Deformation registration method and device, storage medium and electronic equipment

Abstract

The application discloses a deformation registration method and device, a storage medium and an electronic device, and relates to the fields of medical technology and image processing. The method comprises the following steps: obtaining reference data and floating data; performing data separation on the reference data and the floating data according to organ types, wherein the data separation is used to separate image data of each independent organ from the reference data and the floating data; performing deformation registration on the image data of each independent organ to obtain a deformation field corresponding to each independent organ; and fusing the deformation field corresponding to each independent organ into a target deformation field, and performing deformation registration on the floating data through the target deformation field. The application solves the technical problem that, in the prior art, when a registration algorithm is used for dose accumulation in radiotherapy, the registration process of local organ tissue structures has alignment redundancy or deficiency, leading to inaccurate dose accumulation in the organ boundary region.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical science and the field of image processing, in particular, to a deformation registration method and device, a storage medium and an electronic device. BACKGROUND

[0002] In the field of radiotherapy, it is common to use related algorithms to convert the dose distribution of each treatment stage into a unified coordinate system for dose accumulation, which helps doctors to evaluate the total dose and dose distribution actually received by the patient and optimize clinical decision-making. The commonly used dose accumulation methods at present include linear DVH parameter accumulation, rigid registration, deformation registration and biological dose accumulation, etc.

[0003] Among them, deformation registration can handle the changes in tissue structure caused by non-rigid motion and reduce the dose accumulation error caused by anatomical deformation, which is a key technology to achieve high-precision dose evaluation. However, in the process of multi-organ contour fusion registration, there is mutual constraint between adjacent organs, and the deformation fields calculated by different data also have significant differences, making the fusion process more difficult.

[0004] Even if a variety of evaluation indexes are introduced into the registration function, and the local tissue structure is adjusted under the premise of global optimization, although it can improve the alignment accuracy of the local structure to a certain extent, it still belongs to global registration in essence, and the core is still to pursue the overall optimization. Only by optimizing the registration function, the local registration accuracy is still insufficient. Overall, most of the existing deformation registration methods are based on mathematical models, and the global deformation of the image is driven by designing a registration function. In the alignment of local anatomical structures, there are often redundancies or deficiencies, which easily lead to inaccurate dose mapping in the boundary region of the tissue structure, thereby affecting the accuracy and reliability of dose accumulation.

[0005] In view of the above problems, no effective solution has been proposed at present. SUMMARY

[0006] The present application provides a deformation registration method, device, storage medium and electronic device to at least solve the technical problem that the dose accumulation is inaccurate in the boundary region of the organ due to the registration process of the local organ tissue structure in the prior art when the registration algorithm is used for dose accumulation in radiotherapy.

[0007] According to an aspect of the present application, a morphing registration method is provided, comprising: obtaining reference data and floating data, wherein the reference data comprises a reference image, a delineation image of the reference image, and a dose map corresponding to the reference image; the floating data comprises a floating image, a delineation image of the floating image, and a dose map corresponding to the floating image; performing data separation on the reference data and the floating data according to organ types, wherein the data separation is used to separate image data of each independent organ from the reference data and the floating data; performing morphing registration on the image data of each independent organ to obtain a morphing field corresponding to each independent organ; and fusing the morphing field corresponding to each independent organ into a target morphing field, and performing morphing registration on the floating data through the target morphing field.

[0008] Optionally, the morphing registration on the floating data through the target morphing field comprises: determining a rigid transformation matrix according to the floating image; performing rigid transformation on the floating data according to the rigid transformation matrix to obtain intermediate-state floating data, wherein the intermediate-state floating data comprises the floating image, the delineation image, and the dose map after the rigid transformation; and performing morphing registration on the intermediate-state floating data through the target morphing field.

[0009] Optionally, the data separation on the reference data and the floating data according to organ types comprises: separately separating each delineation region according to delineation information of each organ in the image to obtain N independent delineation reference data of the same size as the reference data and N independent delineation floating data of the same size as the floating data; segmenting the reference image into N independent organ reference images according to the N independent delineation reference data corresponding to the reference data, and taking an image region of the reference image other than the N independent organ reference images as a background reference image; and segmenting the floating image into N independent organ floating images according to the N independent delineation floating data corresponding to the floating data, and taking an image region of the floating image other than the N independent organ floating images as a background floating image.

[0010] Optionally, the morphing registration on the image data of each independent organ to obtain a morphing field corresponding to each independent organ comprises: constructing a first function, a second function, and a third function, wherein the first function is used to correct contour alignment error between the floating data and the reference data based on each organ; the second function is used to correct contour registration redundancy between the floating data and the reference data based on each organ, the contour registration redundancy representing that the organ contour after registration exceeds a boundary range corresponding to the organ in the reference image; and the third function is used to constrain the morphing degree of each organ in the registration process; performing weighted summation calculation on the first function, the second function, and the third function to obtain a target function; and performing morphing registration on the image data of each independent organ according to the target function to obtain the morphing field corresponding to each independent organ.

[0011] Optionally, the first function, the second function and the third function are constructed, comprising: constructing the first function and the second function according to the independent delineation reference data and the independent delineation floating data corresponding to the ith organ, wherein i is a positive integer, the first function is used to determine the content overlap degree between the independent delineation reference data and the independent delineation floating data corresponding to the ith organ; the second function is used to determine the contour redundancy of the independent delineation reference data corresponding to the ith organ relative to the independent delineation floating data corresponding to the ith organ, and determine the contour redundancy of the independent delineation floating data corresponding to the ith organ relative to the independent delineation reference data corresponding to the ith organ; constructing the third function according to the independent organ floating image and the independent organ reference image corresponding to the ith organ, wherein the third function is used to determine the pixel coincidence degree between the independent organ floating image and the independent organ reference image corresponding to the ith organ.

