Crystal pixel lookup table generation method and device, computer equipment and storage medium

Abstract

The application relates to a crystal pixel lookup table generation method and device, computer equipment and a storage medium. A preset number of first pixel peak points are determined from a first crystal pixel lookup table, data enhancement processing is performed on the first pixel peak points in the first crystal pixel lookup table to obtain a second crystal pixel lookup table, data enhancement processing is performed on the first pixel peak points in the first crystal pixel lookup table to obtain a second crystal pixel lookup table, and a target crystal pixel lookup table is obtained based on the first crystal pixel lookup table and the second crystal pixel lookup table. In the embodiment, the data enhancement processing is performed on the first pixel peak points to obtain the second crystal pixel lookup table, the phenomenon that a medical device crystal disappears along with the use time is simulated, the target crystal pixel lookup table is obtained based on the first crystal pixel lookup table and the second crystal pixel lookup table, the number and diversity of the crystal pixel lookup table data set are improved, and the complexity of the crystal pixel lookup table generation is reduced.

Description

Technical Field

[0001] This application relates to the field of medical technology, and in particular to a method, apparatus, computer device, and storage medium for generating a crystal pixel lookup table. Background Technology

[0002] The detector in a positron emission tomography (PET) device is a crystal array coupled with a photoelectric conversion device. A PET device contains tens of thousands of crystals. When gamma photons are incident on the crystals, a Crystal Lookup Table (LUT) is generated based on the count of the incident gamma photons. The peak pixel points in the LUT are located to determine the crystal's position within the LUT. This crystal position can then be used to correct and adjust the reconstructed image. Therefore, improving the accuracy of the peak pixel location is crucial for improving the final imaging.

[0003] Thanks to the rapid advancements in deep neural networks, pixel peak point localization can be achieved using deep neural networks. However, this requires a large and rich LUT dataset to train the deep neural network; otherwise, the accuracy of pixel peak point localization based on the deep neural network is poor.

[0004] Currently, LUT datasets are obtained from different PET devices, but this presents a problem of complexity in obtaining LUT datasets. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, computer device, and storage medium for generating crystal pixel lookup tables that can reduce the complexity of obtaining LUT datasets, in order to address the above-mentioned technical problems.

[0006] In a first aspect, this application provides a method for generating a crystal pixel lookup table, including:

[0007] Determine a preset number of first pixel peak points from the first crystal pixel lookup table;

[0008] Data enhancement processing is performed on the first pixel peak points in the first crystal pixel lookup table to obtain the second crystal pixel lookup table;

[0009] Based on the first crystal pixel lookup table and the second crystal pixel lookup table, the target crystal pixel lookup table is obtained.

[0010] In one embodiment, determining a preset number of first pixel peak points from a first crystal pixel lookup table includes:

[0011] The preset number of first pixel peak points are determined from the second pixel peak points; the second pixel peak points are pixel peak points located at the edge position in the first crystal pixel lookup table.

[0012] In one embodiment, determining a preset number of first pixel peak points from a first crystal pixel lookup table includes:

[0013] The preset number of first pixel peak points are determined from the pixel peak points of the first crystal pixel lookup table.

[0014] In one embodiment, the step of performing data enhancement processing on the first pixel peak points in the first crystal pixel lookup table to obtain a second crystal pixel lookup table includes:

[0015] Gaussian processing is performed on the first pixel peak point to obtain the first Gaussian distribution value of the first pixel peak point;

[0016] The first Gaussian distribution value is transformed according to a preset value to obtain the second Gaussian distribution value;

[0017] The second crystal pixel lookup table is obtained based on the second Gaussian distribution value and the first crystal pixel lookup table.

[0018] In one embodiment, obtaining the second crystal pixel lookup table based on the second Gaussian distribution value and the first crystal pixel lookup table includes:

[0019] The second crystal pixel lookup table is obtained by multiplying the second Gaussian distribution value with the pixel value of each pixel in the first crystal pixel lookup table.

[0020] In one embodiment, obtaining the target crystal pixel lookup table based on the first crystal pixel lookup table and the second crystal pixel lookup table includes:

[0021] The target crystal pixel lookup table is obtained by performing image enhancement processing on the first crystal pixel lookup table and the second crystal pixel lookup table.

[0022] The image enhancement process includes at least one of the following methods:

[0023] Perform a flip operation on the first crystal pixel lookup table and the second crystal pixel lookup table;

[0024] Perform a noise addition operation on the first crystal pixel lookup table and the second crystal pixel lookup table;

[0025] Perform a smoothing operation on the first crystal pixel lookup table and the second crystal pixel lookup table;

[0026] Perform contrast processing on the first crystal pixel lookup table and the second crystal pixel lookup table.

