A vascular OCE adaptive endoscopic plaque grading method and system

Abstract

The present invention discloses a method and system for adaptive endoscopic plaque grading using vascular OCE, which relates to the field of intravascular elastic imaging. The method comprises: using a flexible endoscopic probe to collect catheter position and trimodal vascular data to construct a sampling point set and using an initial registration transformation based on the sampling point set to obtain a trimodal field; constructing a transformation field based on the registration transformation, and using the transformation field to quantify the mechanical properties of the tissue to generate an elastic response map; defining a structural elastic coupling tensor field through the elastic response map, and calculating a complexity factor; constructing a stability scoring function based on the complexity factor, and constructing a risk label based on the stability score. Submicron-level registration of multimodal data is achieved through a three-dimensional B-spline fitting graph attention network, plaque mechanical characteristics are comprehensively quantified through an asymmetric integral path, and intelligent risk assessment is achieved based on the coupling tensor field, which significantly improves the detection sensitivity and the accuracy of high-risk plaque identification.

Description

Technical Field

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

[0002] In recent years, accurate assessment of atherosclerotic plaques has become a key issue in the diagnosis and treatment of cardiovascular disease. Plaque stability is closely related to its 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 accurately assess plaque stability in real time to guide interventional therapy and risk stratification.

[0003] Currently, intravascular imaging technologies primarily include optical coherence tomography (OCT) and intravascular ultrasound (IVUS). OCT provides high-resolution images of the vessel wall structure but cannot directly quantify the mechanical properties of plaques. IVUS can reflect tissue stiffness, but its resolution is low, making it difficult to identify micron-scale fragile features. Optical coherence elastography (OCE) combines the high resolution of OCT with the mechanical quantification capabilities of elastography, providing a new technical approach for assessing plaque stability. However, existing OCE technology still has the following issues:

[0004] Multimodal data registration is difficult: The spatiotemporal alignment of OCE elastic data and OCT structural images relies on manual or semi-automatic registration, which is easily affected by vascular pulsation and catheter movement, resulting in inaccurate mechanical-structural correlation analysis.

[0005] 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 assess the risk of plaque instability.

[0006] Limited automated grading capabilities: Existing methods mostly rely on manual extraction of plaque features and lack adaptive algorithms to handle individual differences and noise interference, limiting their clinical applicability.

[0007] Furthermore, existing techniques typically use fixed thresholds or simple weighted models for plaque grading, which cannot adapt to the differences in mechanical properties of different vascular segments and can easily lead to misjudgment. Therefore, there is an urgent need for an intravascular imaging analysis method that can adaptively fuse multimodal data and achieve automated grading. Summary of the Invention

[0008] Based on the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a method and system for adaptive endoscopic plaque grading in a vascular OCE to solve the above-mentioned technical problems.

[0009] To achieve the above objectives, the present invention provides the following technical solution: a method for adaptive endoscopic plaque grading using vascular OCE, comprising:

[0010] S1. Use a flexible endovascular probe to collect catheter position and trimodal vascular data to construct a sampling point set. Based on the sampling point set, perform an initial registration transformation to obtain a trimodal field.

[0011] S2. Construct a transformation field based on the registration transformation, and use the transformation field to quantify the mechanical properties of the tissue and generate an elastic response map;

[0012] S3. Define the structural elastic coupling tensor field through the elastic response spectrum and calculate the complexity factor;

[0013] S4. Construct a stability scoring function based on the complexity factor and construct a risk label based on the stability score.

[0014] The present invention is further configured such that S1 specifically includes:

[0015] The sampling point set includes: catheter position, OCE elasticity data, OCT structural images, and local vascular flow velocity;

[0016] The sampling point set is used to construct an initial registration transformation through three-dimensional B-spline fitting, and the trimodal field is obtained by interpolating the initial registration transformation and the data in the sampling point set.

