment, each of the radiation images in the radiation image combination is smoothed to obtain the updated radiation image combination; under the pixel set corresponding to the updated radiation image combination, the projection images of the floating registration result under the first viewing angle and the second viewing angle are determined to obtain a projection image combination. By smoothing each of the radiation images in the radiation image combination, the image quality of each radiation image in the radiation image combination, such as the smoothness of the radiation image, can be improved, thereby improving the accuracy of the pixel set corresponding to the radiation image combination.

[0072] Specifically, μ and standard deviation σ are selected according to the size of each ray image in the ray image combination, and the one-dimensional Gaussian convolution kernel is calculated. The first ray image and the second ray image are sequentially convolved with the Gaussian convolution kernel on the x, y, and z axes to obtain updated first ray images and second ray images.

[0073] S140, determining a similarity measure between the projection image combination and the radiation image combination, and outputting a registration matrix when the similarity measure meets a predetermined screening condition.

[0074] Similarity measure is a quantitative metric that describes or explains the degree of similarity between matching entities. Similarity measure is usually calculated through cost function.

[0075] The similarity measure in this embodiment is used to describe the overall similarity between the ray image combination and the projection image combination. The similarity measure is the average of the similarities of the corresponding images in the ray image combination and the projection image combination.

[0076] Specifically, a first similarity measure between the ray image and the projection image at a first viewing angle, and a second similarity measure between the ray image and the projection image at a second viewing angle are determined, and the average between the first similarity measure and the second similarity measure is used as the similarity measure between the ray image combination and the projection image combination.

[0077] Further, the ray image combination includes a first ray image corresponding to the first viewing angle and a second ray image corresponding to the second viewing angle, and the projection image combination includes a first projection image corresponding to the first viewing angle and a second projection image corresponding to the second viewing angle. After the ray image combination and the projection image combination are determined, the sum of square errors between corresponding pixels between the first projection image and the first ray image is determined, and the sum of square errors corresponding to the first projection image and the first ray image is used as a first similarity measure; the sum of square errors between corresponding pixels between the second projection image and the second ray image is determined, and the sum of square errors corresponding to the second projection image and the second ray image is used as a second similarity measure; the average of the first similarity measure and the second similarity measure is used as a similarity measure between the projection image combination and the ray image combination.

[0078] In summary, the first similarity measure is used to reflect the similarity between the first projection image and the first ray image, and the lower the first similarity measure is, the higher the similarity between the first projection image and the first ray image is; the second similarity measure is used to reflect the similarity between the second projection image and the second ray image, and the lower the second similarity measure is, the higher the similarity between the second projection image and the second ray image is. Similarly, the lower the similarity measure is, the higher the similarity between the projection image combination and the ray image combination is.

[0079] The predetermined screening condition is a condition that can make the cost function obtain an extreme value, such as a minimum value.

[0080] After the registration matrix is ​​determined, the processor determines the image registration result of the three-dimensional medical image (or the smoothed three-dimensional medical image) and the surface image based on the registration matrix; reads the radiotherapy plan information corresponding to the three-dimensional medical image, and generates control information for controlling the radiotherapy equipment to perform radiotherapy based on the image registration result and the radiotherapy plan information, so that the radiotherapy equipment performs radiotherapy on the target object according to the control information.

[0081] In this embodiment, if the similarity measure is the minimum value of the cost function, it is determined that the similarity measure meets the predetermined screening condition, and the surface contour image corresponding to the current projection image combination is the required target surface contour image, so the registration matrix is ​​output.

[0082] Figure 2A The green image on the left side is the first ray image under the AP perspective (first perspective) provided by the embodiment of the present invention. Figure 2A The red image on the right side is the first projection image under the AP viewing angle (first viewing angle) provided by the embodiment of the present invention; Figure 2B The green image on the left side is the second ray image under the LAP viewing angle (second viewing angle) provided by an embodiment of the present invention. Figure 2B The red image on the middle right is the second projection image under the LAP viewing angle (second viewing angle) provided by the embodiment of the present invention; Figure 2C A schematic diagram of a superposition result of a first ray image and a first projection image provided by an embodiment of the present invention, Figure 2D A schematic diagram of a superposition result of a second ray image and a second projection image provided by an embodiment of the present invention; Figure 2E A schematic diagram of an image registration result between a first ray image and a first projection image provided by an embodiment of the present invention; Figure 2F Schematic diagram of the image registration result of the second ray image and the second projection image provided by the embodiment of the present invention. Figure 2C and Figure 2D , Figure 2E and Figure 2F The image registration result in has a high accuracy. Therefore, the registration matrix determined by the embodiment of the present invention can accurately complete the registration of the combination of three-dimensional medical images and radiographic images, and obtain a high-accuracy image registration result, and the high-accuracy image registration result can ensure the effect of radiotherapy.

