Angiography high-pressure injection system

Abstract

The invention belongs to the technical field of medical imaging, and discloses an angiography high-pressure injection system which comprises the following steps: acquiring physiological data information of a patient, and calculating an individualized contrast agent injection parameter coefficient based on the physiological data information; acquiring anatomical structure information of a blood vessel region of the target patient, and performing pressure evaluation based on hemodynamic characteristics to obtain blood vessel pressure bearing capacity and injection pressure regulation factors; performing physiological status assessment based on the physiological data information of the patient to obtain a physiological status influence factor and generate a risk marker value; performing multi-source data fusion according to the injection pressure regulation factor, the physiological status risk marker value and the historical radiography record, and constructing the radiography safety degree of the blood vessel sub-region; an optimal injection parameter path is obtained based on the radiography safety degree in combination with a deep reinforcement learning algorithm, and high-pressure injection equipment is controlled to execute injection operation; according to the invention, accurate and personalized control of contrast agent injection is realized, and the safety and imaging effect of contrast examination are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of medical imaging technology, and more specifically, the present invention relates to an angiography high-pressure injection system. Background Art

[0002] With the wide application of medical imaging technology in clinical diagnosis, contrast agent injection has become a key link in improving image quality and diagnostic accuracy. However, the existing contrast agent injection systems have the following technical defects: The existing contrast agent injection systems have limited patient data acquisition capabilities, mainly relying on discrete medical records or single-parameter monitoring, lacking a systematic and standardized data integration mechanism, and unable to comprehensively obtain key information such as the patient's physiological characteristics, renal function status, and historical contrast reactions, resulting in difficulty in formulating individualized injection plans; Traditional injection systems generally lack an accurate parameter calculation mechanism, mostly using a linear dose adjustment method based on body weight, and failing to fully consider multi-dimensional factors such as the patient's age, renal function status, and contrast agent characteristics, unable to achieve true individualized parameter optimization, and increasing the risk of adverse reactions such as contrast-induced nephropathy; In terms of vascular analysis, the existing technologies oversimplify the assessment of vascular anatomical structures, lacking accurate analysis of microscopic structures such as vascular diameter distribution, curvature, and branching characteristics, especially insufficient quantification of hemodynamic characteristics, resulting in the inability to accurately evaluate the actual bearing capacity of different vascular regions and increasing the risk of vascular injury; Physiological state monitoring systems are mostly static assessments, lacking a dynamic risk assessment mechanism, unable to capture the fluctuation patterns of physiological parameters such as the patient's respiration, heart rate, and blood oxygen in real time and their impact on the contrast process, resulting in difficulty in timely identifying potential risk states; In terms of safety assessment, the existing technologies mostly use single-dimensional or simple threshold judgments, lacking the ability of multi-source data fusion and comprehensive risk assessment, unable to establish an association model between injection pressure, physiological state, and historical reactions, resulting in one-sided safety assessment results and difficulty in accurately predicting individualized risks; Injection control strategies generally adopt preset schemes or simple feedback adjustments, lacking intelligent parameter optimization algorithms and dynamic regulation mechanisms, unable to perform precise control according to the patient's real-time state and vascular characteristics, which not only affects the contrast effect but also fails to maximize the protection of patient safety. In view of this, the present invention proposes an angiography high-pressure injection system to solve the above problems. Summary of the Invention

[0003] In order to overcome the above-mentioned defects of the prior art and to achieve the above object, the present invention provides the following technical solutions: An angiography high-pressure injection system, comprising: A data acquisition module for acquiring physiological data and medical records of a target patient to obtain corresponding patient physiological data information; the patient physiological data information includes standardized patient information, physiological monitoring data, renal function assessment data, and historical contrast examination records; A parameter calculation module that, based on the standardized patient information and renal function assessment data, combines with the contrast agent type to obtain corresponding individualized contrast agent injection parameter coefficients; A vascular analysis module for obtaining vascular anatomical structure information corresponding to the vascular region of a target patient, performing pressure assessment based on hemodynamic characteristics to obtain the vascular bearing capacity corresponding to each vascular sub-region within the corresponding vascular region; and obtaining an injection pressure adjustment factor corresponding to each vascular sub-region in combination with the patient physiological data information; A physiological assessment module that, based on the patient physiological data information, assesses the physiological state of the vascular region of the target patient to obtain corresponding physiological state impact factors, and combines with a pre-constructed physiological state safety threshold for risk marking to obtain corresponding physiological state risk marking values at different times; A safety construction module for performing multi-source data fusion based on the obtained injection pressure adjustment factor, physiological state risk marking value, and historical contrast examination records, and constructing a corresponding contrast safety degree for each vascular sub-region based on the above; An injection control module for obtaining the optimal parameter path of contrast agent injection corresponding to the target patient based on the obtained contrast safety degree, combining with a deep reinforcement learning algorithm, and controlling a high-pressure injection device to perform an injection operation based on the above; Further, the process of obtaining patient physiological data information includes: Setting up a data acquisition unit to perform data crawling based on the data acquisition unit to obtain corresponding basic file information and historical contrast examination records; Performing digital processing and standardized storage on the collected basic file information to obtain corresponding standardized patient information; Setting up a data monitoring unit to perform real-time acquisition of the physiological parameters of the patient based on the data monitoring unit; obtaining corresponding physiological parameter data; and performing data filtering and noise elimination processing on the collected physiological parameters to obtain smooth physiological monitoring data; The data monitoring unit is also used to collect data on renal function-related indicators of the patient to obtain corresponding renal function assessment data; Summarizing the obtained standardized patient information, physiological monitoring data, renal function assessment data, and historical contrast examination records to obtain corresponding patient physiological data information.

[0004] Further, the process of obtaining individualized contrast agent injection parameter coefficients includes: Obtain the physical health index corresponding to the target patient based on the standardized information; and obtain the weight range corresponding to the target patient based on the physical health index; Perform benchmark dose mapping based on the weight range where the target patient is located to obtain the benchmark dose value corresponding to the target patient's weight; and perform unit body weight injection volume adjustment and upper limit control on the obtained benchmark dose value to obtain the corresponding weight adjustment coefficient; Obtain the age grouping result corresponding to the corresponding patient based on the standardized patient information; and perform physiological function attenuation estimation and compensation factor calculation based on the age grouping result to obtain the corresponding age correction coefficient; Classify the renal function assessment data collected into renal function grades and conduct risk assessment to obtain the corresponding renal function status index; Construct a corresponding renal load assessment model based on the obtained renal function status index, and combine the renal function assessment data to divide the renal function of the corresponding patient into risk levels to obtain the corresponding renal function risk grade; Predict the contrast agent clearance rate and set the safety threshold according to the renal function risk grade corresponding to the patient; obtain the corresponding renal function protection coefficient; Obtain the contrast agent type information; perform hydrodynamic analysis and injection characteristic simulation based on the contrast agent type information to obtain the corresponding contrast agent characteristic correction factor; Take the weight adjustment coefficient, age correction coefficient, renal function protection coefficient, and contrast agent characteristic correction factor as input variables; and assign weights to each input variable; integrate each input variable by applying a weighted fusion algorithm to obtain the corresponding individualized contrast agent injection parameter coefficient.

