An image registration fusion method and device, a storage medium and a computer device

Abstract

The application relates to the technical field of image processing, and particularly discloses an image registration and fusion method and device, a storage medium and computer equipment. The method comprises the following steps: acquiring PET scanning data and CT scanning data; determining a PET field of view angle corresponding to the PET scanning data and a CT field of view angle corresponding to the CT scanning data; performing three-dimensional image reconstruction on the CT scanning data according to the CT field of view angle to obtain a target CT image, and performing three-dimensional image reconstruction on the PET scanning data according to the target CT image and the PET field of view angle to obtain a target PET image; and performing registration and fusion processing on the target CT image and the target PET image to obtain a target fusion image. The application can more accurately and efficiently integrate PET images and CT images, and can effectively improve the registration effect and overall quality of the PET / CT fusion image.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to an image registration and fusion method and apparatus, storage medium, and computer equipment. Background Technology

[0002] With the rise of PET / CT technology, it can support functions such as disease-aided diagnosis and health management. PET / CT is a fusion imaging technique combining PET and CT. PET provides detailed functional and metabolic molecular information about lesions, while CT provides precise anatomical localization. Therefore, PET / CT can obtain tomographic images of the entire body in a single imaging session. PET / CT itself is characterized by its sensitivity, accuracy, specificity, and precise localization, thus playing an irreplaceable role in the early detection of lesions and disease diagnosis.

[0003] The quality of PET / CT fused images directly impacts the accuracy and comprehensiveness of disease diagnosis. However, current PET / CT image registration is not ideal; therefore, improving the registration effect and overall quality of PET / CT fused images has become a pressing technical problem in this field. Summary of the Invention

[0004] In view of this, this application provides an image registration and fusion method, apparatus, storage medium, and computer equipment. By using a field-of-view-based PET / CT image registration and fusion method, image registration and fusion are achieved through a natural simulated image imaging method. This method can more accurately and efficiently fuse PET and CT images into one, effectively improving the registration effect and overall quality of fused PET / CT images.

[0005] According to one aspect of this application, an image registration and fusion method is provided, comprising:

[0006] Acquire PET scan data and CT scan data;

[0007] Determine the PET field of view corresponding to the PET scan data, and determine the CT field of view corresponding to the CT scan data;

[0008] Based on the CT field of view, the CT scan data is reconstructed into a three-dimensional image to obtain a target CT image. Based on the target CT image and the PET field of view, the PET scan data is reconstructed into a three-dimensional image to obtain a target PET image.

[0009] The target CT image and the target PET image are registered and fused to obtain the target fused image.

[0010] According to another aspect of this application, an image registration and fusion apparatus is provided, comprising:

[0011] The scan data acquisition module is used to acquire PET scan data and CT scan data;

[0012] The field of view determination module is used to determine the PET field of view corresponding to the PET scan data and the CT field of view corresponding to the CT scan data;

[0013] The image reconstruction module is used to perform three-dimensional image reconstruction on the CT scan data based on the CT field of view to obtain a target CT image, and to perform three-dimensional image reconstruction on the PET scan data based on the target CT image and the PET field of view to obtain a target PET image;

[0014] The image fusion module is used to register and fuse the target CT image and the target PET image to obtain a target fused image.

[0015] According to another aspect of this application, a storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described image registration and fusion method.

[0016] According to another aspect of this application, a computer device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the program to implement the above-described image registration and fusion method.

[0017] By employing the above technical solutions, the image registration and fusion method, apparatus, storage medium, and computer equipment provided in this application can first acquire PET scan data and CT scan data before performing image registration and fusion. After acquiring the PET scan data and CT scan data, on the one hand, the PET field of view can be determined based on the PET scan data, and on the other hand, the CT field of view can be determined based on the CT scan data. After determining the CT field of view, three-dimensional image reconstruction can be performed on the CT scan data based on the CT field of view, thereby reconstructing the target CT image. After obtaining the target CT image, in order to ensure that the target PET image obtained from the three-dimensional image reconstruction is the same size as the target CT image, when performing three-dimensional reconstruction on the target PET image, three-dimensional image reconstruction can be performed on the PET scan data based on the target CT image and the PET field of view, thereby obtaining a target PET image of the same size as the target CT image. After obtaining the target CT image and the target PET image, the target CT image and the target PET image can be registered with each other, and then fused together to obtain the target fused image, i.e., the PET / CT image. This application embodiment uses a field-of-view-based PET / CT image registration and fusion method to achieve image registration and fusion through a natural simulated image imaging method. This method can more accurately and efficiently fuse PET and CT images into one, effectively improving the registration effect and overall quality of fused PET / CT images.

