Image processing method and device, computer equipment and storage medium

Abstract

The invention relates to an image processing method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a blood flow information enhanced image of an original blood flow image; determining a target area with image features meeting a preset condition in the blood flow information enhanced image; and performing image optimization processing on the target area in the blood flow information enhanced image by adopting at least part of the original blood flow image to obtain a target blood flow image. By adopting the method, the distortion of blood flow imaging can be effectively reduced, and the definition and accuracy of the blood flow image are remarkably improved.

Description

Technical Field

[0001] The present application relates to the technical field of medical image processing, and in particular to an image processing method, apparatus, computer equipment, storage medium and computer program product. Background Art

[0002] With the development of ultrasound imaging technology, it is widely used in clinical examinations due to its safety, low cost and non-invasive characteristics. Ultrasonic micro-blood flow imaging technology is a new high-resolution blood flow imaging technology developed based on the Doppler principle, which has high sensitivity to low-speed microvessels. It uses advanced tissue clutter filters (such as feature filters, singular value decomposition SVD) to help eliminate clutter and display low-speed blood flow signals in tissue microvessels, thereby improving the display rate of low-speed microvascular blood flow. Due to its powerful display ability for low-speed blood flow, it has gradually been used in clinical practice in recent years.

[0003] In the process of micro blood flow imaging, traditional technology uses morphological filtering algorithms (such as Frangi filter, Jerman filter, etc.) to process micro blood flow images. Although this type of algorithm takes multi-scale blood flow information into consideration at the beginning of its design, when the blood flow size of large vessels is significantly larger than that of small vessels, if you want to ensure that the blood flow of small vessels has a good morphology, the blood flow morphology of large vessels will be destroyed; if you want to ensure that the blood flow of large vessels has a good morphology, the blood flow size of small vessels will become larger, resulting in a certain degree of distortion in micro blood flow imaging using traditional technology. Summary of the invention

[0004] Based on this, it is necessary to provide an image processing method, apparatus, computer equipment, computer-readable storage medium and computer program product that can effectively reduce blood flow imaging distortion in response to the above technical problems.

[0005] In a first aspect, the present application provides an image processing method, comprising:

[0006] Acquire a blood flow information enhanced image of the original blood flow image;

[0007] Determine a target area in the blood flow information enhanced image whose image characteristics meet preset conditions;

[0008] At least a portion of the original blood flow image is used to perform image optimization processing on the target area in the blood flow information enhanced image to obtain a target blood flow image.

[0009] In a second aspect, the present application further provides an image processing device, comprising:

[0010] An image acquisition module, used for acquiring a blood flow information enhanced image of an original blood flow image;

[0011] An image detection module, used to determine a target area in the blood flow information enhanced image whose image features meet preset conditions;

[0012] The image optimization module is used to use at least part of the original blood flow image to perform image optimization processing on the target area in the blood flow information enhanced image to obtain a target blood flow image.

[0013] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0014] Acquire a blood flow information enhanced image of the original blood flow image;

[0015] Determine a target area in the blood flow information enhanced image whose image characteristics meet preset conditions;

[0016] At least a portion of the original blood flow image is used to perform image optimization processing on the target area in the blood flow information enhanced image to obtain a target blood flow image.

[0017] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0018] Acquire a blood flow information enhanced image of the original blood flow image;

[0019] Determine a target area in the blood flow information enhanced image whose image characteristics meet preset conditions;

[0020] At least a portion of the original blood flow image is used to perform image optimization processing on the target area in the blood flow information enhanced image to obtain a target blood flow image.

[0021] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0022] Acquire a blood flow information enhanced image of the original blood flow image;

[0023] Determine a target area in the blood flow information enhanced image whose image characteristics meet preset conditions;

[0024] At least a portion of the original blood flow image is used to perform image optimization processing on the target area in the blood flow information enhanced image to obtain a target blood flow image.

[0025] The above-mentioned image processing method, device, computer equipment, storage medium and computer program product obtain a blood flow information enhanced image of an original blood flow image; determine a target area whose image characteristics meet preset conditions in the blood flow information enhanced image, and use at least part of the original blood flow image to perform image optimization processing on the target area in the blood flow information enhanced image to obtain a target blood flow image; thus, by determining the target area whose image characteristics meet preset conditions in the blood flow information enhanced image of the original blood flow image, it is possible to effectively identify the image area of ​​the blood flow information enhanced image that is destroyed by the blood flow information enhancement operation, and optimize the target area in combination with the original blood flow image. Optimization processing is performed to protect the image area destroyed by the blood flow information enhancement operation, which effectively suppresses the noise interference in the original blood flow image and improves the signal-to-noise ratio of the blood flow image. At the same time, the blood flow signal expression of the target blood flow image is more prominent, and the resolution of hemodynamic characteristics is enhanced, making the blood flow structure and changes more clearly visible. It can not only effectively reduce the distortion of blood flow imaging, but also significantly improve the practicability of the target blood flow image in clinical diagnosis, meet the needs of complex hemodynamic characteristic analysis, and provide high-precision and high-reliability support for the early detection of abnormal areas, precise positioning and dynamic monitoring of subsequent treatment effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 A diagram of an application environment of an image processing method in an embodiment;

[0028] Figure 2 is a schematic flow chart of an image processing method in an embodiment;

[0029] Figure 3 is a flow chart of a first blood flow image protection algorithm in one embodiment;

[0030] Figure 4 is a flow chart of a second blood flow image protection algorithm in one embodiment;

[0031] Figure 5 is a schematic flow chart of a third blood flow image protection algorithm in one embodiment;

[0032] Figure 6 It is a flowchart of a first configuration parameter updating method in an embodiment;

[0033] Figure 7 is a flow chart of a second configuration parameter updating method in an embodiment;

[0034] Figure 8 A schematic diagram of a flow chart of a target area identification method in an embodiment;

[0035] Fig. 9 A processing effect diagram of an image processing method in one embodiment;

[0036] Fig.10 A schematic diagram of a flow chart of an ultrasonic micro-blood flow image processing algorithm in one embodiment;

[0037] Fig.11 A morphological result diagram of ensuring large blood flow and small blood flow morphology respectively by morphological filtering in one embodiment;

[0038] Fig.12 is a structural block diagram of an image processing device in one embodiment;

[0039] Fig.13 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0041] An image processing method provided in an embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 obtains the blood flow information enhanced image through the terminal 102; detects the target area whose image features meet the preset conditions in the blood flow information enhanced image; uses the blood flow information enhanced image or the micro blood flow imaging acquisition data corresponding to the blood flow information enhanced image to optimize the image of the target area in the blood flow information enhanced image to obtain a target blood flow energy map. Among them, the server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0042] In an exemplary embodiment, Figure 2 As shown, an image processing method is provided, which is applied to Figure 1 The server in the example is used to illustrate, including the following steps 202 to 206. Among them:

[0043] Step 202: Acquire a blood flow information enhanced image of the original blood flow image.

