An intelligent acupoint positioning method and system based on multi-modal imaging

Abstract

The application relates to the technical field of medical positioning, and discloses an acupoint intelligent positioning method and system based on multi-modal imaging. The method comprises the following steps: decoupling infrared thermal imaging data and ultrasonic elastic imaging data of a target patient to obtain a feature waveform set; matching the feature waveform set with an acupoint initial position marker point set corresponding to a preset acupoint waveform template library; projecting the acupoint initial position marker point set to a body surface area corresponding to the target patient, and correcting distortion of acupoint projection to obtain a high-precision acupoint coordinate set; mapping the high-precision acupoint coordinate set to a three-dimensional space to obtain a three-dimensional acupoint model; performing real-time parameter registration on the three-dimensional acupoint model based on a real-time physiological state of the target patient to obtain a standard space parameter set of the three-dimensional acupoint model; and superimposing the standard space parameter set on the three-dimensional acupoint model to obtain a visual acupoint view. The application can improve the accuracy of acupoint intelligent positioning based on multi-modal imaging.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical positioning, in particular to a meridian point intelligent positioning method and system based on multi-modal imaging. BACKGROUND

[0002] In the prior art, the processing of multi-modal imaging data lacks depth integration capability in meridian point intelligent positioning, and effective decoupling and feature fusion of infrared thermal imaging and ultrasonic elastic imaging data cannot be achieved, resulting in incomplete extraction of meridian point related frequency energy distribution and spatial gradient features, and inability to accurately construct feature waveforms reflecting the essential properties of meridian points, so that the reliability of the basic data of initial positioning is insufficient.

[0003] At the same time, the existing technology has obvious defects in the projection conversion and dynamic adaptation of the meridian point position, neither an effective body surface distortion correction mechanism nor a three-dimensional modeling and parameter registration method combined with human anatomical rules and real-time physiological state is established, resulting in that the positioning result is easily affected by individual differences, body shape and physiological fluctuations, not only the three-dimensional model has low fitting degree with the actual anatomical structure, but also the spatial accuracy of the visual view is difficult to guarantee, which cannot meet the high-precision and dynamic meridian point positioning requirements. SUMMARY

[0004] The present application provides a meridian point intelligent positioning method and system based on multi-modal imaging to solve the problems raised in the background art.

[0005] To achieve the above purpose, the present application provides a meridian point intelligent positioning method based on multi-modal imaging, comprising:

[0006] S1, dual-modal feature decoupling is performed on the infrared thermal imaging data and ultrasonic elastic imaging data of a target patient to obtain a feature waveform set of the target patient;

[0007] S2, the feature waveform set is matched with a corresponding initial position marker point set of a meridian point in a preset meridian point waveform template library;

[0008] S3, the initial position marker point set of the meridian point is projected to a corresponding body surface area of the target patient, and distortion correction is performed on the meridian point projection to obtain a high-precision meridian point coordinate set of the target patient;

[0009] S4, the high-precision meridian point coordinate set is mapped to a three-dimensional space to obtain a three-dimensional meridian point model of the target patient;

[0010] S5, real-time parameter registration is performed on the three-dimensional meridian point model based on the real-time physiological state of the target patient to obtain a standard space parameter set of the three-dimensional meridian point model;

[0011] S6, superimpose the standard space parameter set to the three-dimensional acupoint model to obtain a visual acupoint view of the target patient.

[0012] In a preferred embodiment, the infrared thermal imaging data and the ultrasonic elastography data of the target patient are decoupled in a dual-mode feature to obtain a feature waveform set of the target patient, including:

[0013] The infrared thermal imaging data is decomposed by wavelet transform to obtain a frequency energy distribution feature set of the infrared thermal imaging data;

[0014] The ultrasonic elastography data is analyzed by time-frequency joint analysis to obtain a spatial gradient tensor set of the ultrasonic elastography data;

[0015] The frequency energy distribution feature set and the spatial gradient tensor set are coupled in a tensor domain to obtain the feature waveform set of the target patient, wherein the tensor domain coupling calculation formula is as follows:

[0016] ;

[0017] In the formula, is the feature waveform set, is the frequency energy distribution feature set, is the spatial gradient tensor set, is the transposed tensor of the spatial gradient tensor, is the coupling coefficient.

[0018] In a preferred embodiment, the feature waveform set is matched with a corresponding acupoint initial position marker point set in a preset acupoint waveform template library, including:

[0019] The feature waveform set is reconstructed in a phase space to obtain a phase space waveform set of the feature waveform set;

[0020] The Euclidean distance between each point in the phase space waveform set and the corresponding waveform marker point in the preset acupoint waveform template library is taken as the dimension matching result of the preset acupoint waveform template library, wherein the Euclidean distance calculation formula is as follows:

[0021] ;

[0022] In the formula, is the dimension matching result, is the feature value of the target patient, is the feature dimension index, is the phase space waveform point index, is the marker point of the phase space waveform set, is the marker point of the preset acupoint template library, is the acupoint template index, is a total number of feature dimensions, is a feature value of a template library;

[0023] mapping the dimension matching result to a bioelectric conduction path marker to obtain an initial position marker point set of an acupoint of the target patient.

[0024] In a preferred embodiment, the feature waveform set is phase space reconstructed to obtain a phase space waveform set of the feature waveform set, including:

[0025] separating the feature waveform set into a dynamic component subset and a static component subset;

[0026] mapping the dynamic component subset and the static component subset to a spatial extension waveform corresponding to a physiological dimension of the target patient;

[0027] fusing a human bioelectric conduction topology rule with the spatial extension waveform to obtain a phase space waveform set of the feature waveform set.

[0028] In a preferred embodiment, the initial position marker point set of the acupoint is projected to a corresponding body surface area of the target patient, and distortion correction is performed on the acupoint projection to obtain a high-precision acupoint coordinate set of the target patient, including:

[0029] mapping the initial position marker point set of the acupoint to a body surface space coordinate system to obtain an original projection coordinate set of the target patient;

[0030] performing spatial position calibration on the original projection coordinate set based on a preset acupoint distribution topology;

[0031] performing optical distortion compensation on the calibrated projection coordinate set according to physical structure parameters of the preset acupoint distribution topology to obtain a high-precision acupoint coordinate set of the target patient.

[0032] In a preferred embodiment, the high-precision acupoint coordinate set is mapped to a three-dimensional space to obtain a three-dimensional acupoint model of the target patient, including:

[0033] expanding two-dimensional surface coordinates of the high-precision acupoint coordinate set in a depth direction to obtain an initial three-dimensional acupoint point cloud of the target patient;

[0034] performing spatial position calibration on the initial three-dimensional acupoint point cloud based on a human acupoint distribution rule;

[0035] topologically connecting the calibrated three-dimensional acupoint point cloud with an anatomical landmark point of the target patient to obtain a three-dimensional acupoint model of the target patient.