[0027] Secondly, this application also provides a crystal pixel lookup table generation apparatus, comprising:

[0028] The first determining module is used to determine a preset number of first pixel peak points from the first crystal pixel lookup table;

[0029] The processing module is used to perform data enhancement processing on the first pixel peak points in the first crystal pixel lookup table to obtain a second crystal pixel lookup table.

[0030] The second determining module is used to obtain a target crystal pixel lookup table based on the first crystal pixel lookup table and the second crystal pixel lookup table.

[0031] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0032] Determine a preset number of first pixel peak points from the first crystal pixel lookup table;

[0033] Data enhancement processing is performed on the first pixel peak points in the first crystal pixel lookup table to obtain the second crystal pixel lookup table;

[0034] Based on the first crystal pixel lookup table and the second crystal pixel lookup table, the target crystal pixel lookup table is obtained.

[0035] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0036] Determine a preset number of first pixel peak points from the first crystal pixel lookup table;

[0037] Data enhancement processing is performed on the first pixel peak points in the first crystal pixel lookup table to obtain the second crystal pixel lookup table;

[0038] Based on the first crystal pixel lookup table and the second crystal pixel lookup table, the target crystal pixel lookup table is obtained.

[0039] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0040] Determine a preset number of first pixel peak points from the first crystal pixel lookup table;

[0041] Data enhancement processing is performed on the first pixel peak points in the first crystal pixel lookup table to obtain the second crystal pixel lookup table;

[0042] Based on the first crystal pixel lookup table and the second crystal pixel lookup table, the target crystal pixel lookup table is obtained.

[0043] The aforementioned crystal pixel lookup table generation method, apparatus, computer device, and storage medium determine a preset number of first pixel peak points from a first crystal pixel lookup table, perform data augmentation processing on the first pixel peak points in the first crystal pixel lookup table to obtain a second crystal pixel lookup table, perform data augmentation processing on the first pixel peak points in the first crystal pixel lookup table to obtain a second crystal pixel lookup table, and obtain a target crystal pixel lookup table based on the first and second crystal pixel lookup tables. In this embodiment, by performing data augmentation processing on the first pixel peak points in the first crystal pixel lookup table to obtain a second crystal pixel lookup table, the phenomenon of crystal disappearance in medical devices over time is simulated. Thus, based on the first and second crystal pixel lookup tables, the target crystal pixel lookup table is obtained, increasing the quantity and diversity of the crystal pixel lookup table dataset, reducing the complexity of crystal pixel lookup table generation, and laying the foundation for subsequent training of deep neural networks based on the crystal pixel lookup table dataset. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is an application environment diagram of the crystal pixel lookup table generation method in one embodiment;

[0046] Figure 2 This is a flowchart illustrating a method for generating a crystal pixel lookup table in one embodiment;

[0047] Figure 3 This is a schematic diagram illustrating the generation of a crystal pixel lookup table in one embodiment;

[0048] Figure 4 This is a schematic diagram of a crystal pixel lookup table in another embodiment;

[0049] Figure 5 This is a schematic diagram of a crystal pixel lookup table in another embodiment;

[0050] Figure 6This is a flowchart illustrating a method for generating a second crystal pixel lookup table in one embodiment;

[0051] Figure 7 This is a schematic diagram of the first crystal pixel lookup table in one embodiment;

[0052] Figure 8 This is a schematic diagram of the first crystal pixel lookup table in another embodiment;

[0053] Figure 9 This is a schematic diagram of the first crystal pixel lookup table in another embodiment;

[0054] Figure 10 This is a schematic diagram of the first Gaussian distribution value in one embodiment;

[0055] Figure 11 This is a schematic diagram of the second Gaussian distribution value in one embodiment;

[0056] Figure 12 This is a schematic diagram of the second crystal pixel lookup table in one embodiment;

[0057] Figure 13 This is a comparative diagram of pixel peak point localization results in one embodiment;

[0058] Figure 14 This is a structural block diagram of a crystal pixel lookup table generation device in one embodiment;

[0059] Figure 15 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0061] Spatial resolution refers to the distance between two point sources that are very close together and can just be distinguished. It is usually expressed as the half-width at half-maximum (FWHM) of the line spread function (LSF), with units of mm. The spatial resolution of PET equipment is divided into axial resolution, transverse radial resolution, and tangential resolution. The main factors affecting resolution include the detector material, size, signal-to-noise ratio, and probe aperture.

