Multi-dimensional data processing method and system for emergency data quality control analysis

Abstract

The embodiment of the invention provides a multi-dimensional data processing method and system for emergency data quality control analysis. The method comprises the following steps: acquiring photoacoustic blood flow imaging data and emergency treatment parameters of a patient, and generating multi-channel time-space associated data; constructing a laser pulse energy density correction module, generating an ultrasonic receiver sensitivity adjustment parameter through a dynamic coupling mechanism of the pain index grade and the capillary density distribution, and synchronously establishing a phase synchronous compensation network of the laser pulse repetition frequency and the heart rate variability; generating a real-time three-dimensional photoacoustic blood flow dynamic image, and dividing a difference region into a high-perfusion core region, a transition region and a low-perfusion marginal region based on blood flow velocity gradient mutation point spatial distribution; and generating an emergency treatment quality control score based on the dynamic correlation function, the mapping relation and the coupling coefficient. According to the technical scheme provided by the embodiment of the invention, real-time three-dimensional blood flow visualization and accurate partition diagnosis of mammary gland lesions are realized, and the pathological relevance of emergency treatment quality control scores is remarkably improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of multi-dimensional data processing, and in particular, to a multi-dimensional data processing method and system for emergency data quality control analysis. Background Art

[0002] With the rapid development of precision medicine and multi-modal imaging technology, the demand for quality control analysis with high pathological relevance and fast dynamic response in breast emergency diagnosis and treatment is becoming increasingly urgent. The current emergency quality control needs to meet the dual requirements of dynamic coupling of multi-source data and real-time image guidance. Pathological features such as abnormal microvascular angiogenesis and oxygen metabolism disorders in breast lesions need to be visualized through photoacoustic / ultrasound dual-modal data fusion, and precise zoning is carried out based on hemodynamic mutation points (such as the boundary of high / low perfusion areas) to support clinical decision-making.

[0003] Traditional methods mostly rely on single-modal data (such as ultrasound or static blood flow parameters), divide the perfusion area through artificial experience, and generate a quality control score based on a linear regression model. For example, the moving average method is used to analyze the trend of emergency parameters, or the abnormal microvascular density is judged through a fixed threshold.

[0004] The existing solutions have the following defects: there is a lack of non-linear coupling analysis between static parameters and dynamic physiological indicators (such as blood pressure fluctuations and pain index), resulting in the quality control score being unable to reflect the complexity of microcirculation and neuro-vascular interaction, and insufficient pathological relevance; the existing equipment parameters (such as laser energy density and ultrasound sensitivity) are not dynamically adapted to the patient's physiological rhythm (such as heart rate variability), and it is easy to reduce the image resolution due to motion artifacts or phase mismatch, resulting in limited real-time performance; the identification of blood flow gradient mutation points relying on artificial experience is likely to miss the discrete characteristics of oxygen saturation in the transition zone, resulting in blurred boundaries of high / low perfusion areas, affecting the formulation of treatment plans, and low zoning accuracy. Summary of the Invention

[0005] The embodiments of the present application provide a multi-dimensional data processing method and system for emergency data quality control analysis to solve the problem of insufficient pathological relevance of emergency quality control scores in the prior art.

[0006] In a first aspect, the embodiments of the present application provide a multi-dimensional data processing method for emergency data quality control analysis, including:

[0007] Obtain photoacoustic blood flow imaging data of a target breast area and patient emergency parameters, where the photoacoustic blood flow imaging data includes blood flow velocity distribution, hemoglobin oxygen saturation distribution, and microvascular density distribution, and the emergency parameters include heart rate variability, blood pressure fluctuation range, and pain index level, and generate multi-channel spatio-temporal correlation data;

[0008] Construct a laser pulse energy density correction module based on the non-linear relationship between the blood pressure fluctuation range and hemoglobin oxygen saturation in the multi-channel spatio-temporal correlation data, generate an ultrasonic receiver sensitivity adjustment parameter through the dynamic coupling mechanism of the pain index level and the microvascular density distribution, and synchronously establish a phase synchronization compensation network between the laser pulse repetition frequency and the heart rate variability;

[0009] Generate a real-time three-dimensional photoacoustic blood flow dynamic image and divide the difference region into a high-perfusion core area, a transition zone, and a low-perfusion edge area based on the spatial distribution of blood flow velocity gradient mutation points;

[0010] Generate an emergency quality control score based on the dynamic correlation function between the area attenuation rate of the high-perfusion core area and the blood pressure fluctuation range, the mapping relationship between the oxygen saturation dispersion degree of the transition zone and the pain index level, and the coupling coefficient between the microvascular density fluctuation amplitude of the low-perfusion edge area and the heart rate variability.

[0011] Optionally, the constructing a laser pulse energy density correction module based on the non-linear relationship between the blood pressure fluctuation range and hemoglobin oxygen saturation in the multi-channel spatio-temporal correlation data, generating an ultrasonic receiver sensitivity adjustment parameter through the dynamic coupling mechanism of the pain index level and the microvascular density distribution, and synchronously establishing a phase synchronization compensation network between the laser pulse repetition frequency and the heart rate variability includes:

[0012] Generate blood flow oscillation entropy based on the phase delay spectrum of the blood pressure fluctuation range and hemoglobin oxygen saturation in the multi-channel spatio-temporal correlation data, input the blood flow oscillation entropy into a frequency-domain convolution kernel to generate a pulse energy density correction coefficient, and the bandwidth of the frequency-domain convolution kernel is dynamically adjusted by the ratio of the fluctuation period of hemoglobin oxygen saturation to the full-width at half-maximum of the blood pressure fluctuation range;

[0013] Extract the microvascular topological entanglement degree through the morphological skeleton of the microvascular density distribution, input the pain index level and the microvascular topological entanglement degree into a path tracing algorithm to generate a receiver sensitivity adjustment parameter, and the backtracking step size of the path tracing algorithm is determined by the spatial density gradient of microvascular branch nodes;

[0014] Perform chaotic phase modulation on the recurrence plot features of the heart rate variability and the laser pulse repetition frequency to generate a pulse synchronization compensation parameter carrying cardiac beat chaos features, and the recurrence plot features are based on the Lyapunov exponent of the heart rate variability and the spectral gap of the laser pulse repetition frequency;

[0015] Input the pulse energy density correction coefficient, the receiver sensitivity adjustment parameter, and the pulse synchronization compensation parameter into a multi-physics field coupler to generate a collaborative regulation instruction set, and synchronously establish a phase synchronization compensation network between the laser pulse repetition frequency and the heart rate variability.

[0016] Optionally, generating an emergency quality control score based on the dynamic association function between the area attenuation rate of the high-perfusion core region and the blood pressure fluctuation range, the mapping relationship between the oxygen saturation dispersion of the transition zone and the pain index level, and the coupling coefficient between the microvascular density fluctuation amplitude of the low-perfusion marginal region and the heart rate variability, includes:

[0017] Input the time-varying differential operator of the area attenuation rate of the high-perfusion core region and the blood pressure fluctuation range into the thermodynamic entropy change model to generate a perfusion instability index, and the non-equilibrium state constraint condition of the thermodynamic entropy change model is determined by the included angle between the half-cycle amplitude of the blood pressure fluctuation range and the gradient direction of the area attenuation rate;

[0018] Generate a pain resonance factor through the phase vortex field of the oxygen saturation dispersion in the three-dimensional space, and the topological structure of the phase vortex field is constructed by the spatio-temporal heterogeneity of the oxygen saturation dispersion and the power spectrum overlapping region of the pain index level;

[0019] Input the recursive features of the microvascular density fluctuation amplitude of the low-perfusion marginal region and the heart rate variability into the vascular oscillation coupler to generate a coupled oscillation spectrum carrying the heart beat-blood flow interference feature, and the resonant cavity parameters of the vascular oscillation coupler are jointly modulated by the peak-valley difference of the microvascular density fluctuation amplitude and the fractal dimension of the heart rate variability;

[0020] Input the perfusion instability index, the pain resonance factor, and the coupled oscillation spectrum into a multi-modal resonator to generate an emergency quality control score, and trigger the adaptive re-optimization of the scanning parameters through a closed-loop feedback channel and update the laser pulse energy density correction module and the phase synchronization compensation network.

[0021] Optionally, the inputting the recursive features of the microvascular density fluctuation amplitude of the low-perfusion marginal region and the heart rate variability into the vascular oscillation coupler to generate a coupled oscillation spectrum carrying the heart beat-blood flow interference feature, and the resonant cavity parameters of the vascular oscillation coupler are jointly modulated by the peak-valley difference of the microvascular density fluctuation amplitude and the fractal dimension of the heart rate variability, includes:

[0022] Set a time window function for the microvascular density fluctuation amplitude of the low-perfusion marginal region, and perform fractal dimension slicing on the time window function and the recursive features of the heart rate variability to generate the fundamental frequency of vascular wall oscillation, and the sliding step of the time window function is dynamically adjusted by the peak-valley difference of the microvascular density fluctuation amplitude;

[0023] Generate oscillation cavity harmonic parameters through the fundamental frequency of the blood vessel wall oscillation and the fractal tuning factor of the heart rate variability, where the fractal tuning factor is calculated from the projected area of the fractal dimension slice on the time-frequency plane and the time-window statistic of the microvascular density fluctuation amplitude;

[0024] Input the oscillation cavity harmonic parameters into a blood flow interference phase detector to generate heartbeat-blood flow interference fringes, and the phase entanglement state of the interference fringes is determined by the energy ratio relationship between the time-window statistic of the microvascular density fluctuation amplitude and the fractal tuning factor;

[0025] Generate dynamic impedance parameters based on the phase entanglement state of the interference fringes, combine the time-window function and the recursive features of the heart rate variability, and input them into a blood vessel oscillation coupler to generate a coupled oscillation spectrum carrying heartbeat-blood flow interference features. The resonant cavity parameters of the blood vessel oscillation coupler are jointly modulated by the peak-valley difference of the microvascular density fluctuation amplitude and the fractal dimension of the heart rate variability.

[0026] Optionally, the generating oscillation cavity harmonic parameters through the fundamental frequency of the blood vessel wall oscillation and the fractal tuning factor of the heart rate variability, where the fractal tuning factor is calculated from the projected area of the fractal dimension slice on the time-frequency plane and the time-window statistic of the microvascular density fluctuation amplitude, includes:

[0027] Perform a time-frequency plane projection on the fractal dimension slice to generate a multi-dimensional fractal topology network, and the grid density of the multi-dimensional fractal topology network is jointly controlled by the time-window statistic of the microvascular density fluctuation amplitude and the spatio-temporal gradient of the projected area;

[0028] Generate a fractal tuning factor through the node energy distribution of the multi-dimensional fractal topology network, where the fractal tuning factor is calculated from the projected area of the fractal dimension slice on the time-frequency plane and the time-window statistic of the microvascular density fluctuation amplitude;

[0029] Input the fractal tuning factor into an oscillation cavity energy converter to generate a harmonic phase group, and the tunneling path of the harmonic phase group is jointly constrained by the energy distribution gradient of the fractal tuning factor and the recursive feature map of the heart rate variability;

[0030] Combine the fundamental frequency of the blood vessel wall oscillation, and generate oscillation cavity harmonic parameters through the tunneling path of the harmonic phase group. The oscillation cavity harmonic parameters synchronously correct the time-frequency distortion compensation amount of the frequency-domain convolution kernel and update the Lyapunov constraint condition of the recursive graph topology structure through waveguide coupling effect.

[0031] Optionally, generating a fractal tuning factor through the node energy distribution of the multi-dimensional fractal topology network, the fractal tuning factor is calculated from the projected area of the fractal dimension slice on the time-frequency plane and the time-window statistic of the microvascular density fluctuation amplitude, including:

[0032] Extracting a phase winding coefficient from the node energy distribution of the multi-dimensional fractal topology network, the phase winding coefficient is generated by the spatio-temporal interference effect of the projected area of the fractal dimension slice on the time-frequency plane and the time-window statistic of the microvascular density fluctuation amplitude;

[0033] Generating a vortex energy flow through the time-frequency distortion rate of the phase winding coefficient and the fundamental frequency of the blood vessel wall oscillation, the precession angle of the vortex energy flow is jointly determined by the energy gradient field of adjacent nodes in the multi-dimensional fractal topology network and the power spectrum offset of the time-window statistic;

[0034] Inputting the vortex energy flow into a fractal tuning field generator to generate a fractal tuning factor carrying the quantum tunneling effect, the constraint condition of the fractal tuning field generator is constructed from the overlapping region of the precession angle of the vortex energy flow and the recursive characteristic map of the heart rate variability;

[0035] Generating a topological entanglement parameter based on the quantum tunneling path density of the fractal tuning factor carrying the quantum tunneling effect, the topological entanglement parameter synchronously adjusts the time-frequency distortion compensation gradient of the frequency-domain convolution kernel through a non-linear resonance mechanism and reconstructs the energy threshold of the Lyapunov constraint condition.

[0036] Optionally, generating a real-time three-dimensional photoacoustic blood flow dynamic image and dividing the difference region into a high-perfusion core area, a transition zone, and a low-perfusion edge area based on the spatial distribution of blood flow velocity gradient mutation points, including:

[0037] Extracting spatio-temporal phase singularities at the blood flow velocity gradient mutation points to generate a phase singularity map, the phase singularity map is topologically wound by the Lorentz divergence of the blood flow velocity gradient mutation points and the time-varying characteristics of the microvascular density fluctuation amplitude;

[0038] Constructing a metabolic vortex field based on the phase singularity map, the vortex core density of the metabolic vortex field is jointly controlled by the spatial gradient of the hemoglobin oxygen saturation dispersion and the winding intensity of the phase singularity map and the initial boundaries of the high-perfusion core area, the transition zone, and the low-perfusion edge area are divided;

[0039] Generating a metabolic entanglement degree through the quantization energy level transition of the microvascular density fluctuation amplitude and the interference effect of the hemoglobin oxygen saturation dispersion, the metabolic entanglement degree drives the dynamic contraction of the initial boundary and generates a modified regional boundary carrying an energy transition marker;

[0040] Input the energy transition marker of the boundary of the corrected area into the photoacoustic energy redistributor to generate a dynamic topology reconstruction instruction, which corrects the distribution of the extreme points of the blood flow velocity gradient in the three-dimensional dynamic image and updates the winding intensity threshold of the phase singularity map.

