Vascular OCE self-adaptive endoscopic plaque grading method and system

Abstract

The invention discloses a blood vessel OCE adaptive endoscopic plaque grading method and system, and relates to the field of intravascular elastography. The method comprises the following steps: collecting a catheter position and three-mode blood vessel data by utilizing a flexible blood vessel endoscopic probe to construct a sampling point set, and obtaining a three-mode field by utilizing initial registration transformation based on the sampling point set; constructing a transformation field based on registration transformation, and quantifying the mechanical characteristics of the tissue by using the transformation field to generate an elastic response map; defining a structural elastic coupling tensor field through an elastic response map, and calculating a complexity factor; and constructing a stability scoring function based on the complexity factor, and constructing a risk tag according to a stability score. Multi-modal data submicron registration is realized through a three-dimensional B-spline fitting graph attention network, plaque mechanical characteristics are comprehensively quantified through an asymmetric integral path, intelligent risk assessment is realized based on a coupling tensor field, and the detection sensitivity and high-risk plaque recognition accuracy are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of intravascular elastography, and specifically to a method and system for adaptive endoscopic plaque grading of vascular OCE. Background Art

[0002] In recent years, the precise assessment of atherosclerotic plaques has become a key issue in the diagnosis and treatment of cardiovascular diseases. The stability of plaques is closely related to their composition and mechanical properties, and vulnerable plaques are prone to rupture and trigger acute cardiovascular events. Therefore, there is an urgent need for a technology that can evaluate plaque stability in real time and with high precision to guide interventional treatment and risk stratification.

[0003] At present, intravascular imaging technologies mainly include optical coherence tomography (OCT) and intravascular ultrasound (IVUS). OCT can provide high-resolution images of the vascular wall structure, but it cannot directly quantify the mechanical properties of plaques; IVUS can reflect tissue hardness, but its resolution is low, making it difficult to identify vulnerable features at the micron level. Optical coherence elastography (OCE) combines the high resolution of OCT and the mechanical quantification ability of elastography, providing a new technical means for plaque stability assessment. However, the existing OCE technologies still have the following problems: Difficult multi-modal data registration: The spatio-temporal alignment of OCE elastic data and OCT structural images depends on manual or semi-automatic registration, which is vulnerable to vascular pulsation and catheter movement interference, resulting in inaccurate mechanical-structural correlation analysis.

[0004] Insufficient quantification of mechanical properties: Traditional elastography only provides static Young's modulus, ignoring key mechanical parameters such as viscoelasticity and dynamic response, making it difficult to comprehensively evaluate the risk of plaque instability.

[0005] Limited automation grading ability: Existing methods mostly rely on manual extraction of plaque features, lacking adaptive algorithms to handle individual differences and noise interference, resulting in limited clinical applicability.

[0006] In addition, existing technologies usually use fixed thresholds or simple weighted models for plaque grading, which cannot adapt to the mechanical property differences of different vascular segments and are prone to misjudgment. Therefore, there is an urgent need for an intravascular imaging analysis method that can adaptively fuse multi-modal data and achieve automated grading. Summary of the Invention

[0007] Based on the above-mentioned disadvantages of the existing technology, the purpose of the present invention is to provide a method and system for adaptive endoscopic plaque grading of vascular OCE to solve the above technical problems.

[0008] To achieve the above purpose, the present invention provides the following technical solution: A method for adaptive endoscopic plaque grading of vascular OCE, including: S1. Use a flexible vascular endoscope probe to collect catheter position and three-modal vascular data to construct a sampling point set, and based on the sampling point set, obtain a three-modal field using an initial registration transformation; S2. Construct a transformation field based on the registration transformation, and use the transformation field to quantify tissue mechanical properties to generate an elastic response map; S3. Define a structural elasticity coupling tensor field through the elastic response map and calculate the complexity factor; S4. Construct a stability scoring function based on the complexity factor and construct a risk label based on the stability score.

[0009] The present invention is further configured such that S1 specifically includes: The sampling point set includes: catheter position, OCE elastic data, OCT structural image, and local blood vessel flow velocity; Use the sampling point set to construct an initial registration transformation through three-dimensional B-spline fitting and perform interpolation according to the initial registration transformation and the data in the sampling point set to obtain a three-modal field.

