Cardiac image reconstruction method, device, computer equipment and storage medium

Abstract

The present application relates to a cardiac image reconstruction method, device, computer equipment and storage medium. The method comprises: acquiring cardiac scan data of a scanned object; reconstructing the cardiac scan data using a first convolution kernel reconstruction algorithm to obtain a first cardiac reconstructed image of the scanned object; reconstructing the cardiac scan data using a second convolution kernel reconstruction algorithm to obtain a second cardiac reconstructed image of the scanned object; and obtaining a cardiac reconstructed image of the scanned object based on the first cardiac reconstructed image and the second cardiac reconstructed image. The method can ensure that the obtained cardiac reconstructed image of the scanned object has less noise while ensuring resolution, thereby improving the quality of the obtained cardiac reconstructed image of the scanned object.

Description

Technical Field

[0001] The present application relates to the field of medical imaging technology, and in particular to a cardiac image reconstruction method, apparatus, computer equipment and storage medium. Background Art

[0002] Heart stents, also known as coronary artery stents, are commonly used medical devices in cardiac interventional surgery, which have the function of dredging arterial blood vessels. The reconstruction of cardiac images is a common image reconstruction method in clinical practice, and cardiac reconstruction images are of great significance for the diagnosis of cardiovascular diseases.

[0003] In traditional technology, when the existing cardiac reconstruction algorithm is used to reconstruct the image of the coronary artery with the stent, the hardening effect of the stent will cause halo artifacts around the stent, which will cause the morphological structure of the stent to become blurred. Some tissues inside the stent may also be affected by the artifacts, resulting in a low resolution of the reconstructed image.

[0004] Therefore, the traditional cardiac image reconstruction algorithm has the problem of low resolution of the reconstructed image. Summary of the invention

[0005] Based on this, it is necessary to provide a cardiac image reconstruction method, apparatus, computer equipment and storage medium that can improve the resolution of cardiac reconstructed images in order to solve the above technical problems.

[0006] A cardiac image reconstruction method, the method comprising:

[0007] Acquiring cardiac scan data of a scanned subject;

[0008] Reconstructing the heart scan data using a first convolution kernel reconstruction algorithm to obtain a first heart reconstructed image of the scanned object;

[0009] Reconstructing the heart scan data using a second convolution kernel reconstruction algorithm to obtain a second heart reconstructed image of the scanned object;

[0010] A heart reconstructed image of the scanned object is obtained according to the first heart reconstructed image and the second heart reconstructed image.

[0011] In one embodiment, obtaining the cardiac reconstructed image of the scanned object according to the first cardiac reconstructed image and the second cardiac reconstructed image includes:

[0012] performing filtering processing on the first cardiac reconstructed image to obtain a processed first cardiac reconstructed image;

[0013] Obtaining a weighted coefficient of a region of interest according to the second heart reconstructed image;

[0014] The processed first cardiac reconstructed image and the second cardiac reconstructed image are weightedly combined according to the weighted coefficient of the region of interest to obtain a cardiac reconstructed image of the scanned object.

[0015] In one embodiment, the region of interest is a region corresponding to the stent, and obtaining a weighted weight coefficient of the region of interest according to the second heart reconstructed image includes:

[0016] performing image segmentation on the second heart reconstructed image to obtain a stent mask image in the second heart reconstructed image;

[0017] A weighted coefficient of the region of interest is obtained according to the stent mask image.

[0018] In one embodiment, the weighted merging of the processed first cardiac reconstructed image and the second cardiac reconstructed image according to the weighted coefficient of the region of interest to obtain the cardiac reconstructed image of the scanned object includes:

[0019] performing weighted processing on the processed first cardiac reconstructed image and the second cardiac reconstructed image according to the weighted coefficient of the region of interest to obtain a weighted first cardiac reconstructed image and a weighted second cardiac reconstructed image;

[0020] The weighted first heart reconstructed image and the weighted second heart reconstructed image are combined to obtain a heart reconstructed image of the scanned object.

[0021] In one embodiment, performing weighted processing on the processed first cardiac reconstructed image and the second cardiac reconstructed image according to the weighted weight coefficient of the region of interest to obtain the weighted first cardiac reconstructed image and the weighted second cardiac reconstructed image includes:

[0022] Using the weighted coefficient of the region of interest, weighted processing is performed on the processed first cardiac reconstructed image to obtain the weighted first cardiac reconstructed image;

[0023] According to the weighted weight coefficient of the region of interest, acquiring the weighted weight coefficient of the second heart reconstructed image;

[0024] The second cardiac reconstructed image is weighted by using the weighted coefficient of the second cardiac reconstructed image to obtain the weighted second cardiac reconstructed image.