[0083] The technical solution provided by the embodiment of the present invention is that since the radiographic image combination can reflect the current body position information of the target object, after determining the registration matrix for registering the surface contour image to the surface image and the floating registration result of the three-dimensional medical image under the action of the registration matrix, under the pixel set corresponding to the radiographic image combination, the projection images of the floating registration result under the first and second viewing angles are determined to obtain the projection image combination, and then the similarity measure between the projection image combination and the radiographic image combination is calculated; the introduction of the voxel set helps to improve the similarity measure between the two image combinations, thereby increasing the probability that the similarity measure between the projection image combination and the radiographic image combination meets the predetermined filtering conditions, and only when the similarity measure between the projection image combination and the radiographic image combination meets the predetermined filtering conditions, the registration matrix is ​​output, which can ensure the accuracy of the registration result and the effect of the radiotherapy performed based on the registration result and the radiotherapy plan information corresponding to the three-dimensional medical image.

[0084] Figure 3 This is another flow chart of the image registration method for radiotherapy provided by an embodiment of the present invention. This embodiment is used to refine the projection image combination determination step. Figure 3 As shown, the method includes:

[0085] S210, obtaining a three-dimensional medical image for formulating a radiotherapy plan for the target object, a surface image of the target object in a predetermined position during the radiotherapy execution phase, and a combination of radiographic images for positioning, wherein the combination of radiographic images includes radiographic images captured at a first viewing angle and a second viewing angle, respectively, and the first viewing angle is orthogonal to the second viewing angle.

[0086] S220, determining a surface contour image corresponding to the three-dimensional medical image, determining a registration matrix for registering the surface contour image to the surface image, and a floating registration result of the three-dimensional medical image under the action of the registration matrix.

[0087] S230 , determining the projection images of the floating registration result at the first viewing angle and the second viewing angle respectively under the pixel set corresponding to the ray image combination, and obtaining a projection image combination.

[0088] S2401. Determine whether a similarity measure between a projection image combination and a radiation image combination meets a predetermined screening condition.

[0089] S2402: If yes, output the registration matrix.

[0090] S2403: If not, determine the contribution of each pixel in the pixel set to the similarity measure, and select pixels that meet the contribution condition from the pixel set to update the pixel set.

[0091] In one embodiment, the contribution of each pixel in the pixel set to the similarity measure is determined based on the image gradient information, as follows:

[0092] Step b1, determine the target residual vector of the projection image combination relative to the ray image combination, the target residual vector comprising a first residual vector between the projection image and the ray image corresponding to the first viewing angle, and a second residual vector between the projection image and the ray image corresponding to the second viewing angle.

[0093] The first residual vector of the projection image at the first viewing angle compared to the ray image at the first viewing angle can be expressed as: Among them, I DRR-AP (n) represents the gray value of the pixel marked as n in the projection image at the first viewing angle, I XG-AP (n) represents the gray value of the pixel marked as n in the radiation image at the first viewing angle.

[0094] The second residual vector of the projection image at the second viewing angle compared to the ray image at the second viewing angle can be expressed as: Among them, I DRR-LAT (n) represents the gray value of the pixel marked as n in the projection image at the second viewing angle, I XG-LAT (n) represents the gray value of the pixel marked as n in the radiographic image at the second viewing angle, b AP With b LAT Each contains n elements.

[0095] The target residual vector can be expressed as:

[0096] Step b2: determining a target matrix based on the target residual vector, wherein the target matrix includes the derivatives of each element of the target residual vector in the direction of each predetermined degree of freedom.

[0097] The target matrix includes the derivatives of each element in b on 6 degrees of freedom, which can be specifically expressed as Among them, b n represents the element marked as n in b. The six degrees of freedom include the translational degree of freedom on each coordinate axis and the rotational degree of freedom on each coordinate axis. Specifically, the six degrees of freedom include the translational degree of freedom tx on the x-axis, the translational degree of freedom ty on the y-axis, the translational degree of freedom tz on the z-axis, the rotational degree of freedom rx on the x-axis, the rotational degree of freedom ty on the y-axis, and the rotational degree of freedom rz on the z-axis.