[0010] The present invention is further configured such that the sampling point set includes: , where is the sampling point set, is the catheter position, is the OCE elastic data, is the OCT structural image, is the local blood vessel flow velocity, is the total number of sampling points; The calculation logic of the three-modal field: , where is the elastic response modal field, is the structural image modal field, is the blood flow modal field, is the initial registration transformation, is the interpolation function.

[0011] The present invention is further configured such that S2 specifically includes: Use the structural image modal field in the three-modal field to construct a dynamic weight; Based on the dynamic weight and the basis function, fine-tune and correct the initial registration transformation to construct a transformation field; Use the transformation field to register the OCE elastic data to the OCT space to generate an elastic response map reflecting the softness, hardness, and viscoelasticity of the plaque.

[0012] The present invention is further configured such that the calculation logic of the dynamic weight: , is the dynamic weight, is the lateral gradient, is the depth gradient, is the curvature, is the kink score, is the sensitivity factor, is the Sigmoid function; Transformation field calculation logic: , where, is the transformation field, is the initial registration transformation, is the number of deformation modes, is the basis function; Elastic response map calculation logic: , where, is the elastic response map, 、 are the start time and end time respectively, is the time point, is the time-domain weight function, is the elastic response signal, is the delayed response window function, is the viscoelastic delay time.

[0013] The present invention is further configured such that S3 specifically includes: Construct a coupling tensor field based on the cross product operation of the structural image gradient direction and the elastic response map gradient direction; Quantify the degree of abnormality of the local blood vessel through the coupling tensor field to generate a complexity factor reflecting the plaque instability risk.

[0014] The present invention is further configured such that the coupling tensor field calculation logic: , where, is the coupling tensor field, 、 are the spatial directions, 、 is the first-order partial derivative of the structural image modal field in the direction 、 , 、 is the first-order partial derivative of the elastic response map in the direction 、 , is the weight factor, is the second-order derivative; Complexity factor calculation logic: , where, is the complexity factor, is the elastic curvature change, is the local integration window.

[0015] The present invention is further configured such that S4 specifically includes: Define an asymmetric integration path, and combine the local gray-scale phase change rate and the change of the structural entropy gradient to obtain a stability score; Based on the stability score, perform binary judgment on each spatial position to construct a risk label.

[0016] The present invention is further set as follows, the integration path calculation logic: , where is the spatial coordinate point on the integration path, is the integration starting coordinate point, is the integration step parameter, is the integration path length, is the normal vector; The stability score calculation logic: , where is the stability score, is the complexity factor, is the phase change attenuation factor, is the local structural entropy mutation factor; The risk label calculation logic: , where is the risk label, is the risk threshold, is high risk, is low risk.

[0017] The present invention also provides a vascular OCE adaptive endoscopic plaque grading system, and the system includes: A data acquisition and processing module: Use a flexible vascular endoscopic probe to collect catheter positions and three-modal vascular data to construct a sampling point set, and use the initial registration transformation based on the sampling point set to obtain a three-modal field; A feature extraction module: Construct a transformation field based on the registration transformation, and use the transformation field to quantify the tissue mechanical properties to generate an elastic response map; An abnormality analysis module: Define a structural elasticity coupling tensor field through the elastic response map, and calculate the complexity factor; A risk assessment module: Construct a stability scoring function based on the complexity factor, and construct a risk label based on the stability score.

[0018] The present invention provides a method and system for adaptive endoscopic plaque grading of blood vessels by OCE. The method includes: S1. Using a flexible blood vessel endoscopic probe to collect catheter positions and three-modal blood vessel data to construct a sampling point set, and obtaining a three-modal field based on the sampling point set using an initial registration transformation; S2. Constructing a transformation field based on the registration transformation, and generating an elastic response map by quantifying tissue mechanical properties using the transformation field; S3. Defining a structural-elastic coupling tensor field through the elastic response map, and calculating a complexity factor; S4. Constructing a stability scoring function based on the complexity factor, and generating risk labels based on the stability score. The beneficial effects include: High-precision registration and fusion of multi-modal data: An initial registration transformation is constructed through three-dimensional B-spline fitting, and the transformation field optimization with dynamic weight adjustment is combined to achieve high-precision spatio-temporal alignment of OCE elastic data, OCT structural images, and hemodynamic parameters. A deformation compensation mechanism based on a graph attention network is adopted to effectively overcome the registration errors caused by blood vessel pulsation and catheter movement, and the registration accuracy reaches the sub-micron level.