[0025] In one of the embodiments, the sum of the weighted weight coefficient of the second cardiac reconstructed image and the weighted weight coefficient of the region of interest is 1.

[0026] In one embodiment, filtering the first cardiac reconstructed image to obtain the processed first cardiac reconstructed image includes:

[0027] The first cardiac reconstructed image is filtered using a bilateral filter to obtain the processed first cardiac reconstructed image.

[0028] A cardiac image reconstruction device, comprising:

[0029] An acquisition module, used for acquiring cardiac scan data of a scanned object;

[0030] A first reconstruction module, configured to reconstruct the heart scan data using a first convolution kernel reconstruction algorithm to obtain a first heart reconstructed image of the scanned object;

[0031] A second reconstruction module, used for reconstructing the heart scan data by using a second convolution kernel reconstruction algorithm to obtain a second heart reconstructed image of the scanned object;

[0032] A merging module is used to obtain a heart reconstructed image of the scanned object according to the first heart reconstructed image and the second heart reconstructed image.

[0033] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0034] Acquiring cardiac scan data of a scanned subject;

[0035] Reconstructing the heart scan data using a first convolution kernel reconstruction algorithm to obtain a first heart reconstructed image of the scanned object;

[0036] Reconstructing the heart scan data using a second convolution kernel reconstruction algorithm to obtain a second heart reconstructed image of the scanned object;

[0037] A heart reconstructed image of the scanned object is obtained according to the first heart reconstructed image and the second heart reconstructed image.

[0038] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0039] Acquiring cardiac scan data of a scanned subject;

[0040] Reconstructing the heart scan data using a first convolution kernel reconstruction algorithm to obtain a first heart reconstructed image of the scanned object;

[0041] Reconstructing the heart scan data using a second convolution kernel reconstruction algorithm to obtain a second heart reconstructed image of the scanned object;

[0042] A heart reconstructed image of the scanned object is obtained according to the first heart reconstructed image and the second heart reconstructed image.

[0043] The above-mentioned cardiac image reconstruction method, device, computer equipment and storage medium can reconstruct the acquired cardiac scanning data of the scanned object by using a first convolution kernel reconstruction algorithm to obtain a first cardiac reconstructed image of the scanned object, and can reconstruct the acquired cardiac scanning data of the scanned object by using a second convolution kernel reconstruction algorithm to obtain a second cardiac reconstructed image of the scanned object, so that the cardiac reconstructed image of the scanned object can be obtained based on the obtained first cardiac reconstructed image and the second cardiac reconstructed image, so that the obtained cardiac reconstructed image of the scanned object is obtained by reconstructing the cardiac scan of the scanned object by two different convolution kernel reconstruction algorithms, avoiding the problem of low resolution or high noise in the obtained reconstructed image when reconstructing the cardiac scanning data of the scanned object by using a single convolution kernel reconstruction algorithm, so that the obtained cardiac reconstructed image of the scanned object can have low noise while ensuring the resolution, thereby improving the quality of the obtained cardiac reconstructed image of the scanned object. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A diagram showing an application environment of a cardiac image reconstruction method in an embodiment;

[0045] Figure 2 is a schematic flow chart of a cardiac image reconstruction method in one embodiment;

[0046] Figure 3 is a schematic flow chart of a cardiac image reconstruction method in another embodiment;

[0047] Figure 3a is a schematic diagram of comparison of filtered reconstructed cardiac images in one embodiment;

[0048] Figure 4 is a schematic flow chart of a cardiac image reconstruction method in another embodiment;

[0049] Figure 4a A schematic diagram of weighted weight coefficients in one embodiment;

[0050] Figure 5 is a schematic flow chart of a cardiac image reconstruction method in another embodiment;

[0051] Figure 5a is a schematic diagram of comparison between a first heart reconstructed image after weighted processing and a second heart reconstructed image after weighted processing in one embodiment;

[0052] Figure 5b is a schematic diagram for comparing different heart reconstruction images in one embodiment;

[0053] Figure 6 is a schematic flow chart of a cardiac image reconstruction method in one embodiment;

[0054] Figure 7 FIG. 4 is a structural block diagram of a cardiac image reconstruction device in one embodiment. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] The cardiac image reconstruction method provided in the embodiment of the present application can be applied to Figure 1 The computer device shown. The computer device includes a processor and a memory connected by a system bus, and a computer program is stored in the memory. When the processor executes the computer program, the steps of the following method embodiment can be executed. Optionally, the computer device may also include a network interface, a display screen and an input device. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory, and the non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. Optionally, the computer device can be a server, a personal computer, a personal digital assistant, or other terminal devices, such as a tablet computer, a mobile phone, etc., or a cloud or remote server. The embodiment of the present application does not limit the specific form of the computer device.