[0036] In a preferred embodiment, the three-dimensional acupoint model is real-time parameter registered based on the real-time physiological state of the target patient, to obtain a standard space parameter set of the three-dimensional acupoint model, including:

[0037] The high-precision acupoint coordinate set is subjected to spatial coordinate collection, to obtain an initial three-dimensional coordinate set of the target patient;

[0038] The initial three-dimensional coordinate set is physically embedded with a structured coordinate topology, to obtain a standard space parameter set of the three-dimensional acupoint model.

[0039] In a preferred embodiment, the standard space parameter set is superimposed to the three-dimensional acupoint model, to obtain a visual acupoint view of the target patient, including:

[0040] The standard space parameter set is projected to a patient coordinate system of the three-dimensional acupoint model, to obtain an initial projection marker point set of the target patient;

[0041] The initial projection marker point set is subjected to deviation comparison with a spatial position of the target patient, to obtain a deviation data set of the spatial position;

[0042] The projection angle is adjusted based on the spatial position deviation data set, to obtain a calibration projection parameter of the target patient;

[0043] The calibration projection parameter is projected to the target patient, and a visual acupoint view of the target patient is obtained.

[0044] In a preferred embodiment, the projection angle is adjusted based on the spatial position deviation data set, to obtain a calibration projection parameter of the target patient, including:

[0045] The deviation direction and deviation amplitude data of the projection angle in the spatial position deviation data set are analyzed;

[0046] The spatial pointing parameter of the projection is dynamically corrected based on the deviation direction and the deviation amplitude data;

[0047] The corrected spatial pointing parameter is registered and verified with a body surface anatomical coordinate system of the target patient, to obtain a calibration projection parameter of the target patient.

[0048] To solve the above problems, the application further provides an acupoint intelligent positioning system based on multi-modal imaging, which comprises:

[0049] A feature decoupling module is configured to decouple infrared thermal imaging data and ultrasonic elastic imaging data of a target patient, to obtain a feature waveform set of the target patient;

[0050] The waveform matching module is configured to match the feature waveform set with a corresponding acupoint initial position marker point set in a preset acupoint waveform template library.

[0051] The projection correction module is configured to project the acupoint initial position marker point set to a body surface area corresponding to the target patient, and correct distortion of acupoint projection to obtain a high-precision acupoint coordinate set of the target patient.

[0052] The three-dimensional acupoint model construction module is configured to map the high-precision acupoint coordinate set to a three-dimensional space to obtain a three-dimensional acupoint model of the target patient.

[0053] The parameter registration module is configured to perform real-time parameter registration on the three-dimensional acupoint model based on a real-time physiological state of the target patient to obtain a standard space parameter set of the three-dimensional acupoint model.

[0054] The visualization superimposition module is configured to superimpose the standard space parameter set on the three-dimensional acupoint model to obtain a visual acupoint view of the target patient.

[0055] Compared with the prior art, the present application has the following beneficial effects:

[0056] 1. The present application can effectively capture the physical and physiological characteristics of acupoints by decoupling the infrared thermal imaging data and the ultrasonic elasticity imaging data, generating a precise feature waveform set in combination with tensor domain coupling, and then matching the phase space reconstruction and the preset acupoint waveform template library, thereby improving the accuracy of acupoint initial positioning and laying a reliable foundation for subsequent processing.

[0057] 2. The present application can accurately present the spatial position and distribution characteristics of acupoints by obtaining a high-precision coordinate set through distortion correction of acupoint projection, mapping to a three-dimensional space to construct a three-dimensional acupoint model, and combining real-time physiological state for parameter registration and visualization superimposition, thereby improving the accuracy and intuitiveness of acupoint positioning and providing precise acupoint positioning support for related medical applications. BRIEF DESCRIPTION OF DRAWINGS

[0058] Figure 1 A flowchart of an acupoint intelligent positioning method based on multi-modal imaging provided by an embodiment of the present application is shown in the figure.

[0059] Figure 2 A functional module diagram of an acupoint intelligent positioning system based on multi-modal imaging provided by an embodiment of the present application is shown in the figure.

[0060] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0061] It is to be understood that the specific embodiments described herein are merely illustrative of the present application and do not limit the scope of the application.

[0062] An embodiment of the present application provides an acupoint intelligent positioning method based on multi-modal imaging. An execution subject of the acupoint intelligent positioning method based on multi-modal imaging includes, but is not limited to, at least one of electronic devices such as a server and a terminal, which can be configured to execute the method provided by the embodiment of the present application. In other words, the acupoint intelligent positioning method based on multi-modal imaging can be executed by software or hardware installed in a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster, etc. The server can be a stand-alone server, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks (CDN), and big data and artificial intelligence platforms, etc. basic cloud computing services.

[0063] Referring to Figure 1 FIG. 1 shows a flowchart of an acupoint intelligent positioning method based on multi-modal imaging provided by an embodiment of the present application. In this embodiment, the acupoint intelligent positioning method based on multi-modal imaging includes:

[0064] S1, decoupling infrared thermal imaging data and ultrasonic elastography data of a target patient to obtain a feature waveform set of the target patient;

[0065] In the embodiment of the present application, the decoupling of the infrared thermal imaging data and the ultrasonic elastography data of the target patient to obtain the feature waveform set of the target patient includes:

[0066] performing wavelet transform decomposition on the infrared thermal imaging data to obtain a frequency energy distribution feature set of the infrared thermal imaging data;

[0067] performing time-frequency joint analysis on the ultrasonic elastography data to obtain a spatial gradient tensor set of the ultrasonic elastography data;

[0068] coupling the frequency energy distribution feature set and the spatial gradient tensor set in a tensor domain to obtain the feature waveform set of the target patient, wherein the coupling calculation formula in the tensor domain is as follows:

[0069] ;

[0070] In the formula, f is the feature waveform set, E is the frequency energy distribution feature set, and G is the spatial gradient tensor set. ;​​ is a transpose tensor of the spatial gradient tensor, is a coupling coefficient.

[0071] Specifically, the infrared thermal imaging data is decomposed by wavelet transform to obtain a frequency energy distribution feature set of the infrared thermal imaging data, the infrared thermal imaging data being a continuous image sequence of temperature distribution on a surface of a target patient, each image containing temperature values at different positions, and a preset wavelet basis function being selected during the wavelet transform decomposition.

[0072] Further, the temperature signal of each image is decomposed into a plurality of sub-signals of different frequencies, wherein a low-frequency sub-signal corresponds to an area with slow temperature change, and a high-frequency sub-signal corresponds to an area with rapid temperature change, and an energy value of each sub-signal is calculated, the energy value being a sum of temperature change intensities contained in the sub-signal.

[0073] Further, the energy values of the sub-signals are associated with corresponding frequency ranges in order from low to high to form an ordered set, which is the frequency energy distribution feature set of the infrared thermal imaging data.

[0074] Further, the ultrasonic elastography data is subjected to time-frequency joint analysis to obtain a spatial gradient tensor set of the ultrasonic elastography data, the ultrasonic elastography data being a sequence of images of elastic deformation of a tissue of a target patient under different pressures, each image containing elastic coefficient values at different positions of the tissue.