[0098] Step b3: taking the concatenation result of the target matrix and the target residual vector as a concatenation matrix, and determining the result of the self-multiplication of the concatenation matrix.

[0099] The concatenation matrix can be expressed as Alpha = [A b]. The concatenation result of the concatenation matrix is ​​the product of the transpose of the concatenation matrix and the concatenation matrix, which can be specifically expressed as: Z = Alpha T ·Alpha.

[0100] Step b4, determining a target vector including the inner product of each row vector of the splicing matrix, and taking the difference between the target vector and the self-multiplication result as a contribution vector, which includes the contribution of each pixel in the pixel set to the similarity measure.

[0101] After the contribution vector is determined, all elements in the contribution vector are sorted. Taking descending sorting as an example, the first N% of the elements in the sorting result are combined as the updated pixel set. Among them, N% is the contribution percentage threshold, and N can be selected as 80, 85, 90, etc. This achieves the maximum retention of image information while reducing the amount of similarity measurement calculations, and improving the speed of determining the similarity measurement and the speed of determining the registration matrix.

[0102] Since both the target residual vector and the target matrix correspond to the projection image combination, and the projection image combination is associated with the pixel set, after the pixel set is updated, the target residual vector and the target matrix are updated synchronously. Specifically, the elements corresponding to the pixels that do not belong to the updated pixel set in the target residual vector are deleted, and only the elements corresponding to the pixels in the updated pixel set are retained; similarly, the elements corresponding to the pixels that do not belong to the updated pixel set in the target matrix are deleted, and only the elements corresponding to the pixels in the updated pixel set are retained.

[0103] S2404. Under the updated pixel set, the derivatives of the projection image combination at each degree of freedom and the target residual vector of the projection image combination compared to the ray image combination are input into the step size update expression to obtain the update step size of the registration matrix. The step size update expression is determined by solving the optimization problem by the least squares method. The optimization problem is the target residual vector minimization problem. The target residual vector is the residual vector of the projection image combination relative to the ray image combination.

[0104] Among them, the step size update expression can be expressed as, ΔM=(A T A) -1 A T b, the calculation result can be expressed as: ΔM = [Δtx, Δty, Δtz, Δrx, Δry, Δrz].

[0105] The step size update expression is determined by solving the optimization problem using the least squares method. The optimization problem can be expressed as:

[0106] argmin||At-b|| 2 2

[0107] This embodiment uses the chain rule and vector orthogonality to use the same gradient matrix in each iteration process, and does not need to recalculate the gradient information of the image after each iteration, thereby reducing the amount of algorithm calculation and improving the algorithm's running speed.

[0108] S2405 , updating the registration matrix based on the registration matrix and the update step size of the registration matrix, and performing image transformation on the three-dimensional medical image based on the updated registration matrix to obtain an updated floating registration result.

[0109] Since the floating registration result is determined based on the registration matrix, after the update step size of the registration matrix is ​​determined, the sum of the current registration matrix and the update step size is used as the updated registration matrix, and then based on the updated registration matrix, the three-dimensional medical image or the smoothed three-dimensional medical image is transformed to obtain the updated floating registration result.

[0110] S2406, returning to determine the projection images of the floating registration result at the first viewing angle and the second viewing angle respectively, and obtaining the step of combining the projection images, until the current similarity measure meets the predetermined screening condition or the number of iterations reaches the predetermined number of conditions, and outputting the current registration matrix.

[0111] After the updated floating registration result is determined, the process returns to S230 until the similarity measure corresponding to the current registration matrix meets the predetermined screening condition, or the number of iterations reaches the set number condition, the iteration is determined to be finished, and the current registration matrix is ​​output.

[0112] The technical solution provided by the embodiment of the present invention updates the pixel set in any iteration round by selecting pixels that meet the pose transformation contribution conditions from the current pixel set, and updates the projection image combination by updating the pixel set, thereby updating the similarity measure, thereby improving the accuracy of the similarity measure update and the accuracy of selecting the alignment matrix based on the similarity measure.

