Radioisotope application planning method and device

Abstract

The invention belongs to the technical field of image processing, and provides a radioactive isotope application planning method and device, and the method comprises the steps: obtaining a three-dimensional image of a human body, and obtaining an affected area in the three-dimensional image; the at least one two-dimensional shape is moved to the three-dimensional image, and the affected area is covered according to the three-dimensional image, so that the two-dimensional shape forms a three-dimensional shape; an affected area contour coordinate in a three-dimensional shape is calculated, then the affected area contour coordinate is unfolded to a coordinate in a two-dimensional space, and the coordinate in the two-dimensional space is expressed as a preparation parameter of the applicator. The method has the advantages that the shape of the applicator can be recognized and the contour of the applicator can be generated in a three-dimensional space, and the precision of the contour of the applicator is improved, so that the applicator prepared according to planning is very fit to the body of a patient.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a radioisotope application planning method and device. Background Art

[0002] Keloids are abnormal growths of scar tissue that usually form after a skin injury. Although not life-threatening, keloids can be unsightly and some patients may experience unbearable itching, pain or tenderness.

[0003] Radioisotope application is one of the treatments for keloids, but the production process of isotope applicators is relatively cumbersome, including rubbing and cutting, area calculation, drug drying, plastic sealing, application and other steps. A complete preparation process requires the cooperation of multiple doctors and cross-person information transmission is prone to errors. At the same time, during the drug drying and plastic sealing stages, doctors are directly exposed to isotopes and have a high risk of radiation exposure. As a result, automated applicator manufacturing equipment came into being. Due to inaccurate estimation of the filter paper area, the amount of radionuclide solution added is inaccurate, resulting in poor treatment effect. In the process of using automated equipment, it can prepare an applicator corresponding to the scar area and contour to avoid the above situation. The most critical part of the automated preparation process is the extraction of scar contours. Scars usually have a three-dimensional shape on the skin surface, while the prepared applicator needs to be close to the skin surface and can only be a two-dimensional shape. In order to achieve the precise fit of the two-dimensional applicator to the scar area, it must be converted from a two-dimensional shape to a three-dimensional shape and then close to the scar area to obtain an accurate scar contour and area. Summary of the invention

[0004] The purpose of the present invention is to provide an isotope patch therapy planning system or other similar surface coverage simulation system, which can solve the above problems by using cheap computing resources to efficiently and accurately realize the coverage simulation of two-dimensional shapes on the surface of three-dimensional models.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is: A radioisotope application planning method comprises the following steps: Acquire a three-dimensional image of a human body, and thereby obtain an affected area in the three-dimensional image; moving at least one two-dimensional shape onto the three-dimensional image and covering the affected area according to the three-dimensional image so that the two-dimensional shape forms a three-dimensional shape; The coordinates of the contour of the affected area within the three-dimensional shape are calculated, and then the coordinates of the contour of the affected area are expanded to coordinates in a two-dimensional space, and the coordinates in the two-dimensional space are represented as preparation parameters of the applicator.

[0006] Further, the step of forming the two-dimensional shape into a three-dimensional shape comprises: A first transformed shape is obtained based on the homography transformation matrix H according to the two-dimensional shape, and the first transformed shape is represented as an optimal posture of the two-dimensional shape placed in the target area without bending deformation; The first transformed shape is transformed into a three-dimensional shape based on a deformation parameter P, where the deformation parameter P is obtained by solving the deformation between the best posture of a preset two-dimensional shape placed in a target area without bending deformation and the preset three-dimensional shape.

[0007] Furthermore, the deformation parameter P is obtained based on the thin plate spline interpolation method.

[0008] Furthermore, the steps of constructing the homography transformation matrix H are: Determine a plurality of first sampling points and a plurality of second sampling points on the three-dimensional image based on the Dijkstra algorithm according to the two-dimensional shape, wherein the first sampling points and the second sampling points are combined to form a first point set; constructing a second point set in the two-dimensional shape with the same number of sample points as the first point set; The transformation parameters are solved between the first point set and the second point set to obtain the optimal homography transformation parameters as the homography transformation matrix H.