[0019] Comprehensive quantification of plaque mechanical properties: An innovative method for generating an elastic response map simultaneously obtains the static elastic modulus and dynamic viscoelastic parameters of the plaque through time-varying integration combined with the viscoelastic delay time calculation. The introduction of an asymmetric integration path design can accurately capture the mechanical-structural mutation characteristics at the plaque edge and improve the detection sensitivity for thin fibrous caps.

[0020] Intelligent plaque risk assessment: The constructed structural-elastic coupling tensor field effectively quantifies the mechanical heterogeneity in the plaque region, and the complexity factor calculation integrates multi-scale spatial features. Anatomical position-adaptive dynamic threshold segmentation algorithm improves the recognition accuracy of high-risk plaques, significantly superior to traditional fixed threshold methods.

[0021] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the following specifically gives the specific implementation manners of this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings. In the drawings: Figure 1 It is a flowchart of a method for adaptive endoscopic plaque grading of blood vessels by OCE shown in an exemplary embodiment of the present invention; Figure 2Schematic diagram of a vascular OCE adaptive endoscopic plaque grading system shown for an exemplary embodiment of the present invention. Detailed implementation manners

[0023] The following will describe the implementation manners of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for explaining the present invention, rather than for limiting the protection scope of the present invention.

[0024] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner. Therefore, only the components related to the present invention are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and ratio of each component in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0025] In the following description, a large number of details are explored to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand. Embodiment 1

[0026] A method for grading vascular OCE adaptive endoscopic plaques, as Figure 1 shown, includes: S1. Use a flexible vascular endoscopic probe to collect catheter positions and three-modal vascular data to construct a sampling point set, and use an initial registration transformation based on the sampling point set to obtain a three-modal field; S2. Construct a transformation field based on the registration transformation, and use the transformation field to quantify tissue mechanical properties to generate an elastic response map; S3. Define a structural elasticity coupling tensor field through the elastic response map, and calculate a complexity factor; S4. Construct a stability scoring function based on the complexity factor, and construct a risk label based on the stability score.

[0027] The present invention is further configured such that S1 specifically includes: The sampling point set includes: catheter position, OCE elastic data, OCT structural image, and local vascular flow rate; Construct an initial registration transformation by fitting a 3D B-spline using a set of sampling points, and obtain a three-modal field by interpolation based on the initial registration transformation and the data in the set of sampling points. Specifically, a flexible vascular endoscope probe integrates an OCE elastic excitation module, an OCT imaging module, and a micro blood flow sensor; the logic for establishing the initial registration transformation and the three-modal field: First, use 3D B-spline fitting to preliminarily align the data of different modalities collected by the endoscope, construct a preliminary spatial correspondence as the initial registration transformation, and through the interpolation method, map the OCE elastic data, OCT images, and blood flow data to the same coordinate system to form a three-modal field containing structure, elasticity, and blood flow.

[0028] The present invention is further configured such that the set of sampling points includes: , where is the set of sampling points, is the catheter position, is the OCE elastic data, is the OCT structural image, is the local blood vessel flow rate, is the total number of sampling points; The calculation logic of the three-modal field: , where is the elastic response modal field, is the structural image modal field, is the blood flow modal field, is the initial registration transformation, is the interpolation function. Specifically, in the set of sampling points: the catheter position represents the real-time position of the probe in the blood vessel, the OCE elastic data represents the hardness and deformation information of the blood vessel tissue, the OTC structural image represents the microscopic structure of the blood vessel, the local blood vessel flow rate represents the hemodynamic parameters; in the calculation of the three-modal field: the initial registration transformation is obtained by performing 3D B-spline fitting on the catheter position based on the Frenet-Serret framework to obtain the main path curve of the blood vessel as the initial spatial reference. Then, all three-modal data are remapped or interpolated around this centerline to construct the initial registration transformation. This method is an existing technology and will not be elaborated here; the interpolation function can select different interpolation algorithms according to requirements. For example, linear interpolation can be used for quick preview or low-computing resource environments, B-spline interpolation can be used for standard medical image processing, and radial basis functions can be used for sparse sampling or complex deformation registration. The interpolation calculation is an existing technology and will not be elaborated here; the elastic response modal field is used to quantify the distribution field of mechanical property parameters at each spatial position of the blood vessel wall, reflecting the mechanical properties such as tissue stiffness and viscoelasticity; the structural image modal field is a high-resolution vascular wall tomography structure image field, characterizing the microscopic morphological characteristics of tissues; blood flow modality field is the spatial distribution field of hemodynamic parameters in the blood vessel lumen, characterizing the interaction between blood flow and the vessel wall.