[0062] Furthermore, the spatial resolution varies slightly depending on the location of the point source within the PET scanner's field of view; the further away from the center of the field of view, the worse the spatial resolution. Each crystal that makes up the detector can be considered a point source. A localized image processing unit (LUT) is obtained based on the count of gamma photons incident on each crystal. The LUT is the raw data input to the reconstruction algorithm for image reconstruction. Spatial resolution is a crucial factor affecting the quality of the reconstructed image; the accuracy of pixel peak point localization directly impacts the spatial resolution. Therefore, improving the accuracy of pixel peak point localization is a sufficient condition for improving the quality of the reconstructed image.

[0063] The location of the crystal within the LUT is determined by the position of the pixel peak points, enabling image reconstruction. Since the workload of pixel peak point localization in each PET scanner is enormous, manual correction is extremely labor-intensive and increases the possibility of human error. Therefore, a pixel peak point localization algorithm applicable to all PET scanners is essential. However, in reality, many objective conditions and factors limit the pixel peak point localization task, making it difficult to complete. For example, due to the hardware structure and organization of PET scanners, the pixel peak points in the LUT are unevenly distributed, sometimes even difficult to distinguish with the naked eye.

[0064] In related technologies, there are generally three methods for locating pixel peaks in crystal pixel lookup tables. The first method is based on deep neural networks. This method uses crystal pixel lookup table samples to model a deep neural network, and then applies the resulting deep neural network to locate the pixel peaks in the crystal pixel lookup table. However, this modeling method is highly dependent on the quantity and quality of the crystal pixel lookup table dataset. Without a sufficient amount of crystal pixel lookup table data as support, the resulting model is prone to overfitting and has poor generalization ability, making it difficult to achieve the optimal performance of this method. In reality, acquiring crystal pixel lookup table datasets is costly, and the crystal pixel lookup table datasets used for training need to meet certain diversity requirements. This diversity is reflected in the usage location of the PET equipment, the usage duration of the PET equipment, and the maintenance status of the PET equipment, etc. The crystal pixel lookup table will exhibit different states depending on the usage time and maintenance condition of the PET equipment. Due to the special nature of PET equipment, it is very difficult to obtain a sufficiently diverse and large dataset of crystal pixel lookup tables for training optimization algorithms. First, the number of PET equipment in stock is relatively small. Second, among these few PET equipment, different PET equipment have different usage conditions, but data can only be collected once for each PET equipment in each condition. Collecting data multiple times for PET equipment in the same condition is meaningless because the data from each PET equipment is homogeneous in a short period of time.

[0065] The second method is based on iterative classification. This method is computationally intensive, requires multiple iterations, and is sensitive to initialization, resulting in low efficiency and poor robustness. The third method involves performing two-dimensional statistics on the incident photon event position information to obtain a photon event position histogram. Then, crystal position detection is performed to obtain a crystal center position map, and the initial position of the crystal center position map is obtained. Next, a matrixed crystal center position map is recursively derived based on the initial position. A spline method is used to establish a grid template by concatenating the matrixed crystal center position maps, and finally, the crystal pixel lookup table is generated. This method cannot effectively handle the situation where the incident photon event position information deteriorates due to the aging of PET equipment, often resulting in positioning failure. Therefore, this application proposes a method, apparatus, computer device, and storage medium for generating a crystal pixel lookup table that can solve the above-mentioned technical problems.

[0066] The crystal pixel lookup table generation method provided in this application embodiment can be applied to, for example... Figure 1 The application environment shown includes a computer device, which may be a server, and its internal structure diagram may be as follows. Figure 1 As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores data related to the generation of crystal pixel lookup tables. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a crystal pixel lookup table generation method. The server can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0067] In one exemplary embodiment, such as Figure 2 As shown, a method for generating a crystal pixel lookup table is provided, which can be applied to... Figure 1 The following explanation uses computer equipment as an example, including the following steps S201 to S203. Wherein:

[0068] S201, determine a preset number of first pixel peak points from the first crystal pixel lookup table.

[0069] In this embodiment, spatial resolution indicates the ability of a PET device to distinguish between two "points" in space. An ideal radioactive point source placed within the field of view (FOV) of the PET device will result in a radioactive distribution image that is not a single point but rather has some extension, forming a "sphere." The size of this sphere reflects the spatial resolution of the PET device. Therefore, a first crystal pixel lookup table is obtained using the PET device, where each crystal has a certain range within the table. The pixel peak points of each crystal are manually marked in the first crystal pixel lookup table, and these peak points represent the crystal's position within the table. The marked result is as follows: Figure 3 As shown.