[0018] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0020] Figure 1 A schematic flowchart of an image registration and fusion method provided in an embodiment of this application is shown;

[0021] Figure 2 This illustration shows a schematic diagram of the field of view of a parallel projection according to an embodiment of this application;

[0022] Figure 3 A flowchart illustrating another image registration and fusion method provided in an embodiment of this application is shown;

[0023] Figure 4A flowchart illustrating another image registration and fusion method provided in an embodiment of this application is shown;

[0024] Figure 5 A schematic diagram of the structure of an image registration and fusion device provided in an embodiment of this application is shown. Detailed Implementation

[0025] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0026] This embodiment provides an image registration and fusion method, such as Figure 1 As shown, the method includes:

[0027] Step 101: Acquire PET scan data and CT scan data;

[0028] The image registration and fusion method provided in this application can be applied to the registration and fusion process of PET (Positron Emission Computed Tomography) images and CT (Computed Tomography) images in the medical field. After the PET image and CT image are registered and fused, a PET / CT image, also known as the target fused image, can be generated. PET / CT stands for Positron Emission Tomography / X-ray Computed Tomography, and it is controlled by a workstation. It is a new type of imaging device that organically combines two advanced imaging technologies, PET (functional metabolic imaging) and CT (anatomical imaging). While PET scans offer unparalleled early detection sensitivity and other advantages compared to other diagnostic equipment, their localization accuracy is limited by the drugs and their mechanisms of action. Therefore, PET and CT were later integrated into a single unit. A small amount of positron-emitting diode (PET) tracer is injected into the body, and a special in vitro detector (PET) probes the distribution of these PET tracers in various organs. Computed tomography (CT) displays the physiological and metabolic functions of major organs, while CT technology precisely locates the distribution of these tracers. This allows the machine to combine the advantages of both PET and CT, maximizing their respective strengths. During scanning, PET and CT images are performed simultaneously as needed, and the workstation fuses the two images for better identification and localization. PET / CT images play an irreplaceable role in disease diagnosis. In PET / CT images, PET provides detailed functional and metabolic molecular information about lesions, while CT provides precise anatomical localization. Therefore, PET / CT can obtain tomographic images of the entire body in a single scan. Before performing image registration and fusion, PET and CT scan data can be acquired. These data can be obtained from the scanning equipment. Specifically, the PET and CT scan data can be whole-body scans of the patient or scans of a specific area, such as the stomach, abdomen, heart, knees, or brain.

[0029] Step 102: Determine the PET field of view corresponding to the PET scan data, and determine the CT field of view corresponding to the CT scan data;

[0030] In this embodiment, after acquiring PET and CT scan data, the PET field of view can be determined based on the PET scan data, and the CT field of view can be determined based on the CT scan data. Specifically, the PET field of view is determined based on the X-axis vector, Y-axis vector, normal vector, pixel size along the X-axis, pixel size along the Y-axis, planar dimensions of the PET imaging plane, center coordinates of the PET imaging plane, and the position data of the first data volume bounding box from the PET scan data. The CT field of view is determined based on the X-axis vector, Y-axis vector, normal vector, pixel size along the X-axis, pixel size along the Y-axis, planar dimensions of the CT imaging plane, center coordinates of the CT imaging plane, and the position data of the second data volume bounding box from the CT scan data. The field of view (FOV) is the visual field angle corresponding to the human eye. When the human eye looks at an object, there is a certain range of visual field above, below, left, right, and in front of the eye. Only objects within this range can be seen; therefore, parameters related to this range are collectively referred to as the visual field angle (FOV). Generally, visual projection methods are divided into perspective projection and parallel projection. However, to prevent distortion of medical images, parallel projection can be used, such as... Figure 2 The image shows the field of view (FOV) of a parallel projection. In parallel projection, the image is transformed onto the projection plane along parallel lines; in perspective projection, the image is transformed onto the projection plane along a straight line converging at a point. For example, regarding the PET field of view, the range of data visible under the PET plane can be determined by using the X-axis vector, Y-axis vector, normal vector, pixel size along the X-axis, pixel size along the Y-axis, plane size of the PET imaging plane, center coordinates of the PET imaging plane, and the position data of the first data volume bounding box from the PET scan data. Then, if the field of view (FOV) under the PET plane is projected using parallel projection, the range of data visible under the PET plane can be projected using parallel projection to obtain the PET field of view, i.e., the PET FOV of the parallel projection. Different field of view sizes result in different sizes of the data range visible under the PET plane.