[0017] The present invention is further configured such that the sampling point set includes: ,in, is the set of sampling points, is the catheter position, For OCE elastic data, is the OCT structural image, is the local vascular flow velocity, is the total number of sampling points;

[0018] Three-modal field calculation logic: ,in, 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.

[0019] The present invention is further configured such that S2 specifically includes:

[0020] The dynamic weight is constructed using the structural image modal field in the three-modal field;

[0021] Fine-tune and correct the initial registration transformation based on dynamic weights and basis functions to construct the transformation field;

[0022] The OCE elastic data were registered to the OCT space using the transformation field to generate an elastic response map reflecting the hardness and viscoelasticity of the plaque.

[0023] The present invention is further configured such that the dynamic weight calculation logic is: , is the dynamic weight, is the horizontal gradient, is the depth gradient, is the curvature, Score the kinks, is the sensitivity factor, is the Sigmoid function;

[0024] Transformation field calculation logic: ,in,

[0025] is the transformation field, is the initial registration transformation, is the number of deformation modes, is the basis function;

[0026] Elastic response spectrum calculation logic: ,in, is the elastic response spectrum, 、 The start time and end time are respectively, For time point, is the time domain weight function, is the elastic response signal, is the delayed response window function, is the viscoelastic delay time.

[0027] The present invention is further configured such that S3 specifically includes:

[0028] The coupled tensor field is constructed based on the cross product operation of the gradient direction of the structural image and the gradient direction of the elastic response spectrum;

[0029] The degree of local abnormality in the blood vessel is quantified by coupling tensor fields to generate a complexity factor reflecting the risk of plaque instability.

[0030] The present invention is further configured to couple the tensor field calculation logic:

[0031] ,in, is the coupled tensor field, 、 is the spatial direction, 、 is the modal field of the structural image in the direction 、 The first-order partial derivative on , 、 The elastic response spectrum in the direction 、 The first-order partial derivative on , is the weight factor, is the second-order derivative;

[0032] Complexity factor calculation logic: ,in, is the complexity factor, is the change in elastic curvature, is the local integration window.

[0033] The present invention is further configured such that S4 specifically includes:

[0034] An asymmetric integral path is defined, and the stability score is obtained by combining the local grayscale phase transition rate and the structural entropy gradient change;

[0035] Based on the stability score, each spatial location is binarized to construct a risk label.

[0036] The present invention is further configured such that the integral path calculation logic is: ,in, is the spatial coordinate point on the integration path, is the starting coordinate point of integration, is the integration step parameter, is the integration path length, is the normal vector;

[0037] Stability score calculation logic: ,in, For stability score, is the complexity factor, is the phase change attenuation factor, is the local structural entropy mutation factor; risk label calculation logic: ,in, is the risk label, is the risk threshold, For high risk, For low risk.

[0038] The present invention also provides a vascular OCE adaptive endoscopic plaque grading system, the system comprising:

[0039] Data acquisition and processing module: uses a flexible endovascular probe to collect catheter position and trimodal vascular data to construct a sampling point set and obtains a trimodal field based on the sampling point set using an initial registration transformation;

[0040] Feature extraction module: constructs a transformation field based on the registration transformation, and uses the transformation field to quantify the mechanical properties of the tissue to generate an elastic response map;

[0041] Abnormal analysis module: defines the structural elastic coupling tensor field through the elastic response spectrum and calculates the complexity factor;

[0042] Risk assessment module: Constructs a stability scoring function based on the complexity factor, and constructs a risk label based on the stability score.