[0044] The original blood flow image may refer to a blood flow image that has not been subjected to a blood flow information enhancement operation.

[0045] The blood flow information enhancement operation may refer to an image processing operation for enhancing blood flow information in an original blood flow image. In practical applications, the blood flow information enhancement operation may refer to morphological filtering processing, such as a Frangi filter filtering algorithm or a Jerman filter (Jerman enhancement filter) filtering algorithm, or other similar morphological filtering algorithms.

[0046] In practical applications, the original blood flow image may refer to micro blood flow imaging acquisition data that has not been subjected to a blood flow information enhancement operation.

[0047] The blood flow information enhanced image may refer to a blood flow image that has undergone a blood flow information enhancement operation. In practical applications, the blood flow information enhanced image may be a blood flow energy image or multiple blood flow energy images.

[0048] Among them, the blood flow information enhanced image can be a micro-blood flow energy map that shows the blood flow intensity and energy distribution in microvessels. Through high-resolution imaging technology, such as ultrasonic micro-blood flow imaging, it can quantify and visualize the energy intensity and spatial distribution of blood flow in microvessels. The micro-blood flow energy map reflects the dynamic changes and energy characteristics of micro-blood flow, and is usually used to evaluate tissue perfusion, detect local ischemia, inflammation or tumor blood supply, and provide important imaging basis for disease diagnosis and evaluation of treatment effects.

[0049] Specifically, the imaging device can be aimed at the target area to ensure stability and reduce external interference, and the target area can be scanned using specific optical or ultrasonic technology to capture the dynamic changes of micro-blood flow; blood flow data can be recorded through high frame rate and high resolution imaging technology to generate original imaging sequences, and these original imaging sequences can be preprocessed to remove noise and artifacts; the preprocessed imaging data can be analyzed using algorithms to extract blood flow velocity, direction and other micro-blood flow characteristics, thereby generating micro-blood flow imaging acquisition data, i.e. the above-mentioned original blood flow image. Among them, micro-blood flow imaging acquisition data can reflect the changes in blood flow velocity, direction, density and vascular structure, and is often used to detect and study pathological processes such as microcirculatory disorders, tissue ischemia, and tumor blood supply, which is helpful for early diagnosis, treatment evaluation and prognosis of diseases.

[0050] The above-mentioned micro-blood flow imaging acquisition data can be subjected to tissue clutter filtering (also known as wall filtering) to obtain a number of blood flow energy images after wall filtering; then the blood flow energy images after wall filtering are further subjected to morphological filtering processing. In some specific embodiments, a Frangi filter filtering algorithm or a Jerman filter filtering algorithm or other similar morphological filtering algorithms can be used to perform morphological filtering processing on a number of blood flow energy images after wall filtering to obtain a blood flow information enhanced image. Fig.11 As shown, Fig.11 The left sub-image is the original blood flow image. Fig.11 The middle sub-image is the blood flow information enhanced image obtained by morphological filtering the original blood flow image. Fig.11 The right sub-image is the target blood flow image.

[0051] Step 204: determine a target area in the blood flow information enhanced image whose image features meet preset conditions.

[0052] The preset condition may be a judgment condition for judging whether there is distortion in the blood flow information enhanced image.

[0053] The target area may be a blood flow area where image distortion exists in the blood flow information enhanced image.

[0054] In practical applications, the target area may refer to the damaged blood flow area of ​​large vessels or small vessels in the blood flow information enhanced image; specifically, when the blood flow information enhanced image is an image obtained by performing a blood flow information enhancement operation on small vessels in the original blood flow image, the target area may refer to the damaged blood flow area of ​​large vessels in the blood flow information enhanced image; conversely, when the blood flow information enhanced image is an image obtained by performing a blood flow information enhancement operation on large vessels in the original blood flow image, the target area may refer to the damaged blood flow area of ​​small vessels in the blood flow information enhanced image. In other words, the target area may refer to the blood flow area of ​​the vessel damaged by the blood flow information enhancement operation.

[0055] Specifically, on the blood flow information enhanced image, image processing technology can be used to extract and analyze the characteristic information of blood flow to detect the target area that meets the preset conditions, that is, the blood flow area with image distortion. In the specific implementation process, edge detection, region growing, convolutional neural network (CNN) and other algorithms can be used to capture the blood flow characteristic information in the image, including signal intensity distribution, gradient changes, morphological characteristics and spatial position. The preset conditions are usually set according to clinical needs, such as image distortion reaching a certain threshold, specific texture features in the image, or unclear anatomical distribution. In order to improve the accuracy of detection, a multi-scale analysis method can be introduced to perform hierarchical screening of regions, combined with morphological operations to eliminate noise interference, and regional classification through statistical evaluation or deep learning models to determine the target area in the blood flow information enhanced image.

[0056] Step 206: Using at least part of the original blood flow image, perform image optimization processing on the target area in the blood flow information enhanced image to obtain a target blood flow image.

[0057] Among them, the original blood flow image includes microblood flow imaging acquisition data, which may refer to the information of blood flow dynamics of tiny blood vessels (microvessels) in tissues captured and recorded by high-resolution imaging technology (such as ultrasonic microblood flow imaging, laser Doppler imaging, photoacoustic imaging, etc.).

[0058] The target blood flow image may be a blood flow energy image excluding distortion of a blood vessel blood flow region (target region).