[0012] Optionally, the deformation field corresponding to each independent organ is fused into the target deformation field, comprising: adding and summing the deformation field corresponding to each independent organ to obtain an organ deformation field; obtaining a deformation field between the reference data and the floating data with respect to an image background region; obtaining a deformation field of an overlapping region between the image background region and an organ region; and summing the organ deformation field, the deformation field of the image background region and the deformation field of the overlapping region to obtain the target deformation field.

[0013] Optionally, the deformation field between the reference data and the floating data with respect to the image background region is obtained, comprising: constructing a fourth function according to the background floating image and the background reference image, wherein the fourth function is used to determine the deformation alignment degree between the background floating image and the background reference image; and performing deformation registration on the background floating image according to the fourth function to obtain the deformation field of the image background region.

[0014] Optionally, the deformation field of the overlapping region between the image background region and the organ region is obtained, comprising: determining a mask corresponding to the overlapping region between the image background region and the organ region according to the intersection between the organ deformation field and the deformation field of the image background region; extracting first deformation field data corresponding to the overlapping region from the organ deformation field according to the mask; extracting second deformation field data corresponding to the overlapping region from the deformation field of the image background region according to the mask; and performing weighted sum calculation on the first deformation field data and the second deformation field data to obtain the deformation field of the overlapping region.

[0015] According to another aspect of the present application, there is also provided a deformation registration apparatus comprising: an acquisition unit configured to acquire reference data and floating data, wherein the reference data comprises a reference image, a delineation image of the reference image, and a dose map corresponding to the reference image; the floating data comprises a floating image, a delineation image of the floating image, and a dose map corresponding to the floating image; a data separation unit configured to separately perform data separation on the reference data and the floating data according to organ types, wherein the data separation is configured to separate image data of each independent organ from the reference data and the floating data; a first registration unit configured to perform deformation registration on the image data of each independent organ to obtain a deformation field corresponding to each independent organ; and a second registration unit configured to fuse the deformation field corresponding to each independent organ into a target deformation field, and perform deformation registration on the floating data through the target deformation field.

[0016] According to another aspect of the present application, there is also provided a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program, when executed, causes a device in which the computer readable storage medium is located to perform the deformation registration method.

[0017] According to another aspect of the present application, there is also provided an electronic device, comprising one or more processors and a memory, the memory configured to store one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the deformation registration method.

[0018] In the present application, first, reference data and floating data are acquired, wherein the reference data comprises a reference image, a delineation image of the reference image, and a dose map corresponding to the reference image; the floating data comprises a floating image, a delineation image of the floating image, and a dose map corresponding to the floating image. Then, data separation is performed on the reference data and the floating data according to organ types, wherein the data separation is configured to separate image data of each independent organ from the reference data and the floating data. Subsequently, deformation registration is performed on the image data of each independent organ to obtain a deformation field corresponding to each independent organ, and the deformation field corresponding to each independent organ is fused into a target deformation field, and the floating data is deformed through the target deformation field.

[0019] From the above, it can be seen that the present application first performs data separation on the reference data and the floating data according to organ types, so as to separately separate image data of each independent organ from the reference data and the floating data, and on this basis, the present application can perform deformation registration on each independent organ to obtain a deformation field corresponding to each independent organ. Subsequently, a specific fusion strategy is used to fuse the deformation fields corresponding to each independent organ into an overall deformation field, and finally the overall data after deformation registration is generated using the overall deformation field obtained through fusion.

[0020] It should be noted that the existing registration technology usually takes all organ information and the whole image as input to perform global registration. The existing technology focuses more on the optimal solution of the overall deformation, ignoring the differences in deformation characteristics between different organs. Since the deformation requirements of each organ are different, the unified global deformation cannot simultaneously achieve the optimal alignment of all organs, and there are mutual constraints between different organs, which further affects the accuracy of local registration.

[0021] According to the organ type, the present application splits the overall delineation information and image information into multiple independent delineation information and image information corresponding to different organs, replacing the traditional overall registration method. By performing registration independently for each organ, the mutual interference between different organs is avoided, effectively solving the problem of alignment redundancy or deficiency of local organ tissue structure in the registration process, thereby improving the accuracy of organ boundary region dose mapping accumulation. BRIEF DESCRIPTION OF DRAWINGS

[0022] The accompanying drawings, which are included to provide a further understanding of the present application, constitute a part of the present application and illustrate the illustrative embodiments of the present application and their description serve to explain the present application, and do not constitute improper limitations on the present application. In the drawings:

[0023] Figure 1 is a flowchart of an optional deformation registration method according to an embodiment of the present application;

[0024] Figure 2 is a schematic diagram of an optional data separation process according to an embodiment of the present application;

[0025] Figure 3 is a schematic diagram of an optional deformation registration process according to an embodiment of the present application;

[0026] Figure 4 is a schematic diagram of an optional deformation registration device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0028] It should be noted that the terms "first", "second", and the like in the description and in the claims of the present application and the above-described accompanying drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or apparatus that includes a series of steps or units does not necessarily have to be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to such a process, method, product, or apparatus.