[0029] The present invention is further configured such that S2 specifically includes: Constructing a dynamic weight using the structural image modality field in the three-modal field; Fine-tuning and correcting the initial registration transformation based on the dynamic weight and basis functions to construct a transformation field; Registering the OCE elastic data to the OCT space using the transformation field to generate an elastic response map reflecting the softness, hardness, and viscoelasticity of the plaque. Specifically, the establishment of the transformation field: Since the blood vessel may undergo local deformation due to heartbeat, respiration, and catheter movement, the initial registration may not be precise enough. Therefore, local deformation mode basis functions are used to fine-tune the initial registration to make the registration more conform to the actual situation; Generation of the elastic response map: Using the optimized transformation field to map the OCE elastic data to the OCT structural image position to generate an elastic response map reflecting the softness, hardness, and relaxation characteristics of the plaque.

[0030] The present invention is further configured such that the calculation logic of the dynamic weight: , is the dynamic weight, is the lateral gradient, is the depth gradient, is the curvature, is the kink score, is the sensitivity factor, is the Sigmoid function; The calculation logic of the transformation field: , where, is the transformation field, is the initial registration transformation, is the number of deformation modes, is the basis function, is the dynamic weight; The calculation logic of the elastic response map: , where, is the elastic response map, 、 are the start time and end time respectively, is the time point, is the time-domain weight function, is the elastic response signal, is the delayed response window function, is the viscoelastic delay time. Specifically, the dynamic weight It is to adaptively adjust the weight of local offset by quantifying the curvature of the structural edge and kink with high-order derivatives, which is used to enhance the response to the calcification or fibrous cap fracture area, and the lateral gradient and the depth gradient are first-order gradients, which respectively represent the sudden change of edge intensity and reflection intensity in the depth direction. The second-order gradient represents curvature, which is used to quantify the concavity and convexity of the fibrous cap. Positive curvature is convex, and negative curvature is concave. The kink score is the mixed reciprocal of the second-order gradient, which is used to detect oblique structural kinks and identify calcification fractures. The item is used to strengthen the response to the convex fibrous cap, indicating the area prone to rupture. It is used to capture oblique calcification fractures, indicating the area of mechanical instability. is the sensitivity factor for vascular type adjustment, and the value range is in , is the Sigmoid function, which is used to compress the output to . In the calculation of the transformation field: the number of deformation modes is controlled by network dynamic pruning, and the value range is in , and the basis function is constructed by jointly modeling the three-modal gradient signals in the voxel neighborhood using a graph attention network to extract discriminative local deformation response patterns. The formula is: , where is the graph attention network, is the gradient tensor of the elastic response modal field, which represents the change gradient of the tissue elastic modulus in space. The tissue hardness difference reflects the potentially ruptured risk area of the plaque, especially sensitive at the fibrous cap. is the gradient tensor of the structural image modal field, which represents the spatial change of tissue optical properties and is used to describe the area of tissue interface or scattering property change, usually changing significantly at the plaque boundary. is the gradient tensor of the hydrodynamic modal field, which is used to describe the velocity distribution of blood in the lumen. The blood flow perturbation area adjacent to the plaque often indicates biomechanical instability. In the calculation of the elastic response map: the elastic response map The larger the value, the more significant and concentrated the response of this point to the excitation within a specific time period, which also means that the potential structure in this area is complex or unstable; the time-domain weight function is used to describe the time point relative to the main excitation time point , and the formula is: , is the rising edge steepness, which is determined by the probe excitation pulse width, and the value range is in between, is the pulse peak time, which is based on the calibration of the device, and the value range is in between; elastic response signal is through the registration field to map the original OCE signal at the time point to the OCT coordinate system; viscoelastic delay time is based on the relaxation time constant of the Maxwell model. The softer the structure, the stronger the viscosity, and the more significant the delay; delay response window function is used to filter out high-frequency noises including blood flow disturbances and retain the inherent relaxation signals of tissues.