[0113] Figure 4 Schematic diagram of the structure of the image registration device for radiotherapy provided by an embodiment of the present invention. Figure 4 As shown, the device comprises:

[0114] An acquisition module 31 is used to acquire a three-dimensional medical image used to formulate a radiotherapy plan for a target object, a surface image of the target object in a predetermined position during the radiotherapy execution phase, and a combination of radiographic images used for positioning, wherein the combination of radiographic images includes radiographic images collected at a first viewing angle and a second viewing angle, respectively, and the first viewing angle is orthogonal to the second viewing angle;

[0115] A registration module 32, used for determining a surface contour image corresponding to the three-dimensional medical image, determining a registration matrix for registering the surface contour image to the surface image, and a floating registration result of the three-dimensional medical image under the action of the registration matrix;

[0116] A projection module 33, configured to determine, under a pixel set corresponding to the ray image combination, projection images of the floating registration result under the first viewing angle and the second viewing angle, respectively, to obtain a projection image combination;

[0117] The decision module 34 is used to determine a similarity measure between the projection image combination and the radiation image combination, and output the registration matrix when the similarity measure meets a predetermined screening condition.

[0118] In one embodiment, the registration module 32 completes the floating registration result of the surface contour image under the action of the registration matrix through a registration unit, and the registration unit is used to:

[0119] Smoothing the three-dimensional medical image to obtain an updated three-dimensional medical image;

[0120] Using the registration matrix to perform spatial transformation on the updated three-dimensional medical image to obtain a floating registration result;

[0121] The step of determining, under a pixel set corresponding to the ray image combination, projection images of the floating registration result under the first viewing angle and the second viewing angle respectively, to obtain a projection image combination, comprises:

[0122] Smoothing each of the ray images in the ray image combination to obtain an updated ray image combination;

[0123] Under the pixel set corresponding to the updated ray image combination, the projection images of the floating registration result under the first viewing angle and the second viewing angle are determined to obtain a projection image combination.

[0124] In one embodiment, the registration module is used to:

[0125] Taking the surface contour image as the floating image and the surface image as the reference image, calculating the similarity measure between the surface contour image and the surface image, and using the similarity measure as the registration similarity measure;

[0126] The initial space transformation matrix is ​​solved by using the least square method according to the registration similarity measure to obtain a registration matrix for registering the surface contour image to the surface image.

[0127] In one embodiment, the decision module 34 is further configured to:

[0128] A pixel selection unit, configured to determine the contribution of each pixel in the pixel set to the similarity measure if the similarity measure does not meet a predetermined screening condition, and select pixels meeting the contribution condition from the pixel set to update the pixel set;

[0129] A step length updating unit, for inputting the derivatives of the projection image combination at each degree of freedom and the residual vector of the projection image combination compared with the ray image combination into a step length updating expression under the updated pixel set, so as to obtain an updating step length of the registration matrix, wherein the step length updating expression is determined by solving an optimization problem by the least square method, wherein the optimization problem is a target residual vector minimization problem, and the target residual vector is a residual vector of the projection image combination relative to the ray image combination;

[0130] A registration matrix updating unit, configured to update the registration matrix based on the registration matrix and an update step size of the registration matrix, and perform image transformation on the three-dimensional medical image based on the updated registration matrix to obtain the updated floating registration result;

[0131] A obtaining unit is used to return the projection images of the floating registration result under the first viewing angle and the second viewing angle respectively, and obtain the projected image combination step until the current similarity measure meets the predetermined screening condition or the number of iterations reaches the predetermined number of conditions, and output the current registration matrix

[0132] In one embodiment, the pixel selection unit determines the contribution of each pixel in the pixel set to the similarity measure through a contribution subunit, and the contribution subunit is specifically used to:

[0133] Determine a target residual vector of the projection image combination relative to the radiation image combination, the target residual vector comprising a first residual vector between the projection image and the radiation image corresponding to the first viewing angle, and a second residual vector between the projection image and the radiation image corresponding to the second viewing angle;

[0134] Determine a target matrix according to the target residual vector, wherein the target matrix includes the derivatives of each element of the target residual vector in each predetermined degree of freedom direction;

[0135] Using the concatenation result of the target matrix and the target residual vector as a concatenation matrix, and determining a self-multiplication result of the concatenation matrix;

[0136] A target vector including the inner product of each row vector of the splicing matrix is ​​determined, and a difference between the target vector and the self-product result is used as a contribution vector, wherein the contribution vector includes the contribution of each pixel in the pixel set to the similarity measure.

[0137] In one embodiment, the ray image combination includes a first ray image corresponding to the first viewing angle and a second ray image corresponding to the second viewing angle, the projection image combination includes a first projection image corresponding to the first viewing angle and a second projection image corresponding to the second viewing angle, and the similarity measurement module is used to:

[0138] Determine the sum of squared errors between corresponding pixels of the first projection image and the first ray image, and use the sum of squared errors corresponding to the first projection image and the first ray image as a first similarity measure;

[0139] determining the sum of squared errors between corresponding pixels of the second projection image and the second ray image, and taking the sum of squared errors corresponding to the second projection image and the second ray image as a second similarity measure;

[0140] An average of the first similarity measure and the second similarity measure is used as a similarity measure between the projection image combination and the radiation image combination.