[0029] According to an embodiment of the present application, a method embodiment of a deformation registration method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0030] In an alternative embodiment, a deformation registration system can be used as an execution subject of the deformation registration method according to an embodiment of the present application, wherein the deformation registration system can be a software system or a combination of software and hardware embedded system. In addition, in addition to using the deformation registration system as an execution subject of the deformation registration method, other forms of execution subjects such as devices and apparatuses can also be used to execute the deformation registration method, and those skilled in the art can understand that the specific form of the execution subject of the method is not particularly limited in the embodiments of the present application.

[0031] Figure 1 is a flowchart of an alternative deformation registration method according to an embodiment of the present application, as shown in Figure 1 , the method comprises the following steps:

[0032] Step S101, obtaining reference data and floating data.

[0033] The reference data includes: reference images, delineation images of the reference images, and dose maps corresponding to the reference images; the floating data includes: floating images, delineation images of the floating images, and dose maps corresponding to the floating images.

[0034] Optionally, the reference data can be a set of image data used as a registration reference in the registration process, wherein the reference data includes: reference images , delineation images of the reference images , and dose maps corresponding to the reference images .

[0035] the delineation image of the reference image the contour delineation information of each organ in the reference image, the dose map corresponding to the reference image the dose information corresponding to each organ region in the reference image.

[0036] Optionally, the floating data refers to image data that needs to be registered with the reference data, wherein the floating data comprises: a floating image , a delineation image of the floating image , and a dose map corresponding to the floating image .

[0037] the delineation image of the floating image the contour delineation information of each organ in the floating image, the dose map corresponding to the floating image the dose information corresponding to each organ region in the floating image.

[0038] It should be noted that the delineation image of the reference image and the delineation image of the floating image store the category information and quantity information of the key tissue structure (independent organ) in radiotherapy. In addition, the number and category of the delineation image and the delineation image have a one-to-one correspondence relationship.

[0039] Step S102, according to the organ type, the reference data and the floating data are respectively separated, wherein the data separation is used to separate the image data of each independent organ from the reference data and the floating data.

[0040] Optionally, first, the morphing registration system can separate and extract each delineation region according to the delineation category of the tissue structure (independent organ) in the delineation image of the reference image , to obtain N independent delineation reference data corresponding to different tissue structures (independent organs) (which can be denoted as ), wherein the size of the independent delineation reference data is the same as that of the delineation image , wherein .

[0041] Secondly, the morphing registration system can separate the reference image into N independent organ reference images corresponding to the independent delineation reference data .

[0042] ​​In addition, after the image separation of the tissue structure (independent organ) is completed, the morphological registration system can extract image regions other than the independent organ reference image from the reference image as background reference images , wherein the background reference images are obtained in the following manner .

[0043] As can be seen from the above, after the reference data is data-separated according to the organ type, the independent delineation reference data , the independent organ reference image and the background reference image are obtained.

[0044] Similarly, the data separation method of the reference data is used. After the floating data is data-separated according to the organ type, the independent delineation floating data , the independent organ floating image and the background floating image are obtained.

[0045] In step S103, the image data of each independent organ is morphologically registered to obtain the morphological field corresponding to each independent organ.

[0046] Optionally, the purpose of morphological registration is to align each independent organ in the floating image to the corresponding organ in the reference image, so as to make the outlines and internal structures of the organs match as much as possible. In the process of morphological registration, the image data of each independent organ is morphologically registered separately, that is, the morphological deformation of each organ is calculated independently, avoiding mutual interference between different organs. In morphological registration, an optimization function can be used to measure the matching degree between the floating organ and the reference organ. Through the calculation of the optimization function, the morphological field corresponding to each organ is generated. The morphological field is a vector field, which can represent the direction and distance of movement of each pixel point in the floating image in the morphological process. The morphological field can be used to guide the deformation of the floating image, so that it is aligned with the corresponding organ in the reference image.

[0047] In step S104, the morphological field corresponding to each independent organ is fused into a target morphological field, and the floating data is morphologically registered through the target morphological field.

[0048] Optionally, the target morphological field can be the complete morphological field of all tissue structures (independent organs), that is, the sum of the morphological fields of all tissue structures (independent organs).

[0049] In addition, the target deformation field can also be a total deformation field obtained by adding a deformation field of the image background region and / or a deformation field of an overlapping region to a deformation field of the intact tissue structure (independent organ).

[0050] According to the above steps S101 to S104, the whole delineation information and image information are split into a plurality of independent delineation information and image information corresponding to different organs according to the organ type, instead of the traditional whole registration mode. By performing registration on each organ independently, the mutual interference between different organs is avoided, the problems of alignment redundancy or deficiency of local organ tissue structure in the registration process are effectively solved, and the accuracy of organ boundary region dose mapping accumulation is improved.

[0051] In an optional embodiment, the floating data is deformed and registered by the target deformation field, including: determining a rigid transformation matrix according to the floating image; performing rigid transformation on the floating data according to the rigid transformation matrix to obtain intermediate state floating data, wherein the intermediate state floating data includes the floating image, the delineation image and the dose map after the rigid transformation; and deforming and registering the intermediate state floating data by the target deformation field.

[0052] Optionally, the deformation registration system can select a rigid registration model, and then perform rigid transformation on the floating image according to the floating image to obtain a rigid transformation matrix R. The deformation registration system can perform rigid transformation on the floating data by using the rigid transformation matrix R to obtain intermediate state floating data. The intermediate state floating data includes: the floating image , the delineation image and the dose map after the rigid transformation.

