A model-based analysis of contrast methods and systems for cardiovascular images

Abstract

The application discloses a model-based analysis and contrast recognition method and system for cardiovascular images, and the method comprises the following steps: acquiring an image of a current cardiovascular and an image of a cardiovascular with a determined lesion, and extracting image information respectively, marking a known lesion position on the image of the current cardiovascular, wherein the image information comprises pixel points at all positions on the image; setting a cardiovascular image contrast model, and calculating a comprehensive contrast metric between the image of the current cardiovascular and the image of the cardiovascular with the determined lesion according to the marked known lesion position and the image information; and when the comprehensive contrast metric exceeds a metric threshold, taking a lesion result corresponding to the image of the cardiovascular with the determined lesion as a final lesion result of the image of the current cardiovascular.

Description

Technical Field

[0001] This invention belongs to the field of cardiovascular image analysis technology, and more specifically, relates to a model-based method and system for analyzing, comparing and recognizing cardiovascular images. Background Technology

[0002] The current state of cardiovascular image analysis technology mainly focuses on the following aspects:

[0003] Imaging technology:

[0004] MRI (Magnetic Resonance Imaging) and CT (Computed Tomography): Used to obtain high-resolution images of the heart and blood vessels, helping doctors assess cardiovascular health.

[0005] Ultrasound imaging: widely used for real-time monitoring of heart structure and function, especially in the diagnosis of heart disease.

[0006] Image processing and analysis techniques:

[0007] Image segmentation: Using algorithms (such as thresholding, region growing, deep learning, etc.) to automatically or semi-automatically segment heart and blood vessel structures to improve diagnostic accuracy.

[0008] Feature extraction: Extract features of cardiac function (such as ventricular volume and ejection fraction) and lesions (such as atherosclerotic plaques) for further analysis.

[0009] Due to the structural complexity of the cardiovascular system, existing technologies have low image processing accuracy and cannot automatically acquire lesion results. Summary of the Invention

[0010] To address the above technical problems, this invention proposes a model-based method for analyzing, comparing, and recognizing cardiovascular images, comprising:

[0011] Acquire current cardiovascular images and cardiovascular images with identified lesions, and extract image information from each. Mark the locations of known lesions on the current cardiovascular image, wherein the image information includes pixels at all locations on the image.

[0012] A cardiovascular image contrast model is set up, and the comprehensive contrast ratio between the current cardiovascular image and the cardiovascular image with identified lesions is calculated based on the marked known lesion locations and the image information.

[0013] When the overall contrast exceeds the measurement threshold, the lesion result corresponding to the cardiovascular image with the identified lesion is taken as the final lesion result of the current cardiovascular image.

[0014] Furthermore, the cardiovascular image comparison model includes:

[0015] ,

[0016] in, Images of the current cardiovascular system Cardiovascular images with identified lesions The overall contrast ratio is used to capture the differences between two cardiovascular images in terms of structure, texture, topological changes, and temporal evolution. Define the domain for the image. For time Time pixel Adaptive weight function, For time Time pixel The morphological energy evolution field function is used to describe the physiological signals and structural evolution in current cardiovascular images. Images of the current cardiovascular system Cardiovascular images with identified lesions Between pixels Image feature matching function at the location, This is a spatiotemporally coupled topological change function representing the change in the angle of cardiovascular structures. This is an adjustment factor for the change in angle. This refers to the change in the geometric angle of the cardiovascular structure. To and The amount of geometric angle change of the cardiovascular structure in the vertical direction. For at pixel The spatial modulation function is used to capture the spatial distribution of image features at different scales.

[0017] Furthermore, time Time pixel Adaptive weight function include:

[0018] ,

[0019] in, The weights are the first-order gradients. For time Current cardiovascular images At pixel The first gradient at that point, The adjustment factor for the first-order gradient. The weights are the second-order gradients. Define the domain of the image subdomains, For time Current cardiovascular images At pixel The first gradient at that point, This is the adjustment factor for the second-order gradient.