[0043] The present invention provides a method and system for adaptive endoscopic plaque grading using OCE. The method comprises: S1. using a flexible endoscopic probe to collect catheter position and trimodal vascular data to construct a sampling point set, and then performing an initial registration transformation based on the sampling point set to obtain a trimodal field; 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 elastic coupling tensor field based on the elastic response map and calculating a complexity factor; and S4. constructing a stability scoring function based on the complexity factor, and constructing a risk label based on the stability score. The method achieves the following beneficial effects:

[0044] High-precision registration and fusion of multimodal data: By constructing the initial registration transformation through 3D B-spline fitting and combining it with transformation field optimization with dynamic weight adjustment, high-precision spatiotemporal alignment of OCE elastic data, OCT structural images, and hemodynamic parameters is achieved. A deformation compensation mechanism based on a graph attention network is used to effectively overcome the registration errors caused by vascular pulsation and catheter movement, achieving sub-micron registration accuracy.

[0045] Comprehensive quantification of plaque mechanical properties: An innovative elastic response map generation method simultaneously obtains the static elastic modulus and dynamic viscoelastic parameters of the plaque through time-varying integration combined with viscoelastic delay time calculation; the introduction of an asymmetric integral path design can accurately capture the mechanical-structural mutation characteristics of the plaque edge and improve the detection sensitivity of thin fibrous caps.

[0046] Intelligent plaque risk assessment: The constructed structural-elastic coupling tensor field effectively quantifies the mechanical heterogeneity of the plaque area, and the complexity factor calculation integrates multi-scale spatial features. The dynamic threshold segmentation algorithm based on anatomical position adaptation improves the identification accuracy of high-risk plaques, significantly outperforming the traditional fixed threshold method.

[0047] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without inventive efforts. In the drawings:

[0049] Figure 1 This is a flow chart showing a method for adaptive endoscopic plaque grading in a blood vessel using OCE according to an exemplary embodiment of the present invention;

[0050] Figure 2 The figure is a schematic structural diagram of a vascular OCE adaptive endoscopic plaque grading system according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following describes the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art will readily appreciate the other advantages and benefits of the present invention from the disclosure herein. The present invention may also be implemented or applied through various other specific embodiments, and the various details in this specification may be modified or altered based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are intended only to illustrate the present invention and are not intended to limit the scope of protection of the present invention.

[0052] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0053] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the embodiments of the present invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring the embodiments of the present invention. Example 1

[0054] A vascular OCE adaptive endoscopic plaque grading method, such as Figure 1 Shown, including:

[0055] S1. Use a flexible endovascular probe to collect catheter position and trimodal vascular data to construct a sampling point set. Based on the sampling point set, perform an initial registration transformation to obtain a trimodal field.

[0056] S2. Construct a transformation field based on the registration transformation, and use the transformation field to quantify the mechanical properties of the tissue and generate an elastic response map;

[0057] S3. Define the structural elastic coupling tensor field through the elastic response spectrum and calculate the complexity factor;

[0058] S4. Construct a stability scoring function based on the complexity factor and construct a risk label based on the stability score.

[0059] The present invention is further configured such that S1 specifically includes:

[0060] The sampling point set includes: catheter position, OCE elasticity data, OCT structural images, and local vascular flow velocity;

[0061] Using a sampling point set, an initial registration transformation is constructed through 3D B-spline fitting. The trimodal field is then interpolated between the initial registration transformation and the data in the sampling point set. Specifically, the flexible endovascular 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 trimodal field is as follows: First, 3D B-spline fitting is used to initially align the data from the different modalities collected by the endoscope, constructing a preliminary spatial correspondence as the initial registration transformation. Through interpolation, the OCE elastic data, OCT images, and blood flow data are mapped to the same coordinate system, forming a trimodal field encompassing structure, elasticity, and blood flow.