[0053] In an optional embodiment, the reference data and the floating data are respectively separated according to the organ type, including: the deformation registration system can separately separate each delineation region according to the delineation information of each organ in the image to obtain N independent delineation reference data with the same size as the reference data and N independent delineation floating data with the same size as the floating data. Then, the deformation registration system can divide the reference image into N independent organ reference images according to the N independent delineation reference data corresponding to the reference data, and regard the image region of the reference image other than the N independent organ reference images as a background reference image. Finally, the deformation registration system divides the floating image into N independent organ floating images according to the N independent delineation floating data corresponding to the floating data, and regards the image region of the floating image other than the N independent organ floating images as a background floating image.

[0054] Optionally, when separating reference data according to organ type, the following steps are included:

[0055] First, the deformation registration system can delineate the image based on the reference image. The delineation categories of tissue structures (individual organs) are determined, and each delineated region is separated and extracted to obtain N independent delineation reference data corresponding to different tissue structures (individual organs) (which can be denoted as N). (Including independently drawn reference data) Size and outline of the image The same, among which, .

[0056] Secondly, the deformation registration system can independently delineate reference data. Reference image Separate into N independent reference data Corresponding independent organ reference images .

[0057] In addition, after completing the image separation of tissue structures (individual organs), the deformation registration system can be used from the reference image. Extract reference images excluding independent organs The image area outside the background reference image Among them, the background reference image The method of obtaining is .

[0058] As can be seen from the above, after separating the reference data according to organ type, independent delineation reference data can be obtained. Independent organ reference images and background reference image .

[0059] Optionally, when separating floating data according to organ type, the following steps are included:

[0060] First, the deformation registration system can delineate the image based on the floating image. The delineation categories of tissue structures (individual organs) are categorized, and each delineated region is separated and extracted to generate N independent delineated floating data corresponding to different tissue structures (individual organs) (which can be denoted as...). (Including independently drawing floating data) Size and outline of the image The same, among which, .

[0061] Secondly, the deformation registration system can independently delineate floating data. , float image Separate into N independent floating data Corresponding independent organ floating images .

[0062] In addition, after completing the image separation of tissue structures (individual organs), the deformation registration system can be used to separate the images from the floating images. Extract floating images excluding independent organs The image area outside the background reference image Among them, the background reference image The method of obtaining is .

[0063] As can be seen from the above, after separating the floating data according to organ type, independently delineated floating data can be obtained. Independent organ floating images and background floating image .

[0064] Optionally, Figure 2 This is a schematic diagram of an optional data separation process according to an embodiment of this application, such as... Figure 2 As shown, based on the initial image delineation information (such as the delineated image of the reference image or the delineated image of the floating image), through data separation, independent delineation data 1, independent delineation data 2, independent delineation data 3, independent delineation data 4, and independent delineation data 6 can be obtained, and each independent delineation data corresponds to an independent organ.

[0065] In one optional embodiment, deformation registration is performed on the image data of each independent organ to obtain the deformation field corresponding to each independent organ. This includes constructing a first function, a second function, and a third function. The first function is used to correct the contour alignment error between the floating data and the reference data based on each organ. The second function is used to correct the contour registration redundancy between the floating data and the reference data based on each organ. Contour registration redundancy indicates that the registered organ contour exceeds the boundary range corresponding to the organ in the reference image. The third function is used to constrain the degree of deformation for each organ during the registration process. The deformation registration system can perform a weighted summation of the first function, the second function, and the third function to obtain a target function, and then perform deformation registration on the image data of each independent organ according to the target function to obtain the deformation field corresponding to each independent organ.

[0066] Optionally, the application designs an optimization function (i.e. the above-mentioned objective function) for the deformation of the organizational structure (independent organ), which involves the delineation information corresponding to the image and the image information of the image itself. The delineation information corresponding to the image is used to ensure the accurate alignment of the outline of the organizational structure (independent organ), and the image information of the image itself is used to constrain the rationality of the deformation and avoid the folding phenomenon. The optimization function of the application has high flexibility and can be seamlessly embedded into other deformation registration optimization frameworks, and has good reusability.

[0067] The optimization function of the application includes a first function, a second function and a third function. Specifically, the optimization function can be a weighted sum of the first function, the second function and the third function.

[0068] Optionally, the design target of the first function is to correct the image data with insufficient outline alignment in the registration process, the design target of the second function is to correct the image data with redundant outline alignment in the registration process, and the design target of the third function is to constrain the deformation degree of each organ in the registration process.

[0069] Wherein, the phenomenon of "alignment redundancy or deficiency" can be illustrated by the bladder registration example: when the bladder in the floating image is deformed and registered to the reference image, if the outline of the bladder after registration exceeds the boundary range of the bladder in the reference image, it is "alignment redundancy"; otherwise, if it fails to completely cover the area of the bladder in the reference image, it is "alignment deficiency".

[0070] In an optional embodiment, the first function, the second function and the third function are constructed, including: constructing the first function and the second function according to the independent delineation reference data and the independent delineation floating data corresponding to the i-th organ, wherein i is a positive integer, the first function is used to determine the content overlap degree between the independent delineation reference data and the independent delineation floating data corresponding to the i-th organ; the second function is used to determine the outline redundancy of the independent delineation reference data corresponding to the i-th organ relative to the independent delineation floating data corresponding to the i-th organ, and the outline redundancy of the independent delineation floating data corresponding to the i-th organ relative to the independent delineation reference data corresponding to the i-th organ; constructing the third function according to the independent organ floating image and the independent organ reference image corresponding to the i-th organ, wherein the third function is used to determine the pixel coincidence degree between the independent organ floating image and the independent organ reference image corresponding to the i-th organ.