[0020] Furthermore, the spatiotemporal coupled topological change function of cardiovascular structural angle changes. include:

[0021] ,

[0022] in, The first adjustment factor for the spatiotemporal coupled topological transformation function. The second adjustment factor for the spatiotemporal coupled topological transformation function. This is the third adjustment factor for the spatiotemporal coupling topological transformation function.

[0023] Furthermore, at the pixel level Spatial modulation function at include:

[0024] ,

[0025] in, This is the first adjustment factor of the spatial modulation function. Images of the current cardiovascular system Known lesion locations on the surface This is the second adjustment factor of the spatial modulation function. Images of the current cardiovascular system pixels on This is the third adjustment factor of the spatial modulation function.

[0026] Furthermore, time Time pixel morphological energy evolution field function include:

[0027] ,

[0028] in, For current cardiovascular images Pixel Place with time Changing signal strength This is the first adjustment factor for the morphological energy evolution field function. This is the second adjustment factor for the morphological energy evolution field function. The third adjustment factor for the morphological energy evolution field function. This is the fourth adjustment factor for the morphological energy evolution field function. This is the fifth adjustment factor for the morphological energy evolution field function. It is the sixth adjustment factor of the morphological energy evolution field function.

[0029] Furthermore, current cardiovascular imaging Cardiovascular images with identified lesions Between pixels Image feature matching function at location for:

[0030] ,

[0031] in, Images of the current cardiovascular system At pixel The mean near that point, Cardiovascular images of identified lesions At pixel The mean near that point, This is the first constant used for stability calculations. Images of the current cardiovascular system Cardiovascular images with identified lesions At pixel covariance at the location, This is the second constant used for stability calculations. Images of the current cardiovascular system At pixel The standard deviation at that point Cardiovascular images of identified lesions At pixel The standard deviation at that point.

[0032] This invention also proposes a model-based cardiovascular image analysis and comparison recognition system, comprising:

[0033] The image information acquisition module is used to acquire the current cardiovascular image and the cardiovascular image with identified lesions, and extract the image information respectively, and mark the known lesion locations on the current cardiovascular image, wherein the image information includes pixels at all locations on the image;

[0034] The model setting module is used to set up a cardiovascular image comparison model and calculate the comprehensive contrast between the current cardiovascular image and the cardiovascular image with identified lesions based on the marked known lesion locations and the image information.

[0035] The lesion identification module is used to take the lesion result corresponding to the identified lesion in the cardiovascular image as the final lesion result of the current cardiovascular image when the comprehensive contrast value exceeds the measurement threshold.

[0036] Furthermore, the cardiovascular image comparison model includes:

[0037] ,

[0038] in, Images of the current cardiovascular system Cardiovascular images with identified lesions The overall contrast ratio is used to capture the differences between two cardiovascular images in terms of structure, texture, topological changes, and temporal evolution. Define the domain for the image. For time Time pixel Adaptive weight function, For time Time pixel The morphological energy evolution field function is used to describe the physiological signals and structural evolution in current cardiovascular images. Images of the current cardiovascular system Cardiovascular images with identified lesions Between pixels Image feature matching function at the location, This is a spatiotemporally coupled topological change function representing the change in the angle of cardiovascular structures. This is an adjustment factor for the change in angle. This refers to the change in the geometric angle of the cardiovascular structure. To and The amount of geometric angle change of the cardiovascular structure in the vertical direction. For at pixel The spatial modulation function is used to capture the spatial distribution of image features at different scales.

[0039] Furthermore, time Time pixel Adaptive weight function include:

[0040] ,

[0041] in, The weights are the first-order gradients. For time Current cardiovascular images At pixel The first gradient at that point, The adjustment factor for the first-order gradient. The weights are the second-order gradients. Define the domain of the image subdomains, For time Current cardiovascular images At pixel The first gradient at that point, This is the adjustment factor for the second-order gradient.