[0041] In a second aspect, an embodiment of the present application provides a multi-dimensional data processing system for emergency data quality control analysis, including:

[0042] An acquisition module, configured to acquire photoacoustic blood flow imaging data and patient emergency parameters of a target breast area, where the photoacoustic blood flow imaging data includes blood flow velocity distribution, hemoglobin oxygen saturation distribution, and microvascular density distribution, and the emergency parameters include heart rate variability, blood pressure fluctuation range, and pain index level, and generate multi-channel spatio-temporal correlation data;

[0043] A construction module, configured to construct a laser pulse energy density correction module based on the non-linear relationship between the blood pressure fluctuation range and the hemoglobin oxygen saturation in the multi-channel spatio-temporal correlation data, generate an ultrasonic receiver sensitivity adjustment parameter through the dynamic coupling mechanism between the pain index level and the microvascular density distribution, and synchronously establish a phase synchronization compensation network between the laser pulse repetition frequency and the heart rate variability;

[0044] A division module, configured to generate a real-time three-dimensional photoacoustic blood flow dynamic image and divide the difference area into a high-perfusion core area, a transition zone, and a low-perfusion edge area based on the spatial distribution of blood flow velocity gradient mutation points;

[0045] A generation module, configured to generate an emergency quality control score based on the dynamic correlation function between the area attenuation rate of the high-perfusion core area and the blood pressure fluctuation range, the mapping relationship between the oxygen saturation dispersion of the transition zone and the pain index level, and the coupling coefficient between the microvascular density fluctuation amplitude of the low-perfusion edge area and the heart rate variability.

[0046] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a multi-dimensional data processing method for emergency data quality control analysis as described in the first aspect above.

[0047] In a fourth aspect, an embodiment of the present application provides a computer storage medium, storing a computer program, and when the computer program is executed by a computer, it implements a multi-dimensional data processing method for emergency data quality control analysis as described in the first aspect.

[0048] In the embodiment of the present application, photoacoustic blood flow imaging data of the target breast region and patient emergency parameters are obtained. The photoacoustic blood flow imaging data includes blood flow velocity distribution, hemoglobin oxygen saturation distribution, and microvascular density distribution. The emergency parameters include heart rate variability, blood pressure fluctuation range, and pain index level, and multi-channel spatio-temporal correlation data is generated. A laser pulse energy density correction module is constructed based on the non-linear relationship between the blood pressure fluctuation range and hemoglobin oxygen saturation in the multi-channel spatio-temporal correlation data. An ultrasonic receiver sensitivity adjustment parameter is generated through the dynamic coupling mechanism between the pain index level and the microvascular density distribution, and a phase synchronization compensation network between the laser pulse repetition frequency and the heart rate variability is established synchronously. A real-time three-dimensional photoacoustic blood flow dynamic image is generated, and the difference region is divided into a high-perfusion core area, a transition zone, and a low-perfusion edge area based on the spatial distribution of blood flow velocity gradient mutation points. An emergency quality control score is generated based on the dynamic correlation function between the area attenuation rate of the high-perfusion core area and the blood pressure fluctuation range, the mapping relationship between the oxygen saturation dispersion degree of the transition zone and the pain index level, and the coupling coefficient between the microvascular density fluctuation amplitude of the low-perfusion edge area and the heart rate variability.

[0049] The technical solution of the present application has the following beneficial effects:

[0050] By synchronously analyzing microvascular generation and tissue oxygenation levels through photoacoustic and ultrasonic dual-modal fusion technology, the diagnostic specificity of breast cancer is improved; based on the dynamic gradient attenuation function, the laser energy density parameters are optimized to enhance the imaging resolution of deep tissues; multi-scale frequency domain decomposition is used to generate ultrasonic sensitivity adjustment parameters to improve the sensitivity of detecting abnormal microcirculation; through the phase synchronization compensation network, the dynamic adaptation of device parameters and physiological rhythms is realized to reduce the interference of motion artifacts; the relevance of blood flow partition parameters is verified by combining the Markov chain state transition model to optimize the perfusion boundary recognition accuracy; the closed-loop feedback mechanism dynamically iterates device parameters through the quality control score to ensure the synchronous optimization of diagnostic decisions and device regulation.

[0051] Furthermore, the blood flow oscillation entropy is generated by the phase delay spectrum of the blood pressure fluctuation range and hemoglobin oxygen saturation in the multi-channel spatio-temporal correlation data, and the pulse energy density correction coefficient is dynamically adjusted based on the frequency domain convolution kernel; the topological entanglement degree is extracted through the morphological skeleton of the microvascular density distribution, and the receiver sensitivity adjustment parameter is generated by combining the pain index level and the path tracing algorithm; the recurrence plot features of the heart rate variability and the laser pulse repetition frequency are subjected to chaotic phase modulation to generate a synchronous compensation parameter carrying the chaotic characteristics of heart beats; finally, the correction coefficient, the adjustment parameter, and the compensation parameter are integrated through a multi-physical field coupler to generate a collaborative control instruction set and construct a phase synchronization compensation network. Through the deep coupling of hemodynamic parameters and microvascular topology, the frequency domain adaptive optimization of the laser energy density is realized, and the imaging resolution of deep tissues and the detection sensitivity of microcirculation abnormalities are improved; based on the heart rate synchronization compensation mechanism of chaotic phase modulation, the phase mismatch between the physiological rhythm and the device parameters is effectively suppressed, and the spatio-temporal consistency of image acquisition is enhanced; the multi-physical field collaborative control network ensures the perfusion boundary recognition accuracy and pathological relevance of photoacoustic blood flow images through dynamic closed-loop feedback optimization, while reducing the interference of motion artifacts on the quantitative analysis of microvascular density.

[0052] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. Brief Description of the Drawings

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0054] Figure 1 Shows a flowchart of a multi-dimensional data processing method for emergency data quality control analysis provided by the present application;

[0055] Figure 2 Shows a schematic structural diagram of a multi-dimensional data processing system for emergency data quality control analysis provided by the present application;

[0056] Figure 3 Shows a schematic structural diagram of a computing device provided by the present application. Detailed Description of the Embodiments

[0057] In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

[0058] In some of the processes described in the specification, claims, and the above-mentioned drawings of this application, multiple operations appear in a specific order. However, it should be clearly understood that these operations can be executed not in the order in which they appear herein or in parallel. The operation numbers such as 101, 102, etc. are only used to distinguish different operations, and the numbers themselves do not represent any execution order. Additionally, these processes can include more or fewer operations, and these operations can be executed sequentially or in parallel. It should be noted that the descriptions such as "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent a sequence, and do not limit that "first" and "second" are of different types.

[0059] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope protected by the present application.

[0060] Figure 1 The flowchart of a multi-dimensional data processing method for emergency data quality control analysis is provided for the embodiments of the present application, as Figure 1 shown. The method includes:

[0061] 101. Obtain photoacoustic blood flow imaging data of the target breast area and patient emergency parameters. The photoacoustic blood flow imaging data includes blood flow velocity distribution, hemoglobin oxygen saturation distribution, and microvascular density distribution. The emergency parameters include heart rate variability, blood pressure fluctuation range, and pain index level, and generate multi-channel spatio-temporal correlation data;

[0062] In this step, the photoacoustic blood flow imaging data is an imaging technology that combines optical and acoustic principles and can provide information such as blood flow velocity distribution, hemoglobin oxygen saturation distribution, and microvascular density distribution. These data are used to evaluate the blood flow dynamics of the breast area.

[0063] The emergency parameters include physiological indicators such as heart rate variability, blood pressure fluctuation range, and pain index level, which reflect the overall health status of the patient. These parameters are used to assist in judging the urgency of the condition and the treatment effect.

[0064] The multi-channel spatio-temporal correlation data is a comprehensive data set that integrates the above two types of data, forming a comprehensive data set that includes the time dimension and the space dimension, facilitating subsequent analysis.

[0065] The multi-channel spatio-temporal correlation data set contains all the collected photoacoustic blood flow imaging data and emergency parameters, providing a basis for the subsequent steps.

[0066] In the embodiments of the present application, first, photoacoustic blood flow imaging data of the target breast region and the patient's emergency parameters are obtained. Specifically, a high-resolution photoacoustic imaging device (such as a photoacoustic tomography scanner) is used to collect data such as the blood flow velocity distribution, hemoglobin oxygen saturation distribution, and microvascular density distribution of the patient. These data are segmented and quantified through image processing techniques (such as the level set method or the watershed algorithm) to form a detailed physiological parameter distribution map. At the same time, sensors (such as an electrocardiogram monitor, a sphygmomanometer, and a pain assessment scale) are used to collect emergency parameters such as the patient's heart rate variability, blood pressure fluctuation range, and pain index level. These data are converted into time series data through signal processing techniques (such as the fast Fourier transform FFT and recurrence plot analysis) and combined with the photoacoustic imaging data to generate multi-channel spatio-temporal correlation data.

[0067] Suppose a patient suspected of having breast inflammation is sent to the emergency room. The doctor first uses a high-resolution photoacoustic imaging device to scan the patient's breast region to obtain detailed information such as the blood flow velocity distribution, hemoglobin oxygen saturation distribution, and microvascular density distribution. The specific data are as follows: the blood flow velocity distribution in the target area is 2.5 cm / s, the average value of the hemoglobin oxygen saturation distribution is 65%, and the peak value of the microvascular density distribution is 120 / mm. 2 At the same time, the electrocardiogram monitor is used to record the patient's heart rate variability, and the measured result is that the standard deviation SDNN value is 50 ms; the sphygmomanometer measures the blood pressure fluctuation range from 120 / 80 mmHg to 130 / 85 mmHg; the pain index level is determined to be 4 (moderate pain) through the pain assessment scale. All these data are converted into time series data through signal processing techniques and combined with the photoacoustic imaging data to generate multi-channel spatio-temporal correlation data, providing a basis for subsequent analysis.

[0068] 102. A laser pulse energy density correction module is constructed based on the non-linear relationship between the blood pressure fluctuation range and the hemoglobin oxygen saturation in the multi-channel spatio-temporal correlation data, an ultrasonic receiver sensitivity adjustment parameter is generated through the dynamic coupling mechanism between the pain index level and the microvascular density distribution, and a phase synchronization compensation network of the laser pulse repetition frequency and the heart rate variability is established synchronously;

[0069] In this step, the laser pulse energy density correction module is a dynamic adjustment mechanism constructed based on the non-linear relationship between the blood pressure fluctuation range and the hemoglobin oxygen saturation, and is used to optimize the energy density of the laser pulse.

[0070] The ultrasonic receiver sensitivity adjustment parameter is a parameter generated according to the dynamic coupling mechanism between the pain index level and the microvascular density distribution, and is used to adjust the sensitivity of the ultrasonic receiver.

[0071] The phase synchronization compensation network is a synchronization mechanism that ensures the stability of system operation by adjusting the phase relationship between the laser pulse repetition frequency and the heart rate variability.

[0072] In the embodiments of this application, a laser pulse energy density correction module is constructed based on the non-linear relationship between the blood pressure fluctuation range and the hemoglobin oxygen saturation in the generated multi-channel spatio-temporal correlation data. Specifically, mutual information and phase space reconstruction techniques are used to analyze the complex non-linear relationship between the blood pressure fluctuation range and the hemoglobin oxygen saturation, and a correction coefficient is generated. Then, a model is trained by recurrent neural networks (RNNs) to optimize the laser pulse energy density correction module. Synchronously, an ultrasonic receiver sensitivity adjustment parameter is generated through the dynamic coupling mechanism between the pain index level and the microvascular density distribution. The specific steps include: using an adaptive filter to adjust the microvascular density distribution according to the pain index level, and combining support vector machines (SVMs) to generate the sensitivity adjustment parameter. Finally, a phase synchronization compensation network between the laser pulse repetition frequency and the heart rate variability is established. This step extracts the time-frequency characteristics of the heart rate variability through the Hilbert-Huang transform (HHT), and realizes the synchronous control of the laser pulse repetition frequency through the phase-locked loop (PLL) technology.

[0073] For example, continuing the above example, after obtaining the multi-channel spatio-temporal correlation data, first, the relationship between the blood pressure fluctuation range and the hemoglobin oxygen saturation is analyzed using mutual information and phase space reconstruction techniques, and the non-linear correlation coefficient between the two is found to be 0.75. Then, a model is trained by recurrent neural networks (RNNs) to optimize the laser pulse energy density correction module, and the adjusted laser pulse energy density is 0.8 J / cm 2 . At the same time, according to the pain index level of 4, the microvascular density distribution is adjusted using an adaptive filter, and the ultrasonic receiver sensitivity adjustment parameter is generated by combining support vector machines (SVMs), and the sensitivity is set to 0.95. Finally, the time-frequency characteristics of the heart rate variability are extracted using the Hilbert-Huang transform (HHT), and the synchronous control of the laser pulse repetition frequency is realized through the phase-locked loop (PLL) technology. The repetition frequency is set to 10 kHz, and a phase synchronization compensation network is established with the heart rate variability;

[0074] 103. Generate a real-time three-dimensional photoacoustic blood flow dynamic image and divide the differential region into a high-perfusion core region, a transition zone, and a low-perfusion edge region based on the spatial distribution of the blood flow velocity gradient mutation points;

[0075] In this step, the real-time three-dimensional photoacoustic blood flow dynamic image is a high-resolution three-dimensional image generated by using the laser pulse energy density correction module and the ultrasonic receiver sensitivity adjustment parameters, which can intuitively display the blood flow dynamics in the breast area.