[0005] Furthermore, the process of obtaining the blood vessel anatomical structure information corresponding to the blood vessel region of the target patient includes: Perform initial impact acquisition on the patient's blood vessel region based on a pre-selected angiography device to obtain the corresponding original blood vessel image; Perform digital enhancement and noise suppression on the obtained original blood vessel image to obtain the corresponding optimized blood vessel image; Perform edge detection and contour extraction on the obtained optimized blood vessel image to obtain the corresponding blood vessel contour data; Obtain the blood vessel diameter corresponding to each blood vessel within the target blood vessel region based on the extracted blood vessel contour data; and generate the corresponding blood vessel diameter distribution map based on it; Perform three-dimensional reconstruction based on the obtained blood vessel diameter distribution map and the blood vessel diameter distribution map to obtain the corresponding spatial structure model of the blood vessel region; Perform curvature quantization calculation and bending point identification based on the spatial structure model to obtain the corresponding blood vessel curvature index set; Identify the branch points in the corresponding spatial structure model by applying a topological analysis algorithm, and measure the angle between the branch vessels and the main vessel at the corresponding branch points; meanwhile, record the three-dimensional coordinates corresponding to the branch points; and construct the corresponding vascular branch topological structure based on the three-dimensional coordinates and angles of the branch points. Based on the obtained vascular branch topological structure, conduct an importance assessment based on the supply tissue range of the branch vessels corresponding to the branch points, and estimate the blood flow ratio in the corresponding branch vessels by applying a pre-constructed hydrodynamic model; summarize the obtained blood flow ratio and importance assessment results to obtain the corresponding branch characteristic data. Identify and extract the anatomical feature points corresponding to the target vascular region based on the obtained vascular diameter distribution map, vascular curvature index set, and branch characteristic data; and divide the corresponding vascular region into several continuous vascular sub-regions based on the anatomical feature points. Establish an anatomical indexing structure for the corresponding vascular sub-regions to form complete vascular anatomical structure information.

[0006] Furthermore, the acquisition of the vascular pressure-bearing capacity corresponding to each vascular sub-region includes: Measure the blood flow velocity and blood flow volume corresponding to each vascular sub-region in combination with the obtained anatomical structure information; conduct three-dimensional reconstruction based on the measurement results to obtain the corresponding blood flow velocity vector field; and obtain the Reynolds number corresponding to each sub-region based on the obtained blood flow velocity vector field; obtain the corresponding set of hemodynamic characteristic indexes based on it. Identify the corresponding optimized vascular image to obtain the vascular wall thickness within each vascular sub-region; and construct the corresponding wall thickness distribution map based on it. Conduct statistical analysis on the obtained wall thickness distribution map to obtain the corresponding statistical characteristic information; identify the wall thickness abnormal points by using an anomaly detection algorithm; obtain the corresponding vascular wall structure characteristics; apply internal pressure load based on the vascular wall structure characteristics to obtain the corresponding stress-strain curve; and calculate the wall tension based on it to obtain the corresponding elastic modulus distribution. Estimate the maximum tolerable pressure according to the obtained elastic modulus distribution to obtain the corresponding theoretical pressure-bearing upper limit. Obtain the vascular health data of the target patient, such as age and vascular disease history, based on the standardized patient information; and conduct vascular wall strength correction and safety factor setting based on the vascular health data; obtain the corresponding vascular state adjustment factor. Obtain the vascular pressure-bearing capacity of each vascular sub-region based on the hemodynamic characteristic indexes, vascular wall structure characteristics, theoretical pressure-bearing upper limit, and vascular state adjustment factor.

[0007] Furthermore, the acquisition process of the injection pressure adjustment factor includes: Obtain the heart rate change curve corresponding to the target patient based on the collected physiological monitoring data, and perform heart rate variability analysis and periodic feature extraction on it to obtain the corresponding heart rate fluctuation pattern; Based on the heart rate fluctuation pattern, divide the cardiac systole and diastole cycles and identify the time windows to obtain the optimal injection timing index; Extract statistical features from the systolic and diastolic blood pressure data of the corresponding patient based on the physiological monitoring data to obtain the corresponding blood pressure state characteristics; Obtain the blood vessel pressure-bearing capacity of each vascular sub-region, and construct a pressure safety threshold curve based on it; Set the upper limit of the injection pressure and divide the risk levels based on the pressure safety threshold curve to obtain the sub-region pressure limit table; Construct a three-dimensional relationship model of heart rate - blood pressure - pressure-bearing capacity, and perform dynamic simulation analysis and sensitivity testing based on it to obtain the parameter sensitivity matrix; Optimize the pressure regulation strategy and design smooth transition according to the parameter sensitivity matrix to obtain the corresponding pressure regulation reference value; Generate the corresponding injection pressure adjustment factor according to the optimal injection timing index, internal pressure fluctuation range, sub-region pressure limit table, and pressure regulation reference value.

[0008] Furthermore, the process of obtaining the physiological state influence factor includes: Extract features from the collected physiological monitoring data to obtain the corresponding respiratory pattern features of the patient; Based on the respiratory pattern features, identify the respiratory cycle and estimate the change in intrathoracic pressure to obtain the respiratory influence coefficient; Obtain the electrocardiogram waveform of the target patient based on the collected physiological monitoring data, and perform waveform feature extraction and abnormal pattern recognition on it to obtain the corresponding heart rhythm state evaluation result; Based on the heart rhythm state evaluation result, predict the change in cardiac output and analyze the hemodynamic influence to obtain the cardiac function influence coefficient; Analyze the trend and monitor the threshold of the change in blood oxygen saturation in the physiological monitoring data to obtain the corresponding oxygenation state data; Based on the oxygenation state data, evaluate tissue perfusion and predict the risk of hypoxia to obtain the oxygenation influence coefficient; Obtain the corresponding regional feature description of the target vascular sub-region based on the obtained vascular anatomical structure information; Based on the regional feature description, allocate risk weights and identify key points to obtain the regional sensitivity coefficient; Integrate the respiratory influence coefficient, cardiac function influence coefficient, oxygenation influence coefficient, and regional sensitivity coefficient to obtain the physiological state influence factor at each moment.