[0042] In summary, the technical solutions conceived by this invention have the following beneficial effects compared with the prior art:

[0043] Through the above technical solutions, this invention further enhances the accuracy of cardiovascular image analysis through innovative designs such as adaptive region weighting, topological coupling, and multi-level spatiotemporal modeling. Attached Figure Description

[0044] Figure 1 This is a flowchart of the method of Embodiment 1 of the present invention;

[0045] Figure 2 This is a structural diagram of the system of Embodiment 2 of the present invention; Detailed Implementation

[0046] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0047] The method provided by this invention can be implemented in a terminal environment that may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, which is loaded and executed by the processor to implement the method described in the following embodiments.

[0048] A processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts of the terminal, and performs various functions and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and by calling data stored in the storage medium.

[0049] Storage media can include random access memory (RAM) or read-only memory (ROM). Storage media can be used to store instructions, programs, code, code sets, or instructions.

[0050] The display screen is used to show the user interface of each application.

[0051] In addition, those skilled in the art will understand that the structure of the terminal described above does not constitute a limitation on the terminal. The terminal may include more or fewer components, or combine certain components, or have different component arrangements. For example, the terminal may also include radio frequency circuits, input units, sensors, audio circuits, power supplies, and other components, which will not be described in detail here.

[0052] Example 1

[0053] like Figure 1 As shown, this embodiment of the invention provides a model-based method for analyzing, comparing, and recognizing cardiovascular images, including:

[0054] Step 101: Obtain the current cardiovascular image and the cardiovascular image with identified lesions, and extract the image information respectively. Mark the known lesion locations on the current cardiovascular image, wherein the image information includes pixels at all locations on the image.

[0055] Step 102: Set up a cardiovascular image comparison model, and calculate the comprehensive contrast between the current cardiovascular image and the cardiovascular image with identified lesions based on the marked known lesion locations and the image information.

[0056] Specifically, the cardiovascular image comparison model includes:

[0057] ,

[0058] in, Images of the current cardiovascular system Cardiovascular images with identified lesions The overall contrast ratio is used to capture the differences between two cardiovascular images in terms of structure, texture, topological changes, and temporal evolution. Define the domain for the image. For time Time pixel Adaptive weight function, For time Time pixel The morphological energy evolution field function is used to describe the physiological signals and structural evolution in current cardiovascular images. Images of the current cardiovascular system Cardiovascular images with identified lesions Between pixels Image feature matching function at the location, This is a spatiotemporally coupled topological change function representing the change in the angle of cardiovascular structures. This is an adjustment factor for the change in angle. This refers to the change in the geometric angle of the cardiovascular structure. To and The amount of geometric angle change of the cardiovascular structure in the vertical direction. For at pixel The spatial modulation function is used to capture the spatial distribution of image features at different scales.

[0059] Specifically, time Time pixel Adaptive weight function include:

[0060] ,

[0061] in, The weights are the first-order gradients. For time Current cardiovascular images At pixel The first gradient at that point, The adjustment factor for the first-order gradient. The weights are the second-order gradients. Define the domain of the image subdomains, For time Current cardiovascular images At pixel The first gradient at that point, This is the adjustment factor for the second-order gradient.

[0062] Specifically, the spatiotemporal coupled topological change function of cardiovascular structural angle changes. include:

[0063] ,

[0064] in, The first adjustment factor for the spatiotemporal coupled topological transformation function. The second adjustment factor for the spatiotemporal coupled topological transformation function. This is the third adjustment factor for the spatiotemporal coupling topological transformation function.

[0065] Specifically, at the pixel Spatial modulation function at include:

[0066] ,

[0067] in, This is the first adjustment factor of the spatial modulation function. Images of the current cardiovascular system Known lesion locations on the surface This is the second adjustment factor of the spatial modulation function. Images of the current cardiovascular system pixels on This is the third adjustment factor of the spatial modulation function.