[0057] In one embodiment, Figure 2 As shown, a cardiac image reconstruction method is provided, which is applied to Figure 1 The computer device in the example is used to illustrate, including the following steps:

[0058] S201, obtaining heart scan data of a scanned object.

[0059] The heart scan data of the scanned object is data obtained by placing the scanned object on a workbench of a scanner of a computer tomography imaging device, bringing the scanned object into a scanning detection range of the scanner, and performing a heart scan and photographing.

[0060] Specifically, the computer device acquires the heart scan data of the scanned object. Optionally, the computer device can acquire the heart scan data of the scanned object in real time from a computer tomography imaging device, or can acquire the heart scan data of the scanned object from a PACS (Picture Archiving and Communication Systems) server.

[0061] S202: Reconstruct the heart scan data using a first convolution kernel reconstruction algorithm to obtain a first heart reconstructed image of the scanned object.

[0062] Specifically, the computer device reconstructs the above-mentioned heart scan data using a first convolution kernel reconstruction algorithm to obtain a first heart reconstructed image of the scanned object. Optionally, the first convolution kernel can be a sharp convolution kernel. It should be noted that the reconstructed image obtained by the sharp convolution kernel retains more high-frequency components after filtering, and the detail information is better preserved, but the noise information is also enhanced at the same time. Optionally, the reconstruction algorithm in this embodiment can be a FBP (Filtered Back Projection) algorithm. It can be understood that the sharpness of the convolution kernel determines the resolution of the reconstructed image, but the higher the resolution, the greater the image noise.

[0063] S203, reconstructing the heart scan data using a second convolution kernel reconstruction algorithm to obtain a second heart reconstructed image of the scanned object.

[0064] Specifically, the computer device reconstructs the above-mentioned heart scan data using a second convolution kernel reconstruction algorithm to obtain a second heart reconstruction image of the scanned object. Optionally, the second convolution kernel can be a smooth convolution kernel. It should be noted that the reconstructed image obtained by the smooth convolution kernel retains more low-frequency components, has less noise, and is suitable for viewing soft tissues, but the detail information is not as clear as the image of the sharp convolution kernel, such as the structure of the heart stent. Optionally, the reconstruction algorithm in this embodiment can be an FBP (Filtered Back Projection, convolution back projection) algorithm. In this embodiment, the first convolution kernel has a higher sharpness than the second convolution kernel, and the cutoff frequency parameter corresponding to the first convolution kernel can be greater than the cutoff frequency parameter of the second convolution kernel. In one embodiment, the first convolution kernel and the second convolution kernel include the data amplitude kernel frequency of the corresponding convolution kernel. The cutoff frequency of the first convolution kernel is greater than the preset frequency, and the cutoff frequency of the second convolution kernel is less than the preset frequency. The first convolution kernel reconstruction algorithm is a reconstruction method using the first convolution kernel as a reconstruction convolution kernel, and the second convolution kernel reconstruction algorithm is a reconstruction method using the second convolution kernel as a reconstruction convolution kernel.

[0065] S204: Obtain a heart reconstructed image of the scanned object according to the first heart reconstructed image and the second heart reconstructed image.

[0066] Specifically, the computer device obtains a cardiac reconstruction image of the scanned object based on the first cardiac reconstruction image and the second cardiac reconstruction image obtained above. Optionally, the computer device may weightedly merge the first cardiac reconstruction image and the second cardiac reconstruction image based on the weighted weight value of the first cardiac reconstruction image and the weighted weight value of the second cardiac reconstruction image to obtain the cardiac reconstruction image of the scanned object. Optionally, the first cardiac reconstruction image and / or the second cardiac reconstruction image may be filtered before weighted merging.