[0076] The high-perfusion core area, the transition zone, and the low-perfusion marginal area are spatial distributions generated based on the sudden change points of the blood flow velocity gradient, which divide the image into three different regions, respectively representing different blood flow conditions.

[0077] The three-dimensional blood flow dynamic image is used to visualize the blood flow dynamics in the breast area and help identify the lesion site.

[0078] In the embodiment of the present application, a real-time three-dimensional photoacoustic blood flow dynamic image is generated, and the differential region is divided into a high-perfusion core area, a transition zone, and a low-perfusion marginal area based on the spatial distribution of the sudden change points of the blood flow velocity gradient. Specifically, first, the three-dimensional reconstruction technology (such as volume rendering and surface reconstruction) is applied to convert the two-dimensional photoacoustic imaging data into a three-dimensional image. Then, the computational fluid dynamics (CFD) is used to simulate the blood flow velocity field, and the finite element analysis (FEA) is used to calculate the blood flow velocity gradient. Based on the spatial distribution of the sudden change points of the blood flow velocity gradient, the graph cut algorithm and the clustering analysis are used to divide the differential region into a high-perfusion core area, a transition zone, and a low-perfusion marginal area. This step provides detailed blood flow dynamic information through accurate three-dimensional reconstruction and fluid dynamics simulation, which helps to accurately identify the lesion area.

[0079] For example, continuing with the above example, the three-dimensional reconstruction technology and the computational fluid dynamics (CFD) simulation are applied to generate a real-time three-dimensional photoacoustic blood flow dynamic image. First, the volume rendering is used to convert the two-dimensional photoacoustic imaging data into a three-dimensional image to display the blood flow distribution in the breast area. Then, the finite element analysis (FEA) is used to calculate the blood flow velocity gradient, and it is found that the maximum blood flow velocity gradient sudden change point is located in the middle of the breast, and its value is 1.5 cm / s 2 . Based on the spatial distribution of these sudden change points, the graph cut algorithm and the clustering analysis are used to divide the differential region into a high-perfusion core area, a transition zone, and a low-perfusion marginal area. The specific partition results are as follows: the area of the high-perfusion core area is 3 cm 2 , the area of the transition zone is 5 cm 2, the area of the hypoperfused marginal zone is 7 cm 2 . These steps help doctors better understand the dynamic changes in blood flow in the breast area, providing strong support for subsequent diagnoses.

[0080] 104. Generate an emergency quality control score based on the dynamic association function between the area attenuation rate of the hyperperfused core area and the blood pressure fluctuation range, the mapping relationship between the oxygen saturation dispersion degree of the transition zone and the pain index level, and the coupling coefficient between the microvascular density fluctuation amplitude of the hypoperfused marginal zone and the heart rate variability.

[0081] In this step, the emergency quality control score is a quantitative score generated based on factors such as the area attenuation rate of the hyperperfused core area, the oxygen saturation dispersion degree of the transition zone, and the microvascular density fluctuation amplitude of the hypoperfused marginal zone, and is used to evaluate the quality of emergency treatment.

[0082] The dynamic association function is a mathematical model that describes the relationship between the area attenuation rate of the hyperperfused core area and the blood pressure fluctuation range.

[0083] The mapping relationship describes the complex relationship between the oxygen saturation dispersion degree of the transition zone and the pain index level.

[0084] The coupling coefficient describes the interaction between the microvascular density fluctuation amplitude of the hypoperfused marginal zone and the heart rate variability.

[0085] The emergency quality control score is used to evaluate the quality of emergency treatment and provide a basis for quality control comparisons between different institutions.

[0086] In the embodiments of this application, an emergency quality control score is generated based on the dynamic association function between the area attenuation rate of the hyperperfused core area and the blood pressure fluctuation range, the mapping relationship between the oxygen saturation dispersion degree of the transition zone and the pain index level, and the coupling coefficient between the microvascular density fluctuation amplitude of the hypoperfused marginal zone and the heart rate variability. Specifically, first, use Grey Relational Analysis (GRA) to calculate the dynamic association function between the area attenuation rate of the hyperperfused core area and the blood pressure fluctuation range. Then, extract the mapping relationship between the oxygen saturation dispersion degree of the transition zone and the pain index level through Principal Component Analysis (PCA). Finally, use Cross-Validation and machine learning algorithms (such as Random Forests) to generate the coupling coefficient between the microvascular density fluctuation amplitude of the hypoperfused marginal zone and the heart rate variability. Based on these parameters, an emergency quality control score is generated to reflect the overall severity of the patient's condition.

[0087] For example, continuing the previous example, use Grey Relational Analysis (GRA) to calculate the area attenuation rate of the hyperperfused core area as 0.05 cm2 / min, the dynamic correlation function of the blood pressure fluctuation range is 0.65. By performing principal component analysis (PCA), the mapping relationship between the oxygen saturation dispersion in the transition zone and the pain index level is extracted, resulting in an oxygen saturation dispersion of 15% and a pain index level of 4. Finally, using cross-validation and the random forest algorithm, the coupling coefficient between the microvascular density fluctuation amplitude in the hypoperfusion marginal zone and the heart rate variability is generated, and the coupling coefficient is 0.8. Based on these parameters, an emergency quality control score is generated, and the comprehensive score is 75 points, reflecting that the overall severity of the patient's condition is moderate. This helps doctors quickly evaluate the severity of the patient's condition and formulate appropriate treatment plans.

[0088] Through the above four steps, this study successfully combines photoacoustic blood flow imaging technology with multiple emergency parameters, achieving comprehensive monitoring and analysis of the blood flow dynamics in the breast area. This method not only improves the accuracy of diagnosis but also provides a scientific basis for the formulation of personalized treatment plans. In addition, it can effectively promote the rational allocation of medical resources and improve the overall quality of medical services. In the entire process, from data acquisition to the generation of the final quality control score, each link is closely connected, jointly constituting a complete diagnostic support system.

[0089] To further improve the accuracy and reliability of photoacoustic blood flow imaging technology in emergency data quality control analysis, a dynamic regulation mechanism based on multi-channel spatio-temporal correlation data is designed. This mechanism realizes real-time optimization and adjustment of the imaging device by constructing a laser pulse energy density correction module, generating ultrasonic receiver sensitivity adjustment parameters, and establishing a phase synchronization compensation network between the laser pulse repetition frequency and the heart rate variability. Specifically, steps 1021 to 1024 are refined and optimized from different angles to adapt to individual patient differences and improve the image quality. In some embodiments, the dynamic regulation mechanism based on multi-channel spatio-temporal correlation data described in step 102 includes:

[0090] 1021. Generate blood flow oscillation entropy based on the phase delay spectrum of the blood pressure fluctuation range and the hemoglobin oxygen saturation in the multi-channel spatio-temporal correlation data, and input the blood flow oscillation entropy into the frequency domain convolution kernel to generate a pulse energy density correction coefficient. The bandwidth of the frequency domain convolution kernel is dynamically adjusted by the ratio of the fluctuation period of the hemoglobin oxygen saturation to the half-peak width of the blood pressure fluctuation range;

[0091] In step 1021, the phase delay spectrum describes the time delay relationship between the blood pressure fluctuation range and the hemoglobin oxygen saturation, and is used to capture the dynamic changes between the two.

[0092] The blood flow oscillation entropy is an index calculated based on the phase delay spectrum, reflecting the complexity and instability of the blood flow system.

[0093] The frequency-domain convolution kernel is a mathematical tool used to convert blood flow oscillation entropy into a pulse energy density correction coefficient. Its bandwidth is dynamically adjusted by the ratio of the fluctuation period of hemoglobin oxygen saturation to the full-width at half-maximum of the blood pressure fluctuation range.

[0094] In the embodiments of the present application, first, time series data of the blood pressure fluctuation range and hemoglobin oxygen saturation are extracted from multi-channel spatio-temporal correlation data. Specifically, a high-resolution photoacoustic imaging device is used to obtain the distribution of hemoglobin oxygen saturation, and a sensor is used to record the time series of the blood pressure fluctuation range. Then, the fast Fourier transform (FFT) is applied to convert these time series into the frequency domain to generate a phase delay spectrum. The phase delay spectrum reflects the relative changes of the blood pressure fluctuation range and hemoglobin oxygen saturation at different frequencies. Next, the sample entropy algorithm is used to calculate the blood flow oscillation entropy, which can measure the complexity and irregularity of the time series data. Based on the generated blood flow oscillation entropy, it is input into the frequency-domain convolution kernel to generate a pulse energy density correction coefficient. The bandwidth of the frequency-domain convolution kernel is dynamically adjusted by the ratio of the fluctuation period of hemoglobin oxygen saturation to the full-width at half-maximum of the blood pressure fluctuation range.

[0095] 1022. Extract the microvascular topological entanglement degree through the morphological skeleton of the microvascular density distribution, input the pain index level and the microvascular topological entanglement degree into a path tracing algorithm to generate a receiver sensitivity adjustment parameter, and the backtracking step size of the path tracing algorithm is determined by the spatial density gradient of the microvascular branch nodes;

[0096] In step 1022, the morphological skeleton of the microvascular density distribution is a simplified structure diagram extracted by performing morphological processing on the microvascular density distribution image, and is used to characterize the topological features of the microvasculature.

[0097] The microvascular topological entanglement degree is an index describing the complexity of microvascular branches, reflecting the connectivity and complexity of the microvascular network.

[0098] The path tracing algorithm is an algorithm used to generate an ultrasonic receiver sensitivity adjustment parameter, and its backtracking step size is determined by the spatial density gradient of the microvascular branch nodes.

[0099] In the embodiments of the present application, first, a morphological skeleton extraction algorithm is used to process the microvascular density distribution image to extract the microvascular topological structure. Specifically, the microvascular density distribution is segmented by the level set method or the watershed algorithm, and then the distance transform and thinning algorithm are applied to generate the morphological skeleton of the microvasculature. Then, graph theory methods (such as node degree, edge weight, etc.) are used to calculate the microvascular topological entanglement degree to quantify the complexity of the microvascular network. Then, combining the pain index level with the microvascular topological entanglement degree, the path tracing algorithm is input to generate the receiver sensitivity adjustment parameter. The backtracking step size of the path tracing algorithm is determined by the spatial density gradient of the microvascular branch nodes.

[0100] 1023. Perform chaotic phase modulation on the recurrence plot features of the heart rate variability and the laser pulse repetition frequency to generate a pulse synchronization compensation parameter carrying the chaotic characteristics of heart beats, where the recurrence plot features are based on the spectral gap between the Lyapunov exponent of the heart rate variability and the laser pulse repetition frequency;

[0101] In step 1023, the recurrence plot feature is a feature map generated based on the Lyapunov exponent of the heart rate variability, and is used to describe the chaotic characteristics of the heartbeat sequence.

[0102] The spectral gap refers to the difference between the laser pulse repetition frequency and the spectrum of the heart rate variability, and is used to determine the degree of chaotic phase modulation.

[0103] Chaotic phase modulation is a technique based on recurrence plot features and spectral gaps, and is used to generate a pulse synchronization compensation parameter carrying the chaotic characteristics of heart beats.

[0104] In the embodiments of the present application, first, recurrence plot features are extracted from the heart rate variability data. Specifically, the recurrence plot analysis method is used to calculate the time series data of the heart rate variability and generate the recurrence plot features. The recurrence plot features provide the non-linear dynamics information of the heart rate variability. Then, chaotic phase modulation is performed on the recurrence plot features and the laser pulse repetition frequency to generate a pulse synchronization compensation parameter carrying the chaotic characteristics of heart beats. The specific steps are as follows: calculate the Lyapunov exponent of the heart rate variability to evaluate the chaotic characteristics of the system; use spectral gap analysis to determine the optimal modulation point of the laser pulse repetition frequency. Based on these two inputs, phase modulation is performed through the chaotic synchronization technique to generate a pulse synchronization compensation parameter carrying the chaotic characteristics of heart beats. These parameters are used to optimize the synchronization control of the laser pulse to ensure synchronization with the heart rate variability.

[0105] 1024. Input the pulse energy density correction coefficient, the receiver sensitivity adjustment parameter, and the pulse synchronization compensation parameter into a multi-physics coupler to generate a collaborative regulation instruction set, and synchronously establish a phase synchronization compensation network between the laser pulse repetition frequency and the heart rate variability.

[0106] In step 1024, the multi-physics coupler is a device integrating multiple physical field effects, which is used to generate a collaborative regulation instruction set to achieve synchronous control of the laser pulse energy density correction coefficient, the receiver sensitivity adjustment parameter, and the pulse synchronization compensation parameter.

[0107] The collaborative regulation instruction set contains a set of all regulation parameters, which is used to guide the real-time adjustment of the imaging device.

[0108] In the embodiment of the present application, first, input the pulse energy density correction coefficient, the receiver sensitivity adjustment parameter, and the pulse synchronization compensation parameter into the multi-physics coupler. Specifically, use finite element analysis (FEA) or multi-physics simulation software (such as COMSOL Multiphysics) to simulate the interaction of each physical field in the photoacoustic imaging process. Then, generate a collaborative regulation instruction set based on the simulation results, which contains precise control instructions for each component of the photoacoustic imaging device, and is used to synchronously adjust the phase synchronization compensation network between the laser pulse repetition frequency and the heart rate variability. The specific steps are as follows: fuse the input parameters through a machine learning algorithm (such as support vector machines SVMs or neural networks NNs) to extract key features; generate a collaborative regulation instruction set to ensure the phase synchronization between the laser pulse repetition frequency and the heart rate variability. Finally, synchronously establish a phase synchronization compensation network between the laser pulse repetition frequency and the heart rate variability, and dynamically adjust the laser pulse repetition frequency according to the collaborative regulation instruction set by real-time monitoring of the heart rate variability data to ensure the phase synchronization between the two. This process improves the quality and accuracy of photoacoustic imaging and provides strong support for subsequent image analysis.

