Nuclear radiation image enhancement system based on artificial intelligence analysis

Abstract

The invention discloses a nuclear radiation image enhancement system based on artificial intelligence analysis, which belongs to the field of nuclear radiation image processing and comprises a data acquisition module and an image enhancement module. The data acquisition module acquires multi-mode nuclear radiation image data; the image enhancement module comprises an image completion unit, an image compression unit, an image fusion unit and an image correction unit; the image complementation unit carries out image complementation, the image compression unit carries out radiation intensity partitioning and compression on an output preliminary complete image, the image fusion unit fuses the compressed image into a two-channel feature map, and the image correction unit carries out nonlinear correction and then inputs the image to the image complementation unit for final complementation. Through efficient cooperation of a plurality of modules, high-quality nuclear radiation monitoring and analysis are realized, the visual quality is improved, the image readability is improved, the image precision is repaired and enhanced, and on the whole, not only are the image quality and the analysis precision improved, but also powerful support is provided for nuclear radiation monitoring and safety protection.

Description

Technical Field

[0001] The invention belongs to the technical field of nuclear radiation image processing, and in particular relates to a nuclear radiation image enhancement system based on artificial intelligence analysis. Background Art

[0002] In recent years, with the development of nuclear radiation monitoring technology, the application of various detectors and imaging technologies in the fields of nuclear safety, environmental monitoring and medical imaging has received widespread attention. In particular, the synchronous application of gamma cameras and neutron imagers makes multimodal nuclear radiation imaging possible, which can simultaneously obtain image data of gamma radiation and neutron radiation, providing a more comprehensive analysis of nuclear radiation sources. However, the existing technology still faces some challenges, such as noise problems in the image acquisition process, difficulties in completing missing areas of the image, and problems in fusing characteristics of different radiation sources. These problems seriously affect the accuracy and real-time performance of radiation monitoring and hinder its effective application in practical applications. Therefore, the development of an efficient nuclear radiation image enhancement system, especially the combination of artificial intelligence technology for image processing to improve image quality and enhance the ability to identify radiation sources, has become an important issue that needs to be solved urgently.

[0003] In the existing technology, most image enhancement methods still rely on traditional image processing techniques, such as filtering, histogram equalization, etc. These methods often do not work well when processing nuclear radiation images with strong noise and missing information. In addition, the existing image enhancement system lacks intelligent dynamic partition management of radiation intensity areas, which leads to insufficient processing of high, medium and low radiation areas, which may cause misjudgment of nuclear radiation monitoring. By analyzing the shortcomings of the existing technology, it can be seen that the image enhancement method based on artificial intelligence can effectively overcome these limitations.

[0004] In view of the above-mentioned deficiencies in the prior art, our invention provides an innovative solution. Summary of the invention

[0005] In view of the above existing problems, the present invention solves the following technical problem: In nuclear radiation images, due to the limitations of detectors and environmental factors, blind spots and noise interference often occur, resulting in incomplete image information.

[0006] Specifically, it is: how to dynamically divide the radiation intensity areas in the image and adopt appropriate processing methods for different areas to ensure the accuracy and reliability of the image; how to effectively integrate data from different imaging devices to improve image quality, make the radionuclide information clearer and easier to analyze and judge later.

[0007] In order to solve the above technical problems, a nuclear radiation image enhancement system based on artificial intelligence analysis is proposed, including a data acquisition module and an image enhancement module; Data acquisition module, which collects multi-modal nuclear radiation image data and synchronously records the physical parameter metadata of the gamma camera and neutron imager; An image enhancement module, including an image completion unit, an image compression unit, an image fusion unit, and an image correction unit; The image completion unit inputs the collected image into a two-stage generative adversarial network. The first-stage generator completes the missing area and outputs the initial completed image, and the second-stage generator performs texture restoration. The image compression unit performs radiation intensity partitioning on the output preliminary complete image, dynamically divides it into three radiation intensity areas of high, medium and low, and compresses it using a combination strategy of logarithmic transformation and local histogram equalization; An image fusion unit inputs the compressed image into a dual-channel neural network, wherein the dual-channel neural network includes a physical feature channel and a visual feature channel, wherein the physical feature channel analyzes the position of the characteristic peak of the gamma energy spectrum, and the visual feature channel extracts the texture feature, and the feature maps of the two channels are fused through a spatial alignment module; The image correction unit performs spatial feature analysis based on the fused two-channel feature map output by the image fusion unit, and matches the pre-stored geometric distortion parameter set to perform nonlinear correction; The image completion unit inputs the corrected image into the second-stage generator of the two-stage generative adversarial network, and outputs the final enhanced image based on the pre-trained optimized texture details.