[0031] The present invention is further configured such that S3 specifically includes: Construct a coupling tensor field based on the cross product operation of the structural image gradient direction and the elastic response atlas gradient direction; Quantify the degree of abnormality in the local blood vessels through the coupling tensor field to generate a complexity factor reflecting the risk of plaque instability. Specifically, the coupling tensor field is used to describe the degree of consistency between the "local blood vessel structure direction" and the "force response direction", and a complexity factor is defined based on this coupling tensor field to identify potential unstable or lesion regions. The essence of this step is to evaluate the consistency or incoordination between the "structural morphology" and the "mechanical response" in different regions within the blood vessel, and finally generate a complexity factor that can reflect the local instability risk of the plaque.

[0032] The present invention is further configured such that the calculation logic of the coupling tensor field: , where is the coupling tensor field, , are spatial directions, , is the first-order partial derivative of the structural image modal field in the direction , , , is the first-order partial derivative of the elastic response atlas in the direction , , is the weight factor, is the second-order derivative; Complexity factor calculation logic: , where is the complexity factor, is the elastic curvature change, is the local integration window. Specifically, the coupling tensor field is a tensor field constructed through the asymmetry between the image gradient and the elastic response gradient and the second-order change of the structural image. Each component of the tensor reflects the "synergy" and "complexity" of the structure and the elastic direction in a specific direction pair; spatial directions , Value , indicating three spatial axes: direction, longitudinal direction, and depth; and It is a mathematical symbol used to represent different directions in three-dimensional space; and Represents the modal field of the structural image in and The speed of the change in direction indicates the intensity of the light and dark changes in the image. If the change is drastic, it proves that there is a patch boundary. , The elastic response spectrum is and The speed of the change in direction indicates the degree of change in hardness and softness. If the change is drastic, it means that there is alternation between hardness and softness. It is a cross term used to compare whether the change directions of "structure" and "elasticity" are consistent. If they are consistent, it means it is safer. If they are inconsistent, it means it is more dangerous and there are unstable plaques. is the structural image modal field in and The second-order derivative in the direction is calculated by Hessian and is used to describe the local perturbation and geometric curvature characteristics of the tissue morphology; the weight factor is the Hessian adjustment weight factor, which is used to control the influence of the second-order information of the structure in the tensor construction. The value range is Complexity factor It is a regional complexity response index obtained by weighted superposition of tensor components using a local integral window. It is used to reflect the directional inconsistency between the local regional structure diagram and the elastic modulus diagram, the rate of change of stiffness and the degree of structural disturbance, and the change of elastic curvature. It is the second-order change of the elastic response spectrum, which is used to determine whether the modulus changes dramatically and identify the modulus mutation area. The greater the change in elastic curvature, the more dramatic the change in elastic modulus, which means the more unstable the structure; local integration window It is defined by a sliding window and is used to ensure local statistical stability and enhance spatial robustness. It is usually taken as , High resolution images can be set as .

[0033] The present invention is further configured that S4 specifically includes: Define an asymmetric integral path and combine the local grayscale phase transition rate with the structural entropy gradient change to obtain a stability score; Construct risk labels by making binary judgments on each spatial position based on stability scores. Specifically, in vascular OCT images, locally plaque-unstable regions typically exhibit: rapid changes in grayscale values, abnormal structural entropy gradients, and the unstable regions are not necessarily symmetrically distributed in space; therefore, by constructing a direction-sensitive asymmetric integration path, fusing the local grayscale phase change rate and the gradient change of structural entropy, a stability score index is constructed, and then it is used to determine whether a certain region is an unstable risk area.