[0109] The following is a specific example:

[0110] Suppose a 52-year-old female patient is admitted to the emergency department due to a left breast mass with persistent pain. The doctor uses a photoacoustic imaging device (wavelength 850 nm, pulse frequency 4 kHz) to collect blood flow data in the breast area. Photoacoustic imaging shows that the blood flow velocity fluctuation range in the mass area is 2.8 - 4.5 mm / s, the hemoglobin oxygen saturation is 68% - 82% (88% - 93% in the surrounding normal tissue), and the microvessel density distribution is 20 - 2 vessels / mm 2。Synchronously monitor the emergency parameters of the patient: the blood pressure fluctuation range is from 98 / 62 mmHg to 132 / 88 mmHg (standard deviation 9.2 mmHg), the pain index level is 8 points (Visual Analogue Scale), and the heart rate variability (SDNN) is 28 ms (LF / HF ratio 0.5).

[0111] Through phase delay spectrum analysis, it is found that there is a significant time delay (about 2.5 seconds) between blood pressure fluctuation and oxygen saturation in the low-frequency band (0.05 - 0.15 Hz). Based on this, the blood flow oscillation entropy is calculated to be 0.47 (normal reference value < 0.3), triggering the dynamic expansion of the bandwidth of the frequency-domain convolution kernel to 1.8 times, and the generated pulse energy density correction coefficient increases from 2.8 J / cm 2 to 3.5 J / cm 2 。Meanwhile, morphological skeleton extraction shows that the microvascular topological entanglement degree is 0.45 (normal < 0.3). Combining with the pain index of 8 points, the backtracking step size of the path tracing algorithm is adjusted to 0.15 mm (determined by the microvascular branch density gradient of 0.18 / mm), and the sensitivity adjustment parameters of the ultrasonic receiver are generated (the central frequency is increased to 10 MHz, and the bandwidth is expanded by 90%). In addition, the recurrence plot features of heart rate variability (Lyapunov exponent 0.25, spectral gap 4.2 Hz) are modulated by chaotic phase, synchronizing the laser pulse repetition frequency from 4 kHz to 4.2 kHz that matches the cardiac phase, and controlling the delay error within 0.2 ms. Finally, the multi-physical field coupler integrates the above parameters to generate a collaborative regulation instruction set, optimizing the energy output, signal reception, and pulse synchronization of the photoacoustic imaging device in real time, and accurately capturing the mass boundary and abnormal blood flow area.

[0112] Through the design and implementation of steps 1021 to 1024, the accuracy and reliability of photoacoustic imaging technology in emergency data quality control analysis have been successfully improved. Specifically, step 1021 optimizes the energy output of the imaging device by dynamically adjusting the laser pulse energy density correction coefficient; step 1022 improves the imaging resolution by generating the sensitivity adjustment parameters of the ultrasonic receiver; step 1023 enhances the synchronization performance of the system through chaotic phase modulation technology; step 1024 realizes the overall optimization of the system by generating a collaborative regulation instruction set through the multi-physical field coupler.

[0113] To further improve the accuracy and reliability of emergency data quality control analysis, an emergency quality control score is generated based on the characteristics of the hyperperfusion core area, the transition zone, and the hypoperfusion marginal area, and the following method is adopted: a perfusion instability index is generated through a thermodynamic entropy change model, a pain resonance factor is generated using a phase vortex field, and a coupled oscillation spectrum is generated through a vascular oscillation coupler. Finally, these parameters are input into a multimodal resonator to generate an emergency quality control score and trigger the adaptive re-optimization of the scanning parameters. In some embodiments, the method for generating an emergency quality control score based on the characteristics of the hyperperfusion core area, the transition zone, and the hypoperfusion marginal area described in step 104 includes:

[0114] 1041. Input the area decay rate of the hyperperfusion core area and the time-varying differential operator of the blood pressure fluctuation range into the thermodynamic entropy change model to generate a perfusion instability index. The non-equilibrium state constraint condition of the thermodynamic entropy change model is determined by the included angle between the half-cycle amplitude of the blood pressure fluctuation range and the gradient direction of the area decay rate;

[0115] In step 1041, the time-varying differential operator is used to describe the time-varying relationship between the area decay rate of the hyperperfusion core area and the blood pressure fluctuation range.

[0116] The thermodynamic entropy change model is a mathematical model used to generate a perfusion instability index, reflecting the instability of the blood flow system. The non-equilibrium state constraint condition of this model is determined by the included angle between the half-cycle amplitude of the blood pressure fluctuation range and the gradient direction of the area decay rate.

[0117] The perfusion instability index is a quantitative indicator used to evaluate the stability of the blood flow system, especially the changes in the hyperperfusion core area.

[0118] In the embodiments of the present application, first, time-series data of the area attenuation rate of the hyperperfusion core region and the blood pressure fluctuation range are extracted from photoacoustic imaging data. Specifically, a convolutional neural network (CNNs) is used to segment the breast region of an image, identify the hyperperfusion core region, and calculate the rate of change of its area over time, that is, the area attenuation rate. At the same time, data on the blood pressure fluctuation range of a patient are obtained through a sensor, and wavelet transform is applied to perform time-frequency analysis on the data to capture its dynamic change characteristics. Next, the area attenuation rate and the result of the time-varying differential operator are input into a thermodynamic entropy change model. The thermodynamic entropy change model is used to quantify the non-equilibrium state characteristics of a system, and its non-equilibrium state constraint condition is determined by the included angle between the half-period amplitude of the blood pressure fluctuation range and the gradient direction of the area attenuation rate. Specifically, first, tensor analysis is used to calculate the half-period amplitude of the blood pressure fluctuation range, and principal component analysis (PCA) is used to determine the gradient direction of the area attenuation rate, and then the included angle between the two is calculated. In addition, an adaptive filter is used to further optimize the signal processing result. Based on the above inputs, the thermodynamic entropy change model generates a perfusion instability index, which reflects the stability of the hyperperfusion core region under physiological state changes.

[0119] 1042. Generate a pain resonance factor through the phase vortex field of the oxygen saturation dispersion in the three-dimensional space, where the topological structure of the phase vortex field is constructed by the spatio-temporal heterogeneity of the oxygen saturation dispersion and the overlapping region of the power spectrum of the pain index level;

[0120] In step 1042, the phase vortex field is a field structure that describes the topological structure of the oxygen saturation dispersion in the three-dimensional space and is used to generate a pain resonance factor. Its topological structure is constructed by the spatio-temporal heterogeneity of the oxygen saturation dispersion and the overlapping region of the power spectrum of the pain index level.

[0121] The pain resonance factor is a quantification index used to evaluate the pain degree and its impact on blood flow dynamics.

[0122] In the embodiments of the present application, first, the oxygen saturation dispersion in the transition band is extracted from photoacoustic imaging data. Specifically, the transition band region is identified through a local binary patterns (LBP) algorithm, and the spatial distribution and dispersion of the oxygen saturation are calculated. Then, a phase vortex field in the three-dimensional space is constructed. The phase vortex field is a field structure that describes complex spatio-temporal characteristics, and its topological structure is constructed by the spatio-temporal heterogeneity of the oxygen saturation dispersion and the overlapping region of the power spectrum of the pain index level.

[0123] The specific steps are as follows: First, calculate the spatio-temporal heterogeneity of the oxygen saturation dispersion using Multiscale Geometric Analysis (MGA); then, obtain the pain index level of the patient and transform it into the frequency domain through Short-Time Fourier Transform (STFT), and calculate its power spectrum. Next, use Support Vector Machines (SVMs) to find the overlapping region between the spatio-temporal heterogeneity of the oxygen saturation dispersion and the power spectrum of the pain index level, and construct the topological structure of the phase vortex field based on this. Based on the phase vortex field, generate a pain resonance factor, which is an index quantifying the impact of pain on hemodynamics. Specifically, by analyzing the topological structure of the phase vortex field, extract the key features therein (such as vortex intensity, direction, etc.) and transform them into the pain resonance factor.

[0124] 1043. Input the fluctuation amplitude of the microvascular density in the low perfusion marginal zone and the recurrence feature of the heart rate variability into a vascular oscillation coupler to generate a coupled oscillation spectrum carrying the heartbeat-blood flow interference feature, where the resonant cavity parameters of the vascular oscillation coupler are jointly modulated by the peak-valley difference of the fluctuation amplitude of the microvascular density and the fractal dimension of the heart rate variability;

[0125] In step 1043, the recurrence feature is a feature map generated based on the Lyapunov exponent of the heart rate variability, which is used to describe the chaotic characteristics of the heartbeat sequence.

[0126] The vascular oscillation coupler is a technique for generating a coupled oscillation spectrum carrying the heartbeat-blood flow interference feature. Its resonant cavity parameters are jointly modulated by the peak-valley difference of the fluctuation amplitude of the microvascular density and the fractal dimension of the heart rate variability.

[0127] In the embodiments of the present application, first, the fluctuation amplitude of the microvascular density in the low-perfusion marginal region and the recurrence features of the heart rate variability are extracted from the photoacoustic imaging data. Specifically, the low-perfusion marginal region is identified by the Superpixel Segmentation technique, and the fluctuation amplitude of the microvascular density is calculated. At the same time, the heart rate variability data of the patient is acquired by a sensor, and the empirical mode decomposition (EMD) is applied to extract its recurrence features. Next, the fluctuation amplitude of the microvascular density and the recurrence features of the heart rate variability are input into the vascular oscillation coupler. The vascular oscillation coupler is used to simulate and analyze the interaction between vascular oscillation and heart rate variability. The specific steps are as follows: The peak-valley difference of the fluctuation amplitude of the microvascular density is calculated using the multifractal analysis (MFA), and the fractal dimension of the heart rate variability is extracted by the recurrence plot analysis method (RPA). These parameters jointly modulate the resonant cavity parameters of the vascular oscillation coupler. In addition, the genetic algorithm (GA) is used to optimize the parameters of the coupler. Based on the above inputs, the vascular oscillation coupler generates a coupled oscillation spectrum carrying the heartbeat-blood flow interference features. The coupled oscillation spectrum describes the interaction pattern between cardiac pulsation and blood flow fluctuations. Specifically, the coupled oscillation spectrum is generated by simulating the interference effects of cardiac pulsation and blood flow fluctuations at different frequencies.

[0128] 1044. Input the perfusion instability index, the pain resonance factor, and the coupled oscillation spectrum into the multimodal resonator to generate an emergency quality control score, and trigger the adaptive re-optimization of the scanning parameters through a closed-loop feedback channel, and update the laser pulse energy density correction module and the phase synchronization compensation network.

[0129] In step 1044, the multimodal resonator is a device integrating multiple physical field effects, used to generate an emergency quality control score, and trigger the adaptive re-optimization of the scanning parameters through a closed-loop feedback channel.

[0130] The closed-loop feedback channel is a real-time adjustment mechanism used to update the laser pulse energy density correction module and the phase synchronization compensation network.

[0131] In the embodiments of the present application, first, the perfusion instability index, pain resonance factor, and coupled oscillation spectrum are input into a multimodal resonator. The multimodal resonator is used to integrate multiple physiological signals and generate a comprehensive evaluation result. Specifically, the input data is fused through the Random Forests (RF) algorithm to extract key features and generate an emergency quality control score. The emergency quality control score reflects the overall severity of the patient's condition and helps doctors make accurate diagnostic and treatment decisions. Next, the adaptive re-optimization of the scanning parameters is triggered through a closed-loop feedback channel. The specific steps are as follows: According to the emergency quality control score, it is judged whether the current imaging quality meets the requirements. If the score is lower than the preset threshold, the adaptive re-optimization mechanism is triggered. This mechanism improves the imaging quality by adjusting the scanning parameters of the photoacoustic imaging device (such as laser pulse energy, repetition frequency, etc.); the Particle Swarm Optimization (PSO) algorithm is used for parameter optimization. Finally, the laser pulse energy density correction module and the phase synchronization compensation network are updated. Specifically, based on the new scanning parameters, the output parameters of the correction module are recalculated, and the settings of the phase synchronization compensation network are adjusted.

[0132] The following is a specific example:

[0133] Suppose a 45-year-old female patient presents with a breast mass. The photoacoustic / ultrasound (PA / US) imaging system shows that the area of the hyperperfusion core region in her left breast is 8.5 mm 2 , and the photoacoustic blood flow parameters show that the oxygen saturation (SO2) in this area is 72%, significantly lower than 85% in the surrounding normal tissue, indicating local hypoxia. After segmentation by a convolutional neural network, the area attenuation rate is calculated to be 0.6 mm 2 / s, and the half-cycle amplitude of blood pressure fluctuation is 18 mmHg. The included angle between the gradient directions of the two is 52°. After input into the thermodynamic entropy change model based on Prigogine's dissipative structure, a perfusion instability index of 0.68 is generated (threshold <0.5 indicates instability), indicating a significant decrease in hemodynamic stability.

[0134] The spatial-temporal heterogeneity index of the oxygen saturation dispersion in the transition zone is 3.2 as shown by three-dimensional phase vortex field analysis. The overlapping ratio of the pain index power spectrum in the frequency band of 0.8 - 1.5 Hz and the oxygen saturation spectrum reaches 58%. The topological defect density of the constructed vortex field is 2.1 rad / mm 2 , generating a pain resonance factor of 1.3 (threshold >1.0 indicates significance), suggesting a strong correlation between pain and microcirculation disorders. The fluctuation amplitude of the microvascular density in the low-perfusion marginal zone is 12 vessels / mm 2, the fractal dimension of heart rate variability is 1.6. A coupled oscillation spectrum is generated by a vascular oscillation coupler, and the amplitude attenuation rate of the heartbeat-blood flow interference is -6 dB / Hz in the 0.2 Hz frequency band, reflecting the desynchronization between autonomic regulation and microvascular oscillation.