[0031] Step 103: Perform three-dimensional image reconstruction on the CT scan data based on the CT field of view to obtain the target CT image, and perform three-dimensional image reconstruction on the PET scan data based on the target CT image and the PET field of view to obtain the target PET image;

[0032] In this embodiment, after determining the CT field of view, a 3D image reconstruction can be performed on the CT scan data based on the CT field of view, thereby reconstructing the target CT image. 3D reconstruction is a visualization method that uses a reconstruction algorithm to reconstruct a 3D entity from a series of 2D images and displays the entity on the 2D image for direct viewing and interactive operation by the user. Here, 3D image reconstruction can utilize a ray casting algorithm. The principle of the ray casting algorithm is as follows: assuming that light rays originate from the imaging plane in a parallel manner and penetrate the entire data volume at a certain step size, during the entire process, the maximum voxel value acquired is mapped to the pixel point of the imaging plane through a grayscale table using a trilinear interpolation resampling method, becoming the pixel value of the resulting image, ultimately obtaining the 2D target CT image. After obtaining the target CT image, to ensure that the target PET image obtained from the 3D image reconstruction has the same image size as the target CT image, when performing 3D reconstruction on the target PET image, a 3D image reconstruction can be performed on the PET scan data based on the target CT image and the PET field of view, thereby obtaining a target PET image of the same size as the target CT image.

[0033] Step 104: Register and fuse the target CT image and the target PET image to obtain the target fused image.

[0034] In this embodiment, after obtaining the target CT image and the target PET image, the target CT image and the target PET image can be registered with each other, and then fused together to obtain the target fused image, i.e., the PET / CT image. In the process of disease diagnosis, PET / CT images can be used to quickly and accurately locate lesions, that is, the parts of the body where diseases occur, such as lesions in the stomach, abdomen, heart, knee, and brain.

[0035] Optionally, in this embodiment of the application, step 103, "performing three-dimensional image reconstruction of the PET scan data based on the target CT image and the PET field of view to obtain the target PET image", includes: obtaining the image size and dot pitch of the target CT image, and performing three-dimensional image reconstruction of the PET scan data based on the image size, the dot pitch and the PET field of view to obtain the target PET image.

[0036] In this embodiment, when performing three-dimensional reconstruction of the target PET image, the image size and pixel pitch of the target CT image can be obtained from the reconstructed target CT image. Then, based on the image size, pixel pitch, and PET field of view of the target CT image, the PET scan data can be reconstructed in three dimensions using the same ray projection algorithm to finally obtain the matching target PET image.

[0037] Optionally, in this embodiment, step 102, "determining the PET field of view corresponding to the PET scan data," includes: based on the PET scan data, obtaining first target information, the first target information including the X-axis vector, Y-axis vector, normal vector, pixel size in the X-axis direction, pixel size in the Y-axis direction of the PET imaging plane, plane size of the PET imaging plane, center coordinates of the PET imaging plane, and position information of the first data volume bounding box; based on the first target information, determining a first visible data range, and determining the PET field of view according to the first visible data range and the target projection method; step 102, "determining the CT field of view corresponding to the CT scan data," includes: based on the CT scan data, obtaining second target information, the second target information including the X-axis vector, Y-axis vector, normal vector, pixel size in the X-axis direction, pixel size in the Y-axis direction of the CT imaging plane, plane size of the CT imaging plane, center coordinates of the CT imaging plane, and position information of the second data volume bounding box; based on the second target information, determining a second visible data range, and determining the CT field of view according to the second visible data range and the target projection method.

[0038] In this embodiment, when determining the PET field of view, the X-axis vector, Y-axis vector, normal vector, pixel size in the X-axis direction, pixel size in the Y-axis direction, planar dimensions of the PET imaging plane, center coordinates of the PET imaging plane, and position information of the first data volume bounding box can be identified from the PET scan data, and this information is used as the first target information. Specifically, the physical size of the pixels in the X-axis and Y-axis directions can be determined from the pixel sizes in the X and Y directions, respectively. The position information of the first data volume bounding box can include maximum and minimum position information. The maximum position information can be the position of the data farthest from the origin, and the minimum position information can be the position of the data closest to the origin. From the position information of the first data volume bounding box, it can be seen which data can be displayed in the PET image. Next, using the X-axis vector, Y-axis vector, normal vector, pixel size along the X-axis, pixel size along the Y-axis, planar dimensions of the PET imaging plane, center coordinates of the PET imaging plane, and position information of the first data volume bounding box contained in the first target information, the first visible data range can be determined. From the first visible data range, the first coordinate system and the entire visible data range within the first coordinate system can be determined. Then, based on the first visible data range, the corresponding PET field of view can be determined according to the selected target projection method. Here, the projection method can include perspective projection, parallel projection, etc. Taking parallel projection as an example, based on the first visible data range, the data within the first visible data range can be projected using parallel projection to obtain the PET field of view. Similarly, this method can be used to determine the CT field of view.