[0008] As a preferred solution of the nuclear radiation image enhancement system based on artificial intelligence analysis described in the present invention, the data acquisition module includes a synchronous acquisition device composed of a gamma camera and a neutron imager, which synchronously acquires and generates gamma radiation images and neutron radiation images with aligned timestamps, and simultaneously obtains physical parameter metadata; The gamma radiation image and the neutron radiation image are spliced ​​to obtain spliced ​​image data which is input into an image enhancement module.

[0009] As a preferred solution of the nuclear radiation image enhancement system based on artificial intelligence analysis described in the present invention, wherein: the image completion unit includes a two-stage generative adversarial network including a first-stage generator and a second-stage generator; In the first stage, the generator receives the spliced ​​image data of the gamma radiation image and the neutron radiation image. The operator selects the confidence threshold of the area to be repaired. The generator dynamically adjusts the structural generation intensity of the complement area according to the threshold to select the convolution kernel and select the radiation intensity gradient characteristics of the adjacent area or the neutron radiation image to allocate the complement method. The first stage outputs the initial complement image. The secondary stage generator optimizes texture completion of the initial completion image generated by the primary stage generator.

[0010] As a preferred solution of the nuclear radiation image enhancement system based on artificial intelligence analysis described in the present invention, wherein: the image compression unit includes: performing radiation intensity partitioning on the output initial supplemented image, performing linear normalization, mapping to a standard radiation intensity unit, generating a full-image radiation intensity distribution matrix of the same size as the input image, and calculating a global reference value and a spatial gradient according to the full-image radiation intensity distribution matrix; When the radiation intensity distribution matrix of the whole image in the continuous pixel block is greater than the sum of the pixel standard deviation of the whole image and the global reference value, the current area is marked as a high radiation area, and the high radiation area is compressed by adaptive logarithmic transformation; When the full-image radiation intensity distribution matrix is ​​less than or equal to the sum of the full-image pixel standard deviation and the global benchmark value and greater than or equal to the difference between the global benchmark value and the full-image pixel standard deviation, the current area is marked as a medium radiation area; when the full-image radiation intensity distribution matrix is ​​less than the difference between the global benchmark value and the full-image pixel standard deviation, the current area is marked as a low radiation area; for medium and low radiation areas, the local histogram equalization window size is used to compress according to the radiation intensity; For medium radiation area and low radiation area, a transition zone with adjustable width is generated at the boundary of adjacent areas. The transition zone range is marked with a semi-transparent color band, and the compression intensity of the pixels in the transition zone is linearly interpolated.

[0011] As a preferred solution of the nuclear radiation image enhancement system based on artificial intelligence analysis described in the present invention, wherein: the image fusion unit includes inputting the compressed image into a dual-channel neural network, including physical features and visual feature channels, and fusing the two-channel feature maps through a spatial alignment module; The physical feature channel analyzes the characteristic peak position of the gamma energy spectrum, selects the characteristic peak position according to the characteristic energy spectrum data of the radionuclide contained in the gamma radiation image, calls the structure generation intensity parameter of the complement area of ​​the initial complement image, applies a compensation offset to the characteristic peak position of the energy spectrum of the complement area, and generates a compensated physical feature map; The visual feature channel extracts texture features, sets extraction weights for the texture features of the complemented area, and generates a weighted visual feature map; A two-dimensional coordinate system is constructed in the compensated physical feature map and the weighted visual feature map, and the energy spectrum peak position coordinates of the compensated physical feature map are matched with the texture centroid coordinates of the weighted visual feature map. Rigid registration is used for the non-completed area, and elastic deformation registration is used for the completed area. The registration error map is output for manual review, and the area with excessive errors is returned to the image completion unit stage for regeneration, and the matched fusion feature map is output.

[0012] As a preferred solution of the nuclear radiation image enhancement system based on artificial intelligence analysis described in the present invention, wherein: the image correction unit includes, based on the output fusion feature map, performing spatial feature analysis, extracting distortion features, superimposing an equally spaced orthogonal line array on the fusion feature map, tracking the grid intersection offset of the feature peak, and identifying radial distortion and tangential distortion; The radial distortion coefficient is calculated by fitting the offset-radius square curve; the tangential distortion coefficient is determined by calculating the average value of the tangential offset vector of the feature point; Construct a two-stream convolutional network containing radial distortion sensitive channels and tangential distortion sensitive channels; A geometric distortion parameter knowledge base is established to store correction parameter combinations under typical working conditions. The radial distortion or tangential distortion feature vector output by the feature analysis layer is used to calculate the cosine similarity with the knowledge base. The top three parameter combinations with the highest similarity are selected, and the selected parameter combinations are weighted averaged. The weights are dynamically adjusted according to the historical correction success rate of each combination. An automatic correction strategy is implemented according to the radial distortion coefficient and the tangential distortion coefficient. Adjustments are made according to the corrected coordinates, and the corrected image data is output.