[0067] In the above-mentioned cardiac image reconstruction method, the computer device can reconstruct the acquired cardiac scanning data of the scanned object by using a first convolution kernel reconstruction algorithm to obtain a first cardiac reconstructed image of the scanned object, and can reconstruct the acquired cardiac scanning data of the scanned object by using a second convolution kernel reconstruction algorithm to obtain a second cardiac reconstructed image of the scanned object, so that the cardiac reconstructed image of the scanned object can be obtained based on the obtained first cardiac reconstructed image and the second cardiac reconstructed image, so that the obtained cardiac reconstructed image of the scanned object is obtained by reconstructing the cardiac scan of the scanned object by two different convolution kernel reconstruction algorithms, avoiding the problem of low resolution or high noise in the obtained reconstructed image by using a single convolution kernel reconstruction algorithm to reconstruct the cardiac scanning data of the scanned object, so that the obtained cardiac reconstructed image of the scanned object can have low noise while ensuring the resolution, thereby improving the quality of the obtained cardiac reconstructed image of the scanned object.

[0068] In the above scenario of obtaining a cardiac reconstruction image of a scanned object according to the first cardiac reconstruction image and the second cardiac reconstruction image, in one embodiment, Figure 3 As shown, the above S204 includes:

[0069] S301, performing filtering processing on a first cardiac reconstructed image to obtain a processed first cardiac reconstructed image.

[0070] Specifically, the computer device performs filtering processing on the above-mentioned first cardiac reconstructed image to obtain a processed first cardiac reconstructed image. Optionally, the computer device may use a bilateral filter to perform filtering processing on the above-mentioned first cardiac reconstructed image to obtain a processed first cardiac reconstructed image. It should be noted that by using a very sharp convolution kernel to reconstruct the cardiac scan data, a stent boundary structure with higher resolution can be obtained, but at the same time, the noise of the first cardiac reconstructed image obtained will also be greatly enhanced, which is not conducive to the diagnosis of non-stent area tissues. Therefore, it is necessary to use a bilateral filter to filter the first cardiac reconstructed image. The function of the bilateral filter is to maintain the boundary of the first cardiac reconstructed image while removing the noise of the first cardiac reconstructed image. For example, if Figure 3a As shown, Figure 3a The image on the left is the control group Ori image. Figure 3a The image in the middle is the image obtained by using the sharp convolution kernel reconstruction algorithm. Figure 3a The image on the right is an image filtered using a bilateral filter. In one embodiment, the boundary pixels of the first cardiac reconstructed image are focus pixels, and the pixels around the boundary pixels are neighboring pixels of the focus pixels. Based on the distance information between the focus pixel and the neighboring pixels and / or the difference information of the pixel values ​​related to the neighboring pixels, the filter coefficients of the bilateral filter can be determined.

[0071] S302: Obtain a weighted coefficient of the region of interest according to the second heart reconstructed image.

[0072] Specifically, the computer device obtains a weighted weight coefficient for weighted merging the filtered first cardiac reconstructed image and the second cardiac reconstructed image based on the second cardiac reconstructed image obtained above. Optionally, the region of interest may be, for example, a heart stent, a bone stent, etc., and the region of interest may have a lower X-ray transmittance than other regions. The computer device may obtain a weighted weight coefficient for the region of interest based on an image corresponding to the stent region in the second cardiac reconstructed image.

[0073] S303: weightedly combine the processed first cardiac reconstructed image and the second cardiac reconstructed image according to the weighted coefficient of the region of interest to obtain a cardiac reconstructed image of the scanned object.

[0074] Specifically, the computer device weights and combines the processed first cardiac reconstructed image and the second cardiac reconstructed image according to the weighted weight coefficient of the region of interest obtained above, to obtain the cardiac reconstructed image of the scanned object. Optionally, the computer device can perform weighted processing on the processed first cardiac reconstructed image and the second cardiac reconstructed image according to the weighted weight coefficient of the region of interest, and then combine the weighted processed first cardiac reconstructed image and the second cardiac reconstructed image to obtain the cardiac reconstructed image of the scanned object.

[0075] In this embodiment, the computer device performs filtering processing on the first cardiac reconstructed image, which can maintain the boundary of the first cardiac reconstructed image while removing the noise of the first cardiac reconstructed image, thereby improving the quality of the processed first cardiac reconstructed image. In addition, based on the second cardiac reconstructed image, a weighted weight coefficient for weighted merging the first cardiac reconstructed image and the second cardiac reconstructed image can be accurately obtained, and then based on the obtained weighted weight coefficient, the processed first cardiac reconstructed image and the second cardiac reconstructed image can be accurately weighted merged, thereby improving the accuracy of the obtained cardiac reconstructed image of the scanned object.