[0075] Further, during the time-frequency joint analysis, an elastic coefficient change signal of each spatial position at different time points is extracted, and then frequency components of the signal in different time periods are analyzed to determine an elastic change frequency feature of each position, and a difference value of the elastic coefficient of each position and its adjacent position at the same time point is calculated to obtain a spatial gradient value.

[0076] Further, the frequency feature and the spatial gradient value of each position are integrated into a multidimensional array in order of three-dimensional spatial coordinates and time, each array element containing time-frequency features and spatial gradient information of the corresponding position, and the formed set is the spatial gradient tensor set of the ultrasonic elastography data.

[0077] Further, the frequency energy distribution feature set and the spatial gradient tensor set are coupled in a tensor domain to obtain a characteristic waveform set of the target patient, and a spatial correspondence relationship of the features in the two sets is determined, i.e., the temperature signal positions in the frequency energy distribution feature set and the tissue elastic positions in the spatial gradient tensor set are matched one by one.

[0078] Furthermore, the frequency domain energy value at the corresponding position is combined with the elements in the spatial gradient tensor according to a preset rule. For example, the energy value at the same position is used as the weight of a certain dimension of the tensor. The tensor values ​​are adjusted to form a fused multidimensional tensor. Then, each fused tensor is expanded along the time axis or frequency axis to obtain a curve that changes with time or frequency. Each curve is a feature waveform, and the set of all feature waveforms is the feature waveform set of the target patient.

[0079] Specifically, It is a frequency domain energy distribution feature set, which is obtained by wavelet transform decomposition of infrared thermal imaging data of the target patient, and contains the energy distribution features of infrared thermal imaging data at different frequencies. It is a set of spatial gradient tensors, which is derived from the time-frequency joint analysis of the ultrasound elastography data of the target patient. It contains the spatial gradient and temporal frequency characteristics of the ultrasound elastography data. It is the transpose of the spatial gradient tensor, derived from the set of spatial gradient tensors. The transpose operation is performed to obtain the result by swapping the elements. The row and column positions of elements are adjusted without changing the numerical values ​​of the elements themselves, only adjusting the dimensional structure of the tensor to meet the dimensional matching requirements of coupled operations.

[0080] Furthermore, The coupling coefficient is a value pre-set based on the modal characteristics of infrared thermal imaging data and ultrasonic elastography data. The setting criteria include the signal-to-noise ratio of the two modal data and their importance in feature description. It is used to balance the contribution ratio of the frequency domain energy distribution feature set and the spatial gradient tensor set in the coupling process.

[0081] Furthermore, the significance of this formula lies in fusing the frequency domain energy distribution feature set with the spatial gradient tensor set through tensor multiplication. Specifically, the spatial gradient tensor set is first multiplied... Transpose to obtain ,make With frequency domain energy distribution feature set Dimensional matching is performed for multiplication, and the product of the two is then combined with the coupling coefficient. Multiplication, through Adjusting the weights of the two feature sets during the fusion process yields the final result. This is a feature waveform set that integrates infrared thermal characteristics and ultrasonic mechanical characteristics, achieving effective integration of dual-modal features.

[0082] Furthermore, when the frequency domain energy distribution feature set When the eigenvalues ​​in the matrix increase, and Under the condition that remains unchanged, the characteristic waveform set The corresponding eigenvalue will increase accordingly, meaning that the energy characteristics in infrared thermal imaging data are affected by... The effect is amplified when the spatial gradient tensor set... As the eigenvalues ​​in the tensor increase, its transpose tensor... The corresponding eigenvalues ​​will also increase, in and If it remains unchanged, The corresponding eigenvalues ​​will increase accordingly, that is, the spatial gradient characteristics of ultrasound elastography data will affect... The effect is amplified when the coupling coefficient is increased. When it increases, at and If it remains unchanged, All feature values ​​will increase proportionally, and the two modal features will increase proportionally. The overall contribution has increased; when When decreasing, All eigenvalues ​​will decrease proportionally, and the overall contribution of both modal features will weaken.

[0083] In summary, wavelet transform decomposition of infrared thermal imaging data yields a frequency domain energy distribution feature set, which can accurately extract temperature energy features at different frequencies, reflecting the differences in thermal metabolism in acupoint areas and providing thermal characteristic basis for subsequent matching.

[0084] In summary, time-frequency joint analysis of ultrasound elastography data yields a spatial gradient tensor set, which can capture the changes in tissue elasticity in the spatiotemporal dimensions, reflect the differences in mechanical properties of acupoint areas, and supplement structural feature information beyond thermal characteristics.

[0085] In summary, the characteristic waveform set obtained by tensor-domain coupling of the frequency domain energy distribution feature set and the spatial gradient tensor set can integrate thermal and mechanical dual-modal features, comprehensively reflect the multi-dimensional attributes of acupoints, improve the completeness and accuracy of feature description, and provide a more reliable feature basis for acupoint positioning.

[0086] S2. Match the feature waveform set with the corresponding acupoint initial position marker point set in the preset acupoint waveform template library;

[0087] In this embodiment of the invention, matching the feature waveform set with the corresponding initial position marker point set of acupoints in a preset acupoint waveform template library includes:

[0088] The phase space of the feature waveform set is reconstructed to obtain the phase space waveform set of the feature waveform set;

[0089] The Euclidean distance between each point of the phase space waveform set and the corresponding waveform marker point in the preset acupoint waveform template library is taken as a dimension matching result of the preset acupoint waveform template library, wherein the Euclidean distance calculation formula is as follows:

[0090]

[0091] In the formula, is the dimension matching result, is a characteristic value of the target patient, is a characteristic dimension index, is a phase space waveform point index, is a marker point of the phase space waveform set, is a marker point of the preset acupoint template library, is an acupoint template index, is a total number of characteristic dimensions, is a characteristic value of the template library;

[0092] The dimension matching result is mapped to a bioelectric conduction path marker to obtain an acupoint initial position marker point set of the target patient.

[0093] The characteristic waveform set is reconstructed in a phase space to obtain a phase space waveform set of the characteristic waveform set, including:

[0094] The characteristic waveform set is separated into a dynamic component subset and a static component subset;

[0095] The dynamic component subset and the static component subset are mapped to a spatial extension waveform corresponding to a physiological dimension of the target patient;

[0096] A human bioelectric conduction topology rule is fused with the spatial extension waveform to obtain a phase space waveform set of the characteristic waveform set.

[0097] Specifically, the characteristic waveform set is reconstructed in a phase space to obtain a phase space waveform set of the characteristic waveform set. The characteristic waveform set is a set of bioelectric signal waveforms related to acupoints collected by a detection device. Each waveform presents changes with time as an axis. Phase space reconstruction is to convert these one-dimensional time waveforms into a point set in a multi-dimensional space.