[0059] Specifically, at least part of the blood flow information in the original blood flow image can be used to perform image optimization processing on at least one target area in the blood flow information enhanced image, that is, each distorted blood vessel blood flow area, such as applying advanced filtering technology, image enhancement algorithm or adaptive smoothing processing to eliminate image distortion and noise, so that the generated target blood flow image not only retains the detailed features of the blood vessels, but also retains the blood flow information of the blood vessels destroyed by the blood flow information enhancement operation. Fig. 9 As shown, Fig. 9 The left sub-image is the original blood flow image. Fig. 9 The middle sub-image is the blood flow information enhanced image obtained after the original blood flow image is filtered by morphology. Fig. 9 The right sub-image is the target blood flow image obtained after image optimization of the target area in the blood flow information enhanced image. Fig. 9 It can be seen from the three sub-figures that after optimizing the image distortion in the target area of ​​the blood flow information enhanced image, the situation of the target object in this area can be seen more clearly. The flowchart of the corresponding ultrasonic micro blood flow image processing algorithm is shown in Fig.10As shown. Among them, the system can obtain a set of micro blood flow imaging acquisition data, perform tissue clutter filtering on the micro blood flow imaging acquisition data, and obtain tissue clutter filtering results; then, perform morphological filtering operations on the tissue clutter filtering results to obtain a blood flow information enhanced image; then, determine whether there is a damaged large blood vessel blood flow area in the blood flow information enhanced image; if so, use a large blood vessel blood flow protection algorithm to optimize the damaged large blood vessel blood flow area, and obtain a target blood flow image after a post-processing module. Then, obtain the next set of micro blood flow imaging acquisition data, and return to the step of performing tissue clutter filtering on the micro blood flow imaging acquisition data.

[0060] In the above-mentioned image processing method, a blood flow information enhanced image of an original blood flow image is obtained; a target area whose image characteristics meet preset conditions in the blood flow information enhanced image is determined, and at least part of the original blood flow image is used to perform image optimization processing on the target area in the blood flow information enhanced image to obtain a target blood flow image; thus, by determining the target area whose image characteristics meet preset conditions in the blood flow information enhanced image of the original blood flow image, it is possible to effectively identify the image area of ​​the blood flow information enhanced image that is destroyed by the blood flow information enhancement operation, and optimize the target area in combination with the original blood flow image, thereby achieving the target blood flow image. The image area destroyed by the blood flow information enhancement operation is protected, which effectively suppresses the noise interference in the original blood flow image and improves the signal-to-noise ratio of the blood flow image. At the same time, the blood flow signal expression of the target blood flow image is more prominent, and the resolution of the hemodynamic characteristics is enhanced, making the blood flow structure and changes more clearly visible. It can not only effectively reduce the distortion of blood flow imaging, but also significantly improve the practicability of the target blood flow image in clinical diagnosis, meet the needs of complex hemodynamic characteristic analysis, and provide high-precision and high-reliability support for the early detection of abnormal areas, precise positioning and dynamic monitoring of subsequent treatment effects.

[0061] In an exemplary embodiment, Figure 3 As shown, at least part of the original blood flow image is used to perform image optimization processing on the target area in the blood flow information enhanced image to obtain a target blood flow image, including steps 302 to 304. Among them:

[0062] Step 302: Determine, in the original blood flow image, an original image region that matches the target position information.

[0063] The target position information is the position information of the target region in the blood flow information enhanced image. In practical applications, the target position information may refer to the boundary information, coordinate information or mask information of the target region in the blood flow information enhanced image.

[0064] Among them, the original blood flow image can be a data set directly obtained by the imaging device without any processing or only after basic preprocessing (such as signal filtering, noise suppression), which is usually used to characterize the basic physical or physiological characteristics of the target area. In the field of micro blood flow imaging, the original blood flow image usually contains high-resolution blood flow signal information, time series data or hemodynamic characteristics related to spatial position, which can reflect the original state of blood flow in the target object.

[0065] Specifically, in the original blood flow image, the boundary information, coordinate information or mask information of the target area in the blood flow information enhanced image can be used to screen out the original image area that matches the position of the target area. This can usually be achieved through a matching algorithm based on spatial coordinate mapping to ensure that the original image area and the target area in the corresponding image are consistent in form and position. At the same time, the blood flow information enhanced image and the original image area can be corrected and aligned in combination with image registration technology (such as feature point matching, optical flow method, etc.) to compensate for motion artifacts or spatial dislocation problems that may exist during the acquisition process, and ensure the accuracy and consistency of the matching data.

[0066] Step 304: Use the original image area to replace the target area in the blood flow information enhanced image to obtain a target blood flow image.

[0067] Specifically, the scope of the replacement operation in the blood flow information enhanced image can be determined based on the position information of the target area in the blood flow information enhanced image. In the replacement process, the corresponding image data in the original image area can be filled into the designated position of the target area in the blood flow information enhanced image by pixel-by-pixel replacement or block-level replacement to cover the image data of the target area in the blood flow information enhanced image. In order to avoid discontinuity or artifacts at the replacement boundary, a smooth fusion algorithm can be used to process the boundary of the replacement area, for example, by using weighted average, gradient fusion or multi-resolution hybrid strategy, so that the replaced image remains naturally coherent in the transition area. At the same time, in order to improve the quality of the target blood flow image, the target blood flow image can be optimized after the replacement, including contrast enhancement, signal equalization and detail enhancement, so as to ensure that the replaced target area can retain the fine characteristics of the original acquisition data and be consistent with the overall information of the blood flow information enhanced image. The target blood flow image finally generated has both high-resolution detail performance and global data consistency and availability.

[0068] In this embodiment, by accurately matching the original image area corresponding to the position of the target area in the original blood flow image, and using the original image area to replace the target area in the blood flow information enhanced image, the target area whose blood flow information is destroyed, such as the blood flow area of ​​large blood vessels, can be eliminated, and the image quality of the target blood flow image can be significantly improved. The replacement process retains the fine blood flow features in the original blood flow image that have not been filtered or simplified, making the blood flow signal in the target area more realistic and dynamically complete. At the same time, this method effectively eliminates artifacts or signal distortion that may exist in the original blood flow image, improves the resolution and contrast of the image, and provides high-quality and reliable data support for accurate analysis of hemodynamics and clinical diagnosis.