[0076] In the above scenario of obtaining the weighted coefficient according to the second heart reconstructed image, in one embodiment, Figure 4 As shown, the above S302 includes:

[0077] S401, performing image segmentation on the second heart reconstructed image to obtain a stent mask image in the second heart reconstructed image.

[0078] Specifically, the computer device performs image segmentation on the second cardiac reconstructed image to obtain the stent mask image in the second cardiac reconstructed image. Optionally, the computer device may input the second cardiac reconstructed image into a preset image segmentation model, perform image segmentation on the second cardiac reconstructed image, and obtain the stent mask image in the second cardiac reconstructed image. Alternatively, the computer device may perform image segmentation on the second cardiac reconstructed image according to an image segmentation algorithm, such as a threshold-based segmentation method, a region-based segmentation method, an edge-based segmentation method, and the like, to obtain the stent mask image in the second cardiac reconstructed image.

[0079] S402, obtaining a weighted coefficient of the region of interest according to the stent mask image.

[0080] Specifically, the computer device obtains the weighted weight coefficient according to the stent mask image in the second heart reconstruction image. Optionally, the computer device can obtain the weighted weight coefficient according to the formula W stent (i,j)=M stent (i,j)*G(σ) and formula Wstent (i,j)=(W stent (i,j)-max(W stent (i,j))) / (max(W stent (i,j)-min(W stent (i, j))) to obtain the above-mentioned weighted weight coefficient, where i represents the horizontal coordinate of the pixel in the second cardiac reconstructed image, j represents the vertical coordinate of the pixel in the second cardiac reconstructed image, and W stent (i, j) represents the weighted weight coefficient of the pixel with coordinates (i, j), specifically the weighted weight coefficient of the pixel in the region of interest, max represents the maximum value operation, and min represents the minimum value operation. stent (i, j)) represents the maximum value of the weighted weight coefficient of the pixel in the second heart reconstruction image, min(W stent (i, j)) represents the minimum value of the weighted coefficient of the pixel in the second heart reconstruction image, G(σ) represents the Gaussian filter function about σ, M stent (i,j) represents the stent mask image, where 1 means the pixel is a bracket, 0 means it is not, T stent is the threshold for judging whether a pixel is a stent; Rcor refers to the coronary region, so the mask image of the stent is first extracted from the coronary region on the original image, and then extracted through threshold segmentation on this basis. ori (i, j) represents the pixel value of the coronary region mentioned by threshold segmentation, i ≥ 0, j ≥ 0. It can be understood that the above weighted weight coefficient is obtained by filtering the stent mask image through a Gaussian filter, and then the weighted weight coefficient is normalized to between 0 and 1 through the formula. The final weighted weight coefficient of the region of interest is as follows Figure 4a shown.

[0081] In this embodiment, the computer device can accurately obtain the stent mask image in the second heart reconstructed image by segmenting the second heart reconstructed image, so that the weighted weight coefficient of the region of interest can be accurately obtained based on the obtained stent mask image, thereby improving the accuracy of the obtained weighted weight coefficient of the region of interest.

[0082] In the above scenario where the processed first cardiac reconstructed image and the second cardiac reconstructed image are weightedly combined according to the weighted coefficient of the region of interest to obtain the cardiac reconstructed image of the scanned object, in one embodiment, Figure 5 As shown, the above S303 includes:

[0083] S501 , performing weighted processing on the processed first cardiac reconstructed image and the processed second cardiac reconstructed image according to the weighted coefficient of the region of interest to obtain the weighted first cardiac reconstructed image and the weighted second cardiac reconstructed image.

[0084] Specifically, the computer device performs weighted processing on the processed first cardiac reconstruction image and the second cardiac reconstruction image according to the weighted weight coefficient of the above-mentioned region of interest, and obtains the weighted first cardiac reconstruction image and the weighted second cardiac reconstruction image. Optionally, the computer device can use the weighted weight coefficient of the above-mentioned region of interest to perform weighted processing on the processed first cardiac reconstruction image to obtain the weighted first cardiac reconstruction image, obtain the weighted weight coefficient of the second cardiac reconstruction image according to the weighted weight coefficient of the region of interest, and perform weighted processing on the second cardiac reconstruction image using the weighted weight coefficient of the second cardiac reconstruction image to obtain the weighted second cardiac reconstruction image. Optionally, the sum of the weighted weight coefficient of the second cardiac reconstruction image and the weighted weight coefficient of the above-mentioned region of interest is 1, that is, the computer device can obtain the weighted weight coefficient of the second cardiac reconstruction image according to the weighted weight coefficient of the above-mentioned region of interest under the condition that the sum of the weighted weight coefficient of the second cardiac reconstruction image and the above-mentioned weighted weight coefficient is 1.