[0039] By applying the technical solution of this embodiment, PET scan data and CT scan data can be acquired before image registration and fusion. After acquiring the PET and CT scan data, the PET field of view can be determined based on the PET scan data, and the CT field of view can be determined based on the CT scan data. After determining the CT field of view, three-dimensional image reconstruction can be performed on the CT scan data based on the CT field of view, thereby reconstructing the target CT image. After obtaining the target CT image, in order to ensure that the target PET image obtained from the three-dimensional image reconstruction is the same size as the target CT image, when performing three-dimensional reconstruction on the target PET image, the PET scan data can be reconstructed based on the target CT image and the PET field of view, thereby obtaining a target PET image of the same size as the target CT image. After obtaining the target CT image and the target PET image, they can be registered with each other and then fused together to obtain the target fused image, i.e., the PET / CT image. This application embodiment uses a field-of-view-based PET / CT image registration and fusion method to achieve image registration and fusion through a natural simulated image imaging method. This method can more accurately and efficiently fuse PET and CT images into one, effectively improving the registration effect and overall quality of fused PET / CT images.

[0040] Furthermore, as a refinement and extension of the specific implementation methods of the above embodiments, and to fully illustrate the specific implementation process of this embodiment, another image registration and fusion method is provided, such as... Figure 3 As shown, the method includes:

[0041] Step 201: Acquire PET scan data and CT scan data;

[0042] Step 202: Determine the PET field of view corresponding to the PET scan data, and determine the CT field of view corresponding to the CT scan data;

[0043] Step 203: Perform three-dimensional image reconstruction on the CT scan data based on the CT field of view to obtain the target CT image, and perform three-dimensional image reconstruction on the PET scan data based on the target CT image and the PET field of view to obtain the target PET image;

[0044] Step 204: Perform coordinate transformation on the target PET image according to the transformation matrix to obtain the target PET image after coordinate transformation. The transformation matrix is ​​used to indicate the transformation from the first coordinate system corresponding to the target PET image to the second coordinate system corresponding to the target CT image.

[0045] In this embodiment, after reconstructing the target PET image and the target CT image respectively, in order to register and fuse the target PET image and the target CT image, the target CT image can be used as a fixed image, and the target PET image as a moving image. Next, the target PET image can be subjected to coordinate transformation processing according to a transformation matrix, so that the coordinate system corresponding to the target PET image changes from the original first coordinate system to a second coordinate system consistent with the target CT image. Thus, the target PET image after coordinate transformation can be registered and fused with the target CT image. Figure 4 As shown, firstly, the target PET image undergoes coordinate transformation. Here, the target PET image is the moving image in the figure; specifically, the moving image can be a PET image of the patient's head, and the fixed image can be a CT image of the patient's head. The coordinate system corresponding to the moving image can be the first coordinate system, while the coordinate system corresponding to the fixed image can be the second coordinate system. By performing coordinate transformation on the moving image according to the transformation matrix, the moving image is transformed from its original first coordinate system to the second coordinate system consistent with the fixed image, thus fulfilling the basic conditions for registration between the fixed and moving images, and allowing subsequent registration and fusion steps to proceed.

[0046] Step 205: Determine the first center of the target PET image, the second center of the target CT image, and the target registration center; perform image registration on the coordinate-transformed target PET image and the target CT image; and perform fusion processing after image registration to obtain the target fused image.

[0047] In this embodiment, after transforming the target PET image from the first coordinate system to the second coordinate system, the registration center between the target PET image and the target CT image can be found. Specifically, a first center can be found in the target PET image, and a second center can be found in the target CT image. Furthermore, the overlapping portion between the target PET image and the target CT image can be found, and the center of this overlapping portion can be used as the target registration center. Then, the target registration center can be used as the basis for registration between the target PET image and the target CT image. Using the target registration center and the first center, the position of the target PET image after coordinate transformation is fixed. Then, using the target registration center and the second center, the position of the target CT image is fixed, thereby achieving registration between the target PET image and the target CT image. Finally, fusion processing can be performed to obtain the target fused image, i.e., the PET / CT image.

[0048] In this embodiment of the application, optionally, the step 205 of "determining the first center of the target PET image, the second center of the target CT image, and the target registration center" includes: determining the coordinates of a first vertex, a first point distance, and the planar dimensions of the PET imaging plane based on the PET scan data, and determining the first center of the target PET image based on the first vertex coordinates, the first point distance, and the planar dimensions of the PET imaging plane; determining the coordinates of a second vertex, a second point distance, and the planar dimensions of the CT imaging plane based on the CT scan data, and determining the second center of the target CT image based on the second vertex coordinates, the second point distance, and the planar dimensions of the CT imaging plane; determining the imaging overlap range based on the PET scan data and the CT scan data, and identifying the center coordinates of the imaging overlap range as the target registration center.