[0069] In an exemplary embodiment, Figure 4 As shown, using at least part of the original blood flow image, image optimization processing is performed on the target area in the blood flow information enhanced image to obtain a target blood flow image, including steps 402 to 406. Among them:

[0070] Step 402: in the original blood flow image, determine the original image region that matches the target position information; the target position information is the position information of the target region in the blood flow information enhanced image.

[0071] Specifically, in the original blood flow image, the boundary information, coordinate information or mask information of the target area in the blood flow information enhanced image can be used to screen out the original image area that matches the position of the target area. This can usually be achieved through a matching algorithm based on spatial coordinate mapping to ensure that the original image area and the target area in the corresponding image are consistent in form and position. At the same time, the blood flow information enhanced image and the original image area can be corrected and aligned in combination with image registration technology (such as feature point matching, optical flow method, etc.) to compensate for motion artifacts or spatial dislocation problems that may exist during the acquisition process, and ensure the accuracy and consistency of the matching data.

[0072] Step 404: fuse the original image area and the target area to obtain an optimized area.

[0073] The optimized region can be the image portion generated after the fusion of the original image region and the target region. It combines the detail enhancement characteristics of the target region and the real dynamic information of the original image region, has clear feature expression, and retains the hemodynamic authenticity of the target region. It is a key intermediate result for further replacing and generating the target blood flow image.

[0074] Specifically, feature extraction and analysis can be performed on the original image area, such as signal intensity distribution, texture characteristics, and image gradient, to determine the weight distribution of different areas in the original image area in the fusion. The fusion algorithms used in the fusion process include alpha fusion, pyramid fusion, and Poisson fusion. For example, a weighted average fusion strategy is used to linearly superimpose the original signals of the original image area and the target area pixel by pixel by setting a fixed or dynamic weight ratio; in addition, a multi-resolution fusion technology based on the Laplacian pyramid can be used to retain more detailed features at the high-frequency level and smooth the contrast changes of large-scale areas at the low-frequency level. In order to enhance the fusion effect, a deep learning model can also be introduced to adaptively optimize the fusion of the original image area and the target area by training a neural network, thereby generating an optimized area with enhanced details.

[0075] Step 406: Use the optimized region to replace the target region in the blood flow information enhanced image to obtain a target blood flow image.

[0076] Specifically, the scope of the replacement operation in the blood flow information enhanced image can be determined based on the position information of the target area in the blood flow information enhanced image. In the replacement process, the corresponding image data in the optimized area can be filled into the designated position of the target area in the blood flow information enhanced image by pixel-by-pixel replacement or block-level replacement to cover the image data of the target area in the blood flow information enhanced image. In order to avoid discontinuity or artifacts at the replacement boundary, a smooth fusion algorithm can be used to process the boundary of the replacement area, for example, by using weighted average, gradient fusion or multi-resolution hybrid strategy, so that the replaced image remains naturally coherent in the transition area. At the same time, in order to improve the quality of the target blood flow image, the target blood flow image can be optimized after replacement, including contrast enhancement, signal equalization and detail enhancement, so as to ensure that the replaced target area can retain the fine characteristics of the original acquisition data and be consistent with the overall information of the blood flow information enhanced image. The target blood flow image finally generated has both high-resolution detail performance and global data consistency and availability.

[0077] In this embodiment, in the original blood flow image, an original image region that matches the position information of the target region in the blood flow information enhanced image is determined, and the original image region is fused with the target region to obtain an optimized region, so that the optimized region combines the detail enhancement characteristics of the target region and the real dynamic information of the original image region, and has both clear feature expression and retains the hemodynamic authenticity of the target region, thereby achieving significant optimization of the original blood flow image, enabling the target blood flow image to more realistically and meticulously reflect the hemodynamic characteristics, and providing more accurate and high-quality image support for clinical diagnosis and research analysis.

[0078] In an exemplary embodiment, Figure 5 As shown, the blood flow information enhanced image is obtained by performing a blood flow information enhancement operation on the original blood flow image, and at least part of the original blood flow image is used to perform image optimization processing on the target area in the blood flow information enhanced image to obtain the target blood flow image, including steps 502 to 506. Wherein:

[0079] Step 502: Adjust the configuration parameters currently used in the blood flow information enhancement operation to obtain new configuration parameters.

[0080] The blood flow information enhancement operation may refer to a morphological filtering operation. The configuration parameters currently used in the blood flow information enhancement operation may refer to morphological filtering parameters.

[0081] The morphological filtering parameters may be parameters that need to be set during the morphological filtering operation.

[0082] The new configuration parameters may be updated values ​​of a set of configuration parameters obtained through adjustment based on the configuration parameters currently used in the blood flow information enhancement operation.

[0083] Specifically, taking the blood flow information enhancement operation as an example of the morphological filtering operation, the morphological filtering parameters can be re-evaluated and optimized according to the specific characteristics of the target area and the effect of the blood flow information enhancement image. The adjustment process can be based on the signal intensity distribution, boundary clarity or texture characteristics of the target area, and the most suitable parameter combination can be selected through experimental testing, parameter iterative optimization or data-driven automated algorithms (such as deep learning optimization), so as to more accurately process the target area, enhance its local details or smooth noise interference.

[0084] Step 504, in the original blood flow image, determine the original image area that matches the target position information, and use the new configuration parameters to perform a blood flow information enhancement operation on the original image area to obtain a secondary enhanced image area; the target position information is the position information of the target area in the blood flow information enhanced image.

[0085] The secondary enhanced image region may be an image result generated by re-performing morphological filtering processing on the original image region based on the adjusted morphological filtering parameters.

[0086] The original image region may refer to an image region in the original blood flow image that matches the position information of the target region in the blood flow information enhanced image.

[0087] Specifically, in the original blood flow image, the boundary information, coordinate information or mask information of the target area in the blood flow information enhanced image can be used to screen out the original image area that matches the position of the target area. This can usually be achieved through a matching algorithm based on spatial coordinate mapping to ensure that the original image area and the target area in the corresponding image are consistent in form and position. At the same time, the blood flow information enhanced image and the original image area can be corrected and aligned in combination with image registration technology (such as feature point matching, optical flow method, etc.) to compensate for motion artifacts or spatial dislocation problems that may exist during the acquisition process, and ensure the accuracy and consistency of the matching data.