[0009] Furthermore, the process of obtaining the physiological state risk marker value includes: Construct a safety reference standard; perform individualized adjustment and special case correction on the obtained safety reference standard to obtain a corresponding set of personalized safety thresholds; Obtain the corresponding physiological state influencing factors at each moment, and perform component decomposition and parameter mapping based on them to obtain a multi-dimensional physiological index vector; Compare the multi-dimensional physiological index vector with the set of personalized safety thresholds one by one and calculate the deviation to obtain a list of parameter deviation degrees; Quantify the risk level and assign weights based on the list of parameter deviation degrees to obtain a weighted risk score; Perform risk level classification and critical state identification according to the weighted risk score to obtain a risk classification result; Perform time-series risk prediction and trend analysis based on the current physiological state influencing factors and the time series corresponding to the physiological monitoring parameters to obtain a risk evolution trend diagram; Determine the warning level and evaluate the risk accumulation effect based on the risk evolution trend diagram to obtain a dynamic risk index; Integrate the risk classification result and the dynamic risk index, generate a comprehensive risk assessment result through a fuzzy logic reasoning algorithm, and perform defuzzification processing on it to obtain a corresponding physiological state risk marker value.

[0010] Furthermore, the process of obtaining the contrast safety degree includes: Obtain the injection pressure adjustment factors corresponding to each vascular sub-region, and perform spatial distribution analysis and key region identification based on them to obtain a pressure-sensitive region diagram; Evaluate the risk level and delimit the safety boundary based on the pressure-sensitive region diagram to obtain a pressure safety score; Organize the physiological state risk marker values at each moment into a time series, and perform time series pattern mining and fluctuation characteristic analysis to obtain risk fluctuation characteristics; Perform stability evaluation and outlier detection based on the description of the risk fluctuation characteristics to obtain a physiological risk score; Extract features from the obtained historical contrast examination records to obtain a corresponding historical contrast feature set; perform contrast tolerance analysis and sensitivity prediction based on the historical contrast feature set to obtain a historical risk score; Establish a three-source data feature space, perform feature extraction and dimensionality reduction processing on the pressure safety score, physiological risk score, and historical risk score to obtain a fused feature vector; the establishment of the three-source data feature space refers to constructing a high-dimensional feature representation framework including three dimensions of pressure, physiology, and history; Construct a multi-level safety assessment model based on the fused feature vector to obtain a preliminary safety degree assessment result; Input the obtained fused feature vector into the constructed multi-level safety assessment model to generate a multi-dimensional preliminary safety degree assessment result; Calibrate and optimize the results of the preliminary safety assessment to obtain the angiography safety degree corresponding to the template patient in the corresponding vascular sub-region.

[0011] Further, the process of obtaining the optimal parameter path for contrast agent injection includes: Obtain the angiography safety degree data of each vascular sub-region and the pre-set imaging quality requirement parameters, and construct the corresponding optimization objective constraint conditions based on them; Based on the optimization objective constraint conditions, establish the mapping relationship between the injection parameters and the safety degree and imaging quality, and construct the corresponding parameter-effect response surface based on it; Based on the contrast agent injection parameters corresponding to the corresponding contrast agent injection process, construct the corresponding parameter state space; Define the action set and state transition function in the parameter space to obtain the injection control Markov decision process model; Based on the parameter state space, action set and state transition function, construct the complete model of the Markov decision process represented by a quadruple; Design a deep reinforcement learning reward function, and based on it, train a deep Q network or a policy gradient network to obtain the corresponding injection policy model; perform real-time adjustment and optimization on the injection policy model through an online learning method to obtain an adaptive injection control strategy; Based on the adaptive injection control strategy, perform path planning and trajectory optimization in the parameter state space to obtain the injection parameter time series; Perform safety verification and robustness testing on the injection parameter time series to obtain the optimal parameter path for contrast agent injection; generate the corresponding injection control instructions based on it and transmit them to the high-pressure injection device for execution.

[0012] The technical effects and advantages of a high-pressure injection system for angiography according to the present invention: 1. By combining the multi-dimensional analysis of the vascular diameter distribution map, the vascular curvature index set and the branch characteristic data, the vascular anatomical structure information and hemodynamic characteristics are obtained, the accurate assessment of the bearing capacity of each vascular sub-region is realized, and the risk of vascular injury is effectively prevented; 2. Through the real-time monitoring and fusion of the respiratory influence coefficient, the cardiac function influence coefficient, the oxygenation influence coefficient and the regional sensitivity coefficient, a dynamic physiological state assessment model is constructed, the real-time marking and early warning of multi-dimensional physiological risks are realized, and the system can timely identify and respond to potential dangerous states; 3. Based on the multi-source data fusion technology of the pressure safety score, the physiological risk score and the historical risk score, a comprehensive angiography safety degree assessment system is established, a quantitative index that comprehensively reflects the individual safety status of the patient is provided, and the accurate prediction and hierarchical management of risks are realized; 4. Through the deep reinforcement learning algorithm and the Markov decision process model, the intelligent planning and dynamic adjustment of the optimal parameter path for contrast agent injection are realized, which maximizes the safety of patients while ensuring the imaging quality, and significantly improves the overall efficiency and quality of contrast examinations. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a schematic diagram of an angiography high-pressure injection system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0015] Embodiment 1 Please refer to Figure 1 As shown, an angiography high-pressure injection system described in this embodiment includes: A data acquisition module for collecting physiological data and medical records of a target patient to obtain corresponding patient physiological data information; the patient physiological data information includes standardized patient information, physiological monitoring data, renal function assessment data, and historical contrast examination records; A parameter calculation module that, based on the standardized patient information and renal function assessment data, and in combination with the contrast agent type, obtains corresponding individualized contrast agent injection parameter coefficients; A vascular analysis module for obtaining vascular anatomical structure information corresponding to the vascular region of a target patient, and performing pressure assessment based on hemodynamic characteristics to obtain the vascular bearing capacity corresponding to each vascular sub-region within the corresponding vascular region; and obtaining the injection pressure adjustment factor corresponding to each vascular sub-region in combination with the patient physiological data information; A physiological assessment module for assessing the physiological state of the vascular region of a target patient based on the patient physiological data information to obtain corresponding physiological state influence factors, and performing risk marking in combination with a pre-constructed physiological state safety threshold to obtain corresponding physiological state risk marking values at different times; A safety construction module for performing multi-source data fusion based on the obtained injection pressure adjustment factor, physiological state risk marking value, and historical contrast examination records, and constructing the corresponding contrast safety degree for each vascular sub-region based on the above; An injection control module for obtaining the optimal parameter path for contrast agent injection corresponding to a target patient based on the obtained contrast safety degree, and controlling a high-pressure injection device to perform an injection operation based on the above; It should be further noted that in the specific implementation process, the process of obtaining the patient's physiological data information includes: Set up a data acquisition unit, and the data acquisition unit is connected to the information resource library in the corresponding medical institution through the API interface; the information resource library includes, but is not limited to, the electronic medical record information library, the pharmaceutical knowledge base, etc.; The data acquisition unit crawls data from the corresponding information resource library based on the API interface to obtain the corresponding basic file information and historical contrast examination records; the basic file information includes basic information such as the patient's age, height, weight, and past medical history; the historical contrast examination records include data such as the patient's historical contrast agent usage and reaction conditions; Perform digital processing and standardized storage on the collected basic file information to obtain the corresponding standardized patient information. The digital processing includes processes such as digital format conversion and numerical unit unification; the standardized storage is to structurally store the digitally processed basic file information through a unified coding standard to ensure the consistency of field naming, unit, and value range; At the same time, set up a data monitoring unit to collect the patient's physiological parameters in real time based on the data monitoring unit to obtain the corresponding physiological parameter data; the physiological parameter data includes time series data corresponding to physiological parameters such as heart rate, blood pressure, respiratory rate, and blood oxygen saturation; and perform data filtering and noise elimination processing on the collected physiological parameters to obtain smooth physiological monitoring data; the data filtering refers to removing signal interference and noise generated during the physiological parameter collection process based on a pre-selected low-pass filter; the noise elimination refers to identifying and deleting abnormal data points caused by factors such as equipment failure, patient movement, or external interference through the median filtering algorithm.