[0071] Optionally, first, the first function is represented by the following formula (1).

[0072] (1)

[0073] wherein in formula (1), the value calculated by the Dice function is used to measure the degree of coincidence between the independently delineated floating data and the independently delineated reference data .

[0074] In addition, it should be noted that in image data, a grid point is usually used to store a pixel value, representing the gray level or color information of the corresponding position on the image. In the deformation field, each grid point stores not a pixel value, but a two-dimensional or three-dimensional coordinate value, which is used to indicate the corresponding sampling position of the position in the data image. In other words, each grid point of the deformation field contains a mapping coordinate, indicating which position in the data image should be used to obtain the pixel value. The " " symbol used in formula (1) means: find the corresponding position in the original image according to the coordinate information in the deformation field, and then extract the pixel value of the point to fill the current grid position. The " " involved in the subsequent formula also has the same meaning, so subsequent descriptions will not be repeated.

[0075] Secondly, the second function is characterized by the following formula (2) and formula (3).

[0076] wherein formula (2) is used to determine the contour redundancy of the independently delineated floating data corresponding to the i-th organ with respect to the independently delineated reference data corresponding to the i-th organ; formula (3) is used to determine the contour redundancy of the independently delineated reference data corresponding to the i-th organ with respect to the independently delineated floating data corresponding to the i-th organ. This corresponds to two cases of alignment redundancy: one is the redundancy of the floating tissue structure with respect to the reference structure, and the other is the redundancy of the reference structure with respect to the floating structure, which are measured by parameters and respectively.

[0077] (2)

[0078] (3)

[0079] wherein the Redun function refers to a redundancy index, which is used to measure the degree to which the coincidence between the floating tissue structure delineation and the reference tissue structure contour exceeds the necessary range in the deformation registration process. In other words, Redun helps to identify and quantify the situation that the floating structure exceeds or overlaps the reference structure boundary during registration, which is particularly important for evaluating the accuracy of the registration algorithm and avoiding excessive deformation.

[0080] Furthermore, the deformation registration system can also use the mutual information index to measure the pixel coincidence degree between the floating tissue structure image and the reference tissue structure image, to constrain the rationality of the deformation, as shown in formula (4):​​

[0081] (4)

[0082] wherein, the formula (4) can represent the third function described above. The MIM function generally refers to "Mutual Information Maximization" function, which is an image registration method in the field of medical image processing and radiation treatment dose accumulation. Mutual information measures the dependency between two random variables and is used to assess the similarity between two images, especially suitable for registration of different types of images, such as CT images and MRI images, because the gray value ranges and physical meanings of these images may be different. In deformation registration, the mutual information function can help the algorithm understand and match the information between two images, even if there are significant differences in brightness or contrast. This is because mutual information focuses on the information sharing between two images, rather than directly comparing gray values. In dose accumulation calculation, using the mutual information function can ensure that the dose distribution is accurately mapped to the reference image even if the anatomical structure changes, thereby improving the accuracy of dose evaluation.

[0083] Then, by weighted summation, the optimization function (i.e. objective function) of the entire deformation registration is obtained, see formula (5).

[0084] (5)

[0085] In formula (5), , , and respectively refer to the preset weight values corresponding to , , and .

[0086] Finally, according to the above optimization function, the intermediate floating data after rigid transformation (including the floating image , the delineation image and the dose map after completing the rigid transformation) can be sequentially deformed and registered to obtain the deformation field corresponding to each tissue structure (independent organ), wherein .

[0087] In an alternative embodiment, fusing the deformation field corresponding to each independent organ into the target deformation field comprises: summing up the deformation field corresponding to each independent organ to obtain an organ deformation field; obtaining a deformation field between the reference data and the floating data with respect to the image background region; obtaining a deformation field of an overlapping region between the image background region and a region where the organ is located; and summing up the organ deformation field, the deformation field of the image background region, and the deformation field of the overlapping region to obtain the target deformation field.

[0088] Optionally, first, because the different tissue structures (independent organs) are highly independent and have little overlap between each other, all the independent deformation fields can be directly fused into a deformation field of the complete tissue structure (i.e., the organ deformation field mentioned above), as shown in equation (6). Optionally, first, because the different tissue structures (independent organs) are highly independent and have little overlap between each other, all the independent deformation fields can be directly fused into a deformation field of the complete tissue structure (i.e., the organ deformation field mentioned above), as shown in equation (6).

[0089] (6)

[0090] Second, the edge continuity between the image background region and the tissue structure (independent organ) is strong, and there is a large amount of overlapping region. In order to ensure the accuracy of the tissue structure (independent organ) during registration, the deformation field of the image background region (which can be denoted as ) and the deformation field of the overlapping region (which can be denoted as ) also need to be obtained.

[0091] Finally, by combining the organ deformation field , the deformation field of the image background region , and the deformation field of the overlapping region , the final target deformation field can be calculated based on the following equation (7).

[0092] (7)

[0093] In an alternative embodiment, obtaining the deformation field between the reference data and the floating data with respect to the image background region comprises: constructing a fourth function according to the background floating image and the background reference image, wherein the fourth function is used to determine the deformation alignment degree between the background floating image and the background reference image. The deformation registration system performs deformation registration on the background floating image according to the fourth function to obtain the deformation field of the image background region.