[0068] Specifically, time Time pixel morphological energy evolution field function include:

[0069] ,

[0070] in, For current cardiovascular images Pixel Place with time Changing signal strength This is the first adjustment factor for the morphological energy evolution field function. This is the second adjustment factor for the morphological energy evolution field function. The third adjustment factor for the morphological energy evolution field function. This is the fourth adjustment factor for the morphological energy evolution field function. This is the fifth adjustment factor for the morphological energy evolution field function. It is the sixth adjustment factor of the morphological energy evolution field function.

[0071] Specifically, current cardiovascular images Cardiovascular images with identified lesions Between pixels Image feature matching function at location for:

[0072] ,

[0073] in, Images of the current cardiovascular system At pixel The mean near that point, Cardiovascular images of identified lesions At pixel The mean near that point, This is the first constant used for stability calculations. Images of the current cardiovascular system Cardiovascular images with identified lesions At pixel covariance at the location, This is the second constant used for stability calculations. Images of the current cardiovascular system At pixel The standard deviation at that point Cardiovascular images of identified lesions At pixel The standard deviation at that point.

[0074] Step 103: When the comprehensive contrast value exceeds the measurement threshold, the lesion result corresponding to the cardiovascular image with the identified lesion is taken as the final lesion result of the current cardiovascular image.

[0075] Example 2

[0076] like Figure 2 As shown, this embodiment of the invention also provides a model-based cardiovascular image analysis, comparison, and recognition system, comprising:

[0077] The image information acquisition module is used to acquire the current cardiovascular image and the cardiovascular image with identified lesions, and extract the image information respectively, and mark the known lesion locations on the current cardiovascular image, wherein the image information includes pixels at all locations on the image;

[0078] The model setting module is used to set up a cardiovascular image comparison model and calculate the comprehensive contrast between the current cardiovascular image and the cardiovascular image with identified lesions based on the marked known lesion locations and the image information.

[0079] Specifically, the cardiovascular image comparison model includes:

[0080] ,

[0081] in, Images of the current cardiovascular system Cardiovascular images with identified lesions The overall contrast ratio is used to capture the differences between two cardiovascular images in terms of structure, texture, topological changes, and temporal evolution. Define the domain for the image. For time Time pixel Adaptive weight function, For time Time pixel The morphological energy evolution field function is used to describe the physiological signals and structural evolution in current cardiovascular images. Images of the current cardiovascular system Cardiovascular images with identified lesions Between pixels Image feature matching function at the location, This is a spatiotemporally coupled topological change function representing the change in the angle of cardiovascular structures. This is an adjustment factor for the change in angle. This refers to the change in the geometric angle of the cardiovascular structure. To and The amount of geometric angle change of the cardiovascular structure in the vertical direction. For at pixel The spatial modulation function is used to capture the spatial distribution of image features at different scales.

[0082] Specifically, time Time pixel Adaptive weight function include:

[0083] ,

[0084] in, The weights are the first-order gradients. For time Current cardiovascular images At pixel The first gradient at that point, The adjustment factor for the first-order gradient. The weights are the second-order gradients. Define the domain of the image subdomains, For time Current cardiovascular images At pixel The first gradient at that point, This is the adjustment factor for the second-order gradient.

[0085] Specifically, the spatiotemporal coupled topological change function of cardiovascular structural angle changes. include:

[0086] ,

[0087] in, The first adjustment factor for the spatiotemporal coupled topological transformation function. The second adjustment factor for the spatiotemporal coupled topological transformation function. This is the third adjustment factor for the spatiotemporal coupling topological transformation function.

[0088] Specifically, at the pixel Spatial modulation function at include:

[0089] ,

[0090] in, This is the first adjustment factor of the spatial modulation function. Images of the current cardiovascular system Known lesion locations on the surface This is the second adjustment factor of the spatial modulation function. Images of the current cardiovascular system pixels on This is the third adjustment factor of the spatial modulation function.