[0013] As a preferred solution of the nuclear radiation image enhancement system based on artificial intelligence analysis described in the present invention, wherein: the image completion unit further comprises: the second-stage generator in the two-stage generative adversarial network adopted by the image completion unit receives the corrected image data; A shared texture feature library is established to store standard texture templates under typical working conditions. According to the correlation mapping relationship between the corrected image data and the shared texture feature library, the standard texture template with the highest matching degree is automatically selected. The matching process is based on the following priority order: The first priority is the standard texture corresponding to the identified nuclides in the current processed image, the second priority is the historical case texture with similar radiation intensity distribution, and the third priority is the general radioactive material basic texture; The second-stage generator receives the corrected image data and the matching texture template, performs gradient detection on the edge connection zone of the completed area, and automatically starts transition smoothing when it detects that the grayscale jump exceeds the average gradient value of the adjacent area; According to the divided radiation intensity areas, the texture generation intensity is dynamically adjusted. High-frequency texture enhancement is used in high-radiation areas, and the basic texture resolution is maintained in low-radiation areas. The corrected coordinate data is called to ensure that the directionality of the generated texture is consistent with the actual radiation distribution pattern.

[0014] Another object of the present invention is to provide a nuclear radiation image enhancement method based on artificial intelligence analysis.

[0015] As a preferred solution of the nuclear radiation image enhancement method based on artificial intelligence analysis described in the present invention, it includes: The data acquisition module collects multi-modal nuclear radiation image data and synchronously records the physical parameter metadata of the gamma camera and neutron imager; The image completion unit inputs the collected image into a two-stage generative adversarial network. The first-stage generator completes the missing area and outputs the initial completed image, and the second-stage generator performs texture restoration. The image compression unit partitions the output preliminary complete image into radiation intensity zones, dynamically divides the zone into three radiation intensity zones: high, medium and low, and compresses the zone using a combination of logarithmic transformation and local histogram equalization strategies. The image fusion unit inputs the compressed image into a dual-channel neural network, wherein the dual-channel neural network includes a physical feature channel and a visual feature channel, wherein the physical feature channel analyzes the characteristic peak position of the gamma energy spectrum, and the visual feature channel extracts the texture feature, and the feature maps of the two channels are fused through a spatial alignment module; The image correction unit performs spatial feature analysis based on the output fusion feature map and matches the pre-stored geometric distortion parameter set for nonlinear correction; The image completion unit inputs the corrected image into the second-stage generator of the two-stage generative adversarial network, and outputs the final enhanced image based on the pre-trained optimized texture details.

[0016] The beneficial effects of the present invention are as follows: high-quality nuclear radiation monitoring and analysis are achieved through efficient collaboration of multiple modules. The data acquisition module uses the synchronous acquisition of the gamma camera and the neutron imager to ensure the accuracy and integrity of the data; the image completion unit in the image enhancement module dynamically optimizes the image completion and texture restoration through a two-stage generative adversarial network to improve the visual quality; the image compression unit distinguishes the compression strategy according to the radiation intensity to improve the image readability; the image fusion unit integrates physical and visual features in a dual-channel neural network to ensure the integrity of the information; the image correction unit enhances the image accuracy through geometric distortion restoration; the second-stage completion unit uses a shared texture feature library to optimize texture matching and improve detail performance. Overall, the optimization of each link of the system not only improves the image quality and analysis accuracy, but also provides strong support for nuclear radiation monitoring and safety protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which: Figure 1 A system solution module diagram of a nuclear radiation image enhancement system based on artificial intelligence analysis provided by one embodiment of the present invention.

[0018] Figure 2 An overall flow chart of a nuclear radiation image enhancement method based on artificial intelligence analysis provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0020] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides a nuclear radiation image enhancement system based on artificial intelligence analysis, including a data acquisition module and an image enhancement module.

[0021] S1: Data acquisition module, which collects multi-modal nuclear radiation image data and synchronously records the physical parameter metadata of the gamma camera and neutron imager.

[0022] It should be noted that the synchronous acquisition device composed of a gamma camera and a neutron imager is used, and the detection plane of the acquisition device is The adjustable angle is fixedly installed to synchronously collect and generate gamma radiation images and neutron radiation images with time stamp alignment, and obtain physical parameter metadata at the same time. By setting up the synchronous acquisition device of the gamma camera and the neutron imager, an efficient data acquisition mechanism is created, and the time stamp alignment of the gamma radiation image and the neutron radiation image is achieved. By recording the radiation parameters and blind area information in detail, the accuracy and integrity of the data are ensured.

[0023] The gamma radiation image includes characteristic energy spectrum data and spatial intensity characteristics of radionuclides.

[0024] The neutron radiation image includes light element attenuation coefficient distribution data and spatial density distribution.

[0025] The gamma radiation image and the neutron radiation image are spliced ​​to obtain spliced ​​image data which is input into the image enhancement module.

[0026] The physical parameter metadata includes the radiation source activity value, the detector distance parameter and the acquisition time length during acquisition, which are embedded in the image file header as metadata.