[0098] Further, a fixed time interval is selected, and signal values at different times are extracted from each waveform in turn. These signal values are taken as coordinates of different dimensions according to the extraction order. Each waveform is thus converted into a point in a multi-dimensional space. A set of points corresponding to all waveforms together is the phase space waveform set of the characteristic waveform set.

[0099] ​Further, the Euclidean distance between each point in the phase space waveform set and the corresponding waveform marker point in the preset acupoint waveform template library is taken as the dimension matching result of the preset acupoint waveform template library.

[0100] Further, the preset acupoint waveform template library stores the marker points of the standard bioelectric signal waveforms of known acupoints in the phase space, and each marker point also contains multiple dimensional coordinates. The Euclidean distance refers to the square root of the sum of squares of the dimensional coordinate differences between two points in a multi-dimensional space.

[0101] Further, the distance between each point in the phase space waveform set and the standard marker point of the corresponding acupoint in the template library is calculated, and the collection of all these distance values arranged according to the corresponding acupoint is the dimension matching result of the preset acupoint waveform template library.

[0102] Further, the dimension matching result is mapped to the bioelectric conduction path marker to obtain the acupoint initial position marker point set of the target patient. The bioelectric conduction path marker refers to the pre-determined bioelectric signal conduction path between different acupoints and the corresponding position marker. Each path marker is associated with a specific acupoint initial position.

[0103] Further, the matching degree is determined according to the size of the distance value in the dimension matching result. The smaller the distance, the higher the matching degree. The path marker with the highest matching degree is selected, and the acupoint position information corresponding to the marker is extracted. The collection of all these position information is the acupoint initial position marker point set of the target patient.

[0104] Specifically, the feature waveform set is separated into a dynamic component subset and a static component subset. Each waveform in the feature waveform set contains a feature component that changes over time. By calculating the change amplitude of each component within a preset time window, the components with a change amplitude greater than a preset threshold are classified as dynamic components, and the components with a change amplitude less than or equal to the preset threshold are classified as static components.

[0105] Further, all dynamic components are arranged according to their corresponding waveform order to form a dynamic component subset, and all static components are arranged in the same order to form a static component subset.

[0106] Further, the dynamic component subset and the static component subset are mapped to the spatial extension waveform corresponding to the physiological dimension of the target patient. The physiological dimension of the target patient includes the body surface coordinate, the tissue depth, and the functional dimension associated with physiological activity. The dynamic component subset corresponds to the physiological activity dimension.

[0107] Further, the waveforms are unfolded in time sequence in the dimension to form a spatial distribution waveform varying with physiological activity; the static component subset corresponds to a fixed anatomical dimension, and the waveforms are arranged in space in the dimension to form a stable spatial distribution waveform, and the two waveforms together constitute a spatial extension waveform of the target patient corresponding to the physiological dimension.

[0108] Further, the human bioelectric conduction topology rule is fused with the spatial extension waveform to obtain a phase space waveform set of the feature waveform set. The human bioelectric conduction topology rule is the path and distribution rule of bioelectric conduction in the body along meridians, nerves and tissue gaps, including conduction direction, node connection relationship and signal attenuation characteristics.

[0109] Further, the connection structure of the spatial extension waveform is adjusted according to the rule, so that the waveforms of the dynamic component are distributed along the bioelectric conduction path, and the waveforms of the static component are matched with the conduction node positions.

[0110] Further, the amplitudes of the waveforms are corrected according to the rule to reflect the attenuation characteristics of the bioelectric signal, and the multi-dimensional waveform set formed after fusion, which contains spatial position, time variation and bioelectric conduction characteristics, is the phase space waveform set of the feature waveform set.

[0111] Specifically, is a dimension matching result, which is obtained by calculating the Euclidean distance between the marker points of the phase space waveform set and the marker points of the preset acupoint template library. is a feature value of the target patient, which is obtained by performing phase space reconstruction on the feature waveform set of the target patient to obtain the dimension feature values of the marker points in the phase space waveform set. These feature values reflect the bioelectric signal characteristics of the acupoints of the target patient. is a feature value of the template library, which is obtained by setting the dimension standard feature values of the marker points in the preset acupoint template library based on the bioelectric signal characteristics of known acupoints. is a feature dimension index, which is obtained from the dimension number corresponding to the feature value. Each number corresponds to a specific feature dimension, such as amplitude, frequency, etc.

[0112] Further, is a phase space waveform point index, which is obtained from the number of each marker point in the phase space waveform set of the target patient. Each number corresponds to a unique waveform point. is an acupoint template index, which is obtained from the number of each standard marker point in the preset acupoint template library. Each number corresponds to a template of a specific acupoint. is the total number of feature dimensions, which is obtained from the number of dimensions contained in the extracted feature values, determined by the feature dimensions of the feature waveform set.

[0113] Further, the meaning of the formula is to calculate the marked point in the phase space waveform set of the target patient and the marked point in the preset acupoint template library The distance in the multi-dimensional feature space is specifically calculated as follows: first, the difference between the feature values of two points in each feature dimension is calculated, each difference is squared, then all the squared results are added, and finally the square root of the sum is taken to obtain the result, which is the Euclidean distance between the two points. This distance is used as the dimension matching result to measure the similarity between the waveform point of the target patient and the standard template point.

[0114] Further, when the feature value of the target patient and the feature value of the template library The squared difference of this dimension will increase when the difference between the two points in this dimension increases, and the sum of the squares of all dimensions will also increase, and finally the Euclidean distance will increase, indicating that the matching degree of the two points decreases. When and The squared sum decreases when the difference between the two points in each feature dimension decreases, and the Euclidean distance decreases, indicating that the matching degree of the two points improves. When and When the difference between the two points in all feature dimensions is zero, the squared sum is zero, and the Euclidean distance is zero, indicating that the two points are completely matched.

[0115] In summary, the phase space waveform set is obtained by reconstructing the phase space of the feature waveform set, which can convert one-dimensional waveform features into a multi-dimensional point set, fully display the spatial distribution of acupoint features, and provide a multi-dimensional basis for subsequent matching.

[0116] In summary, the Euclidean distance between each point in the phase space waveform set and the corresponding point in the preset template is used as the dimension matching result, which can accurately measure the feature similarity by quantifying the distance, and provide an objective basis for the matching degree determination.

[0117] In summary, the dimension matching result is mapped to the acupoint initial position marked point set of the bioelectricity conduction path, which can determine the initial position combined with the bioelectricity conduction rule, so that the marked point set not only conforms to the waveform matching result but also fits the physiological characteristics, improving the accuracy of the initial positioning and laying a foundation for subsequent projection correction.

[0118] In summary, the feature waveform set is separated into a dynamic component subset and a static component subset, which can distinguish the dynamic features that change with physiological activity from the stable static features in the waveform, providing classified and clear basic data for subsequent mapping.

[0119] In general, mapping the dynamic component set and the static component set to the spatial extension waveform corresponding to the physiological dimension of the target patient can accurately correspond the characteristics of the two components to the physiological structure and function dimensions of the patient, and form a spatial distribution waveform that fits the actual patient.