[0016] At the same time, the data monitoring unit is also used to collect data on the patient's renal function-related indicators to obtain the corresponding renal function assessment data, and the renal function assessment data includes creatinine, blood urea nitrogen, and estimated glomerular filtration rate, etc.; Summarize the obtained standardized patient information, physiological monitoring data, renal function assessment data, and historical contrast examination records to obtain the corresponding patient physiological data information.

[0017] It should be further noted that in the specific implementation process, the process of obtaining the individualized contrast agent injection parameter coefficient includes: Based on the standardized information, obtain the body health index BMI corresponding to the target patient, and the body health index represents the ratio of the patient's weight to the square of the height; and based on the body health index BMI, obtain the weight range corresponding to the target patient, and the weight range includes the low weight range (BMI < 18.5), the standard weight range (18.5 ≤ BMI ≤ 24), and the high weight range (BMI > 24); Perform reference dose mapping based on the weight range of the target patient; the reference dose mapping refers to establishing a basic dose mapping table according to clinical medicine guidelines, combined with different contrast agent types and iodine concentrations; and obtaining a reference dose value corresponding to the weight of the target patient based on it; and adjusting the injection amount per unit weight and upper limit control of the obtained reference dose value to obtain a corresponding weight adjustment coefficient; wherein, the adjustment of the injection amount per unit weight refers to adjusting the obtained reference dose value based on the examination type and vascular region required by the patient; for example: if the examination type is CT pulmonary angiography and the corresponding vascular region is thinner; then the obtained reference dose value needs to be adaptively increased; the upper limit control value is set based on clinical medicine guidelines to the maximum allowable reference dose value to prevent over-injection; the weight adjustment coefficient refers to the ratio between the reference dose values before and after adjustment; Obtain the age grouping result corresponding to the corresponding patient based on the standardized patient information, and the age grouping includes children, youth, middle-aged and elderly; and perform physiological function attenuation estimation and compensation factor calculation based on the age grouping result to obtain a corresponding age correction coefficient; the function attenuation estimation refers to obtaining the corresponding physiological characteristics of the target patient based on the patient's physiological data information, and performing mathematical modeling based on it to obtain a corresponding physiological function attenuation model, and obtaining a corresponding function attenuation index based on it; the physiological function attenuation model is used to quantify the influence degree of age growth on the patient's kidney clearance function, heart function and vascular elasticity change; the compensation factor calculation is to compensate the contrast agent metabolism and excretion process of the corresponding patient based on the function attenuation index; for example: for elderly patients, due to the attenuation of their physiological functions caused by age growth, the dosage and injection rate of the contrast agent need to be adjusted to adapt to the reduced metabolism and excretion ability of the patient; furthermore, a corresponding age correction coefficient is obtained based on the results of physiological function attenuation estimation and compensation factor calculation; Classify the collected renal function assessment data into renal function grades and perform risk assessment to obtain a corresponding renal function status index; the renal function grade classification refers to grading the patient's renal function based on the KDIGO standard and assigning grade scores; for example: five grades of normal, mild decline, moderate decline, moderate to severe decline and renal failure; wherein, the KDIGO standard represents the clinical practice guidelines formulated by the Kidney Disease: Improving Global Outcomes organization; the risk assessment refers to considering the patient's age, past medical history and the results of renal function grade classification to perform contrast-induced nephropathy risk scoring to form a corresponding renal function status index; and the lower the renal function status index, the better the renal function status of the corresponding patient and the lower the risk of contrast agent use; Construct a corresponding kidney load assessment model based on the obtained renal function status index. Through the kidney load assessment model, combined with renal function assessment data, classify the renal function of the corresponding patient into risk levels to obtain the corresponding renal function risk levels, which include low risk, medium risk, and high risk; Furthermore, predict the contrast agent clearance rate and set the safety threshold according to the renal function risk level corresponding to the patient; in the contrast agent clearance prediction formula, based on the pharmacokinetic theory, comprehensively consider the influence of physiological function attenuation to predict the clearance rate and half-life of the contrast agent in the target patient; the safety threshold setting refers to adjusting the upper limit of the reference injection dose and the injection rate limit of the contrast agent based on the contrast agent clearance rate prediction result and clinical medicine guidelines; furthermore, obtain the corresponding renal function protection coefficient based on the contrast agent clearance rate prediction result and the safety threshold setting result; the process of obtaining the renal function protection coefficient includes: respectively compare the adjusted upper limit of the reference injection dose and the injection rate limit of the contrast agent with the maximum allowable reference injection dose and injection rate to obtain the corresponding ratio results and sum them to obtain the corresponding safety threshold compensation coefficient; similarly, compare the predicted contrast agent clearance rate with the pre-set standard contrast agent clearance rate to obtain the corresponding ratio result and use it as the clearance rate compensation factor; furthermore, add the clearance rate compensation factor, the safety threshold compensation coefficient, and the pre-set reference renal function protection coefficient to obtain the corresponding renal function protection coefficient; Retrieve information from the corresponding pharmaceutical knowledge base to obtain the corresponding contrast agent type information, which includes contrast agent physical and chemical characteristic parameters such as iodine concentration, viscosity, and osmotic pressure data; based on the contrast agent type information, conduct hydrodynamic analysis and injection characteristic simulation to obtain the corresponding contrast agent characteristic correction factor, which reflects the influence of the physical and chemical characteristics of the contrast agent on the injection parameters; hydrodynamic analysis refers to quantifying the flow resistance, viscosity change, and pressure flow change of the contrast agent under different iodine concentrations and temperature conditions through Poiseuille's law; injection characteristic simulation is to simulate and predict the flow behavior of the contrast agent in the injection device and blood vessels through computer simulation, and the flow behavior includes laminar / turbulent transition and pressure wave propagation to evaluate the performance differences of different types of contrast agents during injection; Take the body weight adjustment coefficient, age correction coefficient, renal function protection coefficient, and contrast agent characteristic correction factor as input variables; and assign weights to each input variable; integrate each input variable by applying the weighted fusion algorithm to obtain the corresponding individualized contrast agent injection parameter coefficient; the individualized contrast agent injection parameter coefficient can be used to adjust the standard injection plan to achieve individualized customization of the contrast agent dosage, injection rate, and pressure, and improve the safety and effectiveness of the contrast examination.