[0091] Specifically, time Time pixel morphological energy evolution field function include:

[0092] ,

[0093] in, For current cardiovascular images Pixel Place with time Changing signal strength This is the first adjustment factor for the morphological energy evolution field function. This is the second adjustment factor for the morphological energy evolution field function. The third adjustment factor for the morphological energy evolution field function. This is the fourth adjustment factor for the morphological energy evolution field function. This is the fifth adjustment factor for the morphological energy evolution field function. It is the sixth adjustment factor of the morphological energy evolution field function.

[0094] Specifically, current cardiovascular images Cardiovascular images with identified lesions Between pixels Image feature matching function at location for:

[0095] ,

[0096] in, Images of the current cardiovascular system At pixel The mean near that point, Cardiovascular images of identified lesions At pixel The mean near that point, This is the first constant used for stability calculations. Images of the current cardiovascular system Cardiovascular images with identified lesions At pixel covariance at the location, This is the second constant used for stability calculations. Images of the current cardiovascular system At pixel The standard deviation at that point Cardiovascular images of identified lesions At pixel The standard deviation at that point.

[0097] The lesion identification module is used to take the lesion result corresponding to the identified lesion in the cardiovascular image as the final lesion result of the current cardiovascular image when the comprehensive contrast value exceeds the measurement threshold.

[0098] Example 3

[0099] This invention also proposes a storage medium storing multiple instructions for implementing the model-based cardiovascular image analysis, comparison, and recognition method.

[0100] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0101] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: Step 101, acquire the current cardiovascular image and the cardiovascular image with identified lesions, and extract image information respectively, and mark the known lesion locations on the current cardiovascular image, wherein the image information includes pixels at all locations on the image;

[0102] Step 102: Set up a cardiovascular image comparison model, and calculate the comprehensive contrast between the current cardiovascular image and the cardiovascular image with identified lesions based on the marked known lesion locations and the image information.

[0103] Specifically, the cardiovascular image comparison model includes:

[0104] ,

[0105] in, Images of the current cardiovascular system Cardiovascular images with identified lesions The overall contrast ratio is used to capture the differences between two cardiovascular images in terms of structure, texture, topological changes, and temporal evolution. Define the domain for the image. For time Time pixel Adaptive weight function, For time Time pixel The morphological energy evolution field function is used to describe the physiological signals and structural evolution in current cardiovascular images. Images of the current cardiovascular system Cardiovascular images with identified lesions Between pixels Image feature matching function at the location, This is a spatiotemporally coupled topological change function representing the change in the angle of cardiovascular structures. This is an adjustment factor for the change in angle. This refers to the change in the geometric angle of the cardiovascular structure. To and The amount of geometric angle change of the cardiovascular structure in the vertical direction. For at pixel The spatial modulation function is used to capture the spatial distribution of image features at different scales.

[0106] Specifically, time Time pixel Adaptive weight function include:

[0107] ,

[0108] in, The weights are the first-order gradients. For time Current cardiovascular images At pixel The first gradient at that point, The adjustment factor for the first-order gradient. The weights are the second-order gradients. Define the domain of the image subdomains, For time Current cardiovascular images At pixel The first gradient at that point, This is the adjustment factor for the second-order gradient.

[0109] Specifically, the spatiotemporal coupled topological change function of cardiovascular structural angle changes. include:

[0110] ,

[0111] in, The first adjustment factor for the spatiotemporal coupled topological transformation function. The second adjustment factor for the spatiotemporal coupled topological transformation function. This is the third adjustment factor for the spatiotemporal coupling topological transformation function.

[0112] Specifically, at the pixel Spatial modulation function at include:

[0113] ,

[0114] in, This is the first adjustment factor of the spatial modulation function. Images of the current cardiovascular system Known lesion locations on the surface This is the second adjustment factor of the spatial modulation function. Images of the current cardiovascular system pixels on This is the third adjustment factor of the spatial modulation function.

[0115] Specifically, time Time pixel morphological energy evolution field function include:

[0116] ,

[0117] in, For current cardiovascular images Pixel Place with time Changing signal strength This is the first adjustment factor for the morphological energy evolution field function. This is the second adjustment factor for the morphological energy evolution field function. The third adjustment factor for the morphological energy evolution field function. This is the fourth adjustment factor for the morphological energy evolution field function. This is the fifth adjustment factor for the morphological energy evolution field function. It is the sixth adjustment factor of the morphological energy evolution field function.