[0120] In general, fusing the human bioelectric conduction topology rule and the spatial extension waveform to obtain the phase space waveform set can integrate the physiological law of bioelectric conduction, make the waveform set more consistent with the biophysical characteristics of the acupoint, improve the representation accuracy of the phase space waveform set to the acupoint characteristics, and provide a more reliable waveform basis for subsequent matching.

[0121] S3, projecting the acupoint initial position marker point set to the body surface area corresponding to the target patient, and correcting the acupoint projection for distortion to obtain a high-precision acupoint coordinate set of the target patient;

[0122] In the embodiment of the application, the acupoint initial position marker point set is projected to the body surface area corresponding to the target patient, and the acupoint projection is corrected for distortion to obtain a high-precision acupoint coordinate set of the target patient, comprising:

[0123] Mapping the acupoint initial position marker point set to the body surface spatial coordinate system to obtain an original projection coordinate set of the target patient;

[0124] Calibrating the original projection coordinate set based on a preset acupoint distribution topology;

[0125] According to the physical structure parameters of the preset acupoint distribution topology, the projection coordinate set after calibration is compensated for optical distortion to obtain a high-precision acupoint coordinate set of the target patient.

[0126] Specifically, the acupoint initial position marker point set is obtained from a preset acupoint waveform template library, and the set contains the position information of each acupoint in the standard coordinate system.

[0127] Further, by identifying the same anatomical reference points in the standard coordinate system and the constructed body surface spatial coordinate system, such as the protrusions of specific bones, the conversion relationship between the two coordinate systems is determined.

[0128] Further, according to the conversion relationship, the position information of each acupoint in the acupoint initial position marker point set is converted to the body surface spatial coordinate system to obtain the specific coordinates of each acupoint in the coordinate system. The set of all these coordinates is the original projection coordinate set of the target patient.

[0129] Further, the preset acupoint distribution topology is a fixed rule based on the relative positions of acupoints determined by human meridians and anatomy, including the distance range, connection angle and arrangement order between related acupoints.

[0130] Further, the actual relative positions of each acupoint in the original projection coordinate set and the surrounding associated acupoints are compared with the corresponding standard relative positions in the preset acupoint distribution topology, and if there is a deviation between the actual positions and the standard positions, the specific distance and direction that need to be adjusted are calculated according to the standard relationship in the topology.

[0131] Further, the coordinates of the corresponding acupoints in the original projection coordinate set are moved so that the relative positions between all the acupoints after adjustment conform to the preset distribution rule, and a calibrated projection coordinate set is obtained.

[0132] Further, the physical structure parameters of the preset acupoint distribution topology include the skin thickness, subcutaneous tissue density, and surrounding bone morphology of the acupoint region, which affect the physical properties of optical imaging. Optical distortion can cause edge stretching or center compression deviation between the projection coordinates and the actual positions.

[0133] Further, the distortion degree of different regions is determined according to these physical structure parameters, for example, the distortion is smaller in the bone protruding area and larger in the soft tissue thick area, for each acupoint in the calibrated projection coordinate set.

[0134] Further, a compensation value is calculated according to the distortion degree of the region where the acupoint is located, and the coordinates of the acupoint in the body surface coordinate system are adjusted according to the compensation value, so that the adjusted coordinates accurately reflect the actual position of the acupoint on the patient's body surface. The set of these adjusted coordinates is the high-precision acupoint coordinate set of the target patient.

[0135] In summary, the original projection coordinate set is obtained by mapping the acupoint initial position marker point set to the body surface coordinate system, the template marker point can be converted to the patient-specific coordinate system, the space correspondence is realized, and a unified reference is provided for subsequent correction.

[0136] In summary, the original projection coordinate set is calibrated based on the preset acupoint distribution topology, the coordinates can be adjusted according to the inherent distribution rule of the acupoint, the deviation caused by individual differences is corrected, and the accuracy of the coordinates is improved.

[0137] In summary, the high-precision coordinate set is obtained by compensating the calibrated coordinate set according to the physical structure parameters of the preset topology, which can eliminate optical distortion, optimize accuracy, provide reliable data for subsequent processing, and ensure accurate positioning.

[0138] S4, mapping the high-precision acupoint coordinate set to a three-dimensional space to obtain a three-dimensional acupoint model of the target patient;

[0139] In the embodiment of the application, the high-precision acupoint coordinate set is mapped to a three-dimensional space to obtain a three-dimensional acupoint model of the target patient, which comprises:

[0140] The two-dimensional surface coordinates of the high-precision acupoint coordinate set are expanded in the depth direction to obtain an initial three-dimensional acupoint point cloud of the target patient;

[0141] The initial three-dimensional acupoint point cloud is corrected in spatial position based on the distribution rule of human acupoints;

[0142] The corrected three-dimensional acupoint point cloud is topologically connected with the anatomical landmark points of the target patient to obtain a three-dimensional acupoint model of the target patient.

[0143] Specifically, the two-dimensional surface coordinates in the high-precision acupoint coordinate set record the front-back and left-right positions of each acupoint on the patient's body surface. According to the subcutaneous depth data of each acupoint in human anatomy, the depth of a muscle layer acupoint is greater than that of a subcutaneous fat layer acupoint.

[0144] Further, a corresponding depth value is added to each two-dimensional coordinate, so that the coordinates of each acupoint are converted from a two-dimensional form containing front-back and left-right to a three-dimensional form containing front-back, left-right and depth. The collection of all these three-dimensional coordinate points is the initial three-dimensional acupoint point cloud of the target patient.

[0145] Further, the distribution rule of human acupoints covers fixed rules such as the arrangement order of acupoints along meridians, the corresponding relationship between acupoints and skeletal gaps, and the depth gradient change of adjacent acupoints. The three-dimensional coordinates of each acupoint in the initial three-dimensional acupoint point cloud are compared with these rules one by one.

[0146] Further, if an acupoint deviates from the direction of the meridian to which it belongs, its front-back or left-right coordinates are adjusted according to the spatial path of the meridian. If the depth value of an acupoint does not conform to the gradient rule of the region, its depth coordinates are corrected by referring to the depth values of adjacent acupoints. After adjustment, the spatial positions of all acupoint points conform to the distribution rule of human acupoints, and a corrected three-dimensional acupoint point cloud is obtained.

[0147] Further, the anatomical landmark points of the target patient include anatomical structure points with fixed spatial positions such as the spinous process of the spine, the edge of the rib, and the gap of the joint. The three-dimensional coordinates of these points have been obtained through previous scanning. According to the correlation between acupoints and anatomical landmark points in traditional Chinese medicine theory.

[0148] For example, an acupoint is located "one and a half inches lateral to the spinous process of the third lumbar vertebra". The spatial distance and connection direction between each acupoint in the corrected three-dimensional acupoint point cloud and the corresponding anatomical landmark point are calculated. The acupoint points and anatomical landmark points are connected in three-dimensional space according to these distances and directions to form a network structure containing acupoint positions and the correlation between acupoints and anatomical structures. This structure is the three-dimensional acupoint model of the target patient.