[0088] Then, the new configuration parameters can be used to perform secondary filtering processing specifically for the original image area to further optimize the image quality of the original image area. In this process, the new morphological filtering parameters can be used to perform morphological filtering operations on the original image area, such as Frangi filter filtering operations or Jerman filter filtering operations, to enhance the structural characteristics of the blood flow signal, while smoothing the local changes in signal intensity and suppressing isolated noise or interference signals. In order to improve the adaptability of the filtering process, the multi-scale filtering technology can be combined to perform hierarchical optimization of signals of different sizes and intensities to ensure that the generated secondary enhanced image area can highlight the blood flow signal characteristics of the target area. In addition, in order to avoid information loss during the processing process, the edge-preserving filtering technology can be introduced to retain the overall contour and dynamic characteristics of the target area while enhancing the local features, so as to ensure the integrity and high quality of the secondary enhanced image area.

[0089] Step 506: Use the secondary enhanced image area to replace the target area in the blood flow information enhanced image to obtain a target blood flow image.

[0090] Specifically, the replacement range is accurately determined according to the position and boundary range of the target area in the blood flow information enhanced image, and then the image portion corresponding to the target area in the secondary enhanced image area is replaced pixel by pixel or block by block to ensure the spatial consistency of the replacement process. In order to avoid artifacts or discontinuities in the replaced boundary area, a fusion algorithm can be used to smoothly transition the boundary of the replacement area, such as Gaussian weighted fusion or gradient-based seamless fusion technology, to ensure the visual consistency between the replacement area and the surrounding image. In addition, in order to optimize the overall image effect, the replaced blood flow image can be fully optimized (such as brightness adjustment, contrast enhancement or pseudo-color mapping) so that the final image retains the high-resolution detail characteristics of the target area and has coherence and analytical value on a global scale, providing reliable data support for clinical applications.

[0091] In this embodiment, the configuration parameters used in the blood flow information enhancement operation are adjusted to obtain new configuration parameters, and based on these new configuration parameters, the image data corresponding to the target area position in the original blood flow image is subjected to secondary filtering processing, thereby effectively improving the accuracy and reliability of the target blood flow image. The secondary blood flow information enhancement operation not only optimizes the image quality of the target area, eliminates the noise and artifacts that may exist in the target area, but also enhances the clarity and details of the blood flow characteristics, making the blood flow information of the target area more realistic and recognizable. Ultimately, by replacing the target area in the blood flow information enhanced image with the secondary enhanced image area, a more accurate and high-quality target blood flow image can be obtained, providing a more accurate visual basis for hemodynamic research, disease diagnosis, and treatment plan formulation.

[0092] In an exemplary embodiment, Figure 6 As shown, after the step of using the new configuration parameters to perform blood flow information enhancement operation on the original image region to obtain the secondary enhanced image region, the method further includes steps 602 to 604. Among them:

[0093] Step 602, when it is identified that the target area still exists in the secondary enhanced image area, the process returns to the step of adjusting the configuration parameters currently used in the blood flow information enhancement operation to obtain new configuration parameters.

[0094] Specifically, a region segmentation algorithm (such as threshold-based segmentation, region growing method or deep learning semantic segmentation network) can be used to extract the boundary of the target region, and the signal characteristics (such as intensity distribution, texture clarity or boundary gradient change) can be combined for analysis. If it is detected that there is still a target region as mentioned above in the secondary enhanced image region, it is determined that the effect of the current blood flow information enhancement operation is insufficient, and the system returns to the step of adjusting the configuration parameters currently used in the blood flow information enhancement operation. At this time, the filtering parameters can be dynamically optimized based on the characteristics or effects of the secondary enhanced image region to solve the residual problem more specifically, thereby providing an optimization basis for the next round of filtering processing.

[0095] Step 604, recording the number of times the configuration parameters are adjusted, and when the number is greater than a preset threshold, stopping and returning to the step of adjusting the configuration parameters currently used in the blood flow information enhancement operation to obtain new configuration parameters.

[0096] The preset number threshold may be a limit value set for the maximum number of iterations in the adjustment process of the configuration parameters currently used in the blood flow information enhancement operation. When the number of adjustments exceeds this threshold, the system will automatically stop returning to the step of adjusting the morphological filter parameters of the morphological filter processing to avoid an infinite loop and output the optimal image result under the current processing level.

[0097] Specifically, each time the configuration parameters currently used in the blood flow information enhancement operation are adjusted, the system needs to record the adjustment operation, including the number of adjustments, changes in configuration parameters and their corresponding processing effects. In the specific implementation, a global counter can be set to accumulate the number of adjustments, and the count is automatically increased each time the configuration parameters are adjusted. At the same time, the detailed information of each adjustment, as well as the analysis results of the target area before and after the adjustment (such as quantitative indicators of signal strength, noise level or boundary clarity) are recorded in the log system. These recorded data not only provide real-time feedback for dynamic adjustments, but can also be used for subsequent optimization and performance evaluation. For example, by analyzing the trend of parameter changes in multiple adjustments, the optimal parameter range can be found to reduce unnecessary iterations. The recorded historical data can also be used to train intelligent optimization algorithms to improve system processing efficiency and effectiveness.

[0098] After each adjustment is completed, the system will compare the number of times the configuration parameters have been adjusted with the preset threshold. Once the preset number threshold is exceeded, the system terminates the current loop iteration and uses the existing configuration parameters to perform the secondary enhanced image area for blood flow information enhancement as the final secondary enhanced image area. At the same time, the system can trigger the corresponding prompt or alarm function to notify the user that the number of iterations has reached the upper limit, and suggest that the user check the parameter configuration or manually intervene in the optimization process. To improve the adaptability of the system, the preset number threshold can be dynamically adjusted according to task requirements. For example, a lower threshold is set for real-time applications to ensure processing speed, and a higher threshold is set for high-precision scenes to fully optimize the target area.