[0085] S502: Merge the weighted first heart reconstructed image and the weighted second heart reconstructed image to obtain a heart reconstructed image of the scanned object.

[0086] Specifically, the computer device combines the first heart reconstruction image after the weighted processing and the second heart reconstruction image after the weighted processing to obtain the heart reconstruction image of the scanned object. out (i,j)=W stent (i,j)*I f (i,j)+(1-W stent (i,j))*I ori (i, j) to obtain the reconstructed image of the heart of the scanned object, where I out (i, j) represents the reconstructed image of the heart of the scanned object, W stent (i,j) represents the weighted coefficient of the region of interest, I f (i, j) represents the first heart reconstruction image after processing, W stent (i,j)*I f (i, j) represents the first heart reconstruction image after weighted processing, I ori (i,j) represents the second heart reconstruction image, (1-W stent (i,j))*I ori(i, j) represents the second heart reconstructed image after weighted processing. Figure 5a , Figure 5b As shown, Figure 5a The middle left picture is the first heart reconstruction image. Figure 5a The middle right image is the first heart reconstruction image after processing. It can be seen that the structure of the stent in the first heart reconstruction image after processing is clearer, and the tissue part of the non-stent area is consistent with the original image. Figure 5b The middle left picture is a reconstructed image of the heart of the scanned object obtained using a traditional image reconstruction algorithm. Figure 5b The middle right image is a reconstructed image of the heart of the scanned object obtained using the solution of the present application.

[0087] In this embodiment, the computer device can accurately weight the processed first cardiac reconstructed image and the second cardiac reconstructed image according to the weighted weight coefficient of the region of interest, thereby improving the accuracy of the weighted first cardiac reconstructed image and the weighted second cardiac reconstructed image. Since the obtained cardiac reconstructed image of the scanned object is obtained by merging the weighted first cardiac reconstructed image and the weighted second cardiac reconstructed image, the accuracy of the weighted first cardiac reconstructed image and the accuracy of the weighted second cardiac reconstructed image are improved, thereby improving the accuracy of the obtained cardiac reconstructed image of the scanned object.

[0088] In order to facilitate the understanding of those skilled in the art, Figure 6 As shown, the cardiac image reconstruction method provided by the present application is described in detail below. The method may include:

[0089] S1, obtaining cardiac scan data of a scanned object.

[0090] S2, reconstructing the heart scan data using a first convolution kernel reconstruction algorithm to obtain a first heart reconstructed image of the scanned object.

[0091] S3, reconstructing the heart scan data using a second convolution kernel reconstruction algorithm to obtain a second heart reconstructed image of the scanned object.

[0092] S4, using a bilateral filter to perform filtering processing on the first cardiac reconstructed image to obtain a processed first cardiac reconstructed image.

[0093] S5, performing image segmentation on the second heart reconstructed image to obtain a stent mask image in the second heart reconstructed image.

[0094] S6, obtaining a weighted coefficient of the region of interest according to the stent mask image.

[0095] S7, using the weighted coefficient of the region of interest to perform weighted processing on the processed first heart reconstructed image to obtain the weighted first heart reconstructed image.

[0096] S8, obtaining a weighted weight coefficient of a second cardiac reconstructed image according to the weighted weight coefficient of the region of interest; wherein the sum of the weighted weight coefficient of the second cardiac reconstructed image and the weighted weight coefficient of the region of interest is 1.

[0097] S9, using the weighted coefficient of the second heart reconstructed image to perform weighted processing on the second heart reconstructed image to obtain the weighted second heart reconstructed image.

[0098] S10, merging the weighted first heart reconstructed image and the weighted second heart reconstructed image to obtain a heart reconstructed image of the scanned object.

[0099] It should be noted that for the description in the above S1-S10, reference may be made to the relevant description in the above embodiment, and the effects are similar, which will not be repeated in this embodiment.