[0149] In summary, the depth expansion of the two-dimensional surface coordinates obtains the initial three-dimensional acupoint point cloud, which can supplement the subcutaneous depth information, lay the foundation for the three-dimensional model, and make the acupoint description more consistent with the human three-dimensional structure.

[0150] In summary, the correction of the initial three-dimensional point cloud based on the acupoint distribution rule can correct the position deviation, ensure that the spatial position of the acupoint conforms to the human physiological structure, and improve the data accuracy.

[0151] In summary, the three-dimensional acupoint model obtained by topologically connecting the corrected point cloud and the anatomical landmark point can associate the acupoint with the fixed structure of the human body, form a three-dimensional model containing the acupoint position and the mutual relationship, provide a complete structure basis for subsequent processing, and improve the positioning reliability.

[0152] S5, real-time parameter registration is performed on the three-dimensional acupoint model based on the real-time physiological state of the target patient, to obtain a standard space parameter set of the three-dimensional acupoint model;

[0153] In the embodiment of the application, real-time parameter registration is performed on the three-dimensional acupoint model based on the real-time physiological state of the target patient, to obtain a standard space parameter set of the three-dimensional acupoint model, including:

[0154] The high-precision acupoint coordinate set is subjected to spatial coordinate collection, to obtain an initial three-dimensional coordinate set of the target patient;

[0155] The initial three-dimensional coordinate set is physically embedded with the structured coordinate topology, to obtain a standard space parameter set of the three-dimensional acupoint model.

[0156] Specifically, the high-precision acupoint coordinate set is subjected to spatial coordinate collection, to obtain an initial three-dimensional coordinate set of the target patient. A real-time three-dimensional scanning device is used to dynamically scan the acupoint region of the target patient. The device can capture the spatial position of the acupoint of the patient under different physiological states (such as breathing and slight body position change) for each acupoint in the high-precision acupoint coordinate set.

[0157] Further, the coordinate values of the front, back, left, right and depth of each acupoint at different time points in the scanning process are recorded. After removing the abnormal values obviously caused by noise, the average coordinates of each acupoint are taken as the real-time three-dimensional coordinates of the acupoint. The set formed by the combination of the real-time three-dimensional coordinates of all acupoints is the initial three-dimensional coordinate set of the target patient.

[0158] Further, the initial three-dimensional coordinate set is physically embedded with a structured coordinate topology to obtain a standard space parameter set of the three-dimensional acupoint model, the structured coordinate topology is an acupoint space relationship framework constructed based on a standard human anatomy structure, and contains fixed space parameters such as standard distances, angles, hierarchical distributions between acupoints, and the like, and the coordinates of each acupoint in the initial three-dimensional coordinate set are compared with standard coordinates of a corresponding acupoint in the structured coordinate topology.

[0159] Further, deviations in front-back, left-right and deep-shallow directions are calculated, and the coordinates of acupoints in the initial three-dimensional coordinate set are adjusted according to the deviation values, so that the space relationships such as distances and angles between the adjusted acupoints are consistent with the standard parameters in the structured coordinate topology.

[0160] Further, the coordinates of all the acupoints after adjustment and the space parameters therebetween are integrated to form a parameter set containing a unified space standard, which is the standard space parameter set of the three-dimensional acupoint model.

[0161] In summary, the initial three-dimensional coordinate set is obtained by collecting space coordinates of a high-precision acupoint coordinate set, can capture dynamic space positions of acupoints of a target patient in a real-time physiological state, ensures that the coordinate data matches the current physiological state of the patient, and provides real-time basic data for parameter registration.

[0162] In summary, the initial three-dimensional coordinate set is physically embedded with a structured coordinate topology to obtain a standard space parameter set, can make the real-time collected coordinate data be fused with a coordinate framework based on a standard anatomy structure, unify the standard of acupoint space parameters, eliminate the influence of individual physiological state fluctuations on model parameters, ensure that the space parameters of the three-dimensional acupoint model have consistency and standardization, provide standardized parameter support for subsequent visualization superposition, and improve the stability and accuracy of acupoint positioning.

[0163] S6, superimposing the standard space parameter set to the three-dimensional acupoint model to obtain a visual acupoint view of the target patient.

[0164] In the embodiment of the present application, the standard space parameter set is superimposed to the three-dimensional acupoint model to obtain a visual acupoint view of the target patient, which comprises:

[0165] The standard space parameter set is projected to a patient coordinate system of the three-dimensional acupoint model to obtain an initial projection marker point set of the target patient;

[0166] The initial projection marker point set is compared with a space position of the target patient to obtain a deviation data set of the space position;

[0167] The projection angle is adjusted based on the space position deviation data set to obtain a calibration projection parameter of the target patient;

[0168] projecting the calibration projection parameter to the target patient, and obtaining a visualized acupoint view of the target patient.

[0169] adjusting a projection angle based on the spatial position deviation dataset to obtain the calibration projection parameter of the target patient, including:

[0170] analyzing a deviation direction of the projection angle and a deviation amplitude data in the spatial position deviation dataset;

[0171] dynamically correcting a spatial pointing parameter of projection based on the deviation direction and the deviation amplitude data;

[0172] verifying the corrected spatial pointing parameter with a body surface anatomical coordinate system of the target patient to obtain the calibration projection parameter of the target patient.

[0173] Specifically, the standard spatial parameter set includes standard spatial positions of acupoints in a three-dimensional acupoint model and mutual relationship parameters, and a patient coordinate system of the three-dimensional acupoint model is a three-dimensional coordinate system established based on a body surface anatomical structure of the target patient.

[0174] Further, each parameter in the standard spatial parameter set is projected into the patient coordinate system one by one according to the corresponding acupoint position, and a corresponding spatial point is marked in the coordinate system for each acupoint, and a set composed of all the marked points is an initial projection marked point set of the target patient.

[0175] Further, the initial projection marked point set records the projection positions of the acupoints in the patient coordinate system, and the spatial position of the target patient refers to the three-dimensional space of each part of the actual body of the patient, and the coordinates of each marked point in the initial projection marked point set are compared with the coordinates of the corresponding acupoint in the actual spatial position of the patient one by one.

[0176] Further, the difference values in the front-back, left-right and deep-shallow directions are calculated, and all the difference values of the marked points are sorted according to the corresponding acupoints to form a dataset containing the position deviation of each acupoint, which is the spatial position deviation dataset.

[0177] Further, each deviation value in the spatial position deviation dataset includes a deviation direction and a deviation size, the direction in which the projection angle needs to be adjusted is determined according to the deviation direction, the amplitude of the adjustment is determined according to the deviation size, the projection angle of the projection device is adjusted according to the determined direction and amplitude, and the projection angle, projection range and other parameters obtained after the adjustment are the calibration projection parameter of the target patient.

[0178] Further, the marked patterns of the acupoints are projected to the corresponding positions on the body surface of the target patient according to the setting of the calibration projection parameter using the projection device, and it is ensured that each marked pattern accurately covers the actual position of the corresponding acupoint during the projection process.