[0118] Specifically, current cardiovascular images Cardiovascular images with identified lesions Between pixels Image feature matching function at location for:

[0119] ,

[0120] in, Images of the current cardiovascular system At pixel The mean near that point, Cardiovascular images of identified lesions At pixel The mean near that point, This is the first constant used for stability calculations. Images of the current cardiovascular system Cardiovascular images with identified lesions At pixel covariance at the location, This is the second constant used for stability calculations. Images of the current cardiovascular system At pixel The standard deviation at that point Cardiovascular images of identified lesions At pixel The standard deviation at that point.

[0121] Step 103: When the comprehensive contrast value exceeds the measurement threshold, the lesion result corresponding to the cardiovascular image with the identified lesion is taken as the final lesion result of the current cardiovascular image.

[0122] Example 4

[0123] This invention also proposes an electronic device, including a processor and a storage medium connected to the processor. The storage medium stores multiple instructions, which can be loaded and executed by the processor to enable the processor to perform the aforementioned model-based cardiovascular image analysis and comparison recognition method.

[0124] Specifically, the electronic device in this embodiment can be a computer terminal, which may include one or more processors and a storage medium.

[0125] The storage medium can be used to store software programs and modules, such as the model-based cardiovascular image analysis and comparison recognition method in this embodiment of the invention. The corresponding program instructions / modules allow the processor to execute various functional applications and data processing by running the software programs and modules stored in the storage medium, thus realizing the aforementioned model-based cardiovascular image analysis and comparison recognition method. The storage medium may include high-speed random access storage media, and may also include non-volatile storage media, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include storage media remotely configured relative to the processor, which can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0126] The processor can call the information and application stored in the storage medium through the transmission system to perform the following steps: Step 101, acquire the current cardiovascular image and the cardiovascular image with identified lesions, and extract the image information respectively, and mark the known lesion locations on the current cardiovascular image, wherein the image information includes pixels at all locations on the image;

[0127] Step 102: Set up a cardiovascular image comparison model, and calculate the comprehensive contrast between the current cardiovascular image and the cardiovascular image with identified lesions based on the marked known lesion locations and the image information.

[0128] Specifically, the cardiovascular image comparison model includes:

[0129] ,

[0130] in, Images of the current cardiovascular system Cardiovascular images with identified lesions The overall contrast ratio is used to capture the differences between two cardiovascular images in terms of structure, texture, topological changes, and temporal evolution. Define the domain for the image. For time Time pixel Adaptive weight function, For time Time pixel The morphological energy evolution field function is used to describe the physiological signals and structural evolution in current cardiovascular images. Images of the current cardiovascular system Cardiovascular images with identified lesions Between pixels Image feature matching function at the location, This is a spatiotemporally coupled topological change function representing the change in the angle of cardiovascular structures. This is an adjustment factor for the change in angle. This refers to the change in the geometric angle of the cardiovascular structure. To and The amount of geometric angle change of the cardiovascular structure in the vertical direction. For at pixel The spatial modulation function is used to capture the spatial distribution of image features at different scales.

[0131] Specifically, time Time pixel Adaptive weight function include:

[0132] ,

[0133] in, The weights are the first-order gradients. For time Current cardiovascular images At pixel The first gradient at that point, The adjustment factor for the first-order gradient. The weights are the second-order gradients. Define the domain of the image subdomains, For time Current cardiovascular images At pixel The first gradient at that point, This is the adjustment factor for the second-order gradient.

[0134] Specifically, the spatiotemporal coupled topological change function of cardiovascular structural angle changes. include:

[0135] ,

[0136] in, The first adjustment factor for the spatiotemporal coupled topological transformation function. The second adjustment factor for the spatiotemporal coupled topological transformation function. This is the third adjustment factor for the spatiotemporal coupling topological transformation function.