[0009] Furthermore, the step of determining a plurality of first sampling points includes: Calculate the minimum circumscribed circle of a two-dimensional shape to obtain the center point and radius of the minimum circumscribed circle; In multiple directions outward from the current center point, determine the contour lines with the distance from the center point as the radius; The perimeter of the contour line is calculated, and according to the perimeter, a plurality of first sampling points are obtained by sampling at equal intervals on the circumference formed by the contour line.

[0010] Furthermore, sampling is performed at equal intervals on the path from the center point to each first sampling point to obtain a plurality of second sampling points.

[0011] Furthermore, obtaining a three-dimensional image of a human body includes: using a 3D scanner to scan human skin to obtain a three-dimensional image of the human body.

[0012] Furthermore, after the corresponding coordinates are obtained by unfolding the contour of the affected area in two-dimensional space, the method includes: inputting the coordinates of the contour of the affected area in two-dimensional space into an applicator production device to produce an applicator having the same contour as the affected area.

[0013] Furthermore, the coordinates of the contour of the affected area are expanded to coordinates in a two-dimensional space, including: obtaining the coordinates by reverse transformation according to a method of forming a three-dimensional shape from a two-dimensional shape.

[0014] On the other hand, the present invention also provides a radioactive isotope application planning device, which includes a memory and at least one processor. The memory stores a computer program, and the processor is used to execute the computer program to implement the above-mentioned radioactive isotope application planning method.

[0015] Compared with the prior art, the present invention has at least the following beneficial effects: (1) It can realize the recognition of the shape of the patch and the generation of its contour in three-dimensional space, which improves the accuracy of the applicator contour and achieves better recognition effect; (2) Realize the coverage simulation of the two-dimensional shape on the surface of the three-dimensional model, and ensure that the simulation area is adaptively changed along with the three-dimensional image of the skin when moving so as to closely follow the skin surface; (3) In the process of expanding the contour coordinates of the affected area to coordinates in two-dimensional space, the constructed homography transformation matrix H and deformation parameter P ensure that the shape of the patch remains accurate when it is inverted from three-dimensional space to a two-dimensional plane, thereby ensuring that the applicator prepared according to the plan fits the patient very well. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 is a flowchart of a planning method provided by an embodiment of the present invention; Figure 2 is a schematic diagram of an application shape obtained through preliminary experiments provided by an embodiment of the present invention; Figure 3 is a schematic diagram of contour lines and sampling points determined by the patch shape provided in an embodiment of the present invention; Figure 4 is a schematic diagram of sampling points of the patch shape provided by an embodiment of the present invention in a two-dimensional space; Figure 5 Schematic diagram of sampling points corresponding to the deformation parameter P provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] It should be noted that in the present invention, descriptions such as "first", "second", "one", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0019] In addition, the technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0020] The following are specific embodiments of the present invention, and the technical solutions of the present invention are further described in conjunction with the accompanying drawings, but the present invention is not limited to these embodiments.

[0021] like Figure 1 As shown, this embodiment provides a radioisotope application planning method, which includes the following steps: S1, obtaining a three-dimensional image of a human body, and obtaining an affected area in the three-dimensional image; S2, moving at least one two-dimensional shape onto the three-dimensional image, and covering the affected area according to the three-dimensional image, so that the two-dimensional shape forms a three-dimensional shape; S3. Calculate the coordinates of the contour of the affected area within the three-dimensional shape, and then expand the coordinates of the contour of the affected area to coordinates in two-dimensional space, and the coordinates in two-dimensional space are represented as preparation parameters of the applicator.

[0022] Among them, in step S1, a three-dimensional image of the human body surface, that is, a three-dimensional image of the skin surface, can be collected by a 3D scanner or a 3D sensor, and then the three-dimensional image is imported into a three-dimensional model to obtain three-dimensional model data.

[0023] Then, the patient's scar tissue area, i.e., the affected area, is selected in the three-dimensional model data; in this step, the affected area can be automatically identified by AI and fine-tuned and confirmed by the doctor, or the doctor can directly manually select the corresponding affected area to form the outline of the affected area.