[0179] Further, after the projection is completed, the directly observable acupoint marking pattern formed on the patient's body surface is the visual acupoint view of the target patient.

[0180] Specifically, to analyze the deviation direction and deviation amplitude data of the projection angle in the spatial position deviation data set, the deviation record of each acupoint projection in the data set needs to be extracted one by one, and it is determined whether the deviation direction corresponding to each record is forward, backward, left, right, deep or shallow.

[0181] Further, the deviation distance values in each direction are extracted at the same time, such as how many distances the projection point of a certain acupoint deviates forward or left, and these direction information and distance values are classified and arranged according to acupoints to form clear deviation direction list and deviation amplitude list.

[0182] Further, based on the deviation direction and deviation amplitude data, the spatial pointing parameters of the projection are dynamically corrected, including the horizontal rotation angle, the vertical inclination angle and the projection depth parameter of the projection device, and the correction direction is determined according to the deviation direction.

[0183] Further, if the deviation is forward, the horizontal rotation angle is adjusted backward, and if the deviation is left, the vertical inclination angle is adjusted right, the correction amplitude is determined according to the deviation amplitude, the greater the deviation distance, the greater the angle adjustment amplitude in the corresponding direction, and through step-by-step fine-tuning, the pointing of the projection device gradually approaches the target position until the adjustment requirement corresponding to the deviation direction and amplitude is completely compensated.

[0184] Further, the corrected spatial pointing parameters are registered and verified with the body surface anatomical coordinate system of the target patient to obtain the calibration projection parameters of the target patient, and the body surface anatomical coordinate system is established based on the skeletal landmarks and joint positions of the patient.

[0185] Further, the corrected spatial pointing parameters are input into the projection device to project a set of verification marking points, and the actual positions of these marking points in the body surface anatomical coordinate system are measured.

[0186] Further, the standard positions of the corresponding acupoints in the coordinate system are compared, if all the verification marking points completely coincide with the standard positions, the current spatial pointing parameters are the calibration projection parameters, if there are marking points that do not coincide, the correction and verification process is repeated until all the marking points coincide with the standard positions.

[0187] In general, projecting the standard spatial parameter set to the patient coordinate system of the three-dimensional acupoint model to obtain the initial projection marking point set can make the standard parameters consistent with the patient's own coordinate system, providing a basis for subsequent deviation comparison and ensuring the preliminary correspondence between the projection marking and the model.

[0188] In summary, deviation data set is obtained by deviation comparison between initial projection marker point set and spatial position of target patient, which can accurately identify the difference between projection marker and actual position, and clearly adjust the direction and amplitude, thereby providing basis for projection angle adjustment.

[0189] In summary, the projection angle is adjusted based on the spatial position deviation data set to obtain the calibrated projection parameter, which can be corrected in a targeted manner, so that the projection parameter is adapted to the actual spatial position of the patient, thereby improving the projection accuracy.

[0190] In summary, the visual acupoint view is obtained by projecting the calibrated projection parameter to the target patient, which can intuitively present accurate acupoint information on the patient's body surface, realize clear visualization of acupoints, and provide accurate and intuitive positioning reference for clinical application, thereby improving the practicability and reliability of acupoint positioning.

[0191] In summary, the deviation direction and amplitude data in the spatial position deviation data set are analyzed, which can accurately locate the deviation source of the projection angle, provide clear adjustment basis for subsequent correction, and ensure the accuracy of the correction direction.

[0192] In summary, the spatial pointing parameter of the projection is dynamically corrected based on the deviation direction and amplitude data, which can adjust the projection angle in a targeted manner, so that the projection parameter is adapted to the actual spatial position of the patient, and the projection deviation is effectively reduced.

[0193] In summary, the corrected spatial pointing parameter is registered and verified with the anatomical coordinate system of the target patient, which can further verify the accuracy of the projection parameter through anatomical reference, ensure that the calibrated projection parameter obtained finally can accurately correspond to the acupoint position on the patient's body surface, provide reliable parameter support for generation of the visual acupoint view, and improve the accuracy of acupoint positioning.

[0194] As shown in Figure 2 Figure 1 is a functional module diagram of an acupoint intelligent positioning system based on multi-modal imaging according to an embodiment of the present application.

[0195] The acupoint intelligent positioning system 100 based on multi-modal imaging according to the present application can be installed in an electronic device. According to the functions to be realized, the acupoint intelligent positioning system 100 based on multi-modal imaging can include a feature decoupling module 101, a waveform matching module 102, a projection correction module 103, a three-dimensional acupoint model construction module 104, a parameter registration module 105, and a visualization superimposition module 106. The modules according to the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, and are stored in the memory of the electronic device.

[0196] In the present embodiment, the functions of each module / unit are as follows:

[0197] The feature decoupling module 101 is configured to perform bimodal feature decoupling on infrared thermal imaging data and ultrasonic elastic imaging data of a target patient to obtain a feature waveform set of the target patient.

[0198] The waveform matching module 102 is configured to match the feature waveform set with a corresponding acupoint initial position marker point set in a preset acupoint waveform template library.

[0199] The projection correction module 103 is configured to project the acupoint initial position marker point set to a corresponding body surface area of the target patient, and perform distortion correction on acupoint projection to obtain a high-precision acupoint coordinate set of the target patient.

[0200] The three-dimensional acupoint model construction module 104 is configured to map the high-precision acupoint coordinate set to a three-dimensional space to obtain a three-dimensional acupoint model of the target patient.

[0201] The parameter registration module 105 is configured to perform real-time parameter registration on the three-dimensional acupoint model based on a real-time physiological state of the target patient to obtain a standard space parameter set of the three-dimensional acupoint model.

[0202] The visualization superimposition module 106 is configured to superimpose the standard space parameter set to the three-dimensional acupoint model to obtain a visual acupoint view of the target patient.

[0203] In several embodiments provided in the present application, it should be understood that the disclosed method and system can be implemented in other ways. For example, the system embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and another division mode can be used in actual implementation.

[0204] The modules described as separate components can or can not be physically separated, and the components displayed as modules can or can not be physical units, that is, they can be located in one place or distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment.

[0205] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional modules.

[0206] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0207] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. The artificial intelligence is to use a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results.