[0137] Specifically, at the pixel Spatial modulation function at include:

[0138] ,

[0139] in, This is the first adjustment factor of the spatial modulation function. Images of the current cardiovascular system Known lesion locations on the surface This is the second adjustment factor of the spatial modulation function. Images of the current cardiovascular system pixels on This is the third adjustment factor of the spatial modulation function.

[0140] Specifically, time Time pixel morphological energy evolution field function include:

[0141] ,

[0142] in, For current cardiovascular images Pixel Place with time Changing signal strength This is the first adjustment factor for the morphological energy evolution field function. This is the second adjustment factor for the morphological energy evolution field function. The third adjustment factor for the morphological energy evolution field function. This is the fourth adjustment factor for the morphological energy evolution field function. This is the fifth adjustment factor for the morphological energy evolution field function. It is the sixth adjustment factor of the morphological energy evolution field function.

[0143] Specifically, current cardiovascular images Cardiovascular images with identified lesions Between pixels Image feature matching function at location for:

[0144] ,

[0145] in, Images of the current cardiovascular system At pixel The mean near that point, Cardiovascular images of identified lesions At pixel The mean near that point, This is the first constant used for stability calculations. Images of the current cardiovascular system Cardiovascular images with identified lesions At pixel covariance at the location, This is the second constant used for stability calculations. Images of the current cardiovascular system At pixel The standard deviation at that point Cardiovascular images of identified lesions At pixel The standard deviation at that point.

[0146] Step 103: When the comprehensive contrast value exceeds the measurement threshold, the lesion result corresponding to the cardiovascular image with the identified lesion is taken as the final lesion result of the current cardiovascular image.

[0147] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0148] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0149] In the several embodiments provided by this invention, it should be understood that the disclosed technical content can be implemented in other ways. The system embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between units or modules, and may be electrical or other forms.

[0150] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0151] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0152] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, optical disks, and other media capable of storing program code.

[0153] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A model-based method for analyzing, comparing, and recognizing cardiovascular images, characterized in that, include: Acquire current cardiovascular images and cardiovascular images with identified lesions, and extract image information from each. Mark the locations of known lesions on the current cardiovascular image, wherein the image information includes pixels at all locations on the image. A cardiovascular image contrast model is set up, and the comprehensive contrast ratio between the current cardiovascular image and the cardiovascular image with identified lesions is calculated based on the marked known lesion locations and the image information. Specifically, the cardiovascular image comparison model includes: ， in, Images of the current cardiovascular system Cardiovascular images with identified lesions The overall contrast ratio is used to capture the differences between two cardiovascular images in terms of structure, texture, topological changes, and temporal evolution. Define the domain for the image. For time Time pixel Adaptive weight function, For time Time pixel The morphological energy evolution field function is used to describe the physiological signals and structural evolution in current cardiovascular images. Images of the current cardiovascular system Cardiovascular images with identified lesions Between pixels Image feature matching function at the location, This is a spatiotemporally coupled topological change function representing the change in the angle of cardiovascular structures. This is an adjustment factor for the change in angle. This refers to the change in the geometric angle of the cardiovascular structure. To and The amount of geometric angle change of the cardiovascular structure in the vertical direction. For at pixel The spatial modulation function at that location is used to capture the spatial distribution of image features at different scales; When the overall contrast exceeds the measurement threshold, the lesion result corresponding to the cardiovascular image with the identified lesion is taken as the final lesion result of the current cardiovascular image.

2. The model-based cardiovascular image analysis, comparison, and recognition method as described in claim 1, characterized in that, time Time pixel Adaptive weight function include: ， in, The weights are the first-order gradients. For time Current cardiovascular images At pixel The first gradient at that point, The adjustment factor for the first-order gradient. The weights are the second-order gradients. Define the domain of the image subdomains, For time Current cardiovascular images At pixel The first gradient at that point, This is the adjustment factor for the second-order gradient.