[0135] After the above parameters are input into the multimodal resonator, the emergency quality control score is 7.2 / 10, triggering the closed-loop feedback channel to increase the laser pulse energy density from 45 mJ / cm 2 to 58 mJ / cm 2 , and adjusting the delay threshold of the phase synchronization compensation network to 12 ms, increasing the imaging signal-to-noise ratio by 35%.

[0136] Through the design and implementation of steps 1041 to 1044, the accuracy and reliability of emergency data quality control analysis have been successfully improved. Specifically, step 1041 accurately reflects the change in blood flow state in the hyperperfusion core area by generating a perfusion instability index; step 1042 evaluates the impact of pain on blood flow dynamics by generating a pain resonance factor; step 1043 captures the interaction between the heartbeat and blood flow by generating a coupled oscillation spectrum; step 1044 ensures the optimal performance of the entire imaging system by generating an emergency quality control score and triggering adaptive re-optimization. These improvements not only improve the diagnostic accuracy but also provide strong support for personalized treatment. At the same time, this mechanism demonstrates its wide applicability and strong expansion ability.

[0137] To further improve the accuracy and reliability of emergency data quality control analysis, especially for the interaction between the microvascular density fluctuation amplitude in the hypoperfusion marginal area and heart rate variability, a method based on a time window function, fractal dimension slicing, and phase entanglement state is used to generate a coupled oscillation spectrum carrying heartbeat-blood flow interference characteristics. This method dynamically adjusts the sliding step of the time window function and combines the fractal tuning factor and phase entanglement state to ensure that the generated coupled oscillation spectrum can accurately reflect the complex relationship between the heartbeat and blood flow. In some embodiments, the method for generating a coupled oscillation spectrum based on the recursive characteristics of the microvascular density fluctuation amplitude in the hypoperfusion marginal area and heart rate variability described in step 1043 includes:

[0138] 201. Set a time window function for the microvascular density fluctuation amplitude in the hypoperfusion marginal area, and perform fractal dimension slicing on the time window function and the recursive characteristics of the heart rate variability to generate the fundamental frequency of vascular wall oscillation. The sliding step of the time window function is dynamically adjusted by the peak-valley difference of the microvascular density fluctuation amplitude;

[0139] In step 201, the time window function is a time window for localizing the microvascular density fluctuation amplitude in the hypoperfusion marginal area.

[0140] The fractal dimension slice performs fractal dimension analysis on the time window function and the recurrence features of heart rate variability to generate the fundamental frequency of vascular wall oscillation. The sliding step of the time window function is dynamically adjusted by the peak-valley difference of the microvascular density fluctuation amplitude.

[0141] In the embodiments of the present application, first, a time window function is set for the microvascular density fluctuation amplitude in the low perfusion marginal area. Specifically, the sliding window technique is used to segment the time series data of the microvascular density fluctuation amplitude. In order to dynamically adjust the sliding step of the time window function, an adaptive filter is used to calculate the peak-valley difference of the microvascular density fluctuation amplitude, and the sliding step is adjusted according to this difference. Then, the time window function is combined with the recurrence features of heart rate variability to generate a fractal dimension slice. The specific steps are as follows: First, the recurrence features of the time series data of heart rate variability are extracted using the recurrence plot analysis method (RPA); then, multifractal analysis (MFA) is applied to perform fractal dimension slicing on these features. Based on the above input, the fundamental frequency of vascular wall oscillation is generated. This fundamental frequency describes the basic vibration frequency of the vascular wall under the action of cardiac pulsation. In addition, locally linear embedding (LLE) is used to further optimize the signal processing results to ensure the accuracy of the fundamental frequency.

[0142] 202. Generate oscillation cavity harmonic parameters through the fundamental frequency of vascular wall oscillation and the fractal tuning factor of heart rate variability, where the fractal tuning factor is calculated from the projected area of the fractal dimension slice in the time-frequency plane and the time window statistic of the microvascular density fluctuation amplitude;

[0143] In step 202, the fractal tuning factor is a parameter calculated from the projected area of the fractal dimension slice in the time-frequency plane and the time window statistic of the microvascular density fluctuation amplitude, and is used to generate oscillation cavity harmonic parameters.

[0144] The oscillation cavity harmonic parameters describe the interaction between the fundamental frequency of vascular wall oscillation and heart rate variability, and generate a signal with specific frequency characteristics.

[0145] In the embodiments of the present application, first, oscillation cavity harmonic parameters are generated based on the generated fundamental frequency of vascular wall oscillation and the fractal tuning factor of heart rate variability. Specifically, the Hilbert-Huang Transform (HHT) is used to perform multi-scale analysis on the fundamental frequency of vascular wall oscillation to extract its variation characteristics at different time and frequency scales. At the same time, a fractal tuning factor is generated by calculating the projection area of the fractal dimension slice on the time-frequency plane and the time-window statistic of the microvascular density fluctuation amplitude. The specific steps are as follows: First, the Fast Fourier Transform (FFT) is used to calculate the projection area of the fractal dimension slice on the time-frequency plane; then, the sliding window technique is used to calculate the time-window statistics (such as mean, variance, etc.) of the microvascular density fluctuation amplitude. Next, an energy field analysis method (EFA) is used to combine these two parameters to generate a fractal tuning factor. Based on the above input, oscillation cavity harmonic parameters are generated, which describe the dynamic process of internal energy conversion in the system. In addition, the particle swarm optimization algorithm (PSO) is used to optimize the harmonic parameters to ensure their accuracy.

[0146] 203. Input the oscillation cavity harmonic parameters into a blood flow interference phase detector to generate heartbeat-blood flow interference fringes, and the phase entanglement state of the interference fringes is determined by the energy ratio relationship between the time-window statistic of the microvascular density fluctuation amplitude and the fractal tuning factor;

[0147] In step 203, the phase entanglement state of the interference fringes is a state determined by the energy ratio relationship between the time-window statistic of the microvascular density fluctuation amplitude and the fractal tuning factor, and is used to generate heartbeat-blood flow interference fringes.

[0148] The blood flow interference phase detector is a device for generating heartbeat-blood flow interference fringes, and its output signal reflects the interference pattern between the heartbeat and the blood flow.

[0149] In the embodiments of the present application, first, the harmonic parameters of the oscillation cavity are input into the blood flow interference phase detector to generate heartbeat-blood flow interference fringes. Specifically, the coherent detection technique is used to simulate the interference effect between the cardiac pulsation and the blood flow fluctuation to generate interference fringes. The phase entanglement state of the interference fringes is determined by the energy ratio relationship between the time-window statistic of the microvascular density fluctuation amplitude and the fractal tuning factor. The specific steps are as follows: First, the mutual information (MI) is used to calculate the energy ratio relationship between the time-window statistic of the microvascular density fluctuation amplitude and the fractal tuning factor; then, based on this ratio relationship, the phase entanglement state of the interference fringes is generated through a random walk model. Based on the above input, the heartbeat-blood flow interference fringes are generated, which describe the interaction mode between the cardiac pulsation and the blood flow fluctuation. In addition, the graph neural networks (GNNs) are used to further optimize the generation process of the interference fringes to ensure its accuracy.

[0150] 204. Generate dynamic impedance parameters based on the phase entanglement state of the interference fringes, and input the time-window function and the recursive features of the heart rate variability into the vascular oscillation coupler to generate a coupled oscillation spectrum carrying heartbeat-blood flow interference features. The resonant cavity parameters of the vascular oscillation coupler are jointly modulated by the peak-valley difference of the microvascular density fluctuation amplitude and the fractal dimension of the heart rate variability.

[0151] In step 204, the dynamic impedance parameter is a parameter generated based on the phase entanglement state of the interference fringes and is used to describe the dynamic characteristics of the system.

[0152] The vascular oscillation coupler is a device integrating multiple physical field effects and is used to generate a coupled oscillation spectrum carrying heartbeat-blood flow interference features. Its resonant cavity parameters are jointly modulated by the peak-valley difference of the microvascular density fluctuation amplitude and the fractal dimension of the heart rate variability.

[0153] In the embodiments of the present application, first, dynamic impedance parameters are generated based on the phase entanglement state of interference fringes. Specifically, impedance spectroscopy analysis (ISA) is used to perform frequency-domain analysis on the phase entanglement state of interference fringes, extract key features therein (such as impedance values, frequency responses, etc.), and generate dynamic impedance parameters. Then, in combination with the time window function and the recursive features of heart rate variability, they are input into a vascular oscillation coupler to generate a coupled oscillation spectrum carrying the heartbeat-blood flow interference feature. The specific steps are as follows: First, a convolutional neural network (CNNs) is used to fuse the time window function and the recursive features of heart rate variability; then, based on the fused features, a coupled oscillation spectrum is generated using multifractal analysis (MFA) and recurrence plot analysis (RPA). The resonant cavity parameters of the vascular oscillation coupler are jointly modulated by the peak-to-valley difference in the amplitude of microvascular density fluctuations and the fractal dimension of heart rate variability. In addition, a genetic algorithm (GA) is used to optimize the coupled oscillation spectrum to ensure its accuracy.

[0154] The following is a specific example:

[0155] Suppose a breast tumor patient undergoes photoacoustic blood flow imaging monitoring, and the peak-to-valley difference in the amplitude of microvascular density fluctuations in the low-perfusion marginal area is 12 vessels / mm after being segmented by the sliding window technique 2 , and the adaptive filter dynamically adjusts the time window sliding step to 0.8 seconds. The deterministic (DET) index of 0.75 is extracted from the recursive features of heart rate variability through recurrence plot analysis, and the multifractal spectrum width Δα = 1.2 is shown in the fractal dimension slice, generating a fundamental frequency of vascular wall oscillation of 0.25 Hz.

[0156] The fractal tuning factor is obtained through the time-frequency projection area (8.6 mm 2 ·Hz) and the mean value of the time window statistic (10.3 vessels / mm 2)Calculated to be 1.45, combined with the proportion of the fundamental frequency multi-scale energy extracted by the Hilbert-Huang transform (65% in the low-frequency band), the harmonic parameter Q factor of the oscillation cavity is generated as 15.6. The blood flow interference phase detector generates a phase entanglement state based on the energy ratio (time window variance / fractal tuning factor = 0.92), and the interference fringes exhibit an amplitude modulation depth of -5 dB in the 0.2 Hz frequency band, with a fringe spacing of 3.2 mm. The dynamic impedance parameter extracts a frequency response slope of -0.8 dB / Hz through impedance spectrum analysis, and the vascular oscillation coupler combines the fractal dimension (D = 1.6) and the peak-valley difference to generate a coupled oscillation spectrum, showing that the energy concentration of heart beat-blood flow interference reaches 82% in the 0.1 - 0.3 Hz frequency band. Finally, through the optimization of the resonator parameters (frequency matching error < 0.01 Hz), a coupled oscillation spectrum with high confidence is output.

[0157] Through the design and implementation of steps 201 to 204, the accuracy and reliability of the emergency data quality control analysis for breast disease patients based on photoacoustic blood flow imaging technology have been successfully improved. Specifically, step 201 accurately reflects the changes in microvascular density fluctuations by generating the fundamental frequency of vascular wall oscillations; step 202 captures the interaction between heart rate variability and microvascular density fluctuations by generating the harmonic parameters of the oscillation cavity; step 203 reflects the interference pattern between the heart beat and blood flow by generating heart beat-blood flow interference fringes; step 204 ensures the optimal performance of the entire imaging system by generating a coupled oscillation spectrum.

[0158] In order to further improve the accuracy and reliability of the emergency data quality control analysis for breast disease patients based on photoacoustic blood flow imaging, especially for the interaction between heart rate variability and microvascular density fluctuations, a method based on fractal dimension slicing, multi-dimensional fractal topology network, and harmonic phase group is adopted to generate the harmonic parameters of the oscillation cavity. This method generates a multi-dimensional fractal topology network through time-frequency plane projection, and combines the node energy distribution to generate a fractal tuning factor, and finally generates the harmonic parameters of the oscillation cavity carrying the heart beat-blood flow interference characteristics. In some embodiments, the method for generating the harmonic parameters of the oscillation cavity based on the fractal tuning factor of the fundamental frequency of vascular wall oscillations and heart rate variability described in step 202 includes:

[0159] 301. Perform a time-frequency plane projection on the fractal dimension slice to generate a multi-dimensional fractal topology network, and the grid density of the multi-dimensional fractal topology network is jointly controlled by the time window statistic of the microvascular density fluctuation amplitude and the spatio-temporal gradient of the projection area;

[0160] In step 301, the fractal dimension slice is a data segment generated by performing fractal dimension analysis on the time window function and the recursive characteristics of heart rate variability.

[0161] The multi-dimensional fractal topology network is a network structure generated by performing time-frequency plane projection on fractal dimension slices, and its grid density is jointly controlled by the time-window statistic of the microvascular density fluctuation amplitude and the spatio-temporal gradient of the projection area.

[0162] In the embodiments of the present application, first, a multi-dimensional fractal topology network is generated by performing time-frequency plane projection on fractal dimension slices. Specifically, the short-time Fourier transform (STFT) is used to transform the fractal dimension slices from the time domain to the time-frequency plane, and a multi-dimensional fractal topology network is generated. The grid density of the multi-dimensional fractal topology network is jointly controlled by the time-window statistic of the microvascular density fluctuation amplitude and the spatio-temporal gradient of the projection area. The specific steps are as follows: The time-window statistic of the microvascular density fluctuation amplitude is calculated using empirical mode decomposition (EMD); the spatio-temporal gradient of the projection area is calculated through spatial gradient analysis (SGA). These two parameters jointly adjust the grid density of the multi-dimensional fractal topology network. In addition, an adaptive filter is used to further optimize the signal processing result to ensure the accuracy of the grid density.