[0027] S2: Image enhancement module, including image completion unit, image compression unit, image fusion unit and image correction unit.

[0028] S201: Image completion unit, inputs the collected image into a two-stage generative adversarial network, the first-stage generator completes the missing area and outputs the initial completed image, and the second-stage generator performs texture repair.

[0029] It should be noted that the image completion unit uses a two-stage generative adversarial network, which includes a first-stage generator and a second-stage generator. The two-stage generative adversarial network is used to achieve image completion and texture restoration, and the missing area can be quickly filled in a short time.

[0030] In the first stage, the generator receives the stitched image data of the gamma radiation image and the neutron radiation image. The operator selects the confidence threshold of the area to be repaired, and the generator dynamically adjusts the structure generation intensity of the completed area according to the threshold.

[0031] The first stage generator receives the stitched image data and receives the confidence threshold parameters set by the operator through the interactive interface. , the range is set to 0.3-0.7. The first stage generator calculates the structure generation strength value according to the confidence threshold parameter, and the first stage outputs the initial completed image.

[0032] When the structure generation strength value is greater than 0.6, the first-stage generator uses a 3×3 small convolution kernel and prioritizes the adjacent region radiation intensity gradient features for completion.

[0033] When the structure generation strength value is less than or equal to 0.6, the first-stage generator switches to a 5×5 large convolution kernel for regional feature inference, and completes it with the light element attenuation coefficient distribution data in the neutron radiation image, calling the light element distribution data of the neutron image to fill in the large missing area; The structure generation strength is defined as the structural continuity level between the completed region and the original region. The structure generation strength determines the reuse priority of adjacent features in the completion process and is calculated as follows: in, Generate strength for the structure, The confidence threshold set by the operator, dimensionless (the operator sets a pure number); is the structural sensitivity coefficient (for example, it can be set to 0.8), dimensionless (the operator sets a pure number); Generates strength as a basis (e.g. can be set to 0.2), dimensionless (the operator sets a pure number).

[0034] The first-stage generator dynamically optimizes the completion process according to the set confidence threshold, so that the completed area maintains a high structural similarity with the original image.

[0035] It should also be noted that the second-stage generator optimizes the texture completion of the image data generated in the first stage, as specifically shown in S205.

[0036] It should be noted that the generators that can be used in both the first-stage generator and the second-stage generator, for example, the first-stage generator can be but not limited to U-Net generator, ResNet generator, and the second-stage generator can be but not limited to Autoencoder (self-encoder), Transformer-based texture generation network; In addition, the input layer of the device generated in the first stage accepts the spliced ​​image data of the gamma radiation image and the neutron radiation image. The convolution layer uses a 3×3 or 5×5 convolution kernel, and the specific selection depends on the structure generation strength; the normalization layer: batch normalization is used to stabilize the training process; the activation function: ReLU is used as a nonlinear transformation to improve the expression ability of the model; the output layer generates the initial completed image; the loss function of the first stage includes structural loss and adversarial loss.

[0037] The structural parameters of the second-stage generator include: input layer, which accepts the initial completed image output by the first-stage generator; texture feature extraction layer, which uses 11×11 or 21×21 convolution windows for local texture extraction; skip connection, adaptive normalization and output layer; the loss function of the second stage includes texture consistency loss and style loss.

[0038] The second-stage generator ensures that the texture of the generated image is natural, achieving the purpose of improving the visual effect. This not only improves the visual quality of the image, but also provides a more reliable information basis for subsequent analysis.

[0039] S202: Image compression unit, which performs radiation intensity partitioning on the output preliminary complete image, dynamically divides it into three radiation intensity areas of high, medium and low, and compresses it using a combination strategy of logarithmic transformation and local histogram equalization. Dynamically dividing the radiation intensity areas and using different compression strategies effectively improves the readability and analysis efficiency of the image.

[0040] It should be noted that the output initial completed image is partitioned by radiation intensity, dynamically divided into three radiation intensity areas of high, medium and low, and compressed using a combination of logarithmic transformation and local histogram equalization strategies.

[0041] The output initial completed image is partitioned by radiation intensity, linearly normalized, and mapped to standard radiation intensity units to generate a full-image radiation intensity distribution matrix of the same size as the input image. The global reference value and spatial gradient are calculated based on the full-image radiation intensity distribution matrix.

[0042] The global benchmark value is calculated by the mean and standard deviation of all pixels in the whole image, and the final benchmark value is determined according to the ratio of the completed area to the total area.

[0043] The spatial gradient calculates the eight-neighborhood comprehensive gradient for each pixel point through the Euclidean distance.

[0044] When the radiation intensity distribution matrix of the entire image in continuous pixel blocks is greater than the sum of the standard deviation of the pixels in the entire image and the global benchmark value, the current area is marked as a high radiation area, the system automatically displays the outline of the high radiation area, and the operator manually excludes the misjudged area.