[0018] It should be further noted that in the specific implementation process, the process of obtaining the vascular anatomical structure information corresponding to the vascular region of the target patient includes: Based on a pre-selected angiography device, initial imaging of the patient's vascular region is performed to obtain the corresponding original vascular image; the angiography device is one of digital subtraction angiography, CT angiography, or magnetic resonance angiography devices; the original vascular image contains the vascular distribution and morphological information of the target region; Furthermore, digital enhancement and noise suppression are performed on the obtained original vascular image to obtain the corresponding optimized vascular image; the digital enhancement refers to performing processing such as contrast enhancement, brightness adjustment, and edge sharpening on the collected original vascular image to improve the visibility of the vascular structure; the noise suppression eliminates the noise in the original vascular image after data enhancement through an adaptive filtering algorithm and retains the detailed information of the vascular structure; the adaptive filtering algorithm is Gaussian filtering or median filtering; Edge detection and contour extraction are performed on the obtained optimized vascular image; the edge detection refers to identifying the edge information of the vascular region by using the Canny edge detection algorithm; the contour extraction refers to based on the edge detection result and using a pre-constructed contour model to extract the vascular contour of the corresponding vascular region to obtain the corresponding vascular contour data; Further, based on the extracted vascular contour data, the vascular diameter corresponding to each blood vessel in the target vascular region is obtained, and the change rate of the vascular diameter along the corresponding blood vessel length direction is calculated based on it to identify the stenosis and dilation regions in the corresponding vascular region; and a corresponding vascular diameter distribution map is generated based on it; Three-dimensional reconstruction is performed based on the obtained vascular diameter distribution map and the vascular diameter distribution map to obtain the corresponding spatial structure model of the vascular region; the three-dimensional reconstruction uses multi-view reconstruction technology to construct a three-dimensional space grid model of the blood vessel; Curvature quantization calculation and bending point identification are performed based on the spatial structure model; a corresponding blood vessel curvature index set is obtained; the curvature quantization calculation is based on the local curvature and torsion corresponding to each node in the spatial structure model to quantify the bending degree corresponding to the corresponding node; the bending point identification identifies the nodes whose bending degree exceeds the preset bending threshold based on the curvature quantization calculation result and marks them as high-curvature points; and a corresponding blood vessel curvature index set is obtained based on it; the blood vessel curvature index set includes the positions, local curvatures, and torsions of each high-curvature point; Further, the branch points in the corresponding spatial structure model are identified by applying a topological analysis algorithm, and the angle between the branch blood vessel and the main blood vessel at the corresponding branch point is measured; at the same time, the three-dimensional coordinates corresponding to the corresponding branch point are recorded; and a corresponding blood vessel branch topological structure is constructed based on the three-dimensional coordinates and the angle of the branch point; Based on the obtained vascular branch topological structure, importance assessment is carried out based on the supply tissue range of the branch vessels corresponding to the branch points, and the blood flow ratio in the corresponding branch vessels is estimated by applying a pre-constructed hydrodynamic model; the obtained blood flow ratio and importance assessment results are summarized to obtain the corresponding branch characteristic data; Furthermore, based on the obtained vascular diameter distribution map, vascular curvature index set and branch characteristic data, anatomical feature points corresponding to the target vascular region are identified and extracted, and the anatomical feature points include stenosis points, dilation points, high curvature points, branch points, etc.; and the corresponding vascular region is divided into several continuous vascular sub-regions based on the anatomical feature points; and each vascular sub-region has relatively consistent anatomical structure and blood flow characteristics; An anatomical index structure is established for the corresponding vascular sub-region, and the anatomical index structure includes information such as the position, length, average diameter, curvature, branching condition and blood supply range of the vascular sub-region; a complete vascular anatomical structure information is formed.

[0019] It should be further noted that in the specific implementation process, the acquisition of the vascular pressure-bearing capacity corresponding to each vascular sub-region includes: Doppler ultrasound technology is adopted, and the blood flow velocity and blood flow volume corresponding to each vascular sub-region are measured in combination with the obtained anatomical structure information; and three-dimensional reconstruction is carried out based on the measurement results to obtain the corresponding blood flow velocity vector field; the blood flow velocity vector field is used to describe the velocity magnitude and direction of each branch point in the corresponding vascular sub-region; and the Reynolds number corresponding to each sub-region is obtained based on the obtained blood flow velocity vector field; the Reynolds number is used to measure the distribution characteristics of blood flow; the distribution characteristics include laminar flow, transitional flow and turbulent flow; and the hemodynamic parameters such as wall shear stress and vorticity at the positions where high-pressure regions and fluid disturbances may occur are identified and extracted based on the distribution characteristics; a corresponding hemodynamic characteristic index set is obtained; The vascular wall thickness in each vascular sub-region is obtained by using high-resolution vascular imaging technology to identify the corresponding optimized vascular image; and a corresponding wall thickness distribution map is constructed based on it, and the wall thickness distribution map is used to reflect the thickness change of the vascular wall at different positions; Statistical analysis is carried out on the obtained wall thickness distribution map to obtain the corresponding statistical feature information; the statistical feature information includes statistical features such as average wall thickness and wall thickness standard deviation; and the wall thickness abnormal points are identified by using an anomaly detection algorithm, and the wall thickness abnormal points include partially thinned or thickened regions (for example: plaque or aneurysmal dilation); the corresponding vascular wall structure characteristics are obtained; Based on the finite element analysis algorithm, the blood vessel wall is simulated as a non-linear and anisotropic elastic material, and an internal pressure load is applied; to simulate the stress-strain relationship of the blood vessel under different internal pressure loads, and obtain the corresponding stress-strain curve; and based on this, wall tension calculation is carried out to obtain the corresponding elastic modulus distribution; the wall tension calculation refers to quantifying the tension level borne by the blood vessel wall based on the Laplace's law; the elastic modulus distribution includes the tangential elastic modulus and the axial elastic modulus; Furthermore, based on the obtained elastic modulus distribution, the maximum tolerable pressure is estimated to obtain the corresponding theoretical pressure-bearing upper limit; the maximum tolerable pressure estimation refers to simulating the expansion degree of the blood vessel under different pressures and predicting the theoretical pressure-bearing upper limit of each blood vessel sub-region according to the clinical safety guidelines; Based on the standardized patient information, vascular health data such as the age and vascular lesion history of the target patient are obtained; and based on the vascular health data, the blood vessel wall strength is corrected and the safety factor is set; to obtain the corresponding blood vessel state adjustment factor; the blood vessel wall correction refers to evaluating the elasticity, thickness and structural integrity of the patient's blood vessel wall based on the vascular health data, and adjusting the theoretical pressure-bearing upper limit of the blood vessel wall based on the evaluation results; the safety factor setting is to reserve a safety margin on the basis of the theoretical maximum pressure-bearing value; to prevent accidental injury; furthermore, through the blood vessel wall strength correction and safety factor setting process, the corresponding blood vessel state adjustment factor is obtained; Furthermore, integrating the hemodynamic characteristic index, the blood vessel wall structure characteristic, the theoretical pressure-bearing upper limit and the blood vessel state adjustment factor, the safe working pressure range of each blood vessel sub-region is calculated through a multi-objective optimization algorithm to obtain the blood vessel pressure-bearing capacity of each blood vessel sub-region; the multi-objective optimization algorithm includes the genetic algorithm and the particle swarm optimization algorithm.