[0163] 302. Generate a fractal tuning factor through the node energy distribution of the multi-dimensional fractal topology network, where the fractal tuning factor is calculated from the projection area of the fractal dimension slice on the time-frequency plane and the time-window statistic of the microvascular density fluctuation amplitude;

[0164] In step 302, the fractal tuning factor is a parameter calculated from the projection area of the fractal dimension slice on the time-frequency plane and the time-window statistic of the microvascular density fluctuation amplitude, and is used to generate the harmonic parameters of the oscillation cavity.

[0165] The node energy distribution describes the energy distribution of each node in the multi-dimensional fractal topology network.

[0166] In the embodiments of the present application, first, a fractal tuning factor is generated based on the node energy distribution of the generated multi-dimensional fractal topology network. Specifically, the Laplacian Matrix in graph theory is used to calculate the energy gradient field of adjacent nodes in the multi-dimensional fractal topology network, and the node energy distribution characteristics are extracted. Then, the projection area of the fractal dimension slice on the time-frequency plane is calculated by the Fast Fourier Transform (FFT), and the fractal tuning factor is generated in combination with the time-window statistic of the microvascular density fluctuation amplitude. The specific steps are as follows: The relationship between the projection area of the fractal dimension slice on the time-frequency plane and the time-window statistic of the microvascular density fluctuation amplitude is calculated using mutual information (MI); Based on this relationship, the fractal tuning factor is generated by the non-linear regression (NR) algorithm. Based on the above input, the fractal tuning factor is generated, which describes the dynamic process of internal energy conversion in the system. In addition, support vector machines (SVMs) are used to further optimize the generation process of the fractal tuning factor to ensure its accuracy.

[0167] 303. Input the fractal tuning factor into the oscillation cavity energy converter to generate a harmonic phase group, and the tunneling path of the harmonic phase group is jointly constrained by the energy distribution gradient of the fractal tuning factor and the recursive feature map of the heart rate variability;

[0168] In step 303, the harmonic phase group is a description of the group characteristics of harmonic signals and is generated by inputting the fractal tuning factor into the oscillation cavity energy converter.

[0169] The tunneling path is a description of the propagation path of the harmonic phase group in the frequency space and is jointly constrained by the energy distribution gradient of the fractal tuning factor and the recursive feature map of the heart rate variability.

[0170] In the embodiments of the present application, first, the fractal tuning factor is input into the oscillating cavity energy converter to generate a harmonic phase group. Specifically, the chaotic dynamics analysis (CDA) is used to simulate the energy distribution gradient of the fractal tuning factor and generate a harmonic phase group. The tunneling path of the harmonic phase group is jointly constrained by the energy distribution gradient of the fractal tuning factor and the recurrence feature map of heart rate variability. The specific steps are as follows: the recurrence feature map of the time series data of heart rate variability is extracted using the recurrence plot analysis (RPA); the harmonic phase group is generated by combining these two parameters through the energy field analysis (EFA). Based on the above input, a harmonic phase group is generated, which describes the complex dynamic pattern of the internal energy conversion of the system. In addition, the particle swarm optimization (PSO) algorithm is used to optimize the harmonic phase group to ensure its accuracy.

[0171] 304. Combine the fundamental frequency of the vascular wall oscillation, and generate the oscillating cavity harmonic parameters through the tunneling path of the harmonic phase group. The oscillating cavity harmonic parameters synchronously correct the time-frequency distortion compensation amount of the frequency-domain convolution kernel and update the Lyapunov constraint condition of the recurrence graph topology through the waveguide coupling effect.

[0172] In step 304, the oscillating cavity harmonic parameters are parameters generated based on the tunneling path of the harmonic phase group, and are used to describe the dynamic characteristics of the system.

[0173] The waveguide coupling effect is a method for synchronously correcting the time-frequency distortion compensation amount of the frequency-domain convolution kernel and updating the Lyapunov constraint condition of the recurrence graph topology.

[0174] In the embodiments of the present application, combined with the fundamental frequency of the vascular wall oscillation, the oscillating cavity harmonic parameters are generated through the tunneling path of the harmonic phase group. Specifically, the waveguide coupling effect (WCE) is used to synchronously correct the time-frequency distortion compensation amount of the frequency-domain convolution kernel and update the Lyapunov constraint condition of the recurrence graph topology. First, the fundamental frequency of the vascular wall oscillation is calculated using the wavelet transform (WT); then, the oscillating cavity harmonic parameters are generated by combining the waveguide coupling effect with the tunneling path of the harmonic phase group. Next, the Lyapunov exponent (LE) analysis is used to update the Lyapunov constraint condition of the recurrence graph topology. Based on the above input, the oscillating cavity harmonic parameters are generated.

[0175] The following is a specific example:

[0176] Suppose a patient with a breast mass undergoes photoacoustic blood flow imaging. After processing by the sliding window technique, the peak-to-valley difference in the microvascular density fluctuation amplitude in the hypoperfused marginal area is 15 vessels / mm 2 , and the mean value of the time window statistic is 12.3 vessels / mm 2 . The fractal dimension slice is projected onto the time-frequency plane through short-time Fourier transform, and the spatio-temporal gradient of the generated multi-dimensional fractal topology network is 0.8 mm 2 / s 2 , and the grid density is dynamically adjusted to 5.2 cells / mm 2 . The node energy distribution calculated by the Laplacian matrix shows that the energy gradient in the core area is 3.5 dB / mm. Combining the mutual information correlation degree of 0.92 between the projected area (8.2 mm 2 ·Hz) and the time window statistic, a fractal tuning factor of 1.45 is generated. The main frequency of the tunneling path extracted from the harmonic phase group through chaotic dynamics analysis is 0.18 Hz, and the amplitude modulation depth is -4 dB. Under the joint constraint with the recurrence characteristic map of heart rate variability (deterministic index DET = 0.78), the time-frequency distortion compensation amount of the frequency-domain convolution kernel is 0.03 ms / Hz. The fundamental frequency of the blood vessel wall oscillation is 0.25 Hz, which synchronously corrects the compensation amount through the waveguide coupling effect. The updated Lyapunov constraint condition (exponent λ = 0.12) optimizes the Q factor of the resonant cavity to 18.6, and finally the energy concentration of the oscillation cavity harmonic parameters in the 0.15 - 0.3 Hz frequency band reaches 85%.

[0177] Through the design and implementation of steps 301 to 304, the accuracy and reliability of the emergency data quality control analysis for breast disease patients based on photoacoustic blood flow imaging technology have been successfully improved. Specifically, step 301 accurately reflects the changes in microvascular density fluctuations by generating a multi-dimensional fractal topology network; step 302 captures the interaction between heart rate variability and microvascular density fluctuations by generating a fractal tuning factor; step 303 reflects the complex relationship between heart beats and blood flow by generating a harmonic phase group; step 304 ensures the optimal performance of the entire imaging system by generating oscillation cavity harmonic parameters.

[0178] In order to further improve the accuracy and reliability of the emergency data quality control analysis for breast disease patients based on photoacoustic blood flow imaging, especially for the interaction between heart rate variability and microvascular density fluctuations, a method based on multi-dimensional fractal topology network, phase winding coefficient and vortex energy flow is used to generate a fractal tuning factor. This method extracts the phase winding coefficient and combines the vortex energy flow to generate a fractal tuning factor carrying the quantum tunneling effect, and finally generates topological entanglement parameters to synchronously adjust the time-frequency distortion compensation amount of the frequency-domain convolution kernel. In some embodiments, the method for generating a fractal tuning factor based on the node energy distribution of the multi-dimensional fractal topology network described in step 302 includes:

[0179] 401. Extract the phase-wrapping coefficient from the node energy distribution of the multi-fractal topological network. The phase-wrapping coefficient is generated by the spatio-temporal interference effect between the projected area of the fractal dimension slice on the time-frequency plane and the time-window statistic of the microvascular density fluctuation amplitude.

[0180] In step 401, the phase-wrapping coefficient is a parameter generated by the spatio-temporal interference effect between the projected area of the fractal dimension slice on the time-frequency plane and the time-window statistic of the microvascular density fluctuation amplitude.

[0181] The multi-fractal topological network is a network structure generated by projecting the fractal dimension slice onto the time-frequency plane.

[0182] In the embodiment of the present application, first, extract the phase-wrapping coefficient from the node energy distribution of the multi-fractal topological network. Specifically, use Graph Neural Networks (GNNs) to analyze the energy distribution of adjacent nodes in the multi-fractal topological network and extract the phase-wrapping coefficient. The phase-wrapping coefficient is generated by the spatio-temporal interference effect between the projected area of the fractal dimension slice on the time-frequency plane and the time-window statistic of the microvascular density fluctuation amplitude. The specific steps are as follows: First, use the Wavelet Packet Transform (WPT) to calculate the projected area of the fractal dimension slice on the time-frequency plane; then, calculate the spatio-temporal interference effect of the time-window statistic of the microvascular density fluctuation amplitude through Cross-Correlation Analysis (CCA). These two parameters jointly generate the phase-wrapping coefficient. In addition, use Bayesian Optimization (BO) to further optimize the signal processing result to ensure the accuracy of the phase-wrapping coefficient.

[0183] 402. Generate the vortex energy flow through the phase-wrapping coefficient and the time-frequency distortion rate of the vascular wall oscillation fundamental frequency. The precession angle of the vortex energy flow is jointly determined by the energy gradient field of adjacent nodes in the multi-fractal topological network and the power spectrum offset of the time-window statistic.

[0184] In step 402, the vortex energy flow is a signal describing the energy flow characteristics, which is generated by the phase-wrapping coefficient and the time-frequency distortion rate of the vascular wall oscillation fundamental frequency.

[0185] The precession angle is the rotation angle of the vortex energy flow in the frequency space, which is jointly determined by the energy gradient field of adjacent nodes in the multi-fractal topological network and the power spectrum offset of the time-window statistic.

[0186] In the embodiments of the present application, first, a vortex energy flow is generated based on the generated phase winding coefficient and the time-frequency distortion rate of the fundamental frequency of the blood vessel wall oscillation. Specifically, the Hilbert Transform (HT) is used to simulate the dynamic relationship between the phase winding coefficient and the time-frequency distortion rate, and generate the vortex energy flow. The precession angle of the vortex energy flow is jointly determined by the energy gradient field of adjacent nodes in the multi-fractal topological network and the power spectrum offset of the time window statistic. The specific steps are as follows: First, the Discrete Cosine Transform (DCT) is used to calculate the energy gradient field of adjacent nodes in the multi-fractal topological network; then, the Fast Fourier Transform (FFT) is used to calculate the power spectrum offset of the time window statistic. These two parameters jointly determine the precession angle of the vortex energy flow. Based on the above input, the vortex energy flow is generated, which describes the complex dynamic pattern of the internal energy conversion of the system.

[0187] 403. Input the vortex energy flow into a fractal tuning field generator to generate a fractal tuning factor carrying the quantum tunneling effect. The constraint condition of the fractal tuning field generator is constructed from the overlapping region of the precession angle of the vortex energy flow and the recurrence feature map of the heart rate variability.

[0188] In step 403, the fractal tuning field generator is a device for generating a fractal tuning factor carrying the quantum tunneling effect, and its constraint condition is constructed from the overlapping region of the precession angle of the vortex energy flow and the recurrence feature map of the heart rate variability.

[0189] The quantum tunneling effect is a phenomenon describing the penetration of energy through a potential barrier and is used to generate the fractal tuning factor.

[0190] In the embodiments of the present application, first, the vortex energy flow is input into a fractal tuning field generator to generate a fractal tuning factor carrying the quantum tunneling effect. Specifically, the Quantum Monte Carlo method (QMC) is used to simulate the energy distribution gradient of the vortex energy flow and generate the fractal tuning factor. The constraint condition of the fractal tuning field generator is constructed from the overlapping region of the precession angle of the vortex energy flow and the recurrence feature map of the heart rate variability. The specific steps are as follows: First, the recurrence feature map of the time series data of the heart rate variability is extracted using the Recurrence Plot Analysis (RPA); then, the fractal tuning factor is generated by combining these two parameters through the Overlap Region Analysis (ORA). Based on the above input, the fractal tuning factor carrying the quantum tunneling effect is generated, which describes the fine adjustment process of the internal energy conversion of the system.

[0191] 404. Generate topological entanglement parameters based on the quantum tunneling path density of the fractal tuning factor with quantum tunneling effect. The topological entanglement parameters synchronously adjust the time-frequency distortion compensation amount gradient of the frequency-domain convolution kernel through a nonlinear resonance mechanism and reconstruct the energy threshold of the Lyapunov constraint condition.

[0192] In step 404, the topological entanglement parameter is a parameter generated based on the quantum tunneling path density of the fractal tuning factor with quantum tunneling effect, and is used to describe the nonlinear resonance mechanism of the system.

[0193] The Lyapunov constraint condition is a mathematical model describing the stability of the system, which synchronously adjusts the time-frequency distortion compensation amount gradient of the frequency-domain convolution kernel through a nonlinear resonance mechanism and reconstructs the energy threshold.

[0194] In the embodiment of the present application, first, generate topological entanglement parameters based on the quantum tunneling path density of the fractal tuning factor with quantum tunneling effect. Specifically, use Nonlinear Dynamics Analysis (NDA) to synchronously adjust the time-frequency distortion compensation amount gradient of the frequency-domain convolution kernel, and reconstruct the energy threshold of the Lyapunov constraint condition. The specific steps are as follows: First, calculate the quantum tunneling path density using Continuous Wavelet Transform (CWT); then, generate topological entanglement parameters by combining these parameters through the Nonlinear Resonance Mechanism (NRM). Next, use Lyapunov Exponent (LE) analysis to update the Lyapunov constraint condition of the recurrence plot topology. Based on the above input, generate topological entanglement parameters, which describe the fine adjustment process of the internal energy conversion of the system. In addition, use the Simulated Annealing (SA) algorithm to optimize the topological entanglement parameters to ensure their accuracy.