[0045] When the radiation intensity distribution matrix of the entire image is less than or equal to the sum of the pixel standard deviation of the entire image and the global benchmark value and is greater than or equal to the difference between the global benchmark value and the pixel standard deviation of the entire image, the current area is marked as a medium radiation area.

[0046] When the radiation intensity distribution matrix of the entire image is smaller than the difference between the global benchmark value and the standard deviation of the pixels in the entire image, the current area is marked as a low radiation area.

[0047] For the medium radiation area and the low radiation area, a transition zone with adjustable width (for example, a width of 5 pixels) is generated at the boundary of adjacent areas.

[0048] Compression processing of different radiation zones: Adaptive logarithmic transformation is used to compress the dynamic range of high-radiance areas to avoid oversaturation while preserving details: ,in, is the dynamic compression result of M(x,y), It is the compression factor that the operator adjusts in real time through the slider, dimensionless (the operator sets a pure number); is the radiation intensity distribution matrix of the whole image, dimensionless (normalized pixel value, range 0~1); The system displays a real-time highlight clipping warning and automatically reduces the threshold when it detects that the ratio of oversaturated pixels exceeds the set threshold. value.

[0049] For medium and low radiation areas, local histogram equalization is used and the window size is dynamically adjusted according to the radiation intensity. An 11×11 window is used in the medium radiation area and a 21×21 window is used in the low radiation area.

[0050] Transition zone processing uses a semi-transparent color band to mark the transition zone range and performs linear interpolation on the compression intensity of pixels within the transition zone.

[0051] Through efficient logarithmic transformation and local histogram equalization, the visualization of important information in the image is enhanced, ensuring that high-radiation areas are clearly identifiable, which facilitates further image analysis and monitoring and improves the ability to respond to potential radiation risks.

[0052] S203: An image fusion unit inputs the compressed image into a dual-channel neural network, wherein the dual-channel neural network includes a physical feature channel and a visual feature channel. The physical feature channel analyzes the characteristic peak position of the gamma energy spectrum, and the visual feature channel extracts texture features. The feature maps of the two channels are fused through a spatial alignment module to achieve more comprehensive information extraction.

[0053] It should be noted that the image fusion unit inputs the compressed image into a dual-channel neural network, including physical feature and visual feature channels, and fuses the two-channel feature maps through a spatial alignment module; The physical characteristic channel analyzes the characteristic peak position of the gamma energy spectrum, selects the characteristic peak position according to the characteristic energy spectrum data of the radionuclide contained in the gamma radiation image, calls the structure generation intensity parameter of the complement area of ​​the initial complement image, and applies a compensation offset to the characteristic peak position of the energy spectrum of the complement area. Calculation Satisfaction ,in, is the preset basic compensation coefficient, pixel unit (such as =2 means maximum compensation of 2 pixels), to generate the compensated physical feature map.

[0054] The visual feature channel extracts texture features and extracts weights for the texture features of the complement area. Set to ,in is an adjustable scaling factor.

[0055] The operator adjusts The system automatically generates a semi-transparent marking frame in the dislocated area when the feature misalignment area is detected. The operator clicks the marking frame to trigger the local realignment operation, and the system automatically optimizes the area. value, and generate a weighted visual feature map.

[0056] A two-dimensional coordinate system is constructed in the compensated physical feature map and the weighted visual feature map. The energy spectrum peak position coordinates of the compensated physical feature map are matched with the texture centroid coordinates of the weighted visual feature map. Rigid registration is used for the non-completed area, and elastic deformation registration is used for the completed area. The registration error map is output for manual review. The area where the error exceeds the limit needs to be returned to the image completion unit stage for regeneration.

[0057] The fused feature map not only ensures the integrity of information, but also improves the accuracy and efficiency of subsequent analysis, making the monitoring and management of nuclear radiation more efficient.

[0058] It should be noted that the physical feature channel mainly focuses on the analysis and compensation of the gamma energy spectrum to ensure that the characteristic energy spectrum data of the radionuclides contained in the gamma radiation image are effectively extracted, and is optimized in combination with the structure completion results, using a common architecture as the basis; The physical feature channel uses a convolutional neural network (CNN) architecture combined with spectrum analysis; The input layer receives the compressed image and generates intensity parameters based on the structure of the initial completed region of the completed image. The feature extraction layer (CNN layer) uses a 3×3 or 5×5 convolution kernel for feature extraction. When analyzing the spectrum, Fourier transform (FFT) or wavelet transform (Wavelet Transform) is used to extract the feature peak position. The output layer generates a physical feature map. Visual feature channel, using but not limited to deep residual network (ResNet) or VGG style feature extraction network; The input layer receives the compressed image and the texture data of the initial completed image, calculates the texture extraction weights, and the feature extraction layer (ResNet / VGG) can, but is not limited to, use 5×5 or 7×7 convolution kernels to extract local texture features, generate weighted visual feature maps, and output the final fusion results.