[0099] In this embodiment, by identifying the target area in the secondary enhanced image area and continuously adjusting the configuration parameters currently used in the blood flow information enhancement operation as needed, it is possible to ensure that the image optimization processing achieves the best effect. After each adjustment, the system will determine whether to continue adjusting the filter parameters based on the performance of the secondary enhanced image area. This dynamic adjustment mechanism can refine the image processing process and avoid image distortion caused by excessive adjustment. In addition, the preset number threshold sets a limit on the number of adjustments, preventing the waste of computing resources or excessive processing time that may be caused by excessive iterations. Ultimately, after an appropriate number of adjustments, the system will output a target blood flow image that meets the quality requirements, which not only improves processing efficiency but also ensures accurate optimization of image quality.

[0100] In an exemplary embodiment, Figure 7 As shown, adjusting the configuration parameters currently used in the blood flow information enhancement operation to obtain new configuration parameters includes steps 702 to 704. Among them:

[0101] Step 702: Obtain the adjustment step value of the configuration parameter setting currently used for the blood flow information enhancement operation.

[0102] Step 704: adjust the configuration parameters currently used for the blood flow information enhancement operation according to the adjustment step value to obtain new configuration parameters.

[0103] The configuration parameters currently used in the blood flow information enhancement operation may refer to blood flow scale parameters of the blood flow information enhancement operation.

[0104] The adjustment step value is used to determine the amplitude of each adjustment of the blood flow scale parameter.

[0105] For example, when the blood flow information enhancement operation is a morphological filtering operation such as a Frangi filtering operation or a Jerman filtering operation, the blood flow scale parameter may refer to a sigma parameter; the sigma parameter is used to represent the sigma value corresponding to the expected minimum blood vessel and the maximum blood vessel; that is, the larger the sigma value, the larger the large blood flow size that can be retained after the morphological filtering operation.

[0106] In the process of adjusting the configuration parameters currently used in the blood flow information enhancement operation to obtain new configuration parameters: combined with the above, since the blood flow scale parameters currently used in the blood flow information enhancement operation will cause the large blood flow information in the original blood flow image to be destroyed; based on this, the blood flow scale parameters currently used in the blood flow information enhancement operation can be adjusted according to the adjustment step value, for example, according to the adjustment amplitude determined by the adjustment step value, the value of the sigma parameter used in the Frangi filter operation or the Jerman filter operation is increased to obtain a new sigma parameter, so as to obtain the new configuration parameters mentioned above, which are used to subsequently use the new configuration parameters to re-perform the blood flow information enhancement operation on the original image area to obtain a secondary enhanced image area, and then use the secondary enhanced image area to detect whether the large blood flow information is still destroyed.

[0107] In practical applications, the number of times the target area is repeatedly identified (the large blood flow information is destroyed) (i.e., the number of repetitions) can be set; when the number of times the target area is repeatedly identified is greater than the preset number, it means that adjusting the sigma parameter used in the Frangi filter operation or the Jerman filter operation cannot avoid the large blood flow information in the original blood flow image from being destroyed. At this time, the adjustment of the sigma parameter used in the Frangi filter operation or the Jerman filter operation can be stopped.

[0108] In this embodiment, by obtaining the adjustment step value set for the configuration parameters currently used in the blood flow information enhancement operation and adjusting the configuration parameters currently used in the blood flow information enhancement operation based on the adjustment step value, accurate optimization of morphological filtering processing is achieved. The introduction of the adjustment step value makes the adjustment process of the configuration parameters of the blood flow information enhancement operation controllable and flexible, and can gradually optimize the filtering effect according to the characteristic changes of the target area, avoiding excessive image processing caused by excessive parameter changes or insufficient optimization caused by too small changes. This refined adjustment method ensures that the new blood flow information enhancement operation is more in line with the actual characteristics of the target area, significantly improves the efficiency and effect of the filtering process, and lays a reliable foundation for generating clearer and more accurate target blood flow energy maps.

[0109] In an exemplary embodiment, Figure 8 As shown, determining a target area in a blood flow information enhanced image where image characteristics meet preset conditions includes steps 802 to 804. Among them:

[0110] Step 802: Screen out candidate regions in the blood flow information enhanced image.

[0111] The candidate area includes a preset number of target pixels.

[0112] The target pixel is a pixel whose pixel intensity value is greater than a preset intensity threshold.

[0113] The preset intensity threshold may be a fixed intensity value used to detect high-intensity signal areas in an image. When the intensity of a pixel exceeds the threshold, the pixel is considered to be a target pixel and is extracted for further analysis or optimization.

[0114] Specifically, the pixel intensity value of each pixel in the blood flow information enhanced image is traversed and analyzed one by one to detect whether there is a pixel whose pixel intensity value is greater than the preset intensity threshold, that is, the target pixel. In order to improve the detection efficiency, an optimized scanning algorithm can be used, such as a parallel computing method based on region segmentation, to divide the image into multiple sub-regions and perform threshold detection at the same time. For each target pixel that meets the conditions, its coordinates are marked and stored as a high-intensity pixel set. Subsequently, the high-intensity pixels in the high-intensity pixel set are clustered into several connected regions through a connectivity analysis algorithm (such as a four-connected or eight-connected algorithm). In order to further optimize the region definition, the region boundary can be smoothed to remove isolated pixels or small noise areas to ensure that the definition of the candidate region is accurate and coherent. Finally, these high-intensity connected regions are used as candidate regions.

[0115] Step 804: when the difference between the first pixel intensity value and the second pixel intensity value is greater than a preset difference threshold, obtain the area of ​​the candidate region.

[0116] The first pixel intensity value is a pixel intensity value corresponding to at least one pixel point in the candidate area in the original blood flow image.

[0117] The second pixel intensity value is a corresponding pixel intensity value in the blood flow information enhanced image of at least one pixel.

[0118] Specifically, for the blood flow information enhanced image, the system needs to identify the pixel points whose pixel intensity is suppressed by the blood flow information enhancement operation and their distribution characteristics. Specifically, when the pixel intensity value corresponding to a certain pixel point in the original blood flow image is lower than the pixel intensity value corresponding to the pixel point in the blood flow information enhanced image to a certain extent, that is, when the difference between the pixel intensity value corresponding to the pixel point in the original blood flow image and the pixel intensity value corresponding to the pixel point in the blood flow information enhanced image is greater than a preset difference threshold, then the pixel point is determined to be a pixel point whose pixel intensity is suppressed by the blood flow information enhancement operation.