[0070] The preset number is less than or equal to the number of pixel peak points in the first crystal pixel lookup table.

[0071] A preset number of first pixel peak points can be randomly determined from the marked pixel peak points, or a preset number of first pixel peak points can be determined from the pixel peak points located at the edge of the marked pixel peak points.

[0072] S202, perform data enhancement processing on the peak points of the first pixel in the first crystal pixel lookup table to obtain the second crystal pixel lookup table.

[0073] In this embodiment, due to the increased usage time of the PET equipment, the original crystal position lookup table will exhibit regular damage and changes, with the crystal imaging at the edges of the lookup table gradually becoming blurry or even disappearing. Therefore, data enhancement processing is performed on the first pixel peak points in the first crystal pixel lookup table to simulate the blurring phenomenon of crystal imaging in the first crystal pixel lookup table, resulting in a second crystal pixel lookup table. For example, Gaussian processing is applied to the first pixel peak points to obtain the Gaussian processing result, and the second crystal pixel lookup table is obtained based on the Gaussian processing result and the first crystal pixel lookup table; alternatively, a smaller weight is assigned to the first pixel peak points, and the pixel values ​​of the first pixel peak points are changed based on the weight, thereby obtaining the second crystal pixel lookup table based on the changed pixel values ​​and the first crystal pixel lookup table.

[0074] Optionally, blurred crystal imaging can refer to the phenomenon that crystals in the crystal lookup table completely disappear or that crystal imaging is weakened.

[0075] S203, based on the first crystal pixel lookup table and the second crystal pixel lookup table, obtain the target crystal pixel lookup table.

[0076] In this embodiment, image enhancement processing can be performed on the first crystal pixel lookup table and the second crystal pixel lookup table to obtain the target crystal pixel lookup table.

[0077] In one possible implementation, the first and second crystal pixel lookup tables can be directly used as the target crystal pixel lookup table. Based on the first, second, and target crystal pixel lookup tables obtained in this application, a deep neural network is trained to obtain a trained deep neural network. This trained deep neural network is then applied to the localization of pixel peak points in the actual crystal pixel lookup table. This solves the problems of the second pixel peak point localization method (high computational load, requiring multiple iterations, sensitivity to initialization, low efficiency, and low robustness) and the third pixel peak point localization method (inability to handle the deterioration of incident photon event position information during PET equipment aging, often leading to localization failure).

[0078] In the aforementioned method for generating a crystal pixel lookup table, a preset number of first pixel peak points are determined from a first crystal pixel lookup table. Data augmentation processing is then performed on these first pixel peak points to obtain a second crystal pixel lookup table. This process is repeated, and a target crystal pixel lookup table is obtained based on both the first and second crystal pixel lookup tables. In this embodiment, by performing data augmentation processing on the first pixel peak points in the first crystal pixel lookup table to obtain the second crystal pixel lookup table, the phenomenon of crystal disappearance in medical devices over time is simulated. This allows the target crystal pixel lookup table to be obtained based on both the first and second crystal pixel lookup tables, increasing the quantity and diversity of the crystal pixel lookup table dataset, reducing the complexity of crystal pixel lookup table generation, and laying the foundation for subsequent training of deep neural networks based on the crystal pixel lookup table dataset.

[0079] In one embodiment, determining a preset number of first pixel peak points from a first crystal pixel lookup table includes the following two methods.

[0080] The first method: Determine a preset number of first pixel peak points from the second pixel peak points; the second pixel peak points are the pixel peak points located at the edge position in the first crystal pixel lookup table.

[0081] In this embodiment, based on observations of PET equipment under different usage durations and conditions, it can be observed that as the PET equipment is used and worn out, the crystal pixel lookup table exhibits a certain pattern of damage and change. For example, as follows: Figure 4 and Figure 5The two crystal pixel lookup tables were obtained from the PET equipment under different usage durations. It can be observed that as usage time increases, the crystal imaging around the edges of the lookup tables gradually becomes blurry (this is determined by the hardware design). Therefore, a preset number of first pixel peak points can be determined from the pixel peak points at the edge positions in the first crystal pixel lookup table, which better reflects the actual usage of the PET equipment. As mentioned above... Figure 3 As shown, there are a total of 22 pixel peak points around the edges, and 7 first pixel peak points are randomly selected from the 22 pixel peak points.

[0082] The second method: Determine a preset number of first pixel peak points from the pixel peak points of the first crystal pixel lookup table.