[0024] Specifically, after the affected area is determined, Figure 2As shown, the two-dimensional shape is covered on the surface of the three-dimensional model with a similar flexible material, so as to simulate the state of the applicator being attached to the affected area after preparation. At this time, the two-dimensional shape does not have the same shape as the scar tissue selected by the frame, but it is only necessary to ensure that the two-dimensional shape can completely cover the contour of the affected area. Therefore, after the two-dimensional shape is covered on the three-dimensional model, the two-dimensional shape will form coordinates in the three-dimensional space, so that the coordinate data of the contour of the affected area in the shape in the three-dimensional space can be calculated in the two-dimensional shape.

[0025] Then how to transform the two-dimensional shape into coordinates in three-dimensional space so that the obtained coordinates in three-dimensional space perfectly match the three-dimensional model data of the human skin surface is the first problem to be solved in this embodiment.

[0026] Therefore, the present embodiment proposes that the steps of forming a two-dimensional shape into a three-dimensional shape include: T1, obtaining a first transformed shape based on the homography transformation matrix H according to the two-dimensional shape, wherein the first transformed shape is represented as an optimal posture of the two-dimensional shape placed in the target area without bending deformation; T2. The first transformed shape is transformed into a three-dimensional shape based on a deformation parameter P, where the deformation parameter P is obtained by solving the deformation between the optimal posture of a preset two-dimensional shape placed in a target area without bending deformation and the preset three-dimensional shape.

[0027] Specifically, homography transformation is also called projection transformation, which can be used to describe rotation, translation, and scaling, but cannot describe complex situations such as geometric deformation. The purpose of using this transformation here is to first transform it to the vicinity of the target position, which can improve the accuracy of the next step for local distortion transformation.

[0028] After the homography transformation matrix H, the deformation parameter P is used to adjust the local deformation distortion of the shape to obtain an accurate three-dimensional shape.

[0029] Among them, the steps of constructing the homography transformation matrix H are: T11. Determine a plurality of first sampling points and a plurality of second sampling points on the three-dimensional image based on the Dijkstra algorithm according to the two-dimensional shape, and combine the first sampling points and the second sampling points to form a first point set; T12, constructing a second point set in the two-dimensional shape with the same number of sampling points as the first point set; T13. Solve the transformation parameters between the first point set and the second point set to obtain the optimal homography transformation parameters as the homography transformation matrix H.

[0030] In determining a plurality of first sampling points, the steps include: T111. Calculate the minimum circumscribed circle of a two-dimensional shape to obtain the center point and radius of the minimum circumscribed circle; T112. Determine the contour lines with the distance from the center point as the radius in multiple directions outward from the current center point; T113. Calculate the perimeter of the contour line, and obtain a plurality of first sampling points by sampling at equal intervals on the circumference formed by the contour line according to the perimeter.

[0031] In determining the second sampling points, sampling is performed at equal intervals on the path from the center point to each first sampling point, thereby obtaining a plurality of second sampling points.

[0032] The Dijkstra algorithm is used to search, and eight directions around the current node are selected as the directions to search outward to find the contour lines with a radius R from the center point. Since the contour lines are generated on a three-dimensional image, the contour lines are projected to obtain the following: Figure 3 The white point set is shown. In special cases, the points on the contour line are affected by the search step size in the above algorithm and are not strictly equal to the radius R. Therefore, linear interpolation is performed on the points in the boundary set to make them fall exactly on the circumference. And by calculating the interpolation ratio of the neighboring nodes, the coordinates of the boundary points in three-dimensional space are updated to make them conform to the shape of the circle.

[0033] Then calculate the perimeter of the contour line (circumference length) and sample K points at equal intervals on the circumference. Figure 3 Take K=8, the outermost 8 green points are the sampling points, that is, the first sampling points obtained.

[0034] During the search process, the shortest path from the K sampled points to the center point has been obtained, such as Figure 3 As shown in the blue point set, the shortest path is along the skin surface. Because the search is from the inside to the outside, we can know how each point on the path moves from the center point to the K sampling points step by step, and then sample N points at equal intervals on the path, for example Figure 3 Take N=5, sample 5 green points on each blue line, and the sampling points on the path form the second sampling points mentioned above. In the above process, a total of K*N points are sampled, which are combined to form the point set V1, that is, the first point set mentioned above, as shown in Figure 3 As shown by the green dots in the middle, the point set V1 is the 3D model data that fits the human skin surface in an ideal state.