[0094] Optionally, after the whole image is separated, the remaining image information is the background information image, and the mutual information index can be directly used to measure the deformation alignment degree of the image background region, as shown in equation (8):

[0095] (8)

[0096] ​According to the formula (8), the deformation registration system can perform deformation registration on the background floating image after rigid transformation to obtain the deformation field of the image background region . The formula (8) is used to represent the fourth function.

[0097] In an optional embodiment, the deformation field of the overlapping region between the image background region and the organ region is obtained by: the deformation registration system determines a mask corresponding to the overlapping region between the image background region and the organ region according to the intersection between the organ deformation field and the deformation field of the image background region, and then extracts first deformation field data corresponding to the overlapping region from the organ deformation field according to the mask; and extracts second deformation field data corresponding to the overlapping region from the deformation field of the image background region according to the mask. Finally, the deformation registration system performs weighted summation calculation on the first deformation field data and the second deformation field data to obtain the deformation field of the overlapping region.

[0098] Optionally, as described above, the edge continuity between the image background region and the tissue structure (independent organ) is strong, and there is a large amount of overlapping region. In order to further improve the registration accuracy of the tissue structure (independent organ), the image data of the tissue structure (independent organ) is used as the main data in the data fusion of the overlapping region.

[0099] In addition, since the complete deformation field of the tissue structure (independent organ) and the deformation field of the image background region are calculated independently, the mask of the overlapping region can be obtained by intersecting the two deformation fields. According to the mask, the values of the corresponding regions in the two deformation fields can be extracted, and the deformation field fusion of the overlapping region is completed accordingly . The specific process is shown in formula (9).

[0100] (9)

[0101] In an optional embodiment, Figure 3 is a schematic diagram of an optional deformation registration process according to an embodiment of the present application, as shown in Figure 3 , the deformation registration process in the embodiment of the present application can be divided into four stages, which are: data acquisition, image decomposition based on the tissue structure (independent organ), construction of a registration model (optimization function) based on the image decomposition data of the tissue structure, and fusion of the deformation field and deformation registration based on the image decomposition data of the tissue structure.

[0102] Optionally, as shown in Figure 3 ​As shown, in the "Data Acquisition" stage, sequential images of the patient during multiple treatments can be acquired, as well as delineated images of the core tissue structure (core independent organs) and sequential treatment dose images generated based on these sequential images.

[0103] Optionally, such as Figure 3 As shown, in the "Image Decomposition Based on Tissue Structure (Independent Organ)" stage, the image to be decomposed and the delineation (reference data, floating data) are first input into the deformation registration system. The reference data includes: a reference image, a delineated image of the reference image, and a dose map corresponding to the reference image; the floating data includes: a floating image, a delineated image of the floating image, and a dose map corresponding to the floating image.

[0104] Then, the deformation registration system separates the reference data and floating data according to the organ type, resulting in N independent delineation reference data of the same size as the reference data, N independent delineation floating data of the same size as the floating data, N independent organ reference images corresponding to the reference image, N independent organ floating images corresponding to the floating image, and one background reference image corresponding to the reference image and one background floating image corresponding to the floating image.

[0105] Therefore, after separating the floating data according to organ type, we can obtain N independent delineation floating data, N independent organ floating images and 1 background floating image as decomposed floating information, and obtain N independent delineation reference data, N independent organ reference images and 1 background reference image as decomposed reference information.

[0106] Optionally, such as Figure 3 As shown, in the stage of "constructing a registration model (optimization function) based on image decomposition data of tissue structure", the deformation registration system can first select a rigid registration model to perform rigid transformation on the floating data based on the decomposed reference information and the decomposed floating information, and then obtain the floating data after rigid transformation (i.e. the intermediate floating data mentioned above). Then, the deformation registration model (optimization function) is used to determine the deformation field corresponding to N tissue structures (independent organs) and the deformation field of the image background area.

[0107] Finally, as Figure 3 As shown, in the stage of "fusion and deformation registration of deformation fields based on image decomposition data of tissue structure", the deformation registration system uses a deformation field fusion strategy to fuse the deformation fields corresponding to N tissue structures (independent organs) and the deformation fields of the image background area to obtain a complete deformation field and deform the floating data, thereby obtaining the deformed floating image, the independent organ delineation image and the dose map.

[0108] According to another aspect of the embodiments of this application, a deformation registration device is also provided, wherein,Figure 4 is a schematic diagram of an optional deformation registration device according to an embodiment of the present application, as shown in Figure 4 The deformation registration device includes an acquisition unit 401, a data separation unit 402, a first registration unit 403, and a second registration unit 404.

[0109] The acquisition unit 401 is configured to acquire reference data and floating data. The reference data includes a reference image, a delineation image of the reference image, and a dose map corresponding to the reference image. The floating data includes a floating image, a delineation image of the floating image, and a dose map corresponding to the floating image. The data separation unit 402 is configured to separately perform data separation on the reference data and the floating data according to organ types. The data separation is configured to separate image data of each independent organ from the reference data and the floating data. The first registration unit 403 is configured to perform deformation registration on the image data of each independent organ to obtain a deformation field corresponding to each independent organ. The second registration unit 404 is configured to fuse the deformation field corresponding to each independent organ into a target deformation field, and perform deformation registration on the floating data through the target deformation field.