[0034] The present invention is further configured as follows for the integration path calculation logic: , where is the spatial coordinate point on the integration path, is the integration starting coordinate point, is the integration step parameter, is the integration path length, is the normal vector; The stability score calculation logic: , where is the stability score, is the complexity factor, is the phase change attenuation factor, is the local structural entropy mutation factor; The risk label calculation logic: , where is the risk label, is the risk threshold, is high risk, is low risk. Specifically, in the integration path calculation: the integration starting coordinate point is the three-dimensional coordinate of the current calculation point, obtained through the voxel coordinates in the structural image modal field; the integration step parameter is the step variable on the integration path, which is the position parameter on the discrete integration path, usually taking a small step of 0.1 or 1, and the specific value is determined according to the resolution and is the same as the resolution; the integration path length is the maximum length of the integration path, set by the image size ratio, and the value range is within the individual voxel length; the normal vector is used to point to the inside of the plaque, which is the direction of integration, obtained by normalizing the differential of the structural image modal field using the image gradient, which is a prior art and will not be elaborated here. In the stability score calculation: the phase change attenuation factor is used to suppress the interference of noise or discontinuous regions through the grayscale change rate and retain stable structural features. This method is a prior art and will not be elaborated here; the local structural entropy mutation factor This method of quantifying tissue complexity by using local entropy and detecting pathological boundaries through its rate of change is a prior art, and will not be elaborated here. In the calculation of risk tags: the risk threshold is the threshold set by experts through clinically annotated data, and its value range is between, such as: the left main coronary artery , branch vessels . Finally, a connected domain is constructed for the points with high-risk risk tags to obtain a candidate region. The calculation logic of the candidate region is: , is the set of candidate regions, is a candidate region, is the total number of candidate regions, is the connected domain function; by calculating the mean stability score of all voxels in the candidate region, if the mean value is higher than the threshold, it is determined as a high-risk region. The threshold is default set to 0.75 and can be modified according to different usage scenarios.

[0035] Example Two Please refer to Figure 2 , an exemplary vascular OCE adaptive endoscopic plaque grading system includes: Data acquisition and processing module: Using a flexible vascular endoscopic probe to collect catheter positions and three-modal vascular data to construct a sampling point set and obtaining a three-modal field based on the sampling point set using an initial registration transformation; Feature extraction module: Constructing a transformation field based on the registration transformation and generating an elastic response map by quantifying tissue mechanical properties using the transformation field; Abnormality analysis module: Defining a structural elasticity coupling tensor field through the elastic response map and calculating the complexity factor; Risk assessment module: Constructing a stability score function based on the complexity factor and constructing risk tags based on the stability score.

[0036] It should be noted that the vascular OCE adaptive endoscopic plaque grading system provided in the above embodiment and the vascular OCE adaptive endoscopic plaque grading method provided in the above embodiment belong to the same concept. The specific ways in which each module and unit perform operations have been described in detail in the method embodiment and will not be elaborated here. In practical applications, the vascular OCE adaptive endoscopic plaque grading system provided in the above embodiment can, according to needs, allocate the above functions to different functional modules, that is, divide the internal structure of the system into different functional modules to complete all or part of the functions described above. This will not be limited here either.

[0037] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0038] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. Additionally, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be understood specifically by referring to the context before and after.

[0039] In this application, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or plural.

[0040] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0041] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0042] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0043] In several embodiments provided in this application, it should be understood that the disclosed systems can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in an electrical, mechanical, or other form.

[0044] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0045] In addition, the functional units in each embodiment of this application can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0046] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this 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 for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0047] As described above, the above are only specific implementation manners of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, and all of them should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. An adaptive endoscopic plaque grading method for blood vessels, characterized in that Including: S1. Using a flexible vascular endoscopy probe to collect catheter position and three-modal vascular data to construct a sampling point set, and based on the sampling point set, obtaining a three-modal field using an initial registration transformation; S2. Constructing a transformation field based on the registration transformation, and using the transformation field to quantify tissue mechanical properties to generate an elastic response map; S3. Defining a structural elasticity coupling tensor field through the elastic response map, and calculating a complexity factor; S4. Constructing a stability scoring function based on the complexity factor, and constructing a risk label according to the stability score.