[0119] Based on this, in a specific implementation, a binary image can be generated through an intensity value screening operation, in which the pixel points whose pixel intensity is suppressed by the blood flow information enhancement operation are marked as "1", and other pixel points are marked as "0". On this basis, when there are pixels marked as "1" in the candidate area, the system can obtain the area of ​​the candidate area and compare the area of ​​the candidate area with the preset area threshold. In practical applications, the number of pixels in the candidate area can be used as a representation of the area of ​​the candidate area. The system determines whether the area of ​​the candidate area is greater than the preset area threshold by determining whether the number of pixels in the candidate area is greater than the preset number threshold.

[0120] In practical applications, the corresponding area threshold can be set according to the type of blood vessel in the candidate area; for example, when identifying whether the candidate area is a damaged large blood vessel blood flow area, the preset area threshold is set to area A; when identifying whether the candidate area is a damaged microvascular blood flow area, the preset area threshold is set to area B; wherein area A and area B may be different, and area A may be larger than area B.

[0121] Step 806: When the area of ​​the candidate region is greater than a preset area threshold, the candidate region is determined to be a target region in the blood flow information enhanced image.

[0122] Specifically, when identifying whether the candidate region is a damaged large vessel blood flow region, when it is detected that the area of ​​the candidate region is larger than the preset area threshold, the system can determine that the damaged large vessel blood flow region in the candidate region blood flow information enhanced image is the target region.

[0123] In this embodiment, by combining multiple conditions to identify the target area in the blood flow information enhanced image, the accuracy and adaptability of the target area detection can be significantly improved. By comparing the pixel intensity value with the preset intensity threshold, the target area with high signal can be quickly identified; by analyzing the pixel points in the blood flow information enhanced image whose pixel intensity is suppressed by the blood flow information enhancement operation, the weak signal area or the blood flow area destroyed by the blood flow information enhancement operation can be accurately located; at the same time, when the target area is a large blood vessel blood flow area, the large-scale, high blood flow target area can be effectively captured based on the area characteristics of the large blood vessel blood flow area. This multi-condition collaborative recognition strategy ensures that target areas of different types and characteristics can be accurately captured, providing a comprehensive and reliable data basis for subsequent image optimization and blood flow analysis.

[0124] In an exemplary embodiment, determining a target area in a blood flow information enhanced image whose image features meet preset conditions includes: in response to a region selection operation on the blood flow information enhanced image, obtaining a region selection boundary input by the region selection operation; and determining an image area in the blood flow information enhanced image that matches the region selection boundary as a target area in the blood flow information enhanced image.

[0125] In a specific implementation, the technical solution of the present application also supports the user to use manual selection to determine the target area in the blood flow information enhanced image whose image features meet preset conditions; specifically, in the manual selection mode, the user can perform area selection operations on the blood flow information enhanced image, such as selecting the regional boundaries of the vascular blood flow area destroyed by the blood flow information enhancement operation in the blood flow information enhanced image.

[0126] The system receives a region selection operation performed by a user on a blood flow information enhanced image, and in response to the region selection operation, obtains a region selection boundary input by the region selection operation; then, an image region in the blood flow information enhanced image that matches the region selection boundary can be determined as a target region in the blood flow information enhanced image, thereby enabling the user to manually specify a target region in the blood flow information enhanced image.

[0127] The technical solution of this embodiment obtains the region selection boundary input by the region selection operation in response to the region selection operation on the blood flow information enhanced image, and determines the image region in the blood flow information enhanced image that matches the region selection boundary as the target region in the blood flow information enhanced image; it can enable the user to manually mark the blood flow region of the blood vessels destroyed by the blood flow information enhancement operation in the blood flow information enhanced image based on the image effect of the blood flow information enhanced image observed by the naked eye, thereby satisfying the user's personalized protection needs for the blood flow information of the blood flow information enhanced image as much as possible, which is conducive to improving the image effect of the target blood flow image.

[0128] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0129] Based on the same inventive concept, the embodiment of the present application also provides an image processing device for implementing the above-mentioned image processing method. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above-mentioned method, so the specific limitations in the one or more image processing device embodiments provided below can refer to the above-mentioned limitations on an image processing method, and will not be repeated here.

[0130] In an exemplary embodiment, Fig.12 As shown, an image processing device is provided, including: an image acquisition module 1202, an image detection module 1204 and an image optimization module 1206, wherein:

[0131] An image acquisition module 1202 is used to acquire a blood flow information enhanced image of an original blood flow image;

[0132] An image detection module 1204 is used to determine a target area in the blood flow information enhanced image whose image features meet preset conditions;

[0133] The image optimization module 1206 is used to use at least part of the original blood flow image to perform image optimization processing on the target area in the blood flow information enhanced image to obtain a target blood flow image.

[0134] In one embodiment, the image optimization module 1206 is also used to determine, in the original blood flow image, an original image region that matches the target position information; the target position information is the position information of the target region in the blood flow information enhanced image; and the target region in the blood flow information enhanced image is replaced using the original image region to obtain the target blood flow image.

[0135] In one embodiment, the image optimization module 1206 is further used to determine, in the original blood flow image, an original image region that matches the target position information; the target position information is the position information of the target region in the blood flow information enhanced image; the original image region and the target region are merged to obtain an optimized region; and the target region in the blood flow information enhanced image is replaced with the optimized region to obtain the target blood flow image.

[0136] In one embodiment, the blood flow information enhanced image is obtained by performing a blood flow information enhancement operation on the original blood flow image, and the image optimization module 1206 is further used to adjust the configuration parameters currently used in the blood flow information enhancement operation to obtain new configuration parameters; in the original blood flow image, determine the original image area that matches the target position information, and use the new configuration parameters to perform a blood flow information enhancement operation on the original image area to obtain a secondary enhanced image area; the target position information is the position information of the target area in the blood flow information enhanced image; and use the secondary enhanced image area to replace the target area in the blood flow information enhanced image to obtain the target blood flow image.

[0137] In one embodiment, the image optimization module 1206 is further used to, when it is identified that the target area still exists in the secondary enhanced image area, return to the step of adjusting the configuration parameters currently used for the blood flow information enhancement operation to obtain new configuration parameters; and record the number of times the configuration parameters are adjusted, and when the number is greater than a preset number threshold, stop returning to the step of adjusting the configuration parameters currently used for the blood flow information enhancement operation to obtain new configuration parameters.