[0020] It should be further noted that in the specific implementation process, the acquisition process of the injection pressure adjustment factor includes: Based on the collected physiological monitoring data, the heart rate change curve corresponding to the target patient is obtained, and heart rate variability analysis and periodic feature extraction are carried out on it to obtain the corresponding heart rate fluctuation pattern. The heart rate fluctuation pattern includes normal sinus rhythm, respiratory heart rate variability and non-periodic fluctuations, etc.; the heart rate fluctuation model is used to reflect the stability and regularity of the cardiac contraction rhythm; the heart rate variability analysis refers to obtaining the stability and fluctuation characteristics corresponding to the heart rate change curve by combining time domain analysis and frequency domain analysis methods; the periodic feature extraction identifies the periodic pattern of heart rate change through Fourier transform; Based on the heart rate fluctuation pattern, the cardiac systole-diastole cycle is divided and the time window is identified to obtain the best injection timing index; the cardiac systole-diastole cycle division refers to dividing the cardiac cycle into the systolic phase and the diastolic phase through R-wave detection, and the time window identification is used to identify the best injection parameters corresponding to different cardiac cycle stages and form the best injection time index based on this; Statistical feature extraction is performed on the systolic and diastolic blood pressure data of the corresponding patient based on the physiological monitoring data to obtain the corresponding blood pressure state features; the blood pressure state features include mean arterial pressure and pulse pressure difference; and based on the obtained blood pressure state features, intravascular pressure estimation and dynamic change prediction are performed to obtain the corresponding internal pressure fluctuation range; the intravascular pressure estimation refers to estimating the actual internal pressure level at different branch points in the blood vessels based on the patient's systolic and diastolic blood pressure data and in combination with anatomical structures, and factors such as blood pressure conduction characteristics, blood vessel diameter changes, and blood flow resistance need to be considered during the corresponding estimation process; and the non-invasive measurement results are converted into pressure estimation values at the target branch points; the dynamic change prediction analyzes the fluctuation pattern of the patient's blood pressure over time, combines physiological factors such as respiratory cycle and heart rate variability, and predicts the possible pressure fluctuation range during the contrast agent injection process; Obtain the blood vessel bearing capacity of each blood vessel sub-region and construct a pressure safety threshold curve based on it; the pressure safety threshold curve defines the safety factor of each blood vessel sub-region at different pressures; Based on the pressure safety threshold curve, set the upper limit of the injection pressure and divide the risk levels to obtain a sub-region pressure limit table; setting the upper limit of the injection pressure is used to ensure that the injection pressure does not exceed the blood vessel bearing capacity during the contrast agent injection process; the risk level division is to divide the injection pressure during the injection process into pressure range intervals of different risk levels and conduct classification management; form the corresponding regional pressure limit table; Construct a three-dimensional relationship model of heart rate - blood pressure - bearing capacity, perform dynamic simulation analysis and sensitivity testing, and obtain a parameter sensitivity matrix; the dynamic simulation analysis refers to simulating the real-time changes of blood vessels during the contrast agent injection process based on computer simulation, and factors such as cardiac cycle changes, blood vessel elastic response, and contrast agent flow characteristics are considered during the simulation process to generate curves of parameters such as blood vessel pressure, flow rate, and wall stress changing with time; the sensitivity testing evaluates the influence degree of the change of each parameter on the injection safety based on the change curves; through dynamic simulation analysis and sensitivity testing, the change degree of the blood vessel bearing capacity under different physiological states can be quantified, and the corresponding parameter sensitivity matrix is formed based on it; for example: by separately changing the value of a physiological parameter and observing the change amplitude of the blood vessel bearing capacity, the sensitivity degree of the corresponding physiological parameter is quantified; Optimize the pressure regulation strategy and design smooth transitions according to the parameter sensitivity matrix to obtain the corresponding pressure regulation reference value; optimizing the pressure regulation strategy means constructing a multi-dimensional optimization model based on the parameter sensitivity matrix, and through comprehensively considering safety and contrast effect, iteratively calculating the optimal pressure control strategy for each vascular sub-region; the smooth transition design means using spline interpolation and Lagrange polynomials to construct a continuously differentiable pressure change curve, and the pressure change curve realizes shock-free transition at the junction of vascular sub-regions, physiological state change points and injection stage transitions, and ensures the smoothness of pressure change through pressure change rate limitation and elastic buffer mechanism; by combining the optimization strategy with the smooth curve, a pressure regulation reference value including the reference pressure value, allowable deviation range, upper limit of change rate and emergency adjustment coefficient is formed. According to the optimal injection timing index, internal pressure fluctuation range, sub-region pressure limit table and pressure regulation reference value, dynamically adjust the contrast agent injection parameters through a proportional-integral-differential (PID) controller, generate a comprehensive parameter matrix including the base pressure value, dynamic adjustment coefficient, timing weight and safety limit factor, and record it as the injection pressure regulation factor.