[0059] S204: The image correction unit performs spatial feature analysis based on the fused two-channel feature map output by the image fusion unit, and matches the pre-stored geometric distortion parameter set to perform nonlinear correction.

[0060] Furthermore, based on the fused two-channel feature map output by the image fusion unit, spatial feature analysis is performed, distortion features are extracted, and an equally spaced orthogonal line array is superimposed on the feature map. The grid intersection offset of the feature peak is tracked, and radial distortion and tangential distortion are identified. This realizes the repair of image geometric distortion and ensures the geometric accuracy of the output image.

[0061] The radial distortion is defined as: calculating the growth rate of the offset from the central area to the edge area, and marking it as radial distortion when the growth rate exceeds a linear threshold; The tangential distortion is defined as: an asymmetric shift of the detection feature point along the diagonal direction of the image, where the shift direction is associated with the detector installation inclination angle; The radial distortion coefficients k1 and k2 are calculated by fitting the offset-radius square curve; the tangential distortion coefficients p1 and p2 are determined by calculating the average value of the tangential offset vector of the feature point, where k1 represents the quadratic radial distortion from the center to the edge of the image (for example, correcting the "barrel distortion" or "pincushion distortion" caused by the curvature of the gamma camera lens), k2 represents the fourth-power radial distortion compensation (for example, correcting the correction residual error of k1 in the high radiation intensity area), p1 represents the rotational asymmetric distortion in the XY plane, and p2 represents the distortion coupling in the diagonal direction; Construct a two-stream convolutional network containing radial distortion sensitive channels and tangential distortion sensitive channels: The radial sensitive channel uses a circular convolution kernel group to detect the curvature abnormality characteristics of the edge area of ​​the image; the tangential sensitive channel uses an oblique convolution kernel to capture the pixel offset characteristics in the diagonal direction; Establish a geometric distortion parameter knowledge base to store correction parameter combinations under typical working conditions. Perform cosine similarity calculation between the radial distortion or tangential distortion feature vector output by the feature analysis layer and the knowledge base. Select the top three parameter combinations with the highest similarity and perform weighted averaging on the selected parameter combinations. The weights are dynamically adjusted based on the historical correction success rate of each combination. An automatic correction strategy is implemented. According to the radial distortion coefficient and the tangential distortion coefficient, the following correction equation is executed to eliminate the radial distortion and tangential distortion caused by the gamma camera lens:

[0062]

[0063] in, is the original coordinate, in pixels; is the corrected coordinate, , pixel square unit; Adjustments are made according to the corrected coordinates and the corrected image data are outputted. The present invention combines the detection of radial and tangential distortions, can accurately identify feature offsets, greatly reduce misjudgments caused by distortion, and improve the credibility of images and their analysis.

[0064] S205: The image completion unit also includes a second-stage generator in a two-stage generative adversarial network adopted by the image completion unit to receive the corrected image data, thereby effectively improving the detail expression of the image.

[0065] A shared texture feature library is established to store standard texture templates under typical working conditions. According to the correlation mapping relationship between the corrected image data and the shared texture feature library, the standard texture template with the highest matching degree is automatically selected. The matching process is based on the following priority order: The first priority is the standard texture corresponding to the identified nuclides in the current processed image, the second priority is the historical case texture with similar radiation intensity distribution, and the third priority is the general radioactive material basic texture; The second-stage generator receives the corrected image data and the matching texture template, performs gradient detection on the edge connection zone of the completed area, and automatically starts transition smoothing when it detects that the grayscale jump exceeds the average gradient value of the adjacent area; According to the divided radiation intensity areas, the texture generation intensity is dynamically adjusted, high-frequency texture enhancement is adopted in high-radiation areas, and the basic texture resolution is maintained in low-radiation areas. The corrected coordinate data is called to ensure that the directionality of the generated texture is consistent with the actual radiation distribution pattern. The present invention can automatically optimize texture matching according to historical cases, ensure the propagation effect and information integrity of the image in the real scene, and help to better reflect the actual radiation distribution.

[0066] Example 2, reference Figure 2 , which is the second embodiment of the present invention, provides a nuclear radiation image enhancement method based on artificial intelligence analysis, comprising: The data acquisition module collects multi-modal nuclear radiation image data and synchronously records the physical parameter metadata of the gamma camera and neutron imager; The image completion unit inputs the collected image into a two-stage generative adversarial network. The first-stage generator completes the missing area and outputs the initial completed image, and the second-stage generator performs texture restoration. The image compression unit partitions the output initial completed image by radiation intensity, dynamically divides it into three radiation intensity areas of high, medium and low, and compresses it by using a combination strategy of logarithmic transformation and local histogram equalization. The image fusion unit inputs the compressed image into a dual-channel neural network, wherein the dual-channel neural network includes a physical feature channel and a visual feature channel, wherein the physical feature channel analyzes the characteristic peak position of the gamma energy spectrum, and the visual feature channel extracts the texture feature, and the feature maps of the two channels are fused through a spatial alignment module; The image correction unit performs spatial feature analysis based on the fused two-channel feature map output by the image fusion unit, and matches the pre-stored geometric distortion parameter set to perform nonlinear correction; The image completion unit inputs the corrected image into the second-stage generator of the two-stage generative adversarial network, and outputs the final enhanced image based on the pre-trained optimized texture details.