[0195] The following is a specific example:

[0196] Suppose a breast mass patient undergoes photoacoustic / ultrasound (PA / US) imaging examination, and the time-frequency projection area calculated by wavelet packet transform for the node energy distribution in its multi-dimensional fractal topology network is 6.8 mm 2 ·Hz, and the peak-valley difference of the time-window statistic of the microvascular density fluctuation amplitude is 14 vessels / mm 2, the spatio-temporal interference effect generates a phase-wrapping coefficient of 0.78 through cross-correlation analysis. The time-frequency distortion rate (distortion amplitude -3.2 dB / Hz) of the fundamental frequency of blood vessel wall oscillation at 0.28 Hz is coupled with the phase-wrapping coefficient through Hilbert transform to generate a main frequency of vortex energy flow at 0.15 Hz, and a precession angle of 52° (determined jointly by the energy gradient field of adjacent nodes of 4.5 dB / mm extracted by discrete cosine transform and the power spectrum offset of 0.4 Hz). After the vortex energy flow is input into the fractal tuning field generator, the overlapping area (area ratio 38%) of the precession angle and the recursive characteristic spectrum of heart rate variability (deterministic index DET = 0.81) is simulated by the quantum Monte Carlo method to generate a fractal tuning factor carrying the quantum tunneling effect, and the tunneling path density is calculated to be 2.3 paths / mm by continuous wavelet transform 2 . Finally, the topological entanglement parameter is generated based on the quantum tunneling path density of the fractal tuning factor carrying the quantum tunneling effect

[0197] Through the design and implementation of steps 401 to 404, significant improvements have been achieved in the quality control analysis of emergency data of breast disease patients based on photoacoustic blood flow imaging technology. By extracting the phase-wrapping coefficient from the node energy distribution of the multi-dimensional fractal topology network, the changes in microvascular density fluctuations and their spatio-temporal interference effect with heart rate variability can be captured more accurately; by calculating the vortex energy flow and determining its precession angle, multiple precession angle parameters are generated, which help to analyze the interference pattern between heartbeat and blood flow more accurately and improve the accuracy of imaging evaluation; by generating the fractal tuning factor, it helps to capture the complex relationship between heartbeat and blood flow more accurately and further improves the reliability of imaging evaluation; by generating the topological entanglement parameter, it helps to analyze the physiological state of the patient more accurately

[0198] In order to further improve the accuracy and reliability of the quality control analysis of emergency data of breast disease patients based on photoacoustic blood flow imaging, especially for the spatial distribution and dynamic changes of the blood flow velocity gradient mutation points, a method based on spatio-temporal phase singularity map, metabolic vortex field and quantization energy level transition is adopted to generate real-time three-dimensional photoacoustic blood flow dynamic images. This method extracts spatio-temporal phase singularities, constructs a metabolic vortex field, and combines the quantization energy level transition of the microvascular density fluctuation amplitude and the interference effect of the hemoglobin oxygen saturation dispersion to finally generate a dynamic topological reconstruction instruction to correct the distribution of the blood flow velocity gradient extreme points of the three-dimensional dynamic image. In some embodiments, the method of generating real-time three-dimensional photoacoustic blood flow dynamic images described in step 103 and dividing the difference region into a high-perfusion core area, a transition zone and a low-perfusion edge area based on the spatial distribution of blood flow velocity gradient mutation points includes:

[0199] 1031. Extract spatiotemporal phase singularities at the blood flow velocity gradient mutation points to generate a phase singularity map, where the phase singularity map is topologically wound by the Lorentz divergence of the blood flow velocity gradient mutation points and the time-varying characteristics of the microvascular density fluctuation amplitude;

[0200] In step 1031, the spatiotemporal phase singularity map is a map generated by topologically winding the Lorentz divergence of the blood flow velocity gradient mutation points and the time-varying characteristics of the microvascular density fluctuation amplitude.

[0201] The Lorentz divergence describes the divergence characteristics of the blood flow velocity gradient mutation points in space-time.

[0202] In the embodiments of the present application, first, extract spatiotemporal phase singularities at the blood flow velocity gradient mutation points to generate a phase singularity map. Specifically, use Topological Data Analysis (TDA) to identify the blood flow velocity gradient mutation points and extract the spatiotemporal phase singularities at these points. The phase singularity map is topologically wound by the Lorentz divergence of the blood flow velocity gradient mutation points and the time-varying characteristics of the microvascular density fluctuation amplitude. The specific steps are as follows: First, use the Lorentz Transformation (LT) to calculate the Lorentz divergence of the blood flow velocity gradient mutation points; then, calculate the time-varying characteristics of the microvascular density fluctuation amplitude through Time Series Analysis (TSA). These two parameters jointly generate the phase singularity map.

[0203] 1032. Construct a metabolic vortex field based on the phase singularity map, where the vortex core density of the metabolic vortex field is jointly controlled by the spatial gradient of the hemoglobin oxygen saturation dispersion and the winding intensity of the phase singularity map, and the initial boundaries of the high-perfusion core area, the transition zone, and the low-perfusion edge area are divided;

[0204] In step 1032, the metabolic vortex field is a field structure that describes the metabolic activities around the blood flow velocity gradient mutation points, and its vortex core density is jointly controlled by the spatial gradient of the hemoglobin oxygen saturation dispersion and the winding intensity of the phase singularity map.

[0205] The initial boundary is the preliminary boundary for dividing the high-perfusion core area, the transition zone, and the low-perfusion edge area.

[0206] In the embodiments of the present application, first, a metabolic vortex field is constructed based on the generated phase singularity map. Specifically, the complex network analysis (CNA) is used to simulate the node connection relationship in the phase singularity map and generate a metabolic vortex field. The vortex core density of the metabolic vortex field is jointly controlled by the spatial gradient of the hemoglobin oxygen saturation dispersion and the winding strength of the phase singularity map, and the initial boundaries of the high-perfusion core region, the transition zone, and the low-perfusion edge region are demarcated. The specific steps are as follows: the spatial gradient analysis (SGA) is used to calculate the spatial gradient of the hemoglobin oxygen saturation dispersion; the winding strength analysis (WSA) is used to calculate the winding strength of the phase singularity map. These two parameters jointly determine the vortex core density of the metabolic vortex field. Based on the above input, a metabolic vortex field is generated, which describes the dynamic pattern of the internal energy conversion of the system.

[0207] 1033. Generate a metabolic entanglement degree through the quantization energy level transition of the microvascular density fluctuation amplitude and the interference effect of the hemoglobin oxygen saturation dispersion, and the metabolic entanglement degree drives the dynamic contraction of the initial boundary and generates a corrected region boundary carrying an energy transition mark;

[0208] In step 1033, the metabolic entanglement degree is a parameter generated by the quantization energy level transition of the microvascular density fluctuation amplitude and the interference effect of the hemoglobin oxygen saturation dispersion, and is used to drive the dynamic contraction of the initial boundary.

[0209] The energy transition mark is a mark describing the energy change generated during the quantization energy level transition.

[0210] In the embodiments of the present application, first, a metabolic entanglement degree is generated through the quantization energy level transition of the microvascular density fluctuation amplitude and the interference effect of the hemoglobin oxygen saturation dispersion. Specifically, the quantum state evolution model (QSEM) is used to simulate the quantization energy level transition of the microvascular density fluctuation amplitude, and combined with the interference effect of the hemoglobin oxygen saturation dispersion to generate a metabolic entanglement degree. The metabolic entanglement degree drives the dynamic contraction of the initial boundary and generates a corrected region boundary carrying an energy transition mark. Specifically, the interferometry (IM) is used to calculate the interference effect of the hemoglobin oxygen saturation dispersion; the quantum state evolution model is combined with these parameters to generate a metabolic entanglement degree.

[0211] 1034. Input the energy transition marker of the boundary of the correction area into the photoacoustic energy redistributor to generate a dynamic topology reconstruction instruction, which corrects the distribution of the extreme points of the blood flow velocity gradient in the three-dimensional dynamic image and updates the winding intensity threshold of the phase singularity map.

[0212] In step 1034, the dynamic topology reconstruction instruction is an instruction for correcting the distribution of the extreme points of the blood flow velocity gradient in the three-dimensional dynamic image, which is generated by inputting the energy transition marker of the boundary of the correction area.

[0213] The winding intensity threshold of the phase singularity map is the threshold for describing the winding intensity in the phase singularity map, which is used to update the stability of the system.

[0214] In the embodiment of the present application, first, input the energy transition marker of the boundary of the correction area into the photoacoustic energy redistributor to generate a dynamic topology reconstruction instruction. Specifically, use multiscale geometric analysis (MGA) to synchronously adjust the distribution of the extreme points of the blood flow velocity gradient in the three-dimensional dynamic image and update the winding intensity threshold of the phase singularity map. Specifically, use continuous wavelet transform (CWT) to calculate the energy transition marker of the boundary of the correction area; combine these parameters through nonlinear dynamics analysis (NDA) to generate a dynamic topology reconstruction instruction. Then, use Lyapunov exponent (LE) analysis to update the Lyapunov constraint conditions of the recursive graph topology. Based on the above input, a dynamic topology reconstruction instruction is generated, which describes the fine adjustment process of the internal energy conversion of the system.

[0215] The following is a specific example:

[0216] Suppose a large hospital admits a breast tumor patient who needs to undergo photoacoustic / ultrasound (PA / US) multimodal imaging examination. The Lorenz divergence of the mutation point of the blood flow velocity gradient in the left breast lesion area is extracted by topological data analysis as 2.8×10 - 3 s -1 The peak-valley difference of the time-varying characteristics of the microvessel density fluctuation amplitude is 14 vessels / mm 2 . A phase singularity map is generated through spatio-temporal phase singularity topology winding, showing a winding intensity threshold of 0.65. The maximum gradient of the hemoglobin oxygen saturation dispersion calculated by spatial gradient analysis is 0.85% / mm, combined with the winding intensity of the phase singularity map (0.72 rad / mm 2)Construct a metabolic vortex field and divide the initial boundaries of the high-perfusion core area (SO2 = 68% ± 3.2%), the transition zone (SO2 = 78% ± 4.1%), and the low-perfusion marginal area (SO2 = 82% ± 2.8%). The fluctuation amplitude of microvascular density is calculated by the quantum state evolution model for the energy level transition amplitude ΔE = 1.45 eV, and the interference effect with the dispersion of hemoglobin oxygen saturation (interference contrast 0.93) generates a metabolic entanglement degree of 1.32. The energy transition markers for correcting the regional boundary after the initial boundary dynamically shrinks show that the radius of the core area is reduced to 4.2 mm. The photoacoustic energy redistributor adjusts the distribution of the extreme points of the blood flow velocity gradient based on the corrected boundary markers, and in the three-dimensional dynamic image, the density of the extreme points is optimized from 8.5 points / mm 3 to 12.3 points / mm 3 . The winding intensity threshold of the updated phase singularity map is increased to 0.81. Finally, the energy transition markers of the corrected regional boundary are input into the photoacoustic energy redistributor to generate dynamic topology reconstruction instructions.

[0217] Through the design and implementation of steps 1031 to 1034, significant technical improvements have been achieved in the following aspects. When evaluating patients suspected of having breast fibroadenomas, by analyzing data at different time periods, multiple phase singularity maps are generated to help doctors more accurately judge local blood flow dynamics; based on the phase singularity maps, a metabolic vortex field is constructed, which can more accurately capture the metabolic activities around the mutation points of the blood flow velocity gradient and divide the initial boundaries of the high-perfusion core area, the transition zone, and the low-perfusion marginal area, enhancing the ability to analyze complex physiological signals; by generating a metabolic entanglement degree to drive the dynamic contraction of the initial boundary and generating a corrected regional boundary carrying energy transition markers, it can more accurately reflect the changes in the fluctuation amplitude of microvascular density and enhance the sensitivity of the analysis process; by generating dynamic topology reconstruction instructions to correct the distribution of the extreme points of the blood flow velocity gradient in the three-dimensional dynamic image and updating the winding intensity threshold of the phase singularity map, this helps to improve the recognition accuracy of the lesion area, especially in complex or subtle blood flow changes.

[0218] Figure 2 The structure diagram of a multi-dimensional data processing device (or system) for emergency data quality control analysis is provided for the embodiments of this application, as Figure 2 shown. The device includes:

[0219] An acquisition module 21, configured to acquire photoacoustic blood flow imaging data of a target breast area and patient emergency parameters. The photoacoustic blood flow imaging data includes blood flow velocity distribution, hemoglobin oxygen saturation distribution, and microvascular density distribution. The emergency parameters include heart rate variability, blood pressure fluctuation range, and pain index level, and generate multi-channel spatio-temporal correlation data;

[0220] A building module 22 is configured to construct a laser pulse energy density correction module based on the non-linear relationship between the blood pressure fluctuation range and the hemoglobin oxygen saturation in the multi-channel spatio-temporal correlation data, generate an ultrasonic receiver sensitivity adjustment parameter through the dynamic coupling mechanism between the pain index level and the microvascular density distribution, and synchronously establish a phase synchronization compensation network between the laser pulse repetition frequency and the heart rate variability;

[0221] A partitioning module 23 is configured to generate a real-time three-dimensional photoacoustic blood flow dynamic image and partition a difference region into a high-perfusion core region, a transition zone, and a low-perfusion marginal region based on the spatial distribution of blood flow velocity gradient mutation points;

[0222] A generation module 24 is configured to generate an emergency quality control score based on the dynamic correlation function between the area attenuation rate of the high-perfusion core region and the blood pressure fluctuation range, the mapping relationship between the oxygen saturation dispersion of the transition zone and the pain index level, and the coupling coefficient between the microvascular density fluctuation amplitude of the low-perfusion marginal region and the heart rate variability.

[0223] Figure 2 The multi-dimensional data processing device for emergency data quality control analysis described above can execute Figure 1 The multi-dimensional data processing method for emergency data quality control analysis described in the embodiments shown. Its implementation principle and technical effects will not be elaborated further. For the multi-dimensional data processing device for emergency data quality control analysis in the above embodiments, the specific manners in which each module and unit perform operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0224] In a possible design, Figure 2 The multi-dimensional data processing device for emergency data quality control analysis in the embodiments shown can be implemented as a computing device. As Figure 3 shown, the computing device may include a storage component 31 and a processing component 32;

[0225] The storage component 31 stores one or more computer instructions, where the one or more computer instructions are called and executed by the processing component 32.