[0062] The present invention is further configured such that the sampling point set includes: ,in, is the set of sampling points, is the catheter position, For OCE elastic data, is the OCT structural image, is the local vascular flow velocity, is the total number of sampling points;

[0063] Three-modal field calculation logic: ,in, 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 sampling point set: the catheter position Indicates the real-time position of the probe in the blood vessel, OCE elasticity data Indicates the hardness and deformation information of vascular tissue, OTC structure image Represents the microstructure of blood vessels and local vascular flow velocity Represents hemodynamic parameters; in the trimodal field calculation: the initial registration transformation is based on the Frenet-Serret framework by performing three-dimensional B-spline fitting on the catheter position to obtain the main path curve of the blood vessel as the initial spatial reference. Then, all trimodal data are remapped or interpolated around this center line to construct the initial registration transformation. This method is an existing technology and will not be described in detail here; interpolation function Different interpolation algorithms can be selected according to needs, such as linear interpolation for fast preview or low computing resource environment, B-spline interpolation for standard medical image processing, radial basis function for sparse sampling or complex deformation registration. Interpolation calculation is an existing technology and will not be described in detail here. Used to quantify the distribution field of mechanical characteristic parameters at each spatial position of the blood vessel wall, reflecting the mechanical properties of the tissue such as stiffness and viscoelasticity; structural image modal field It is a high-resolution vascular wall tomographic structure image field that characterizes the microscopic morphological characteristics of the tissue; blood flow modal field It is the spatial distribution field of hemodynamic parameters in the blood vessel lumen, characterizing the interaction between blood flow and the vessel wall.

[0064] The present invention is further configured such that S2 specifically includes:

[0065] The dynamic weight is constructed using the structural image modal field in the three-modal field;

[0066] Fine-tune and correct the initial registration transformation based on dynamic weights and basis functions to construct the transformation field;

[0067] A transformation field is used to register the OCE elasticity data to OCT space, generating an elastic response map reflecting the plaque's hardness and viscoelastic properties. Specifically, the transformation field is established: Because blood vessels can undergo local deformation due to heartbeat, respiration, and catheter movement, initial registration may be inaccurate. Therefore, local deformation pattern basis functions are used to fine-tune the initial registration to better align it with reality. Elastic response map generation: Using the optimized transformation field, the OCE elasticity data is mapped to the OCT structural image position, generating an elastic response map reflecting the plaque's hardness and tissue relaxation properties.

[0068] The present invention is further configured such that the dynamic weight calculation logic is: , is the dynamic weight, is the horizontal gradient, is the depth gradient, is the curvature, Score the kinks, is the sensitivity factor, is the Sigmoid function;

[0069] Transformation field calculation logic: ,in, is the transformation field, is the initial registration transformation, is the number of deformation modes, is the basis function, is the dynamic weight;

[0070] Elastic response spectrum calculation logic: ,in, is the elastic response spectrum, 、 The start time and end time are respectively, For 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 The adaptive adjustment of the local offset weight by quantifying the edge curvature and kink of the structure through high-order derivatives is used to enhance the response to the calcification or fibrous cap rupture area, the lateral gradient With depth gradient is a first-order gradient, representing the sudden change of edge intensity and reflection intensity in the depth direction, The curvature is represented by a second-order gradient, which is used to quantify the convexity of the fiber cap. Positive curvature is convex, negative curvature is concave, and kink score It is the mixed inverse of the second-order gradient, used to detect oblique structural kinks and identify calcification breaks. The item is used to strengthen the response to the raised fiber cap, indicating the vulnerable area. Used to capture oblique calcified fractures, indicating areas of mechanical instability, The sensitivity factor is used to adjust the value range of blood vessel type. , is the Sigmoid function, which is used to compress the output to . Transformation field calculation: number of deformation modes Controlled by network dynamic pruning, the value range is , basis functions It uses the graph attention network to jointly model the trimodal gradient signals in the voxel neighborhood and extract the discriminative local deformation response pattern. The formula is: ,in, is the graph attention network, is the gradient tensor of the elastic response modal field, which represents the change gradient of tissue elastic modulus in space. The difference in tissue hardness reflects the potential risk area of ​​plaque rupture, especially in the fibrous cap. It is the gradient tensor of the structural image modal field, which represents the spatial variation of the optical properties of the tissue and is used to describe the area where the tissue interface or scattering properties change. It usually changes significantly at the plaque boundary. It is the gradient tensor of the fluid dynamics modal field, used to describe the velocity distribution of blood in the lumen. Plaques adjacent to blood flow disturbance areas often indicate biomechanical instability. Elastic response map calculation: Elastic response map The larger the value, the more significant and concentrated the response of the point to the stimulus in a specific period of time, which also means that the potential structure of the area is complex or unstable; the time domain weight function It is used to describe a point in time Relative to the main excitation time point The weight of is: , The rising edge steepness is determined by the probe excitation pulse width and has a value range of between, is the pulse peak time, based on the calibration of the device, the value range is between; elastic response signal By registering the field The time point The original OCE signal is mapped to the OCT coordinate system; the viscoelastic delay time It is the relaxation time constant based on the Maxwell model. The softer the structure, the stronger the viscosity and the more significant the delay. The delayed response window function It is used to filter out high-frequency noise including blood flow disturbance and retain the intrinsic relaxation signal of tissue.