[0138] In one embodiment, the image optimization module 1206 is further used to obtain an adjustment step value for the configuration parameter settings currently used for the blood flow information enhancement operation; and adjust the configuration parameters currently used for the blood flow information enhancement operation according to the adjustment step value to obtain the new configuration parameters.

[0139] In one embodiment, the image detection module 1204 is also used to screen out candidate areas in the blood flow information enhanced image; the candidate area includes a preset number of target pixels; the target pixel is a pixel whose pixel intensity value is greater than a preset intensity threshold; when the difference between the first pixel intensity value and the second pixel intensity value is greater than the preset difference threshold, the area of ​​the candidate area is obtained; the first pixel intensity value is the pixel intensity value corresponding to at least one pixel in the candidate area in the original blood flow image; the second pixel intensity value is the pixel intensity value corresponding to at least one pixel in the blood flow information enhanced image; when the area of ​​the candidate area is greater than the preset area area threshold, the candidate area is determined to be the target area in the blood flow information enhanced image.

[0140] In one embodiment, the image detection module 1204 is further used to obtain the region selection boundary input by the region selection operation in response to the region selection operation on the blood flow information enhanced image; and determine the image region in the blood flow information enhanced image that matches the region selection boundary as the target region in the blood flow information enhanced image.

[0141] Each module in the above-mentioned image processing device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0142] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.13 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store server data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an image processing method is implemented.

[0143] Those skilled in the art will understand that Fig.13The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0144] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0145] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0146] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-mentioned method embodiments.

[0147] 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, stored data, displayed data, 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 relevant data must comply with relevant regulations.

[0148] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium 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), magnetoresistive 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0149] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0150] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An image processing method, characterized in that: The method comprises: Acquire a blood flow information enhanced image of the original blood flow image; Determine a target area in the blood flow information enhanced image whose image characteristics meet preset conditions; At least a portion of the original blood flow image is used to perform image optimization processing on the target area in the blood flow information enhanced image to obtain a target blood flow image.

2. The method according to claim 1, characterized in that: The step of using at least part of the original blood flow image to perform image optimization processing on the target area in the blood flow information enhanced image to obtain a target blood flow image includes: In the original blood flow image, determining an original image region that matches the target position information; the target position information is position information of the target region in the blood flow information enhanced image; The target area in the blood flow information enhanced image is replaced by using the original image area to obtain the target blood flow image.

3. The method according to claim 1, characterized in that The step of using at least part of the original blood flow image to perform image optimization processing on the target area in the blood flow information enhanced image to obtain a target blood flow image includes: In the original blood flow image, determining an original image region that matches the target position information; the target position information is position information of the target region in the blood flow information enhanced image; The original image region and the target region are fused to obtain an optimized region; The target area in the blood flow information enhanced image is replaced by the optimized area to obtain the target blood flow image.

4. The method according to claim 1, characterized in that: The blood flow information enhanced image is obtained by performing a blood flow information enhancement operation on the original blood flow image, and the step of using at least a portion of the original blood flow image to perform image optimization processing on the target area in the blood flow information enhanced image to obtain a target blood flow image includes: Adjusting the configuration parameters currently used in the blood flow information enhancement operation to obtain new configuration parameters; In the original blood flow image, an original image region matching the target position information is determined, and the blood flow information enhancement operation is performed on the original image region using the new configuration parameters to obtain a secondary enhanced image region; the target position information is the position information of the target region in the blood flow information enhanced image; The target area in the blood flow information enhanced image is replaced by the secondary enhanced image area to obtain the target blood flow image.

5. The method according to claim 4, characterized in that After the step of adopting the new configuration parameters to perform a blood flow information enhancement operation on the original image region to obtain a secondary enhanced image region, the method further includes: In the case where it is identified that the target area still exists in the secondary enhanced image area, returning to the step of adjusting the configuration parameters currently used in the blood flow information enhancement operation to obtain new configuration parameters; The number of times the configuration parameters are adjusted is recorded. When the number is greater than a preset number threshold, the step of returning to the step of adjusting the configuration parameters currently used in the blood flow information enhancement operation to obtain new configuration parameters is stopped.

6. The method according to claim 4, characterized in that The adjusting the configuration parameters currently used in the blood flow information enhancement operation to obtain new configuration parameters includes: Acquire an adjustment step value of a configuration parameter setting currently adopted for the blood flow information enhancement operation; According to the adjustment step value, the configuration parameters currently used in the blood flow information enhancement operation are adjusted to obtain the new configuration parameters.

7. The method according to claim 1, characterized in that The step of determining a target area in the blood flow information enhanced image where image characteristics satisfy preset conditions comprises: Screening out a candidate area in the blood flow information enhanced image; the candidate area includes a preset number of target pixels; the target pixels are pixels whose pixel intensity values ​​are greater than a preset intensity threshold; When the difference between the first pixel intensity value and the second pixel intensity value is greater than a preset difference threshold, the area of ​​the candidate region is obtained; the first pixel intensity value is the pixel intensity value corresponding to at least one pixel point in the candidate region in the original blood flow image; the second pixel intensity value is the pixel intensity value corresponding to at least one pixel point in the blood flow information enhanced image; When the area of ​​the candidate region is greater than a preset area threshold, the candidate region is determined to be a target region in the blood flow information enhanced image.

8. The method according to claim 1, characterized in that: The step of determining a target area in the blood flow information enhanced image where image characteristics satisfy preset conditions comprises: In response to a region selection operation on the blood flow information enhanced image, obtaining a region selection boundary input by the region selection operation; An image region in the blood flow information enhanced image that matches the region selection boundary is determined as a target region in the blood flow information enhanced image.

9. An image processing device, characterized in that: The device comprises: An image acquisition module, used for acquiring a blood flow information enhanced image of an original blood flow image; An image detection module, used to determine a target area in the blood flow information enhanced image whose image features meet preset conditions; The image optimization module is used to use at least part of the original blood flow image to perform image optimization processing on the target area in the blood flow information enhanced image to obtain a target blood flow image.

10. 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, the steps of the method according to any one of claims 1 to 8 are implemented.

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

Images