[0083] In this embodiment, a preset number of first pixel peak points can be randomly determined from the pixel peak points of the first crystal pixel lookup table, or a preset number of first pixel peak points can be determined from the marked pixel peak points at equal intervals. As described above. Figure 3 As shown, the first crystal pixel lookup table includes 42 pixel peak points. 15 pixel peak points are randomly selected from the 42 pixel peak points; alternatively, 3 pixel peak points can be selected from the pixel peak points in each row.

[0084] In this embodiment, a preset number of first pixel peak points are determined from the pixel peak points at the edge positions in the first crystal pixel lookup table, or a preset number of first pixel peak points are determined from all pixel peak points in the first crystal pixel lookup table. This embodiment provides two methods for determining the first pixel peak points, making the determination more flexible and improving the diversity of determining the target crystal pixel lookup table based on the first pixel peak points.

[0085] Figure 6 This is a flowchart illustrating a method for generating a second crystal pixel lookup table in one embodiment, as shown below. Figure 6 As shown, this application embodiment relates to a possible implementation of how to perform data enhancement processing on the peak points of the first pixel in the first crystal pixel lookup table to obtain the second crystal pixel lookup table, including the following steps:

[0086] S601, Gaussian processing is performed on the peak point of the first pixel to obtain the first Gaussian distribution value of the peak point of the first pixel.

[0087] In this embodiment, a hyperparameter can be set for each first pixel peak point. value, The value is a floating-point number, and its range can generally be set to [3, 50]. The following formula can be used to perform Gaussian processing on the first pixel peak point to obtain the first Gaussian distribution value centered on the first pixel peak point:

[0088]

[0089] Where (x, y) represents the coordinates of the first pixel peak point, and a and b are the two-sided critical values ​​of the Gaussian processing. Optionally, the value of a can be in the range of (-3). , 3 The value of b can be in the range of (-3). , 3 ).

[0090] like Figure 7 As shown, Figure 7 This is a schematic diagram of a first crystal pixel lookup table in one embodiment. The peak points of each pixel are marked in the first crystal pixel lookup table, and the marking result is as follows: Figure 8 As shown. From Figure 8 In the first crystal pixel lookup table showing the results of each pixel peak point marker, a pixel peak point is randomly selected as the first pixel peak point (represented by a pentagram), and the result is as follows. Figure 9 This indicates that, by applying the above formula to the Gaussian processing of the first pixel peak point, the resulting first Gaussian distribution value is as follows: Figure 10 As shown.

[0091] S602, transform the first Gaussian distribution value according to the preset value to obtain the second Gaussian distribution value.

[0092] In this embodiment, the first Gaussian distribution value can be inverted using the following formula to obtain the second Gaussian distribution value G1:

[0093]

[0094] In one example, regarding the above Figure 10 The first Gaussian distribution value is inverted to obtain the second Gaussian distribution value, as shown in the figure. Figure 11 As shown.

[0095] S603, based on the second Gaussian distribution value and the first crystal pixel lookup table, obtain the second crystal pixel lookup table.

[0096] In this embodiment, the second Gaussian distribution value and each pixel value in the first crystal pixel lookup table can be multiplied together to obtain the second crystal pixel lookup table.

[0097] In one possible implementation, the second Gaussian distribution value can be finely adjusted, and the second crystal pixel lookup table can be obtained based on the adjusted second Gaussian distribution value and the first crystal pixel lookup table.

[0098] Further, based on the second Gaussian distribution value and the first crystal pixel lookup table, a second crystal pixel lookup table is obtained, including: obtaining the second crystal pixel lookup table based on the product of the second Gaussian distribution value and the pixel value of each pixel in the first crystal pixel lookup table.

[0099] In this embodiment, the second Gaussian distribution value is multiplied by the pixel values ​​of each pixel in the first crystal pixel lookup table to obtain the second crystal pixel lookup table Aug, that is, according to... This yields the second crystal pixel lookup table. For example, the above... Figure 7 The first crystal pixel lookup table and Figure 11 Multiplying the values ​​of the second Gaussian distribution, the resulting second crystal pixel lookup table is as follows: Figure 12 As shown. Comparison Figure 7 and Figure 12 You can see Figure 12 The crystal at the location of the first pixel peak has disappeared. Figure 7 and Figure 12 The area indicated by the middle arrow shows the differences between the first pixel peak data before and after enhancement.

[0100] In this embodiment, Gaussian processing is performed on the first pixel peak point to obtain the first Gaussian distribution value of the first pixel peak point. The first Gaussian distribution value is then transformed according to a preset value to obtain the second Gaussian distribution value. Based on the second Gaussian distribution value and the first crystal pixel lookup table, the second crystal pixel lookup table is obtained. In this embodiment, Gaussian processing is performed on the first pixel peak point, which allows for the setting of very few hyperparameters to obtain the second crystal pixel lookup table, thereby improving the generation efficiency of the second crystal pixel lookup table.