[0049] In this embodiment, when determining the first center of the target PET image, the coordinates of the first vertex, the first pixel distance, and the planar dimensions of the PET imaging plane can be identified from the acquired PET scan data. The first vertex coordinates can be the coordinates of the upper left corner of the PET imaging plane, the first pixel distance can be the pixel distance on the PET imaging plane, and the planar dimensions of the PET imaging plane can be the dimensions of the target PET image's imaging plane in the x-axis and y-axis directions. Then, based on this information, the first center of the target PET image can be determined. Similarly, the second center of the target CT image can be determined using this method. The second vertex coordinates can be the coordinates of the upper left corner of the CT imaging plane, the second pixel distance can be the pixel distance on the CT imaging plane, and the planar dimensions of the CT imaging plane can be the dimensions of the target CT image's imaging plane in the x-axis and y-axis directions.

[0050] When determining the target registration center, the overlapping area of ​​the target PET image and the target CT image can be found based on the PET scan data and CT scan data. Then, the center coordinates of the overlapping area can be determined and used as the target registration center.

[0051] Optionally, in this embodiment of the application, step 205, "performing fusion processing after image registration to obtain a target fused image", includes: after image registration, performing fusion processing on the registered images according to the first weight corresponding to the target PET image and the second weight corresponding to the target CT image to obtain a target fused image.

[0052] In this embodiment, after the target PET image and target CT image are registered following coordinate transformation, the two images can be fused according to a first weight pre-set for the target PET image and a second weight pre-set for the target CT image to obtain the final target fused image. The first and second weights can each be set to 50%, or set according to other requirements, with the sum of the first and second weights being 100%.

[0053] Optionally, before step 204, the method further includes: determining an X-axis vector, a Y-axis vector, and a normal vector from the PET scan data; generating a flip sub-matrix based on the X-axis vector, the Y-axis vector, and the normal vector; determining a first origin of a first coordinate system corresponding to the PET scan data and a second origin of a second coordinate system corresponding to the CT scan data; generating a translation sub-matrix based on the first origin and the second origin; generating a scaling sub-matrix based on the first coordinate system and the second coordinate system; and generating the transformation matrix based on the flip sub-matrix, the translation sub-matrix, and the scaling sub-matrix.

[0054] In this embodiment, the transformation matrix can consist of three parts: a flip submatrix, a translation submatrix, and a scaling submatrix. The transformation matrix can be written in the form of matrix 1 below, where a 11 ~a 33 Form a flipped submatrix, t x ~t z Form a scaling submatrix, p x ~p z Form a translation submatrix, where s is a constant.

[0055]

[0056] Specifically, the X-axis vector, Y-axis vector, and normal vector can be determined from PET scan data. Then, a flipped submatrix can be generated based on these vectors. Here, a 11 a 12 a 13 It can be used to represent the X-axis vector, a 21 a 22 a 23 It can be used to represent the Y-axis vector, a 31 a 32 a 33It can be used to represent normal vectors. Furthermore, it can determine the first origin of the first coordinate system corresponding to PET scan data and the second origin of the second coordinate system corresponding to CT scan data. Then, based on the first and second origins, the translation dimensions in the X, Y, and Z axes are determined, and corresponding translation sub-matrices are generated. It can also determine the scaling from the first coordinate system to the second coordinate system based on the first and second coordinate systems, and generate corresponding scaling sub-matrices.

[0057] Optionally, before step 201, the method further includes: filtering the initial PET data and initial CT data by direction source, removing initial PET data and initial CT data from non-target direction sources to obtain the PET scan data and CT scan data; and / or, filtering the initial PET data and initial CT data by image index, removing initial PET data and initial CT data with duplicate image indexes to obtain the PET scan data and CT scan data; and / or, filtering the initial PET data and initial CT data by inter-slice spacing, removing initial PET data and initial CT data from non-target inter-slice spacings to obtain the PET scan data and CT scan data.

[0058] In this embodiment, to avoid image distortion or value errors during subsequent 3D image reconstruction, PET scan data can be identified from the acquired initial PET data, and CT scan data can be identified from the initial CT data. Since the identified PET and CT scan data are obtained from the same scan, image distortion or value errors can be avoided. Both the initial PET and initial CT data correspond to a direction source, which can include head-to-toe scanning, foot-to-head scanning, etc. The direction source with the most occurrences in the initial PET and initial CT data can be used as the target direction source. Then, non-target direction sources are removed from the initial PET and initial CT data, resulting in the PET and CT scan data. Furthermore, the initial PET and initial CT data also correspond to image indexes. Initial PET and initial CT data with duplicate image indexes can be removed, thus obtaining the PET and CT scan data. Initial PET and CT data can correspond to different slice intervals. Since different slice intervals actually belong to different scans, the slice interval with the highest frequency in the initial PET and CT data can be used as the target slice interval. Then, by removing non-target slice intervals from the initial PET and CT data, the remaining data are the PET and CT scan data. This embodiment of the application, by ensuring that the PET and CT scan data were obtained during the same scan before performing 3D image reconstruction, effectively guarantees the accuracy of subsequent 3D image reconstruction.