[0071] The present invention is further configured such that S3 specifically includes:

[0072] The coupled tensor field is constructed based on the cross product operation of the gradient direction of the structural image and the gradient direction of the elastic response spectrum;

[0073] The degree of local vascular abnormality is quantified using a coupled tensor field to generate a complexity factor reflecting the risk of plaque instability. Specifically, the coupled tensor field describes the degree of consistency between the "local vascular structural direction" and the "force response direction." Based on this coupled tensor field, a complexity factor is defined to identify potential unstable or lesion areas. This step essentially assesses the consistency or inconsistency between the "structural morphology" and "mechanical response" of different regions within the vessel, ultimately generating a complexity factor that reflects the risk of local plaque instability.

[0074] The present invention is further configured to couple the tensor field calculation logic: ,in, is the coupled tensor field, 、 is the spatial direction, 、 is the modal field of the structural image in the direction 、 The first-order partial derivative on , 、 The elastic response spectrum in the direction 、 The first-order partial derivative on , is the weight factor, is the second-order derivative;

[0075] Complexity factor calculation logic: ,in, is the complexity factor, is the change in elastic curvature, is the local integration window. Specifically, the coupled tensor field It is a tensor field constructed by 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 "cooperativity" and "complexity" of the structure and elastic direction in a specific direction pair; spatial direction 、 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 structural image modal field 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 indicates the presence of patch boundaries. 、 Indicates the elastic response spectrum in and The speed of the change in direction indicates the degree of change in softness and hardness. If the change is drastic, it indicates that there is alternation between softness and hardness. 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 is an unstable plaque. is the structural image modal field in and The second-order derivative in the direction is obtained by Hessian calculation and is used to describe the local perturbation and geometric curvature characteristics of the tissue morphology; the weight factor It 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. Its 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 judge whether the modulus changes dramatically and identify the area of ​​modulus mutation. The greater the change in elastic curvature, the more dramatic the change in elastic modulus, which means the more unstable the structure. 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 .

[0076] The present invention is further configured such that S4 specifically includes:

[0077] An asymmetric integral path is defined, and the stability score is obtained by combining the local grayscale phase transition rate and the structural entropy gradient change;

[0078] Based on the stability score, each spatial location is binarized to construct a risk label. Specifically, in vascular OCT images, localized plaque instability often manifests as rapidly changing grayscale values, abnormal structural entropy gradients, and unstable regions that are not necessarily symmetrically distributed in space. Therefore, by constructing a direction-sensitive asymmetric integral path, integrating the local grayscale phase transition rate and the structural entropy gradient, a stability score is constructed, which is then used to determine whether a region is at risk of instability.