[0067] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A nuclear radiation image enhancement system based on artificial intelligence analysis, characterized by: Including data acquisition module and image enhancement module; Data acquisition module, which collects multi-modal nuclear radiation image data and synchronously records the physical parameter metadata of the gamma camera and neutron imager; An image enhancement module, including an image completion unit, an image compression unit, an image fusion unit, and an image correction unit; The image completion unit inputs the collected image into a two-stage generative adversarial network. The first-stage generator completes the missing area and outputs the initial completed image, and the second-stage generator performs texture restoration. The first-stage generator is based on the architecture of the U-Net generator, and the second-stage generator is based on the architecture of the texture generation network. The image compression unit performs radiation intensity partitioning on the output preliminary complete image, dynamically divides it into three radiation intensity areas of high, medium and low, and compresses it using a combination strategy of logarithmic transformation and local histogram equalization; The image fusion unit inputs the compressed image into a dual-channel neural network, wherein the dual-channel neural network includes a physical feature channel and a visual feature channel, wherein the physical feature channel analyzes the characteristic peak position of the gamma energy spectrum, and the visual feature channel extracts the texture feature, and fuses the two-channel feature maps through a spatial alignment module; wherein the physical feature channel adopts a convolutional neural network combined with a spectrum analysis architecture, and the visual feature channel adopts a deep residual network or a VGG style feature extraction network architecture; The image correction unit performs spatial feature analysis based on the fused two-channel feature map output by the image fusion unit, and matches the pre-stored geometric distortion parameter set to perform nonlinear correction; The image completion unit inputs the corrected image into the second-stage generator of the two-stage generative adversarial network, and outputs the final enhanced image based on the pre-trained optimized texture details.

2. The nuclear radiation image enhancement system based on artificial intelligence analysis as claimed in claim 1, characterized in that: The data acquisition module includes a synchronous acquisition device composed of a gamma camera and a neutron imager, which synchronously acquires and generates gamma radiation images and neutron radiation images with aligned timestamps, and simultaneously acquires physical parameter metadata; The gamma radiation image and the neutron radiation image are spliced ​​to obtain spliced ​​image data which is input into an image enhancement module.

3. The nuclear radiation image enhancement system based on artificial intelligence analysis as claimed in claim 2, characterized in that: The image completion unit includes, using a two-stage generative adversarial network including a first-stage generator and a second-stage generator; In the first stage, the generator receives the spliced ​​image data of the gamma radiation image and the neutron radiation image. The operator selects the confidence threshold of the area to be repaired. The generator dynamically adjusts the structural generation intensity of the complement area according to the threshold to select the convolution kernel and select the radiation intensity gradient characteristics of the adjacent area or the neutron radiation image to allocate the complement method. The first stage outputs the initial complement image. The secondary stage generator optimizes texture completion of the initial completion image generated by the primary stage generator.

4. The nuclear radiation image enhancement system based on artificial intelligence analysis as claimed in claim 3, characterized in that: The image compression unit includes: partitioning the output initial complement image by radiation intensity, performing linear normalization, mapping to a standard radiation intensity unit, generating a full-image radiation intensity distribution matrix of the same size as the input image, and calculating a global reference value and a spatial gradient according to the full-image radiation intensity distribution matrix; When the radiation intensity distribution matrix of the whole image in the continuous pixel block is greater than the sum of the pixel standard deviation of the whole image and the global reference value, the current area is marked as a high radiation area, and the high radiation area is compressed by adaptive logarithmic transformation; When the full-image radiation intensity distribution matrix is ​​less than or equal to the sum of the full-image pixel standard deviation and the global benchmark value and greater than or equal to the difference between the global benchmark value and the full-image pixel standard deviation, the current area is marked as a medium radiation area; when the full-image radiation intensity distribution matrix is ​​less than the difference between the global benchmark value and the full-image pixel standard deviation, the current area is marked as a low radiation area; For medium and low radiation areas, the window size of local histogram equalization is compressed according to the radiation intensity; For medium radiation area and low radiation area, a transition zone with adjustable width is generated at the boundary of adjacent areas. The transition zone range is marked with a semi-transparent color band, and the compression intensity of the pixels in the transition zone is linearly interpolated.