3. The model-based cardiovascular image analysis, comparison, and recognition method as described in claim 1, characterized in that, Spatiotemporal coupled topological change function of cardiovascular structural angle change include: ， in, The first adjustment factor for the spatiotemporal coupled topological transformation function. The second adjustment factor for the spatiotemporal coupled topological transformation function. This is the third adjustment factor for the spatiotemporal coupling topological transformation function.

4. The model-based cardiovascular image analysis, comparison, and recognition method as described in claim 1, characterized in that, At pixel Spatial modulation function at include: ， in, This is the first adjustment factor of the spatial modulation function. Images of the current cardiovascular system Known lesion locations on the surface This is the second adjustment factor of the spatial modulation function. Images of the current cardiovascular system pixels on This is the third adjustment factor of the spatial modulation function.

5. The model-based cardiovascular image analysis and comparison recognition method as described in claim 1, characterized in that, time Time pixel morphological energy evolution field function include: ， in, For current cardiovascular images Pixel Place with time Changing signal strength This is the first adjustment factor for the morphological energy evolution field function. This is the second adjustment factor for the morphological energy evolution field function. The third adjustment factor for the morphological energy evolution field function. This is the fourth adjustment factor for the morphological energy evolution field function. This is the fifth adjustment factor for the morphological energy evolution field function. It is the sixth adjustment factor of the morphological energy evolution field function.

6. The model-based cardiovascular image analysis, comparison, and recognition method as described in claim 1, characterized in that, Current cardiovascular images Cardiovascular images with identified lesions Between pixels Image feature matching function at location for: ， in, Images of the current cardiovascular system At pixel The mean near that point, Cardiovascular images of identified lesions At pixel The mean near that point, This is the first constant used for stability calculations. Images of the current cardiovascular system Cardiovascular images with identified lesions At pixel covariance at the location, This is the second constant used for stability calculations. Images of the current cardiovascular system At pixel The standard deviation at that point Cardiovascular images of identified lesions At pixel The standard deviation at that point.

7. A model-based system for analyzing, comparing, and recognizing cardiovascular images, characterized in that, include: The image information acquisition module is used to acquire the current cardiovascular image and the cardiovascular image with identified lesions, and extract the image information respectively, and mark the known lesion locations on the current cardiovascular image, wherein the image information includes pixels at all locations on the image; The model setting module is used to set up a cardiovascular image comparison model and calculate the comprehensive contrast between the current cardiovascular image and the cardiovascular image with identified lesions based on the marked known lesion locations and the image information. Specifically, the cardiovascular image comparison model includes: ， in, Images of the current cardiovascular system Cardiovascular images with identified lesions The overall contrast ratio is used to capture the differences between two cardiovascular images in terms of structure, texture, topological changes, and temporal evolution. Define the domain for the image. For time Time pixel Adaptive weight function, For time Time pixel The morphological energy evolution field function is used to describe the physiological signals and structural evolution in current cardiovascular images. Images of the current cardiovascular system Cardiovascular images with identified lesions Between pixels Image feature matching function at the location, This is a spatiotemporally coupled topological change function representing the change in the angle of cardiovascular structures. This is an adjustment factor for the change in angle. This refers to the change in the geometric angle of the cardiovascular structure. To and The amount of geometric angle change of the cardiovascular structure in the vertical direction. For at pixel The spatial modulation function at that location is used to capture the spatial distribution of image features at different scales; The lesion identification module is used to take the lesion result corresponding to the identified lesion in the cardiovascular image as the final lesion result of the current cardiovascular image when the comprehensive contrast value exceeds the measurement threshold.

8. The model-based cardiovascular image analysis, comparison, and recognition system as described in claim 7, characterized in that, time Time pixel Adaptive weight function include: ， in, The weights are the first-order gradients. For time Current cardiovascular images At pixel The first gradient at that point, The adjustment factor for the first-order gradient. The weights are the second-order gradients. Define the domain of the image subdomains, For time Current cardiovascular images At pixel The first gradient at that point, This is the adjustment factor for the second-order gradient.

Images