[0101] One embodiment relates to how to obtain a target crystal pixel lookup table based on a first crystal pixel lookup table and a second crystal pixel lookup table, including: performing image enhancement processing on the first crystal pixel lookup table and the second crystal pixel lookup table to obtain the target crystal pixel lookup table; the image enhancement processing includes at least one of the following methods: performing a flip operation on the first crystal pixel lookup table and the second crystal pixel lookup table; performing a noise addition operation on the first crystal pixel lookup table and the second crystal pixel lookup table; performing a smoothing operation on the first crystal pixel lookup table and the second crystal pixel lookup table; and performing a contrast processing operation on the first crystal pixel lookup table and the second crystal pixel lookup table.

[0102] In this embodiment, a flipping operation can be performed on the first crystal pixel lookup table and the second crystal pixel lookup table. It should be noted that both the first crystal pixel lookup table and the second crystal pixel lookup table include corresponding pixel peak points. When the first crystal pixel lookup table and the second crystal pixel lookup table are flipped, the pixel peak points are also flipped.

[0103] Image enhancement techniques such as noise, contrast enhancement and reduction, smoothing, cropping, rotation, and translation can be added to the first crystal pixel lookup table and the second crystal pixel lookup table to obtain the target crystal pixel lookup table.

[0104] Furthermore, using the same pixel peak point localization model, the same parameter configuration, and the same number of training iterations, the pixel peak point localization model was trained using both the original crystal pixel lookup table samples and the enhanced crystal pixel lookup table samples of this application. For example... Figure 13 As shown, the trained pixel peak point localization model was tested on the crystal pixel lookup tables of different product models (product model 1 and product model 2). The root mean square error (RMSE) was used to evaluate the test results. The smaller the RMSE value, the better the prediction performance of the pixel peak point localization model. It can be seen that using the method proposed in this application can improve the algorithm performance by about 20% compared with not using it.

[0105] The formula for calculating the RMSE evaluation index is as follows: , (x label y label (x) represents manually marked pixel peaks. pred y pred ) represents the pixel peak points predicted by the pixel peak point localization model.

[0106] In this embodiment, the first crystal pixel lookup table and the second crystal pixel lookup table are subjected to image enhancement processing to obtain the target crystal pixel lookup table. In this embodiment, the first crystal pixel lookup table and the second crystal pixel lookup table are further subjected to image enhancement to further increase the number and data diversity of the crystal pixel lookup tables.

[0107] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0108] Based on the same inventive concept, this application also provides a crystal pixel lookup table generation apparatus for implementing the crystal pixel lookup table generation method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more crystal pixel lookup table generation apparatus embodiments provided below can be found in the limitations of the crystal pixel lookup table generation method described above, and will not be repeated here.

[0109] In one exemplary embodiment, such as Figure 14 As shown, a crystal pixel lookup table generation device is provided, comprising: a first determining module 11, a processing module 12, and a second determining module 13, wherein:

[0110] The first determining module 11 is used to determine a preset number of first pixel peak points from the first crystal pixel lookup table;

[0111] Processing module 12 is used to perform data enhancement processing on the peak points of the first pixel in the first crystal pixel lookup table to obtain the second crystal pixel lookup table;

[0112] The second determining module 13 is used to obtain the target crystal pixel lookup table based on the first crystal pixel lookup table and the second crystal pixel lookup table.

[0113] In one embodiment, the first determining module includes:

[0114] The first determining unit is used to determine a preset number of first pixel peak points from the second pixel peak points; the second pixel peak points are pixel peak points located at the edge position in the first crystal pixel lookup table.

[0115] In one embodiment, the first determining module includes:

[0116] The second determining unit is used to determine a preset number of first pixel peak points from each pixel peak point in the first crystal pixel lookup table.

[0117] In one embodiment, the processing module includes:

[0118] The first processing unit is used to perform Gaussian processing on the peak point of the first pixel to obtain the first Gaussian distribution value of the peak point of the first pixel.

[0119] The second processing unit is used to transform the first Gaussian distribution value according to the preset value to obtain the second Gaussian distribution value.

[0120] The third determining unit is used to obtain the second crystal pixel lookup table based on the second Gaussian distribution value and the first crystal pixel lookup table.

[0121] In one embodiment, the third determining unit is further configured to obtain the second crystal pixel lookup table based on the product of the second Gaussian distribution value and the pixel value of each pixel in the first crystal pixel lookup table.