5. The nuclear radiation image enhancement system based on artificial intelligence analysis as claimed in claim 4, characterized in that: The image fusion unit includes inputting the compressed image into a dual-channel neural network, including physical feature and visual feature channels, and fusing the two-channel feature maps through a spatial alignment module; The physical feature channel analyzes the characteristic peak position of the gamma energy spectrum, selects the characteristic peak position according to the characteristic energy spectrum data of the radionuclide contained in the gamma radiation image, calls the structure generation intensity parameter of the complement area of ​​the initial complement image, applies a compensation offset to the characteristic peak position of the energy spectrum of the complement area, and generates a compensated physical feature map; The visual feature channel extracts texture features, sets extraction weights for the texture features of the complemented area, and generates a weighted visual feature map; A two-dimensional coordinate system is constructed in the compensated physical feature map and the weighted visual feature map, and the energy spectrum peak position coordinates of the compensated physical feature map are matched with the texture centroid coordinates of the weighted visual feature map. Rigid registration is used for the non-completed area, and elastic deformation registration is used for the completed area. The registration error map is output for manual review, and the area with excessive errors is returned to the image completion unit stage for regeneration, and the matched fusion feature map is output.

6. The nuclear radiation image enhancement system based on artificial intelligence analysis as claimed in claim 5, characterized in that: The image correction unit includes, based on the output fusion feature map, performing spatial feature analysis, extracting distortion features, superimposing an equally spaced orthogonal line array on the fusion feature map, tracking the grid intersection offset of the feature peak, and identifying radial distortion and tangential distortion; The radial distortion coefficient is calculated by fitting the offset-radius square curve; the tangential distortion coefficient is determined by calculating the average value of the tangential offset vector of the feature point; Construct a two-stream convolutional network containing radial distortion sensitive channels and tangential distortion sensitive channels; A geometric distortion parameter knowledge base is established to store correction parameter combinations under typical working conditions. The radial distortion or tangential distortion feature vector output by the feature analysis layer is used to calculate the cosine similarity with the knowledge base. The top three parameter combinations with the highest similarity are selected, and the selected parameter combinations are weighted averaged. The weights are dynamically adjusted according to the historical correction success rate of each combination. An automatic correction strategy is implemented according to the radial distortion coefficient and the tangential distortion coefficient. Adjustments are made according to the corrected coordinates, and the corrected image data is output.

7. The nuclear radiation image enhancement system based on artificial intelligence analysis as claimed in claim 6, characterized in that: The image completion unit further includes a second-stage generator in a two-stage generative adversarial network adopted by the image completion unit receiving the corrected image data; A shared texture feature library is established to store standard texture templates under typical working conditions. According to the correlation mapping relationship between the corrected image data and the shared texture feature library, the standard texture template with the highest matching degree is automatically selected. The matching process is based on the following priority order: The first priority is the standard texture corresponding to the identified nuclides in the current processed image, the second priority is the historical case texture with similar radiation intensity distribution, and the third priority is the general radioactive material basic texture; The second-stage generator receives the corrected image data and the matching texture template, performs gradient detection on the edge connection zone of the completed area, and automatically starts transition smoothing when it detects that the grayscale jump exceeds the average gradient value of the adjacent area; According to the divided radiation intensity areas, the texture generation intensity is dynamically adjusted. High-frequency texture enhancement is used in high-radiation areas, and the basic texture resolution is maintained in low-radiation areas. The corrected coordinate data is called to ensure that the directionality of the generated texture is consistent with the actual radiation distribution pattern.

8. A method for enhancing nuclear radiation images based on artificial intelligence analysis, applied to a nuclear radiation image enhancement system based on artificial intelligence analysis as claimed in any one of claims 1 to 7, characterized in that: include, The data acquisition module collects multi-modal nuclear radiation image data and synchronously records the physical parameter metadata of the gamma camera and neutron imager; The image completion unit inputs the collected image into a two-stage generative adversarial network. The first-stage generator completes the missing area and outputs the initial completed image, and the second-stage generator performs texture restoration. The image compression unit partitions the output preliminary complete image into radiation intensity zones, dynamically divides the zone into three radiation intensity zones: high, medium and low, and compresses the zone using a combination of logarithmic transformation and local histogram equalization strategies. The image fusion unit inputs the compressed image into a dual-channel neural network, wherein the dual-channel neural network includes a physical feature channel and a visual feature channel, wherein the physical feature channel analyzes the characteristic peak position of the gamma energy spectrum, and the visual feature channel extracts the texture feature, and the feature maps of the two channels are fused through a spatial alignment module; The image correction unit performs spatial feature analysis based on the fused two-channel feature map output by the image fusion unit, and matches the pre-stored geometric distortion parameter set to perform nonlinear correction; The image completion unit inputs the corrected image into the second-stage generator of the two-stage generative adversarial network, and outputs the final enhanced image based on the pre-trained optimized texture details.

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 nuclear radiation image enhancement system based on artificial intelligence analysis described in any one of claims 1 to 7 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 nuclear radiation image enhancement system based on artificial intelligence analysis described in any one of claims 1 to 7 are implemented.

Images