[0100] It should be understood that although Figure 2-6 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-6 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0101] In one embodiment, Figure 7 As shown, a cardiac image reconstruction device is provided, comprising: an acquisition module, a first reconstruction module, a second reconstruction module and a merging module, wherein:

[0102] The acquisition module is used to acquire the heart scanning data of the scanned object.

[0103] The first reconstruction module is used to reconstruct the heart scan data by using a first convolution kernel reconstruction algorithm to obtain a first heart reconstructed image of the scanned object.

[0104] The second reconstruction module is used to reconstruct the heart scan data by using a second convolution kernel reconstruction algorithm to obtain a second heart reconstructed image of the scanned object.

[0105] The merging module is used to obtain a heart reconstructed image of the scanned object according to the first heart reconstructed image and the second heart reconstructed image.

[0106] The cardiac image reconstruction device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0107] Based on the above embodiment, optionally, the above merging module includes: a processing unit, a first acquisition unit and a second acquisition unit, wherein:

[0108] The processing unit is used to perform filtering processing on the first cardiac reconstructed image to obtain a processed first cardiac reconstructed image.

[0109] The first acquisition unit is used to obtain a weighted weight coefficient of the region of interest according to the second heart reconstruction image.

[0110] The second acquisition unit is used to perform weighted combination on the processed first cardiac reconstructed image and the second cardiac reconstructed image according to the weighted coefficient of the region of interest to obtain a cardiac reconstructed image of the scanned object.

[0111] The cardiac image reconstruction device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0112] On the basis of the above embodiment, optionally, the above second acquisition unit is specifically used to perform image segmentation on the second heart reconstructed image to obtain a stent mask image in the second heart reconstructed image; and obtain a weighted weight coefficient of the region of interest based on the stent mask image.

[0113] The cardiac image reconstruction device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0114] On the basis of the above-mentioned embodiment, optionally, the above-mentioned second acquisition unit is specifically used to perform weighted processing on the processed first cardiac reconstructed image and the second cardiac reconstructed image according to the weighted weight coefficient of the region of interest to obtain the weighted first cardiac reconstructed image and the weighted second cardiac reconstructed image; and merge the weighted first cardiac reconstructed image and the weighted second cardiac reconstructed image to obtain the cardiac reconstructed image of the scanned object.

[0115] The cardiac image reconstruction device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0116] On the basis of the above embodiment, optionally, the above second acquisition unit is specifically used to use the weighted weight coefficient of the region of interest to perform weighted processing on the processed first cardiac reconstructed image to obtain the weighted first cardiac reconstructed image; according to the weighted weight coefficient of the region of interest, the weighted weight coefficient of the second cardiac reconstructed image is obtained; and the weighted weight coefficient of the second cardiac reconstructed image is used to perform weighted processing on the second cardiac reconstructed image to obtain the weighted second cardiac reconstructed image.

[0117] Optionally, the sum of the weighted weight coefficient of the second heart reconstructed image and the weighted weight coefficient of the region of interest is 1.

[0118] The cardiac image reconstruction device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0119] On the basis of the above embodiment, optionally, the above processing unit is specifically configured to filter the first cardiac reconstructed image using a bilateral filter to obtain a processed first cardiac reconstructed image.

[0120] The cardiac image reconstruction device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0121] For the specific definition of the cardiac image reconstruction device, please refer to the definition of the cardiac image reconstruction method above, which will not be repeated here. Each module in the above cardiac image reconstruction device can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0122] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0123] Acquiring cardiac scan data of a scanned subject;

[0124] Reconstructing the heart scan data using a first convolution kernel reconstruction algorithm to obtain a first heart reconstructed image of the scanned object;

[0125] Reconstructing the heart scan data using a second convolution kernel reconstruction algorithm to obtain a second heart reconstructed image of the scanned object;

[0126] A heart reconstructed image of the scanned object is obtained according to the first heart reconstructed image and the second heart reconstructed image.

[0127] The implementation principle and technical effect of the computer device provided in the above embodiment are similar to those of the above method embodiment, and will not be repeated here.

[0128] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0129] Acquiring cardiac scan data of a scanned subject;

[0130] Reconstructing the heart scan data using a first convolution kernel reconstruction algorithm to obtain a first heart reconstructed image of the scanned object;

[0131] Reconstructing the heart scan data using a second convolution kernel reconstruction algorithm to obtain a second heart reconstructed image of the scanned object;

[0132] A heart reconstructed image of the scanned object is obtained according to the first heart reconstructed image and the second heart reconstructed image.