[0226] The processing component 32 is used for the Figure 1 multi-dimensional data processing method for emergency data quality control analysis in the above

[0227] Among them, the processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above-mentioned method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above-mentioned method.

[0228] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0229] Of course, the computing device may also necessarily include other components, such as input / output interfaces, display components, communication components, etc.

[0230] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above-mentioned peripheral interface module may be an output device, an input device, etc.

[0231] The communication component is configured to facilitate wired or wireless communication between the computing device and other devices, etc.

[0232] Among them, the computing device may be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device may refer to a cloud server, and the above-mentioned processing component, storage component, etc. may be basic server resources leased or purchased from a cloud computing platform.

[0233] The embodiment of the present application also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above-mentioned Figure 1 multi-dimensional data processing method for emergency data quality control analysis shown in the above-mentioned embodiment.

[0234] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0235] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative work.

[0236] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0237] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A multi-dimensional data processing method for emergency data quality control analysis, characterized in that Including: Obtain photoacoustic blood flow imaging data of the target breast region and the patient's emergency parameters. The photoacoustic blood flow imaging data includes blood flow velocity distribution, hemoglobin oxygen saturation distribution, and microvascular density distribution. The emergency parameters include heart rate variability, blood pressure fluctuation range, and pain index level, and generate multi-channel spatio-temporal correlation data; Construct a laser pulse energy density correction module based on the non-linear relationship between the blood pressure fluctuation range and hemoglobin oxygen saturation in the multi-channel spatio-temporal correlation data. Generate ultrasonic receiver sensitivity adjustment parameters through the dynamic coupling mechanism of the pain index level and the microvascular density distribution. Synchronously establish a phase synchronization compensation network between the laser pulse repetition frequency and the heart rate variability; Generate real-time three-dimensional photoacoustic blood flow dynamic images and divide the differential regions into a high-perfusion core area, a transition zone, and a low-perfusion edge area based on the spatial distribution of blood flow velocity gradient mutation points; Generate an emergency quality control score based on the dynamic correlation function between the area attenuation rate of the high-perfusion core area and the blood pressure fluctuation range, the mapping relationship between the oxygen saturation dispersion of the transition zone and the pain index level, and the coupling coefficient between the microvascular density fluctuation amplitude of the low-perfusion edge area and the heart rate variability.

2. The method according to claim 1, wherein The constructing a laser pulse energy density correction module based on the non-linear relationship between the blood pressure fluctuation range and hemoglobin oxygen saturation in the multi-channel spatio-temporal correlation data, generating ultrasonic receiver sensitivity adjustment parameters through the dynamic coupling mechanism of the pain index level and the microvascular density distribution, and synchronously establishing a phase synchronization compensation network between the laser pulse repetition frequency and the heart rate variability includes: Generate blood flow oscillation entropy based on the phase delay spectrum of the blood pressure fluctuation range and hemoglobin oxygen saturation in the multi-channel spatio-temporal correlation data. Input the blood flow oscillation entropy into a frequency-domain convolution kernel to generate a pulse energy density correction coefficient. The bandwidth of the frequency-domain convolution kernel is dynamically adjusted by the ratio of the fluctuation period of hemoglobin oxygen saturation to the full width at half maximum of the blood pressure fluctuation range; Extract the microvascular topological entanglement degree through the morphological skeleton of the microvascular density distribution. Input the pain index level and the microvascular topological entanglement degree into a path tracing algorithm to generate receiver sensitivity adjustment parameters. The backtracking step size of the path tracing algorithm is determined by the spatial density gradient of microvascular branch nodes; Perform chaotic phase modulation on the recurrence plot features of the heart rate variability and the laser pulse repetition frequency to generate pulse synchronization compensation parameters carrying cardiac beat chaotic features. The recurrence plot features are based on the Lyapunov exponent of the heart rate variability and the spectral gap of the laser pulse repetition frequency; Input the pulse energy density correction coefficient, the receiver sensitivity adjustment parameters, and the pulse synchronization compensation parameters into a multi-physical field coupler to generate a collaborative regulation instruction set, and synchronously establish a phase synchronization compensation network between the laser pulse repetition frequency and the heart rate variability.

3. The method according to claim 1, wherein Generating an emergency quality control score based on the dynamic association function between the area attenuation rate of the high-perfusion core region and the blood pressure fluctuation range, the mapping relationship between the oxygen saturation dispersion degree of the transition zone and the pain index level, and the coupling coefficient between the microvascular density fluctuation amplitude of the low-perfusion marginal region and the heart rate variability, includes: Inputting the time-varying differential operator of the area attenuation rate of the high-perfusion core region and the blood pressure fluctuation range into the thermodynamic entropy change model to generate a perfusion instability index, and the non-equilibrium state constraint condition of the thermodynamic entropy change model is determined by the included angle between the half-cycle amplitude of the blood pressure fluctuation range and the gradient direction of the area attenuation rate; Generating a pain resonance factor through the phase vortex field of the oxygen saturation dispersion degree in the three-dimensional space, and the topological structure of the phase vortex field is constructed by the spatio-temporal heterogeneity of the oxygen saturation dispersion degree and the power spectrum overlapping region of the pain index level; Inputting the recursive features of the microvascular density fluctuation amplitude of the low-perfusion marginal region and the heart rate variability into the vascular oscillation coupler to generate a coupling oscillation spectrum carrying the heart beat-blood flow interference feature, and the resonant cavity parameters of the vascular oscillation coupler are jointly modulated by the peak-valley difference of the microvascular density fluctuation amplitude and the fractal dimension of the heart rate variability; Inputting the perfusion instability index, the pain resonance factor and the coupling oscillation spectrum into a multi-modal resonator to generate an emergency quality control score, and triggering the adaptive re-optimization of the scanning parameters through a closed-loop feedback channel and updating the laser pulse energy density correction module and the phase synchronization compensation network.

4. The method according to claim 3, wherein The inputting the recursive features of the microvascular density fluctuation amplitude of the low-perfusion marginal region and the heart rate variability into the vascular oscillation coupler to generate a coupling oscillation spectrum carrying the heart beat-blood flow interference feature, and the resonant cavity parameters of the vascular oscillation coupler are jointly modulated by the peak-valley difference of the microvascular density fluctuation amplitude and the fractal dimension of the heart rate variability, includes: Setting a time window function for the microvascular density fluctuation amplitude of the low-perfusion marginal region, and performing fractal dimension slicing on the time window function and the recursive features of the heart rate variability to generate the fundamental frequency of vascular wall oscillation, and the sliding step length of the time window function is dynamically adjusted by the peak-valley difference of the microvascular density fluctuation amplitude; Generating oscillation cavity harmonic parameters through the fundamental frequency of vascular wall oscillation and the fractal tuning factor of the heart rate variability, and the fractal tuning factor is calculated from the projected area of the fractal dimension slice on the time-frequency plane and the time window statistic of the microvascular density fluctuation amplitude; Inputting the oscillation cavity harmonic parameters into a blood flow interference phase detector to generate heart beat-blood flow interference fringes, and the phase entanglement state of the interference fringes is determined by the energy ratio relationship between the time window statistic of the microvascular density fluctuation amplitude and the fractal tuning factor; Generate dynamic impedance parameters based on the phase entanglement state of the interference fringes, and combine the time window function and the recursive features of the heart rate variability to input into the vascular oscillation coupler, generating a coupled oscillation spectrum carrying the heart beat-blood flow interference features. The resonant cavity parameters of the vascular oscillation coupler are jointly modulated by the peak-valley difference of the microvascular density fluctuation amplitude and the fractal dimension of the heart rate variability.

5. The method according to claim 4, characterized in that, Generate oscillation cavity harmonic parameters through the fundamental frequency of the vascular wall oscillation and the fractal tuning factor of the heart rate variability. The fractal tuning factor is calculated from the projected area of the fractal dimension slice on the time-frequency plane and the time window statistic of the microvascular density fluctuation amplitude, including: Perform a time-frequency plane projection on the fractal dimension slice to generate a multi-dimensional fractal topology network. The grid density of the multi-dimensional fractal topology network is jointly controlled by the time window statistic of the microvascular density fluctuation amplitude and the spatio-temporal gradient of the projected area. Generate a fractal tuning factor through the node energy distribution of the multi-dimensional fractal topology network. The fractal tuning factor is calculated from the projected area of the fractal dimension slice on the time-frequency plane and the time window statistic of the microvascular density fluctuation amplitude. Input the fractal tuning factor into the oscillation cavity energy converter to generate a harmonic phase group. The tunneling path of the harmonic phase group is jointly constrained by the energy distribution gradient of the fractal tuning factor and the recursive feature map of the heart rate variability. Combine the fundamental frequency of the vascular wall oscillation, and generate oscillation cavity harmonic parameters through the tunneling path of the harmonic phase group. The oscillation cavity harmonic parameters synchronously correct the time-frequency distortion compensation amount of the frequency domain convolution kernel and update the Lyapunov constraint condition of the recursive graph topology through the waveguide coupling effect.

6. The method according to claim 5, characterized in that Generate a fractal tuning factor through the node energy distribution of the multi-dimensional fractal topology network. The fractal tuning factor is calculated from the projected area of the fractal dimension slice on the time-frequency plane and the time window statistic of the microvascular density fluctuation amplitude, including: Extract the phase winding coefficient in the node energy distribution of the multi-dimensional fractal topology network. The phase winding coefficient is generated by the spatio-temporal interference effect of the projected area of the fractal dimension slice on the time-frequency plane and the time window statistic of the microvascular density fluctuation amplitude. Generate a vortex energy flow through the time-frequency distortion rate of the phase winding coefficient and the fundamental frequency of the vascular wall oscillation. The precession angle of the vortex energy flow is jointly determined by the energy gradient field of adjacent nodes in the multi-dimensional fractal topology network and the power spectrum offset of the time window statistic. Input the vortex energy flow into the fractal tuning field generator to generate a fractal tuning factor carrying the quantum tunneling effect. The constraint condition of the fractal tuning field generator is constructed from the overlapping region of the precession angle of the vortex energy flow and the recursive feature map of the heart rate variability. Generate topological entanglement parameters based on the quantum tunneling path density of the fractal tuning factor carrying the quantum tunneling effect. The topological entanglement parameters synchronously adjust the gradient of the time-frequency distortion compensation amount of the frequency domain convolution kernel and reconstruct the energy threshold of the Lyapunov constraint condition through the nonlinear resonance mechanism.

7. The method according to claim 1, characterized in that Generating a real-time three-dimensional photoacoustic blood flow dynamic image and dividing the differential region into a high-perfusion core region, a transition zone, and a low-perfusion marginal zone based on the spatial distribution of blood flow velocity gradient mutation points, including: Extracting spatio-temporal phase singularities at the blood flow velocity gradient mutation points to generate a phase singularity map, which is topologically wound by the Lorentz divergence of the blood flow velocity gradient mutation points and the time-varying characteristics of the microvascular density fluctuation amplitude; Constructing a metabolic vortex field based on the phase singularity map, where the vortex core density of the metabolic vortex field is jointly controlled by the spatial gradient of the hemoglobin oxygen saturation dispersion and the winding intensity of the phase singularity map, and the initial boundaries of the high-perfusion core region, the transition zone, and the low-perfusion marginal zone are divided; Generating a metabolic entanglement degree through the quantization energy level transition of the microvascular density fluctuation amplitude and the interference effect of the hemoglobin oxygen saturation dispersion, and the metabolic entanglement degree drives the dynamic contraction of the initial boundary and generates a corrected regional boundary carrying energy transition marks; Inputting the energy transition marks of the corrected regional boundary into a photoacoustic energy redistributor to generate a dynamic topology reconstruction instruction, and the dynamic topology reconstruction instruction corrects the distribution of the blood flow velocity gradient extreme points of the three-dimensional dynamic image and updates the winding intensity threshold of the phase singularity map.

8. A multi-dimensional data processing system for emergency data quality control analysis, characterized in that, Including: An acquisition module, configured to acquire photoacoustic blood flow imaging data of a target breast region and patient emergency parameters, where the photoacoustic blood flow imaging data includes blood flow velocity distribution, hemoglobin oxygen saturation distribution, and microvascular density distribution, and the emergency parameters include heart rate variability, blood pressure fluctuation range, and pain index level, and generate multi-channel spatio-temporal correlation data; A construction module, configured to construct a laser pulse energy density correction module based on the non-linear relationship between the blood pressure fluctuation range and the hemoglobin oxygen saturation in the multi-channel spatio-temporal correlation data, generate an ultrasonic receiver sensitivity adjustment parameter through the dynamic coupling mechanism between the pain index level and the microvascular density distribution, and synchronously establish a phase synchronization compensation network between the laser pulse repetition frequency and the heart rate variability; A division module, configured to generate a real-time three-dimensional photoacoustic blood flow dynamic image and divide the differential region into a high-perfusion core region, a transition zone, and a low-perfusion marginal zone based on the spatial distribution of blood flow velocity gradient mutation points; A generation module, configured to generate an emergency quality control score based on the dynamic correlation function between the area attenuation rate of the high-perfusion core region and the blood pressure fluctuation range, the mapping relationship between the oxygen saturation dispersion of the transition zone and the pain index level, and the coupling coefficient between the microvascular density fluctuation amplitude of the low-perfusion marginal zone and the heart rate variability.

9. A computing device, characterized in that, Including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a multi-dimensional data processing method for emergency data quality control analysis as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, Stored with a computer program, when the computer program is executed by a computer, it implements a multi-dimensional data processing method for emergency data quality control analysis as described in any one of claims 1 to 7.

Images