[0059] Furthermore, as Figure 1 To specifically implement the method, this application provides an image registration and fusion apparatus, such as... Figure 5 As shown, the device includes:

[0060] The scan data acquisition module is used to acquire PET scan data and CT scan data;

[0061] The field of view determination module is used to determine the PET field of view corresponding to the PET scan data and the CT field of view corresponding to the CT scan data;

[0062] The image reconstruction module is used to perform three-dimensional image reconstruction on the CT scan data based on the CT field of view to obtain a target CT image, and to perform three-dimensional image reconstruction on the PET scan data based on the target CT image and the PET field of view to obtain a target PET image;

[0063] The image fusion module is used to register and fuse the target CT image and the target PET image to obtain a target fused image.

[0064] Optionally, the field of view determination module includes:

[0065] The first information acquisition unit is used to acquire first target information based on the PET scan data. The first target information includes the X-axis vector, Y-axis vector, normal vector, pixel size in the X-axis direction, pixel size in the Y-axis direction, plane size of the PET imaging plane, center coordinates of the PET imaging plane, and position information of the first data volume bounding box.

[0066] The first field of view determination unit is used to determine the first visible data range based on the first target information, and to determine the PET field of view according to the first visible data range and the target projection method.

[0067] The field of view determination module further includes:

[0068] The second information acquisition unit is used to acquire second target information based on the CT scan data. The second target information includes the X-axis vector, Y-axis vector, normal vector, pixel size in the X-axis direction, pixel size in the Y-axis direction, plane size of the CT imaging plane, center coordinates of the CT imaging plane, and position information of the second data volume bounding box.

[0069] The second field of view determination unit is used to determine the second visible data range based on the second target information, and to determine the CT field of view according to the second visible data range and the target projection method.

[0070] Optionally, the image reconstruction module is used for:

[0071] The image size and dot pitch of the target CT image are obtained. Based on the image size, the dot pitch, and the PET field of view, a three-dimensional image reconstruction is performed on the PET scan data to obtain the target PET image.

[0072] Optionally, the image fusion module includes:

[0073] A coordinate transformation processing unit is used to perform coordinate transformation processing on the target PET image according to a transformation matrix to obtain a coordinate-transformed target PET image. The transformation matrix is ​​used to indicate the transformation from the first coordinate system corresponding to the target PET image to the second coordinate system corresponding to the target CT image.

[0074] The registration and fusion unit is used to determine the first center of the target PET image, the second center of the target CT image, and the target registration center, perform image registration on the coordinate-transformed target PET image and the target CT image, and perform fusion processing after image registration to obtain the target fused image.

[0075] Optionally, the registration and fusion unit is used for:

[0076] After image registration, the registered images are fused according to the first weight corresponding to the target PET image and the second weight corresponding to the target CT image to obtain the target fused image.

[0077] Optionally, the device further includes:

[0078] The first submatrix generation module is used to determine the X-axis vector, Y-axis vector, and normal vector from the PET scan data before performing coordinate transformation processing on the target PET image according to the transformation matrix, and to generate a flipped submatrix based on the X-axis vector, the Y-axis vector, and the normal vector.

[0079] The second submatrix generation module is used to determine the first origin of the first coordinate system corresponding to the PET scan data and the second origin of the second coordinate system corresponding to the CT scan data, and to generate a translation submatrix based on the first origin and the second origin.

[0080] The third submatrix generation module is used to generate a scaled submatrix based on the first coordinate system and the second coordinate system;

[0081] The transformation matrix generation module is used to generate the transformation matrix based on the flip submatrix, the translation submatrix, and the scaling submatrix.

[0082] Optionally, the registration and fusion unit is further configured to:

[0083] Based on the PET scan data, the coordinates of a first vertex, the first point distance, and the planar dimensions of the PET imaging plane are determined. Then, based on the first vertex coordinates, the first point distance, and the planar dimensions of the PET imaging plane, a first center of the target PET image is determined. Based on the CT scan data, the coordinates of a second vertex, the second point distance, and the planar dimensions of the CT imaging plane are determined. Then, based on the second vertex coordinates, the second point distance, and the planar dimensions of the CT imaging plane, a second center of the target CT image is determined. Based on the PET scan data and the CT scan data, the imaging overlap range is determined, and the center coordinates of the imaging overlap range are identified as the target registration center.