[0079] The present invention is further configured such that the integral path calculation logic is: ,in, is the spatial coordinate point on the integration path, is the starting coordinate point of integration, is the integration step parameter, is the integration path length, is the normal vector;

[0080] Stability score calculation logic: ,in, For stability score, is the complexity factor, is the phase change attenuation factor, is the local structural entropy mutation factor;

[0081] Risk label calculation logic: ,in, is the risk label, is the risk threshold, For high risk, The risk is low. Specifically, in the integral path calculation: the integral starting coordinate point is the three-dimensional coordinate of the current calculation point, which is obtained through the voxel coordinates in the modal field of the structural image; the integration step parameter It is the step size variable on the integral path and the position parameter on the discrete integral path. It usually takes a small step size of 0.1 or 1. The specific value is determined by the resolution and is consistent with the resolution. The integral path length The maximum length of the integral path is set by the image size ratio, and the value range is Voxel length; normal vector It is used to point to the inside of the plaque and is the direction of integration. The image gradient is used to differentiate the modal field of the structural image and then normalize it. The result is the existing technology and will not be described in detail here. In the calculation of stability score: phase change attenuation factor It is used to suppress the interference of noise or discontinuous areas by grayscale change rate and retain stable structural features. This method is an existing technology and will not be described in detail here; local structure entropy mutation factor This method is based on existing technologies and is used to quantify tissue complexity and detect pathological boundaries by using its rate of change. It is the threshold set by experts through clinical annotation data, and its value range is Between, such as: left main coronary artery , branch vessels Finally, we construct a connected domain for the points with high risk labels to obtain candidate regions. The candidate region calculation logic is as follows: , is the candidate region set, is the candidate region, is the total number of candidate regions, is a connected domain function; by calculating the mean stability score of all voxels in the candidate region, if the mean is higher than the threshold, it is determined to be a high-risk area. The threshold is set to 0.75 by default and can be modified according to different usage scenarios. Example 2

[0082] See also Figure 2 The exemplary vascular OCE adaptive endoscopic plaque grading system includes:

[0083] Data acquisition and processing module: uses a flexible endovascular probe to collect catheter position and trimodal vascular data to construct a sampling point set and obtains a trimodal field based on the sampling point set using an initial registration transformation;

[0084] Feature extraction module: constructs a transformation field based on the registration transformation, and uses the transformation field to quantify the mechanical properties of the tissue to generate an elastic response map;

[0085] Abnormal analysis module: defines the structural elastic coupling tensor field through the elastic response spectrum and calculates the complexity factor;

[0086] Risk assessment module: Constructs a stability scoring function based on the complexity factor, and constructs a risk label based on the stability score.