[0141] In one embodiment, the registration matrix module determines a surface contour image corresponding to the three-dimensional medical image through a surface contour unit, and the surface contour unit is specifically used to:

[0142] Determine an energy function for the three-dimensional medical image, the energy function comprising a length constraint term, an area constraint term, a first intensity constraint term, and a second intensity constraint term, the first intensity constraint term being used to determine intensity constraint information corresponding to all pixels in the three-dimensional medical image whose pixel values ​​are greater than zero, and the second intensity constraint term being used to determine intensity constraint information corresponding to all pixels in the three-dimensional medical image whose pixel values ​​are less than 1 and greater than zero;

[0143] Determining a partial differential equation of the energy function by solving an extreme value of the energy function;

[0144] An evolution curve is determined based on the partial differential equation, and the evolution curve is used as a surface contour image corresponding to the three-dimensional medical image.

[0145] The technical solution provided by the embodiment of the present invention is that since the radiographic image combination can reflect the current body position information of the target object, after determining the registration matrix for registering the surface contour image to the surface image and the floating registration result of the three-dimensional medical image under the action of the registration matrix, under the pixel set corresponding to the radiographic image combination, the projection images of the floating registration result under the first and second viewing angles are determined to obtain the projection image combination, and then the similarity measure between the projection image combination and the radiographic image combination is calculated; the introduction of the voxel set helps to improve the similarity measure between the two image combinations, thereby increasing the probability that the similarity measure between the projection image combination and the radiographic image combination meets the predetermined filtering conditions, and only when the similarity measure between the projection image combination and the radiographic image combination meets the predetermined filtering conditions, the registration matrix is ​​output, which can ensure the accuracy of the registration result and the effect of the radiotherapy performed based on the registration result and the radiotherapy plan information corresponding to the three-dimensional medical image.

[0146] The image registration device for radiotherapy provided by the embodiment of the present invention can execute the image registration method for radiotherapy provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0147] Figure 5 A schematic diagram of a computer device 10 that can be used to implement an embodiment of the present invention is shown. Computer device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0148] like Figure 5 As shown, the computer device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the computer device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0149] A number of components in the computer device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the computer device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0150] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 performs the various methods and processes described above, such as an image registration method for radiotherapy.

[0151] In some embodiments, the image registration method for radiotherapy may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the computer device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the image registration method for radiotherapy described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the image registration method for radiotherapy in any other suitable manner (e.g., by means of firmware).

[0152] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0153] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0154] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0155] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0156] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0157] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0158] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the image registration device for radiotherapy provided in any embodiment of the present application.

[0159] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0160] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0161] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An image registration method for radiotherapy, characterized in that: include: Acquire a three-dimensional medical image for formulating a radiotherapy plan for a target object, a surface image of the target object in a predetermined position during the radiotherapy execution phase, and a combination of radiographic images for positioning, wherein the combination of radiographic images includes radiographic images acquired at a first viewing angle and a second viewing angle, respectively, and the first viewing angle is orthogonal to the second viewing angle; Determine a surface contour image corresponding to the three-dimensional medical image, determine a registration matrix for registering the surface contour image to the surface image, and a floating registration result of the three-dimensional medical image under the action of the registration matrix; Under the pixel set corresponding to the radiation image combination, determining the projection images of the floating registration result under the first viewing angle and the second viewing angle respectively, to obtain a projection image combination; A similarity measure between the projection image combination and the radiation image combination is determined, and the registration matrix is ​​output if the similarity measure meets a predetermined screening condition.

2. The method according to claim 1, characterized in that The floating registration result of the three-dimensional medical image under the action of the registration matrix is ​​determined by the following steps: Smoothing the three-dimensional medical image to obtain an updated three-dimensional medical image; Using the registration matrix to perform spatial transformation on the updated three-dimensional medical image to obtain a floating registration result; The step of determining, under a pixel set corresponding to the ray image combination, projection images of the floating registration result under the first viewing angle and the second viewing angle respectively, to obtain a projection image combination, comprises: Smoothing each of the ray images in the ray image combination to obtain an updated ray image combination; Under the pixel set corresponding to the updated ray image combination, the projection images of the floating registration result under the first viewing angle and the second viewing angle are determined to obtain a projection image combination.