[0084] Optionally, the device further includes:

[0085] The rejection module is used to, before acquiring PET scan data and CT scan data, filter the initial PET data and initial CT data by direction source, rejecting the initial PET data and initial CT data from non-target direction sources, thus obtaining the PET scan data and CT scan data; and / or, filter the initial PET data and initial CT data by image index, rejecting the initial PET data and initial CT data with duplicate image indexes, thus obtaining the PET scan data and CT scan data; and / or, filter the initial PET data and initial CT data by inter-slice spacing, rejecting the initial PET data and initial CT data from non-target inter-slice spacings, thus obtaining the PET scan data and CT scan data.

[0086] It should be noted that other corresponding descriptions of the functional units involved in the image registration and fusion apparatus provided in this application embodiment can be found by referring to... Figures 1 to 4 The corresponding descriptions in the method will not be repeated here.

[0087] Based on the above, Figures 1 to 4 Accordingly, this application also provides a storage medium storing a computer program, which, when executed by a processor, implements the above-described method. Figures 1 to 4 The image registration and fusion method shown is illustrated.

[0088] Based on this understanding, the technical solution of this application can be embodied in the form of a software product. This software product can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or portable hard drive), and includes several instructions to cause a computer device (such as a personal computer, server, or network device) to execute the methods described in the various implementation scenarios of this application.

[0089] Based on the above, Figures 1 to 4 The method shown, and Figure 5 To achieve the above objectives, the present application also provides a computer device, specifically a personal computer, server, network device, etc., as shown in the virtual device embodiment. This computer device includes a storage medium and a processor; the storage medium stores a computer program; the processor executes the computer program to achieve the above-described objectives. Figures 1 to 4 The image registration and fusion method shown is illustrated.

[0090] Optionally, the computer device may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Bluetooth interfaces, Wi-Fi interfaces), etc.

[0091] Those skilled in the art will understand that the computer device structure provided in this embodiment does not constitute a limitation on the computer device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0092] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages and stores the hardware and software resources of a computer device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software within the physical device.

[0093] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented using software plus necessary general-purpose hardware platforms, or it can be implemented using hardware. Before performing image registration and fusion, PET scan data and CT scan data can be acquired first. After acquiring the PET scan data and CT scan data, on the one hand, the PET field of view can be determined based on the PET scan data, and on the other hand, the CT field of view can be determined based on the CT scan data. After determining the CT field of view, three-dimensional image reconstruction can be performed on the CT scan data based on the CT field of view, thereby reconstructing the target CT image. After obtaining the target CT image, in order to ensure that the target PET image obtained by three-dimensional image reconstruction is the same size as the target CT image, when performing three-dimensional reconstruction on the target PET image, three-dimensional image reconstruction can be performed on the PET scan data based on the target CT image and the PET field of view, thereby obtaining a target PET image of the same size as the target CT image. After obtaining the target CT image and the target PET image, the target CT image and the target PET image can be registered with each other, and then fused together to obtain the target fused image, that is, the PET / CT image. This application embodiment uses a field-of-view-based PET / CT image registration and fusion method to achieve image registration and fusion through a natural simulated image imaging method. This method can more accurately and efficiently fuse PET and CT images into one, effectively improving the registration effect and overall quality of fused PET / CT images.

[0094] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of a preferred embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing this application. Those skilled in the art will understand that the modules in the apparatus of the embodiment can be distributed within the apparatus of the embodiment as described, or can be modified to be located in one or more apparatuses different from this embodiment. The modules of the above-described embodiment can be combined into one module, or further divided into multiple sub-modules.

[0095] The serial numbers in this application are for descriptive purposes only and do not represent the superiority or inferiority of any particular implementation scenario. The above disclosures are merely a few specific implementation scenarios of this application; however, this application is not limited thereto, and any variations conceived by those skilled in the art should fall within the protection scope of this application.

Claims

1. An image registration and fusion method, characterized in that, include: Acquire PET scan data and CT scan data; Determine the PET field of view corresponding to the PET scan data, and determine the CT field of view corresponding to the CT scan data; Based on the CT field of view, the CT scan data is reconstructed into a three-dimensional image to obtain a target CT image. Based on the target CT image and the PET field of view, the PET scan data is reconstructed into a three-dimensional image to obtain a target PET image. The target PET image is subjected to coordinate transformation processing according to the transformation matrix to obtain the coordinate-transformed target PET image. The transformation matrix is ​​used to indicate the transformation from the first coordinate system corresponding to the target PET image to the second coordinate system corresponding to the target CT image. A first center of the target PET image and a second center of the target CT image are determined, and the overlapping portion between the target PET image and the target CT image is determined. The center of the overlapping portion is found as the target registration center. The position of the target PET image after coordinate transformation is fixed using the target registration center and the first center. Then, the position of the target CT image is fixed using the target registration center and the second center. Image registration is performed on the target PET image and the target CT image after coordinate transformation. After image registration, fusion processing is performed to obtain the target fused image.