[0087] It should be noted that the vascular OCE adaptive endoscopic plaque grading system provided in the above-mentioned embodiment and the vascular OCE adaptive endoscopic plaque grading method provided in the above-mentioned embodiment are based on the same concept. The specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here. In actual applications, the vascular OCE adaptive endoscopic plaque grading system provided in the above-mentioned embodiment can distribute the above-mentioned functions among different functional modules as needed, that is, divide the internal structure of the system into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0088] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. 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 program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., infrared, wireless, microwave, etc.) method. 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 available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0089] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0090] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0091] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0092] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0093] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0094] In the several embodiments provided in this application, it should be understood that the disclosed system can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0095] The units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0096] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0097] If the 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 the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0098] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A vascular OCE adaptive endoscopic plaque grading method, characterized by: include: S1. Using a flexible endovascular probe to collect catheter position and trimodal vascular data, a sampling point set is constructed. Based on the sampling point set, an initial registration transformation is performed to obtain a trimodal field. The sampling point set includes: catheter position, optical coherence elastography (OCE) elasticity data, optical coherence tomography (OCT) structural images, and local vascular flow velocity. An initial registration transformation is constructed using the sampling point set through three-dimensional B-spline fitting. The trimodal field is obtained by interpolating the initial registration transformation with the data in the sampling point set. The sampling point set includes: ,in, is the set of sampling points, is the catheter position, For optical coherence elastography (OCE) elastic data, This is the optical coherence tomography (OCT) structural image. is the local vascular flow velocity, is the total number of sampling points; the calculation logic of the three-modal field is: ,in, 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; S2. Construct a transformation field based on the initial registration transformation, and use the transformation field to quantify the mechanical properties of the tissue and generate an elastic response map, including: constructing dynamic weights using the modal field of the structural image in the three-modal field; fine-tuning and correcting the initial registration transformation based on the basis function controlled by the dynamic weight, generating a transformation field, basis function The method uses a graph attention network to jointly model the trimodal gradient signals within the voxel neighborhood and extract discriminative local deformation response patterns. It also uses a transformation field to register the OCE elastic data to the OCT space and generate an elastic response map reflecting the hardness and viscoelasticity of the plaque. S3. Define the structural elastic coupling tensor field using the elastic response map and calculate the complexity factor, including: constructing the structural elastic coupling tensor field based on the cross product of the gradient direction of the structural image modal field and the gradient direction of the elastic response map; quantifying the degree of local vascular abnormality using the structural elastic coupling tensor field to generate a complexity factor reflecting the risk of plaque instability; S4. Construct a stability scoring function based on the complexity factor and construct a risk label based on the stability score. This includes: defining an asymmetric integral path, combining the local grayscale phase transition rate with the structural entropy gradient to derive a stability score; performing a binary judgment on each spatial position based on the stability score to construct a risk label. The integral path calculation logic is as follows: ,in, is the spatial coordinate point on the integration path, is the starting coordinate point of integration, is the integration step parameter, is the integration path length, is the normal vector; stability score calculation logic: ,in, For stability score, is the complexity factor, is the phase change attenuation factor, is the local structural entropy mutation factor; risk label calculation logic: ,in, is the risk label, is the risk threshold, For high risk, For low risk.

2. The method for adaptive endoscopic plaque grading using vascular OCE according to claim 1, characterized in that: Dynamic weight calculation logic: , is the dynamic weight, is the horizontal gradient, is the depth gradient, is the curvature, Score the kinks, is the sensitivity factor, is the Sigmoid function; Transformation field calculation logic: ,in, is the transformation field, is the initial registration transformation, is the number of deformation modes, is the basis function; Elastic response spectrum calculation logic: ,in, is the elastic response spectrum, 、 The start time and end time are respectively, For time point, is the time domain weight function, is the elastic response signal, the elastic response signal By registering the field The time point The original OCE signal is mapped to the OCT coordinate system, is the delayed response window function, the delayed response window function It is used to filter out high-frequency noise including blood flow disturbance and retain the intrinsic relaxation signal of tissue. is the viscoelastic delay time, the viscoelastic delay time It is the relaxation time constant based on the Maxwell model. The softer the structure, the stronger the viscosity and the more significant the delay.

3. The method for adaptive endoscopic plaque grading using vascular OCE according to claim 1, characterized in that: Structural elastic coupling tensor field calculation logic: ,in, is the structural elastic coupling tensor field, 、 is the spatial direction, 、 is the modal field of the structural image in the direction 、 The first-order partial derivative on , 、 The elastic response spectrum in the direction 、 The first-order partial derivative on , is the weight factor, is the second-order derivative; Complexity factor calculation logic: ,in, is the complexity factor, is the change in elastic curvature, is the local integration window.

4. A vascular OCE adaptive endoscopic plaque grading system, used to implement the vascular OCE adaptive endoscopic plaque grading method according to any one of claims 1 to 3, characterized in that: include: Data acquisition and processing module: uses a flexible endovascular probe to collect catheter position and trimodal vascular data to construct a sampling point set and obtains a trimodal field based on the sampling point set using an initial registration transformation; Feature extraction module: constructs a transformation field based on the initial registration transformation, and uses the transformation field to quantify the mechanical properties of the tissue to generate an elastic response map; Abnormal analysis module: defines the structural elastic coupling tensor field through the elastic response spectrum and calculates the complexity factor; Risk assessment module: Constructs a stability scoring function based on the complexity factor, and constructs a risk label based on the stability score.

Images