[0110] Optionally, the second registration unit 404 includes a first determination subunit configured to determine a rigid transformation matrix according to the floating image, a rigid transformation subunit configured to perform rigid transformation on the floating data according to the rigid transformation matrix to obtain intermediate-state floating data, wherein the intermediate-state floating data includes the floating image, the delineation image, and the dose map after the rigid transformation, and a deformation registration subunit configured to perform deformation registration on the intermediate-state floating data through the target deformation field.

[0111] Optionally, the data separation unit 402 includes a data separation subunit configured to separately separate each delineation region according to delineation information of each organ in the image to obtain N independent delineation reference data of the same size as the reference data and N independent delineation floating data of the same size as the floating data, and an image segmentation subunit configured to segment the reference image into N independent organ reference images according to the N independent delineation reference data corresponding to the reference data, and take an image region of the reference image other than the N independent organ reference images as a background reference image, and segment the floating image into N independent organ floating images according to the N independent delineation floating data corresponding to the floating data, and take an image region of the floating image other than the N independent organ floating images as a background floating image.

[0112] Optionally, the first registration unit 403 comprises: a function constructing subunit, configured to construct a first function, a second function and a third function, wherein the first function is configured to correct contour alignment error between the floating data and the reference data based on each organ; the second function is configured to correct contour registration redundancy between the floating data and the reference data based on each organ, the contour registration redundancy representing that the contour of the registered organ exceeds the boundary range corresponding to the organ in the reference image; and the third function is configured to constrain the deformation degree of each organ in the registration process; a function calculating subunit, configured to perform weighted sum calculation on the first function, the second function and the third function to obtain a target function; and a registration subunit, configured to perform deformation registration on the image data of each independent organ according to the target function to obtain a deformation field corresponding to each independent organ.

[0113] Optionally, the function constructing subunit comprises: a first processing module, configured to construct a first function and a second function according to the independent delineation reference data and the independent delineation floating data corresponding to the i-th organ, wherein i is a positive integer, the first function is configured to determine the content overlap degree between the independent delineation reference data and the independent delineation floating data corresponding to the i-th organ; and the second function is configured to determine the contour redundancy of the independent delineation reference data corresponding to the i-th organ relative to the independent delineation floating data corresponding to the i-th organ, and determine the contour redundancy of the independent delineation floating data corresponding to the i-th organ relative to the independent delineation reference data corresponding to the i-th organ; and a second processing module, configured to construct a third function according to the independent organ floating image and the independent organ reference image corresponding to the i-th organ, wherein the third function is configured to determine the pixel coincidence degree between the independent organ floating image and the independent organ reference image corresponding to the i-th organ.

[0114] Optionally, the second registration unit 404 comprises: a deformation field calculating subunit, configured to add and sum the deformation fields corresponding to each independent organ to obtain an organ deformation field; a first obtaining subunit, configured to obtain the deformation field between the reference data and the floating data with respect to the image background region; a second obtaining subunit, configured to obtain the deformation field of an overlapping region between the image background region and the region where the organ is located; and a deformation field sum calculating subunit, configured to perform sum calculation on the organ deformation field, the deformation field of the image background region and the deformation field of the overlapping region to obtain a target deformation field.

[0115] Optionally, the first obtaining subunit comprises: a third processing module, configured to construct a fourth function according to the background floating image and the background reference image, wherein the fourth function is configured to determine the deformation alignment degree between the background floating image and the background reference image; and a fourth processing module, configured to perform deformation registration on the background floating image according to the fourth function to obtain the deformation field of the image background region.

[0116] Optionally, the second obtaining sub-unit comprises: a fifth processing module configured to determine a mask corresponding to an overlapping region between the image background region and the organ region according to an intersection between the organ deformation field and the deformation field of the image background region; a sixth processing module configured to extract first deformation field data corresponding to the overlapping region from the organ deformation field according to the mask; a seventh processing module configured to extract second deformation field data corresponding to the overlapping region from the deformation field of the image background region according to the mask; and an eighth processing module configured to perform weighted summation calculation on the first deformation field data and the second deformation field data to obtain the deformation field of the overlapping region.

[0117] According to another aspect of the embodiments of the present application, a computer readable storage medium is also provided, and the computer readable storage medium stores a computer program. When the computer program runs, the computer readable storage medium makes a device where the computer readable storage medium is located execute the deformation registration method.

[0118] According to another aspect of the embodiments of the present application, an electronic device is also provided, which comprises one or more processors and a memory. The memory is configured to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors execute the deformation registration method.

[0119] The serial numbers of the embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

[0120] In the above embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0121] In the several embodiments provided by the present application, it should be understood that the disclosed technology can be implemented in other ways. Of course, the unit described as the division is only a logical function division, and there can be other division manners in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, units or modules, and can be electrical or other forms.

[0122] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiments.

[0123] In addition, each function unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software function unit.

[0124] When the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in the form of a contribution to the prior art, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes various media that can store program codes, such as a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, etc.

[0125] The above is only the preferred embodiment of the present application, and it should be pointed out that, for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. A method of deformation registration, the method comprising: The method comprises the following steps: obtaining reference data and floating data, wherein the reference data comprises a reference image, a delineation image of the reference image and a dose map corresponding to the reference image; the floating data comprises a floating image, a delineation image of the floating image and a dose map corresponding to the floating image; performing data separation on the reference data and the floating data according to organ types, wherein the data separation is used to separate image data of each independent organ from the reference data and the floating data; performing morphological registration on the image data of each independent organ to obtain a morphological field corresponding to each independent organ; fusing the morphological field corresponding to each independent organ into a target morphological field, and performing morphological registration on the floating data through the target morphological field.