[0035] like Figure 4 As shown, in the two-dimensional space of the applicator, sampling points are selected in the same manner as described above, for example: 8 red dotted lines are extended outward from the center point, and 5 red points are sampled equidistantly on each dotted line, thereby forming a point set V2.

[0036] Therefore, after obtaining the point sets V1 and V2, the homography transformation matrix from V2 to V1 can be solved. Since the solution of the homography transformation matrix is ​​not unique, the best homography transformation matrix H is obtained from multiple solutions to simulate the fitting state of the applicator placed on the skin surface without deformation. Solving the homography transformation matrix is ​​actually an optimization problem. In this embodiment, the optimization goal is to minimize the distance between the points in the point set V2 and their corresponding points in the point set V1 after applying the homography transformation, so as to obtain the best homography transformation matrix H.

[0037] like Figure 5 As shown, the red point set V3 is the position of the point set V2 after the optimal homography transformation H, that is, multiple sampling points on the patch shape, which are represented by the sampling points as the optimal posture of the patch shape placed in the target area without any deformation.

[0038] Since the homography transformation cannot describe the distortion, the point set V3 obtained is only near the point set V1, and the local distortion needs to be further described by the deformation parameter P. Therefore, the deformation parameter P between the point set V1 and the point set V3 can be solved. Of course, the deformation parameter P can also be obtained by solving the transformation parameters between the point set V1 and the point set formed by the three-dimensional shape in the ideal state.

[0039] Preferably, thin plate spline interpolation or other interpolation methods may be used to represent the optimal deformation between the point set V3 and the point set V1, so as to obtain the deformation parameter P by solving.

[0040] After the homography transformation, the sampling points are only placed near the actual 3D sampling points (the transformed shape is still flat), and the deformation parameter P is used to truly place the sampling points on the actual 3D surface. At this point, the 2D shape truly has a curvature that fits the human body surface.

[0041] Therefore, after determining the homography transformation matrix H and the deformation parameter P, the two-dimensional shape can be represented by three-dimensional coordinates to represent the area covered on the three-dimensional model data of the human body, and the contour coordinate data of the affected area within the shape can be calculated.

[0042] After obtaining the contour coordinate data within the shape, since the contour of the affected area is represented in the three-dimensional model, the obtained contour coordinates will obviously be represented in the form of three-dimensional coordinates. As for the applicator (which can be represented as a piece of paper), it can only be prepared with two-dimensional coordinate data. Therefore, how to convert the contour of the affected area into the two-dimensional coordinate data required for preparing the applicator is also a problem to be solved in this embodiment.

[0043] Expanding the coordinates of the contour of the affected area to the coordinates in the two-dimensional space includes: obtaining the coordinates by reverse transformation based on the method of forming a three-dimensional shape from a two-dimensional shape. Specifically, the point set C represented by the contour information of the affected area actually photographed is reversed, and the positions of the control points are exchanged in the deformation parameter P, and the homography transformation is to find the inverse of the homography transformation matrix H, and then the obtained C'' is transformed to the coordinate system of the applicator in the two-dimensional space:

[0044] .

[0045] In one embodiment, a three-dimensional image of a human body can be obtained by a 3D scanner, and then the same method as steps S1-S3 above can be used to obtain a picture with a scar outline and at least one patch coverage effect. The scar outline area and the patch coverage area are then intersected in turn to obtain the outline of the scar area that can be covered by each applicator. These outlines are input into a laser cutting machine in units of one applicator, and the patch material is cut to obtain an applicator for treating scars, so that the shape and size of the applicator are more closely matched to the scar outline.

[0046] The embodiment of the present application also provides a radioisotope application planning device, for example, the device can be, but is not limited to, a desktop computer, a notebook, etc., and its existence form is not limited, mainly depending on whether it needs to support the interface display function of a browser web page, etc. Exemplarily, the device includes a memory and at least one processor, the memory stores a computer program, and the processor is used to execute the computer program to implement the above-mentioned radioisotope application planning method.

[0047] Among them, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or at least one of other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application.

[0048] The memory may be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc. The memory is used to store a computer program, and the processor may execute the computer program accordingly after receiving an execution instruction.