2. The method for self-adaptive endoscopic plaque grading of blood vessels according to claim 1, characterized in that Specifically, S1 includes: The sampling point set includes: catheter position, OCE elastic data, OCT structural image, and local vascular flow rate; Using the sampling point set to construct an initial registration transformation through three-dimensional B-spline fitting, and performing interpolation based on the initial registration transformation and the data in the sampling point set to obtain a three-modal field.

3. The method for grading vascular OCE adaptive endoscopic plaques according to claim 2, wherein The set of sampling points includes: , where is the set of sampling points, is the catheter position, is the OCE elastic data, is the OCT structural image, is the local blood vessel flow velocity, is the total number of sampling points; Three-modal field calculation logic: , where is the elastic response modal field, is the structural image modal field, is the blood flow modal field, is the initial registration transformation, is the interpolation function.

4. A method for grading vascular OCE adaptive endoscopic plaques according to claim 1, characterized in that, Specifically, S2 includes: Using the structural image modal field in the three-modal field to construct a dynamic weight; Based on the dynamic weight and basis functions, fine-tuning and correcting the initial registration transformation to construct a transformation field; Using the transformation field to register the OCE elastic data to the OCT space, and generating an elastic response map reflecting plaque softness, hardness, and viscoelasticity.

5. The method for adaptively endoscopically grading vascular OCE plaques according to claim 4, wherein Dynamic weight calculation logic: , is the dynamic weight, is the horizontal gradient, is the depth gradient, is the curvature, is the kink score, is the sensitivity factor, is the Sigmoid function; Transformation field calculation logic: , where is the transformation field, is the initial registration transformation, is the number of deformation modes, is the basis function; Elastic response spectrum calculation logic: , where is the elastic response spectrum, and are the start time and end time respectively, is the time point, is the time-domain weight function, is the elastic response signal, is the delayed response window function, is the viscoelastic delay time.

6. The method for adaptively endoscopically grading vascular OCE plaques according to claim 1, wherein, Specifically, S3 includes: Constructing a coupling tensor field based on the cross product operation of the gradient direction of the structural image and the gradient direction of the elastic response map; Quantifying the degree of abnormality of the local blood vessel through the coupling tensor field to generate a complexity factor reflecting plaque instability risk.

7. A method for adaptive endoscopic plaque grading of blood vessels according to claim 6, characterized in that Coupled tensor field calculation logic: , where is the coupled tensor field, , are the spatial directions, , are the first-order partial derivatives of the structural image modality field in the directions , , , are the first-order partial derivatives of the elastic response spectrum in the directions , , is the weight factor, is the second derivative; Complexity factor calculation logic: , where is the complexity factor, is the elastic curvature change, is the local integration window.

8. The method for grading vascular OCE adaptive endoscopic plaques according to claim 1, characterized in that, Specifically, S4 includes: Defining an asymmetric integration path, and combining the local gray phase change rate and the structural entropy gradient change to obtain a stability score; Based on the stability score, performing binary judgment on each spatial position to construct a risk label.

9. A method for adaptive endoscopic plaque grading of blood vessels OCE according to claim 8, characterized in that Integral path calculation logic: , where is the spatial coordinate point on the integral path, is the integral starting coordinate point, is the integral step parameter, is the integral path length, is the normal vector; Stability score calculation logic: , where is the stability score, is the complexity factor, is the phase transition attenuation factor, is the local structure entropy mutation factor; Risk label calculation logic: , where is the risk label, is the risk threshold, is high risk, is low risk.

10. A vascular OCE adaptive endoscopic plaque grading system for implementing the vascular OCE adaptive endoscopic plaque grading method according to any one of claims 1-9, characterized in that, Including: Data acquisition and processing module: Using a flexible vascular endoscopy probe to collect catheter position and three-modal vascular data to construct a sampling point set, and based on the sampling point set, obtaining a three-modal field using an initial registration transformation; Feature extraction module: Constructing a transformation field based on the registration transformation, and using the transformation field to quantify tissue mechanical properties to generate an elastic response map; Abnormality analysis module: Defining a structural elasticity coupling tensor field through the elastic response map, and calculating a complexity factor; Risk assessment module: Constructing a stability scoring function based on the complexity factor, and constructing a risk label according to the stability score.

Images