2. The method according to claim 1, characterized in that, Determining the PET field of view corresponding to the PET scan data includes: Based on the PET scan data, first target information is obtained, which includes the X-axis vector, Y-axis vector, normal vector, pixel size in the X-axis direction, pixel size in the Y-axis direction, plane size of the PET imaging plane, center coordinates of the PET imaging plane, and position information of the first data volume bounding box. Based on the first target information, a first visible data range is determined, and the PET field of view is determined according to the first visible data range and the target projection method. Determining the CT field of view corresponding to the CT scan data includes: Based on the CT scan data, second target information is obtained. The second target information includes the X-axis vector, Y-axis vector, normal vector, pixel size in the X-axis direction, pixel size in the Y-axis direction, plane size of the CT imaging plane, center coordinates of the CT imaging plane, and position information of the second data volume bounding box. Based on the second target information, a second visible data range is determined, and the CT field of view is determined according to the second visible data range and the target projection method.

3. The method according to claim 2, characterized in that, The step of reconstructing a three-dimensional image from the PET scan data based on the target CT image and the PET field of view to obtain the target PET image includes: The image size and dot pitch of the target CT image are obtained. Based on the image size, the dot pitch, and the PET field of view, a three-dimensional image reconstruction is performed on the PET scan data to obtain the target PET image.

4. The method according to claim 1, characterized in that, The step of performing fusion processing after image registration to obtain the target fused image includes: After image registration, the registered images are fused according to the first weight corresponding to the target PET image and the second weight corresponding to the target CT image to obtain the target fused image.

5. The method according to claim 4, characterized in that, Before performing coordinate transformation on the target PET image according to the transformation matrix, the method further includes: The X-axis vector, Y-axis vector, and normal vector are determined from the PET scan data, and a flipped submatrix is ​​generated based on the X-axis vector, the Y-axis vector, and the normal vector. Determine the first origin of the first coordinate system corresponding to the PET scan data and the second origin of the second coordinate system corresponding to the CT scan data, and generate a translation sub-matrix based on the first origin and the second origin; Generate a scaling submatrix based on the first coordinate system and the second coordinate system; The transformation matrix is ​​generated based on the flip submatrix, the translation submatrix, and the scaling submatrix.

6. The method according to claim 5, characterized in that, Determining the first center of the target PET image, the second center of the target CT image, and the target registration center includes: Based on the PET scan data, the coordinates of the first vertex, the first point distance, and the planar dimensions of the PET imaging plane are determined. Based on the coordinates of the first vertex, the first point distance, and the planar dimensions of the PET imaging plane, the first center of the target PET image is determined. Based on the CT scan data, the coordinates of the second vertex, the second point distance, and the planar dimensions of the CT imaging plane are determined. Based on the coordinates of the second vertex, the second point distance, and the planar dimensions of the CT imaging plane, the second center of the target CT image is determined. Based on the PET scan data and the CT scan data, the imaging overlap range is determined, and the center coordinates of the imaging overlap range are identified as the target registration center.

7. The method according to claim 1, characterized in that, Before acquiring PET scan data and CT scan data, the method further includes: The initial PET and CT data are filtered by direction of origin, and the initial PET and CT data from non-target direction sources are removed to obtain the PET scan data and CT scan data; and / or, The initial PET and initial CT data are filtered using image indexing to remove duplicate initial PET and CT data, thus obtaining the PET scan data and CT scan data; and / or, The initial PET and CT data are filtered by inter-slice spacing, and the initial PET and CT data with non-target inter-slice spacing are removed to obtain the PET scan data and CT scan data.

8. An image registration and fusion device, characterized in that, include: The scan data acquisition module is used to acquire PET scan data and CT scan data; The field of view determination module is used to determine the PET field of view corresponding to the PET scan data and the CT field of view corresponding to the CT scan data; The image reconstruction module is used to perform three-dimensional image reconstruction on the CT scan data based on the CT field of view to obtain a target CT image, and to perform three-dimensional image reconstruction on the PET scan data based on the target CT image and the PET field of view to obtain a target PET image; A coordinate transformation processing unit is used to perform coordinate transformation processing on the target PET image according to a transformation matrix to obtain a coordinate-transformed target PET image. The transformation matrix is ​​used to indicate the transformation from the first coordinate system corresponding to the target PET image to the second coordinate system corresponding to the target CT image. The registration and fusion unit is used to determine the first center of the target PET image and the second center of the target CT image, and to determine the overlapping portion between the target PET image and the target CT image. The center of the overlapping portion is found as the target registration center. The target registration center and the first center are used to fix the position of the target PET image after coordinate transformation. Then, the target registration center and the second center are used to fix the position of the target CT image, so as to perform image registration on the target PET image and the target CT image after coordinate transformation. After image registration, fusion processing is performed to obtain the target fused image.

9. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

10. A computer device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 7.

Images