[0208] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. An intelligent acupoint positioning method based on multi-modal imaging, characterized in that, The method comprises: S1, decoupling the infrared thermal imaging data and the ultrasonic elastography data of the target patient to obtain a feature waveform set of the target patient, comprising: wavelet transform decomposition of the infrared thermal imaging data to obtain a frequency energy distribution feature set of the infrared thermal imaging data; time-frequency joint analysis of the ultrasonic elastography data to obtain a spatial gradient tensor set of the ultrasonic elastography data; tensor domain coupling of the frequency energy distribution feature set and the spatial gradient tensor set to obtain the feature waveform set of the target patient, wherein the tensor domain coupling calculation formula is as follows: ； wherein is a set of characteristic waveforms, is a set of frequency domain energy distribution features, is a set of spatial gradient tensors, is a transpose tensor of the spatial gradient tensor, is a coupling coefficient; S2, matching the feature waveform set with a corresponding initial position marker point set of an acupoint in a preset acupoint waveform template library; S3, projecting the initial position marker point set of the acupoint to a corresponding body surface area of the target patient, and correcting the distortion of the acupoint projection to obtain a high-precision acupoint coordinate set of the target patient; S4, mapping the high-precision acupoint coordinate set to a three-dimensional space to obtain a three-dimensional acupoint model of the target patient; S5, real-time parameter registration of the three-dimensional acupoint model based on the real-time physiological state of the target patient to obtain a standard space parameter set of the three-dimensional acupoint model; S6, superimposing the standard space parameter set to the three-dimensional acupoint model to obtain a visual acupoint view of the target patient.

2. The multi-modal imaging based intelligent acupoint positioning method according to claim 1, wherein, Matching the feature waveform set with a corresponding initial position marker point set of an acupoint in a preset acupoint waveform template library comprises: phase space reconstruction of the feature waveform set to obtain a phase space waveform set of the feature waveform set; taking the Euclidean distance between each point in the phase space waveform set and the corresponding waveform marker point in the preset acupoint waveform template library as the dimension matching result of the preset acupoint waveform template library, wherein the Euclidean distance calculation formula is as follows: ； In the formula, is a dimension matching result, is a feature value of a target patient, is a feature dimension index, is a phase space waveform point index, is a marked point of a phase space waveform set, is a marked point of a preset acupoint template library, is an acupoint template index, is a total number of feature dimensions, is a feature value of a template library; mapping the dimension matching result to a bioelectric conduction path marker to obtain the initial position marker point set of the acupoint of the target patient.

3. The multi-modal imaging based intelligent acupoint positioning method according to claim 2, wherein, Phase space reconstruction of the feature waveform set to obtain a phase space waveform set of the feature waveform set comprises: separating the feature waveform set into a dynamic component subset and a static component subset; mapping the dynamic component subset and the static component subset to a spatial extension waveform corresponding to the physiological dimension of the target patient; fusing the bioelectric conduction topology rule of the human body with the spatial extension waveform to obtain the phase space waveform set of the feature waveform set.

4. The multi-modal imaging based intelligent acupoint positioning method according to claim 1, wherein, Projecting the initial position marker point set of the acupoint to the corresponding body surface area of the target patient and correcting the distortion of the acupoint projection to obtain a high-precision acupoint coordinate set of the target patient comprises: mapping the initial position marker point set of the acupoint to a body surface coordinate system to obtain an original projection coordinate set of the target patient; spatial position calibration of the original projection coordinate set based on a preset acupoint distribution topology; optical distortion compensation of the calibrated projection coordinate set according to the physical structure parameters of the preset acupoint distribution topology to obtain a high-precision acupoint coordinate set of the target patient.

5. The multi-modal imaging based intelligent acupoint positioning method according to claim 1, wherein, Mapping the high-precision acupoint coordinate set to a three-dimensional space to obtain a three-dimensional acupoint model of the target patient, including: Depth direction expansion is performed on the two-dimensional surface coordinates of the high-precision acupoint coordinate set to obtain an initial three-dimensional acupoint point cloud of the target patient; Spatial position correction is performed on the initial three-dimensional acupoint point cloud based on the distribution rule of human acupoints; The corrected three-dimensional acupoint point cloud is topologically connected with the anatomical landmark points of the target patient to obtain the three-dimensional acupoint model of the target patient.

6. The multi-modal imaging based intelligent acupoint positioning method according to claim 1, wherein, Real-time parameter registration is performed on the three-dimensional acupoint model based on the real-time physiological state of the target patient to obtain a standard space parameter set of the three-dimensional acupoint model, including: Spatial coordinate collection is performed on the high-precision acupoint coordinate set to obtain an initial three-dimensional coordinate set of the target patient; The initial three-dimensional coordinate set is physically embedded with a structured coordinate topology to obtain the standard space parameter set of the three-dimensional acupoint model.

7. The multi-modal imaging based intelligent acupoint positioning method according to claim 1, wherein, The standard space parameter set is superimposed on the three-dimensional acupoint model to obtain a visual acupoint view of the target patient, including: The standard space parameter set is projected onto the patient coordinate system of the three-dimensional acupoint model to obtain an initial projection marker point set of the target patient; Deviation comparison is performed on the initial projection marker point set and the spatial position of the target patient to obtain a deviation data set of the spatial position; Based on the spatial position deviation data set, the projection angle is adjusted to obtain the calibration projection parameter of the target patient; The calibration projection parameter is projected to the target patient, and the visual acupoint view of the target patient is obtained.

8. The multi-modal imaging based intelligent acupoint positioning method according to claim 7, wherein, Based on the spatial position deviation data set, the projection angle is adjusted to obtain the calibration projection parameter of the target patient, including: Analyzing the deviation direction and deviation amplitude data of the projection angle in the spatial position deviation data set; Based on the deviation direction and the deviation amplitude data, the spatial pointing parameter of the projection is dynamically corrected; The corrected spatial pointing parameter is registered and verified with the body surface anatomical coordinate system of the target patient to obtain the calibration projection parameter of the target patient.

9. An intelligent acupoint positioning system based on multi-modal imaging, characterized in that, The system includes: A feature decoupling module for decoupling infrared thermal imaging data and ultrasonic elastography data of a target patient to obtain a feature waveform set of the target patient, including: Wavelet transform decomposition is performed on the infrared thermal imaging data to obtain a frequency energy distribution feature set of the infrared thermal imaging data; Time-frequency joint analysis is performed on the ultrasonic elastography data to obtain a spatial gradient tensor set of the ultrasonic elastography data; The frequency energy distribution feature set and the spatial gradient tensor set are coupled in a tensor domain to obtain the feature waveform set of the target patient, wherein the tensor domain coupling calculation formula is as follows: ； wherein is a set of characteristic waveforms, is a set of frequency energy distribution characteristics, is a set of spatial gradient tensors, is a transpose tensor of the spatial gradient tensor, is a coupling coefficient; A waveform matching module for matching the feature waveform set with a corresponding acupoint initial position marker point set in a preset acupoint waveform template library; A projection correction module for projecting the acupoint initial position marker point set to a corresponding body surface region of the target patient and performing distortion correction on the acupoint projection to obtain a high-precision acupoint coordinate set of the target patient; The three-dimensional acupoint model construction module is configured to map the high-precision acupoint coordinate set to a three-dimensional space to obtain a three-dimensional acupoint model of the target patient; The parameter registration module is configured to perform real-time parameter registration on the three-dimensional acupoint model based on a real-time physiological state of the target patient to obtain a standard space parameter set of the three-dimensional acupoint model; The visualization superimposition module is configured to superimpose the standard space parameter set on the three-dimensional acupoint model to obtain a visual acupoint view of the target patient.

Images