[0133] The computer-readable storage medium provided in the above embodiment has similar implementation principles and technical effects as those of the above method embodiment, and will not be described in detail here.

[0134] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0135] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0136] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A cardiac image reconstruction method, characterized in that: The method comprises: Acquiring cardiac scan data of a scanned subject; Reconstructing the heart scan data using a first convolution kernel reconstruction algorithm to obtain a first heart reconstructed image of the scanned object; Reconstructing the heart scan data using a second convolution kernel reconstruction algorithm to obtain a second heart reconstructed image of the scanned object; the cutoff frequency parameter corresponding to the first convolution kernel is greater than the cutoff frequency parameter of the second convolution kernel; performing filtering processing on the first cardiac reconstructed image to obtain a processed first cardiac reconstructed image; Obtaining a weighted coefficient of a region of interest according to the second heart reconstructed image, wherein the region of interest has a lower X-ray transmittance than other regions; The processed first cardiac reconstructed image and the second cardiac reconstructed image are weightedly combined according to the weighted coefficient of the region of interest to obtain a cardiac reconstructed image of the scanned object.

2. The method according to claim 1, characterized in that The region of interest is a region corresponding to the stent, and obtaining a weighted weight coefficient of the region of interest according to the second heart reconstructed image includes: performing image segmentation on the second heart reconstructed image to obtain a stent mask image in the second heart reconstructed image; A weighted coefficient of the region of interest is obtained according to the stent mask image.

3. The method according to claim 2, characterized in that The step of weighting and merging the processed first cardiac reconstructed image and the second cardiac reconstructed image according to the weighted coefficient of the region of interest to obtain the cardiac reconstructed image of the scanned object includes: performing weighted processing on the processed first cardiac reconstructed image and the second cardiac reconstructed image according to the weighted coefficient of the region of interest to obtain the weighted first cardiac reconstructed image and the weighted second cardiac reconstructed image; The weighted first heart reconstructed image and the weighted second heart reconstructed image are combined to obtain a heart reconstructed image of the scanned object.

4. The method according to claim 3, characterized in that The step of performing weighted processing on the processed first cardiac reconstructed image and the second cardiac reconstructed image according to the weighted coefficient of the region of interest to obtain the weighted first cardiac reconstructed image and the weighted second cardiac reconstructed image comprises: Using the weighted coefficient of the region of interest, weighted processing is performed on the processed first cardiac reconstructed image to obtain the weighted first cardiac reconstructed image; According to the weighted weight coefficient of the region of interest, acquiring the weighted weight coefficient of the second heart reconstructed image; The second cardiac reconstructed image is weighted by using the weighted coefficient of the second cardiac reconstructed image to obtain the weighted second cardiac reconstructed image.

5. The method according to claim 4, characterized in that The sum of the weighted weight coefficient of the second heart reconstructed image and the weighted weight coefficient of the region of interest is 1.

6. The method according to claim 1, characterized in that The filtering process is performed on the first cardiac reconstructed image to obtain the processed first cardiac reconstructed image, including: The first cardiac reconstructed image is filtered using a bilateral filter to obtain the processed first cardiac reconstructed image.

7. A cardiac image reconstruction device, characterized in that: The device comprises: An acquisition module, used for acquiring cardiac scan data of a scanned object; A first reconstruction module, configured to reconstruct the heart scan data using a first convolution kernel reconstruction algorithm to obtain a first heart reconstructed image of the scanned object; a second reconstruction module, configured to reconstruct the heart scan data by using a second convolution kernel reconstruction algorithm to obtain a second heart reconstructed image of the scanned object; wherein a cutoff frequency parameter corresponding to the first convolution kernel is greater than a cutoff frequency parameter of the second convolution kernel; A merging module is used to filter the first cardiac reconstructed image to obtain a processed first cardiac reconstructed image; obtain a weighted weight coefficient of a region of interest based on the second cardiac reconstructed image, wherein the region of interest has a low X-ray transmittance relative to other regions; and perform weighted merging of the processed first cardiac reconstructed image and the second cardiac reconstructed image based on the weighted weight coefficient of the region of interest to obtain a cardiac reconstructed image of the scanned object.

8. The device according to claim 7, characterized in that The merging module is specifically used for: Perform image segmentation on the second heart reconstructed image to obtain a stent mask image in the second heart reconstructed image; and obtain a weighted weight coefficient of the region of interest based on the stent mask image.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images