[0049] Furthermore, the memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data (such as iteration data, version data, etc.) created according to the use of the computer device, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0050] The specific embodiments described herein are merely examples of the spirit of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in similar ways, but they will not deviate from the spirit of the present invention or exceed the scope defined by the appended claims.

Claims

1. A radioisotope application planning method, characterized in that: Includes steps: Acquire a three-dimensional image of a human body, and thereby obtain an affected area in the three-dimensional image; Moving at least one two-dimensional shape onto the three-dimensional image and covering the affected area according to the three-dimensional image, so that the two-dimensional shape forms a three-dimensional shape based on a preset homography transformation matrix H and a preset deformation parameter P; The preset homography transformation matrix H is constructed by solving the transformation parameters between the points determined on the three-dimensional image and the corresponding points determined on the two-dimensional shape based on the Dijkstra algorithm; the preset deformation parameter P is represented by the transformation between the shape transformed by the preset homography transformation matrix H and the three-dimensional shape; The coordinates of the contour of the affected area within the three-dimensional shape are calculated, and then the coordinates of the contour of the affected area are expanded to coordinates in a two-dimensional space, and the coordinates in the two-dimensional space are represented as preparation parameters of the applicator.

2. A radioisotope application planning method according to claim 1, characterized in that: The step of transforming the two-dimensional shape into a three-dimensional shape based on a preset homography transformation matrix H and a preset deformation parameter P comprises: Obtaining a first transformed shape according to the two-dimensional shape based on a preset homography transformation matrix H, wherein the first transformed shape represents an optimal posture of the two-dimensional shape placed in the target area without bending deformation; The first transformed shape is used to obtain the three-dimensional shape based on a preset deformation parameter P, where the preset deformation parameter P is obtained by solving the deformation between the preset three-dimensional shape and the optimal posture of the preset two-dimensional shape placed in the target area without bending deformation.

3. A radioisotope application planning method according to claim 2, characterized in that: The preset deformation parameter P is obtained based on a thin plate spline interpolation method.

4. A radioisotope application planning method according to claim 2, characterized in that: The steps of constructing the preset homography transformation matrix H are: Determine a plurality of first sampling points and a plurality of second sampling points on the three-dimensional image based on the Dijkstra algorithm according to the two-dimensional shape, wherein the first sampling points and the second sampling points are combined to form a first point set; Constructing a second point set in the two-dimensional shape having the same number of sampling points as that in the first point set; Transformation parameters are solved between the first point set and the second point set to obtain optimal homography transformation parameters as the homography transformation matrix H.

5. A radioisotope application planning method according to claim 4, characterized in that: The step of determining a plurality of said first sampling points comprises: Calculating the minimum circumscribed circle of the two-dimensional shape to obtain the center point and radius of the minimum circumscribed circle; Determine, in multiple directions outward from the current center point, contour lines whose distances from the center point are radiuses; The perimeter of the contour line is calculated, and according to the perimeter, a plurality of first sampling points are obtained by sampling at equal intervals on the circumference formed by the contour line.

6. A radioisotope application planning method according to claim 5, characterized in that: Sampling is performed at equal intervals on the path from the center point to each of the first sampling points to obtain a plurality of second sampling points.

7. A radioisotope application planning method according to claim 1, characterized in that: The method of obtaining the three-dimensional image of the human body comprises: using a 3D scanner to scan the human skin to obtain the three-dimensional image of the human body.

8. A radioisotope application planning method according to claim 1, characterized in that: After the corresponding coordinates are obtained by unfolding the contour of the affected area in two-dimensional space, the method includes: inputting the coordinates of the contour of the affected area in two-dimensional space into an applicator production device to produce an applicator with the same contour as the affected area.

9. A radioisotope application planning method according to claim 1, characterized in that: Expanding the coordinates of the contour of the affected area to coordinates in a two-dimensional space includes: obtaining the coordinates by reverse transformation according to the method of forming a three-dimensional shape from the two-dimensional shape.

10. A radioisotope application planning device, characterized in that: The device comprises a memory and at least one processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the radioisotope application planning method as claimed in any one of claims 1 to 9.

Images