2. The morphing registration method of claim 1, wherein, The morphological registration on the floating data through the target morphological field comprises: determining a rigid transformation matrix according to the floating image; performing rigid transformation on the floating data according to the rigid transformation matrix to obtain intermediate-state floating data, wherein the intermediate-state floating data comprises a floating image, a delineation image and a dose map after the rigid transformation is completed; performing morphological registration on the intermediate-state floating data through the target morphological field.

3. The method of deformation registration of claim 1, wherein, The data separation on the reference data and the floating data according to organ types comprises: separating each delineation region according to delineation information of each organ in the image to obtain N independent delineation reference data with the same size as the reference data and N independent delineation floating data with the same size as the floating data; segmenting the reference image into N independent organ reference images according to the N independent delineation reference data corresponding to the reference data, and taking an image region of the reference image other than the N independent organ reference images as a background reference image; segmenting the floating image into N independent organ floating images according to the N independent delineation floating data corresponding to the floating data, and taking an image region of the floating image other than the N independent organ floating images as a background floating image.

4. The method of deformable registration of claim 1, wherein, The morphological registration on the image data of each independent organ to obtain a morphological field corresponding to each independent organ comprises: constructing a first function, a second function and a third function, wherein the first function is used to correct contour alignment error between the floating data and the reference data based on each organ; the second function is used to correct contour registration redundancy between the floating data and the reference data based on each organ, wherein the contour registration redundancy represents that the organ contour after registration exceeds the boundary range corresponding to the organ in the reference image; and the third function is used to constrain the deformation degree of each organ in the registration process; performing weighted summation calculation on the first function, the second function and the third function to obtain a target function; performing morphological registration on the image data of each independent organ according to the target function to obtain a morphological field corresponding to each independent organ.

5. The method of deformable registration of claim 4, wherein, The construction of the first function, the second function and the third function comprises: constructing the first function and the second function according to the independent delineation reference data and the independent delineation floating data corresponding to the ith organ, wherein i is a positive integer, the first function is used to determine the content overlap degree between the independent delineation reference data and the independent delineation floating data corresponding to the ith organ; the second function is used to determine the contour redundancy of the independent delineation reference data corresponding to the ith organ relative to the independent delineation floating data corresponding to the ith organ, and to determine the contour redundancy of the independent delineation floating data corresponding to the ith organ relative to the independent delineation reference data corresponding to the ith organ; constructing the third function according to the independent organ floating image and the independent organ reference image corresponding to the ith organ, wherein the third function is used to determine the pixel coincidence degree between the independent organ floating image and the independent organ reference image corresponding to the ith organ.

6. The method of deformable registration of claim 1, wherein, fusing the deformation field corresponding to each independent organ into a target deformation field, comprising: adding and summing the deformation field corresponding to each independent organ to obtain an organ deformation field; obtaining a deformation field between the reference data and the floating data with respect to an image background region; obtaining a deformation field of an overlapping region between the image background region and an organ region; adding and summing the organ deformation field, the deformation field of the image background region and the deformation field of the overlapping region to obtain the target deformation field.

7. The method of deformable registration of claim 6, wherein, obtaining a deformation field between the reference data and the floating data with respect to an image background region, comprising: constructing a fourth function according to a background floating image and a background reference image, wherein the fourth function is used to determine the deformation alignment degree between the background floating image and the background reference image; deformation registration of the background floating image according to the fourth function to obtain the deformation field of the image background region.

8. The morphing registration method of claim 6, wherein, obtaining a deformation field of an overlapping region between the image background region and an organ region, comprising: determining a mask corresponding to the overlapping region between the image background region and the organ region according to the intersection between the organ deformation field and the deformation field of the image background region; extracting first deformation field data corresponding to the overlapping region from the organ deformation field according to the mask; extracting second deformation field data corresponding to the overlapping region from the deformation field of the image background region according to the mask; weighting and summing the first deformation field data and the second deformation field data to obtain the deformation field of the overlapping region.

9. A morphing registration apparatus, characterized by comprising: an obtaining unit, configured to obtain reference data and floating data, wherein the reference data comprises: a reference image, a delineation image of the reference image and a dose map corresponding to the reference image; the floating data comprises: a floating image, a delineation image of the floating image and a dose map corresponding to the floating image; a data separation unit, configured to separately perform data separation on the reference data and the floating data according to organ types, wherein the data separation is used to separate image data of each independent organ from the reference data and the floating data; a first registration unit configured to perform morphological registration on the image data of each independent organ to obtain a corresponding morphological field of each independent organ; a second registration unit configured to fuse the corresponding morphological field of each independent organ into a target morphological field, and perform morphological registration on the floating data through the target morphological field.

10. A computer-readable storage medium, characterized in that, In the computer program, when the computer program is executed, the computer readable storage medium makes the device in which the computer readable storage medium is located execute the morphological registration method in any one of claims 1 to 8. A computer readable storage medium having stored therein a computer program, wherein, when the computer program is executed, the computer readable storage medium makes a device in which the computer readable storage medium is located execute the morphological registration method in any one of claims 1 to 8.

11. An electronic device, comprising: A device comprising one or more processors and memory storing one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors execute the morphological registration method in any one of claims 1 to 8.

Images