[0021] It should be further noted that in the specific implementation process, the acquisition process of the physiological state influence factor includes: Extract the features of the collected physiological monitoring data to obtain the corresponding respiratory pattern features of the patient; the respiratory pattern features describe the rhythm and intensity of the patient's breathing. Based on the respiratory pattern features, identify the respiratory cycle and estimate the change in intrathoracic pressure to obtain the respiratory influence coefficient; respiratory cycle identification means extracting the time-domain and frequency-domain features of respiratory data through signal processing algorithms, identifying key time nodes such as the start of inspiration, peak inspiration, start of expiration and end of expiration, so as to construct a complete respiratory cycle; the estimation of intrathoracic pressure change deduces the change of intrathoracic pressure over time through the respiratory depth, frequency and rhythm parameters within the corresponding respiratory cycle, and obtains the influence degree of the respiratory process on the change of intrathoracic pressure based on it; the respiratory image coefficient refers to a comprehensive parameter that quantifies the influence degree of the patient's respiratory state on the intravascular pressure and contrast agent distribution. Obtain the electrocardiogram waveform of the target patient based on the collected physiological monitoring data, and perform waveform feature extraction and abnormal pattern recognition on it to obtain the corresponding heart rhythm state evaluation result; the waveform feature extraction means extracting waveform features through the application of wavelet transform and morphological analysis methods, and the waveform features include the morphology, amplitude and time interval of the P wave, QRS complex wave and T wave; the abnormal pattern refers to the identification and extraction of abnormal heart rhythm patterns such as premature beats, tachycardia and conduction block in the electrocardiogram waveform based on machine learning algorithms; through waveform feature extraction and abnormal pattern recognition, a heart rhythm state evaluation result including heart rate stability, heart rhythm type, conduction function and abnormal event statistics is generated. Predict the change of cardiac output and analyze the hemodynamic impact based on the evaluation result of the heart rhythm state, and obtain the cardiac function impact coefficient; the prediction of the change of cardiac output refers to estimating the change of cardiac output based on the heart rate and the evaluation result of the heart rhythm state; the cardiac output refers to the total amount of blood ejected from the left ventricle or the right ventricle into the aorta or the pulmonary artery per minute; the hemodynamic impact analysis is based on the fluid mechanics method, combines the cardiac output prediction result and the spatial structure model, simulates the blood flow distribution, blood flow velocity and wall shear stress changes under different heart rhythm states, and evaluates the impact degree and duration of the heart rhythm change on the hemodynamic parameters of the target vascular region based on them; by integrating the cardiac output change prediction and the hemodynamic impact analysis results, and applying the weighted fusion algorithm, the cardiac function impact coefficient that can be used to quantify the impact of cardiac function on the contrast process is obtained; Conduct trend analysis and threshold monitoring on the change of blood oxygen saturation in the physiological monitoring data to obtain the corresponding oxygenation state data, which can be used to reflect the oxygen-carrying capacity of the blood and the tissue oxygen supply status; the trend analysis refers to identifying the downward trend and fluctuation trend in the time series data corresponding to the blood oxygen saturation; the threshold monitoring is based on the pre-set multi-level blood oxygen saturation thresholds and combines the duration to evaluate the severity of the patient's hypoxemia; Conduct tissue perfusion evaluation and hypoxic risk prediction based on the oxygenation state data to obtain the oxygenation impact coefficient; the tissue perfusion evaluation refers to using the blood oxygen saturation, pulse waveform and heart rate variability data to construct a tissue oxygen supply and demand balance evaluation system, and obtaining indicators such as oxygen delivery efficiency and perfusion inhomogeneity based on it, and quantifying the blood supply status and oxygenation level in the target vascular region based on it; the hypoxic risk prediction is used to predict the hypoxia risk according to the blood supply status and oxygenation level in the blood; by comprehensively combining the tissue perfusion evaluation result and the hypoxic risk prediction result, and applying the fuzzy logic reasoning algorithm, the oxygenation impact coefficient that can be used to reflect the impact degree of the patient's oxygenation status on the contrast agent injection is obtained; Obtain the corresponding regional feature description of the target vascular sub-region based on the obtained vascular anatomical structure information, and the regional feature description includes the vascular position, functional importance and adjacent organ relationship; Risk weight allocation and key point identification are performed based on regional feature descriptions to obtain regional sensitivity coefficients. Risk weight allocation refers to applying the Analytic Hierarchy Process (AHP) and Delphi expert scoring theory to construct a multi-level risk assessment matrix according to vascular location, physiological function importance, and clinical risk statistical data. The multi-level risk assessment matrix assigns normalized risk weight values to each vascular sub-region by comparing the clinical vulnerability, complication incidence, and functional damage consequences of different vascular sub-regions. The key point identification is based on vascular morphology analysis and hemodynamics, and combines computer vision algorithms to identify special structural points in the blood vessels. The special structural points include bifurcation points, stenosis segments, aneurysmal dilation areas, and abnormally curved regions. The topological importance and blood flow distribution impact of the corresponding special structural points in the vascular network are evaluated using a graph theory-based network analysis method, and the corresponding evaluation results are integrated with the corresponding risk weight matrix, and a non-linear mapping function is applied to quantify the regional sensitivity coefficients corresponding to each vascular sub-region. The regional sensitivity coefficients can be used to measure the sensitivity of each vascular sub-region to pressure changes. The respiratory impact coefficient, cardiac function impact coefficient, oxygenation impact coefficient, and regional sensitivity coefficients are integrated through multi-sensor data fusion technology to construct a real-time physiological state assessment model, and physiological state impact factors at each moment are obtained. The multi-sensor data fusion technology refers to applying Kalman filtering and Bayesian network frameworks to achieve time synchronization and feature-level fusion of heterogeneous physiological signals. The input parameters of the physiological state assessment model are the corresponding respiratory impact coefficient, cardiac function impact coefficient, oxygenation impact coefficient, and regional sensitivity coefficients. The real-time physiological state assessment model realizes non-linear mapping through a multi-layer perceptron, and at the same time introduces expert knowledge constraints to ensure that the model output conforms to physiological laws, generating physiological state impact factors that comprehensively reflect the impact degree of the patient's current physiological state on the angiography process.