3. The method according to claim 1 or 2, characterized in that: The determining of a registration matrix for registering the surface contour image to the surface image comprises: Taking the surface contour image as the floating image and the surface image as the reference image, calculating the similarity measure between the surface contour image and the surface image, and using the similarity measure as the registration similarity measure; The initial space transformation matrix is ​​solved by using the least square method according to the registration similarity measure to obtain a registration matrix for registering the surface contour image to the surface image.

4. The method according to claim 1, characterized in that: After determining the similarity measure between the ray image combination and the projection image combination, the method further includes: If the similarity measure does not meet the predetermined screening condition, determining the contribution of each pixel in the pixel set to the similarity measure, and selecting pixels meeting the contribution condition from the pixel set to update the pixel set; Under the updated pixel set, the derivatives of the projection image combination at each degree of freedom and the residual vector of the projection image combination compared with the ray image combination are input into a step size update expression to obtain an update step size of the registration matrix, wherein the step size update expression is determined by solving an optimization problem, wherein the optimization problem is a target residual vector minimization problem, and the target residual vector is a residual vector of the projection image combination relative to the ray image combination; updating the registration matrix based on the registration matrix and the update step size of the registration matrix, and performing image transformation on the three-dimensional medical image based on the updated registration matrix to obtain the updated floating registration result; Returning to the step of determining the projection images of the floating registration result under the first viewing angle and the second viewing angle respectively, and obtaining a projection image combination, until the current similarity measure meets a predetermined screening condition or the number of iterations reaches a predetermined number of conditions, the current registration matrix is ​​output.

5. The method according to claim 4, characterized in that The determining the contribution of each pixel in the pixel set to the similarity measure includes: Determine a target residual vector of the projection image combination relative to the radiation image combination, the target residual vector comprising a first residual vector between the projection image and the radiation image corresponding to the first viewing angle, and a second residual vector between the projection image and the radiation image corresponding to the second viewing angle; Determine a target matrix according to the target residual vector, wherein the target matrix includes the derivatives of each element of the target residual vector in each predetermined degree of freedom direction; Using the concatenation result of the target matrix and the target residual vector as a concatenation matrix, and determining a self-multiplication result of the concatenation matrix; A target vector including the inner product of each row vector of the splicing matrix is ​​determined, and a difference between the target vector and the self-product result is used as a contribution vector, wherein the contribution vector includes the contribution of each pixel in the pixel set to the similarity measure.

6. The method according to claim 1, characterized in that The ray image combination includes a first ray image corresponding to the first viewing angle and a second ray image corresponding to the second viewing angle, the projection image combination includes a first projection image corresponding to the first viewing angle and a second projection image corresponding to the second viewing angle, and determining a similarity measure between the projection image combination and the ray image combination under the pixel set includes: Determine the sum of squared errors between corresponding pixels of the first projection image and the first ray image, and use the sum of squared errors corresponding to the first projection image and the first ray image as a first similarity measure; determining the sum of squared errors between corresponding pixels of the second projection image and the second ray image, and taking the sum of squared errors corresponding to the second projection image and the second ray image as a second similarity measure; An average of the first similarity measure and the second similarity measure is used as a similarity measure between the projection image combination and the radiation image combination.

7. An image registration device for radiotherapy, characterized in that: include: an acquisition module, configured to acquire a three-dimensional medical image for formulating a radiotherapy plan for a target object, a surface image of the target object in a predetermined position during the radiotherapy execution phase, and a combination of radiographic images for positioning, wherein the combination of radiographic images comprises radiographic images acquired at a first viewing angle and a second viewing angle, respectively, and the first viewing angle is orthogonal to the second viewing angle; A registration matrix module, used to determine a surface contour image corresponding to the three-dimensional medical image, determine a registration matrix for registering the surface contour image to the surface image, and a floating registration result of the three-dimensional medical image under the action of the registration matrix; A projection module, configured to determine, under a pixel set corresponding to the ray image combination, projection images of the floating registration result under the first viewing angle and the second viewing angle, respectively, to obtain a projection image combination; The decision module is used to determine a similarity measure between the projection image combination and the radiation image combination, and output the registration matrix when the similarity measure meets a predetermined screening condition.

8. A computer device, characterized in that: The computer device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the image registration method for radiotherapy described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the image registration method for radiotherapy described in any one of claims 1-6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the image registration method for radiotherapy according to any one of claims 1-6.

Images