[0122] In one embodiment, the first determining module is specifically used to perform image enhancement processing on the first crystal pixel lookup table and the second crystal pixel lookup table to obtain the target crystal pixel lookup table.

[0123] Image enhancement processing includes at least one of the following methods:

[0124] Perform a flip operation on the first crystal pixel lookup table and the second crystal pixel lookup table;

[0125] Perform a noise addition operation on the first crystal pixel lookup table and the second crystal pixel lookup table;

[0126] Perform a smoothing operation on the first crystal pixel lookup table and the second crystal pixel lookup table;

[0127] Perform contrast processing on the first crystal pixel lookup table and the second crystal pixel lookup table.

[0128] Each module in the aforementioned crystal pixel lookup table generation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0129] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 15As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for generating a crystal pixel lookup table. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0130] Those skilled in the art will understand that Figure 15 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0131] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0132] Determine a preset number of first pixel peak points from the first crystal pixel lookup table;

[0133] Data enhancement processing is performed on the peak points of the first pixel in the first crystal pixel lookup table to obtain the second crystal pixel lookup table;

[0134] Based on the first crystal pixel lookup table and the second crystal pixel lookup table, the target crystal pixel lookup table is obtained.

[0135] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0136] A preset number of first pixel peak points are determined from the second pixel peak points; the second pixel peak points are the pixel peak points located at the edge position in the first crystal pixel lookup table.

[0137] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0138] A preset number of first pixel peak points are determined from the pixel peak points of the first crystal pixel lookup table.

[0139] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0140] Gaussian processing is performed on the peak point of the first pixel to obtain the first Gaussian distribution value of the peak point of the first pixel.

[0141] The first Gaussian distribution value is transformed according to the preset value to obtain the second Gaussian distribution value;

[0142] The second crystal pixel lookup table is obtained based on the second Gaussian distribution value and the first crystal pixel lookup table.

[0143] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0144] The second crystal pixel lookup table is obtained by multiplying the second Gaussian distribution value with the pixel value of each pixel in the first crystal pixel lookup table.

[0145] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0146] Image enhancement processing is performed on the first crystal pixel lookup table and the second crystal pixel lookup table to obtain the target crystal pixel lookup table;

[0147] Image enhancement processing includes at least one of the following methods:

[0148] Perform a flip operation on the first crystal pixel lookup table and the second crystal pixel lookup table;

[0149] Perform a noise addition operation on the first crystal pixel lookup table and the second crystal pixel lookup table;

[0150] Perform a smoothing operation on the first crystal pixel lookup table and the second crystal pixel lookup table;

[0151] Perform contrast processing on the first crystal pixel lookup table and the second crystal pixel lookup table.

[0152] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0153] Determine a preset number of first pixel peak points from the first crystal pixel lookup table;

[0154] Data enhancement processing is performed on the peak points of the first pixel in the first crystal pixel lookup table to obtain the second crystal pixel lookup table;

[0155] The target crystal pixel lookup table is obtained based on the first crystal pixel lookup table and the second crystal pixel lookup table.

[0156] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0157] A preset number of first pixel peak points are determined from the second pixel peak points; the second pixel peak points are the pixel peak points located at the edge position in the first crystal pixel lookup table.

[0158] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0159] A preset number of first pixel peak points are determined from the pixel peak points of the first crystal pixel lookup table.

[0160] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0161] Gaussian processing is performed on the peak point of the first pixel to obtain the first Gaussian distribution value of the peak point of the first pixel.

[0162] The first Gaussian distribution value is transformed according to the preset value to obtain the second Gaussian distribution value;

[0163] The second crystal pixel lookup table is obtained based on the second Gaussian distribution value and the first crystal pixel lookup table.

[0164] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0165] The second crystal pixel lookup table is obtained by multiplying the second Gaussian distribution value with the pixel value of each pixel in the first crystal pixel lookup table.

[0166] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0167] Image enhancement processing is performed on the first crystal pixel lookup table and the second crystal pixel lookup table to obtain the target crystal pixel lookup table;

[0168] Image enhancement processing includes at least one of the following methods:

[0169] Perform a flip operation on the first crystal pixel lookup table and the second crystal pixel lookup table;

[0170] Perform a noise addition operation on the first crystal pixel lookup table and the second crystal pixel lookup table;

[0171] Perform a smoothing operation on the first crystal pixel lookup table and the second crystal pixel lookup table;

[0172] Perform contrast processing on the first crystal pixel lookup table and the second crystal pixel lookup table.

[0173] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0174] Determine a preset number of first pixel peak points from the first crystal pixel lookup table;

[0175] Data enhancement processing is performed on the peak points of the first pixel in the first crystal pixel lookup table to obtain the second crystal pixel lookup table;

[0176] The target crystal pixel lookup table is obtained based on the first crystal pixel lookup table and the second crystal pixel lookup table.

[0177] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0178] A preset number of first pixel peak points are determined from the second pixel peak points; the second pixel peak points are the pixel peak points located at the edge position in the first crystal pixel lookup table.

[0179] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0180] A preset number of first pixel peak points are determined from the pixel peak points of the first crystal pixel lookup table.

[0181] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0182] Gaussian processing is performed on the peak point of the first pixel to obtain the first Gaussian distribution value of the peak point of the first pixel.

[0183] The first Gaussian distribution value is transformed according to the preset value to obtain the second Gaussian distribution value;

[0184] The second crystal pixel lookup table is obtained based on the second Gaussian distribution value and the first crystal pixel lookup table.

[0185] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0186] The second crystal pixel lookup table is obtained by multiplying the second Gaussian distribution value with the pixel value of each pixel in the first crystal pixel lookup table.

[0187] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0188] Image enhancement processing is performed on the first crystal pixel lookup table and the second crystal pixel lookup table to obtain the target crystal pixel lookup table;

[0189] Image enhancement processing includes at least one of the following methods:

[0190] Perform a flip operation on the first crystal pixel lookup table and the second crystal pixel lookup table;

[0191] Perform a noise addition operation on the first crystal pixel lookup table and the second crystal pixel lookup table;

[0192] Perform a smoothing operation on the first crystal pixel lookup table and the second crystal pixel lookup table;

[0193] Perform contrast processing on the first crystal pixel lookup table and the second crystal pixel lookup table.

[0194] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0195] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, 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, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0196] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0197] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for generating a crystal pixel lookup table, characterized in that, The method includes: Determine a preset number of first pixel peak points from the first crystal pixel lookup table; Gaussian processing is performed on the first pixel peak point to obtain a first Gaussian distribution value of the first pixel peak point; the first Gaussian distribution value is inverted according to a preset value to obtain a second Gaussian distribution value; a second crystal pixel lookup table is obtained according to the second Gaussian distribution value and the first crystal pixel lookup table; Based on the first crystal pixel lookup table and the second crystal pixel lookup table, the target crystal pixel lookup table is obtained.

2. The method according to claim 1, characterized in that, Determining a preset number of first pixel peak points from the first crystal pixel lookup table includes: The preset number of first pixel peak points are determined from the second pixel peak points; the second pixel peak points are pixel peak points located at the edge position in the first crystal pixel lookup table.

3. The method according to claim 1, characterized in that, Determining a preset number of first pixel peak points from the first crystal pixel lookup table includes: The preset number of first pixel peak points are determined from the pixel peak points of the first crystal pixel lookup table.

4. The method according to claim 1, characterized in that, The step of obtaining the second crystal pixel lookup table based on the second Gaussian distribution value and the first crystal pixel lookup table includes: The second crystal pixel lookup table is obtained by multiplying the second Gaussian distribution value with the pixel value of each pixel in the first crystal pixel lookup table.

5. The method according to claim 1, characterized in that, The step of obtaining the target crystal pixel lookup table based on the first crystal pixel lookup table and the second crystal pixel lookup table includes: The target crystal pixel lookup table is obtained by performing image enhancement processing on the first crystal pixel lookup table and the second crystal pixel lookup table. The image enhancement process includes at least one of the following methods: Perform a flip operation on the first crystal pixel lookup table and the second crystal pixel lookup table; Perform a noise addition operation on the first crystal pixel lookup table and the second crystal pixel lookup table; Perform a smoothing operation on the first crystal pixel lookup table and the second crystal pixel lookup table; Perform contrast processing on the first crystal pixel lookup table and the second crystal pixel lookup table.

6. A crystal pixel lookup table generation device, characterized in that, The device includes: The first determining module is used to determine a preset number of first pixel peak points from the first crystal pixel lookup table; The processing module is used to perform Gaussian processing on the peak points of the first pixel to obtain a first Gaussian distribution value of the peak points of the first pixel; to invert the first Gaussian distribution value according to a preset value to obtain a second Gaussian distribution value; and to obtain a second crystal pixel lookup table according to the second Gaussian distribution value and the first crystal pixel lookup table. The second determining module is used to obtain a target crystal pixel lookup table based on the first crystal pixel lookup table and the second crystal pixel lookup table.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images