[0022] It should be further noted that in the specific implementation process, the process of obtaining the physiological state risk marker value includes: Based on clinical safety guidelines, multi-parameter physiological safety thresholds are constructed to obtain corresponding safety reference standards. The safety reference standards include the normal ranges and safety limits of physiological parameters such as respiratory rate, heart rate variability, blood oxygen saturation, and blood pressure fluctuation range. Individually adjust the obtained safety reference standards and make corrections for special cases to obtain a corresponding set of personalized safety thresholds; individual adjustment refers to the targeted adjustment of the constructed safety reference standards based on the patient's actual physiological parameters, and the adjustment process takes into account factors such as patient age stratification, body mass index differences, underlying disease conditions, and organ function reserve, generating a safety parameter matrix adapted to individual characteristics. The personalized parameter standards include numerical values such as heart rate variability range, blood pressure fluctuation limit, respiratory rate safety interval, and lower limit of blood oxygen saturation, etc.; special case correction further refines the individualized parameters based on the patient's special physiological state or pathological conditions, including narrowing of the heart rate tolerance range for cardiovascular disease patients, reduction of the blood pressure fluctuation limit for patients with renal insufficiency, setting of special oxygenation index thresholds for patients with respiratory diseases, and adjustment of sensitivity parameters for patients with a history of contrast agent allergy, etc., to form the final set of personalized safety thresholds; Obtain the corresponding physiological state influencing factors at each moment, and perform component decomposition and parameter mapping based on them to obtain a multi-dimensional physiological index vector; component decomposition refers to separating the physiological state influencing factors into several independent components; parameter mapping is used to map the corresponding independent vectors into a standardized metric space to form a multi-dimensional physiological index vector; Compare the multi-dimensional physiological index vector with the set of personalized safety thresholds one by one and calculate the deviation to obtain a list of parameter deviation degrees; one-by-one comparison means comparing the obtained multi-dimensional physiological index vector with the corresponding set of personalized safety thresholds respectively, and the corresponding comparison process needs to consider the differential processing of parameter types. The differential processing of parameter types includes methods such as judging the upper and lower limits of single-threshold parameters, performing range inclusion tests on interval-type parameters, and evaluating the trend compliance of time-series parameters, etc.; deviation calculation quantifies the deviation degree of each physiological parameter based on the comparison results, generating a list of parameter deviation degrees containing deviation indicators such as deviation direction, deviation amplitude, deviation duration, and deviation rate; Quantify the risk level and assign weights based on the list of parameter deviation degrees to obtain a weighted risk score; risk level quantification refers to converting each deviation indicator in the list of parameter deviation degrees into a standardized risk value. The quantification process takes into account factors such as the danger difference of the deviation direction, the non-linear risk mapping of the deviation amplitude, and the cumulative effect of the deviation duration, etc., and sets corresponding risk levels based on different degrees of deviation to generate the original risk scores of each deviation indicator; weight assignment assigns weights to each deviation indicator based on clinical importance and physiological impact degree, and uses the importance scoring driven by the expert knowledge base for weight assignment; based on the results of risk level quantification and weight assignment, perform weighted summation to obtain a weighted risk score that can be used to reflect the patient's current overall risk state; Risk level classification and critical state identification are performed according to the weighted risk score to obtain the risk classification result. Risk level classification refers to setting multi-level risk classification criteria based on the weighted risk score, and based on clinical medicine guidelines, dividing it into different level regions such as safe, attention, warning, and danger, and obtaining the level region to which the current weighted risk score belongs. Critical state identification is based on boundary condition analysis using a mutation point detection algorithm to accurately capture the critical state where the risk level is about to undergo a transition, and generate a risk classification result that includes comprehensive information such as the current risk level, critical state flag, risk change trend, and warning time window. Based on the current physiological state influencing factors and the time series corresponding to the physiological monitoring parameters, time-series risk prediction and trend analysis are performed to obtain a risk evolution trend graph. Time-series risk prediction refers to predicting the risk state by applying the sliding time window technique to generate the risk change trend at multiple future time points. The trend analysis refers to evaluating the change direction and speed of the corresponding risk change trend based on the time-series analysis algorithm to generate the corresponding risk evolution trend graph. Based on the risk evolution trend graph, early warning level determination and risk accumulation effect evaluation are performed to obtain a dynamic risk index. Early warning level determination refers to performing multi-level early warning analysis on the risk change trend in the risk evolution trend graph, and using a hierarchical early warning algorithm to divide the predicted risk change trend into different early warning levels such as routine monitoring, close observation, early warning, and emergency intervention, and generating an early warning decision table that includes the early warning level, trigger condition, and recommended intervention time. Risk accumulation effect evaluation is based on the risk change trend to perform risk accumulation quantification, integrating the early warning decision table and the risk accumulation quantification result to generate a dynamic risk index that reflects the real-time risk state and change trend. Integrate the risk classification result and the dynamic risk index, and generate a comprehensive risk assessment result through a fuzzy logic inference algorithm, and perform defuzzification processing on it to obtain the corresponding physiological state risk marker value.

[0023] It should be further noted that in the specific implementation process, the process of obtaining the angiography safety degree includes: Obtain the injection pressure adjustment factors corresponding to each vascular sub-region, and based on them, perform spatial distribution analysis and key region identification to obtain a pressure-sensitive region map. Spatial distribution analysis refers to performing topographic spatial mapping and distribution feature extraction on the injection pressure adjustment factors based on the vascular sub-region to form the corresponding spatial distribution pattern. Key region identification is based on the spatial distribution pattern, and through computer vision technology, accurately locate abnormal regions and risk hotspots to accurately mark local regions and potential risk points where the pressure sensitivity is significantly higher than the surrounding regions, and generate a pressure-sensitive region map that includes the location, range size, sensitivity level classification, and adjacent relationship of the sensitive region. Based on the pressure-sensitive area map, risk level assessment and safety boundary delineation are carried out to obtain a pressure safety score; risk level assessment refers to the quantitative analysis and risk classification of the pressure sensitivity of each area in the pressure-sensitive area map to obtain the corresponding area risk index for each area; safety boundary delineation is based on computer image processing algorithms and combines the risk level assessment results to accurately define the safe operation range, generate a safe operation boundary with buffer design, integrate the area risk index and the safe operation boundary, and obtain a pressure safety score that can be used to reflect the pressure safety status through a multi-objective optimization algorithm; Organize the physiological state risk marker values at each moment into a time series, conduct time series pattern mining and fluctuation characteristic analysis to obtain risk fluctuation characteristics; time series pattern mining refers to the in-depth analysis and pattern recognition of the time series data corresponding to the physiological state risk marker values to obtain the time series pattern of the corresponding physiological state risk marker values, and the time series pattern includes time series information such as periodic characteristics, trend components, mutation points, and state transition characteristics; fluctuation characteristic analysis is based on the time series pattern and uses fluctuation spectrum analysis to quantitatively evaluate the dynamic characteristics such as the change amplitude, change rate, fluctuation frequency, and stability of the risk marker values; by integrating the time series pattern information and the fluctuation characteristic evaluation results, and using principal component analysis and clustering algorithms for feature dimensionality reduction and pattern classification, a risk fluctuation characteristic description that can be used to reflect the time evolution law of physiological state risk is finally formed; Based on the risk fluctuation characteristic description, stability assessment and outlier detection are carried out to obtain a physiological risk score; stability assessment refers to the statistical analysis of the time series of physiological state risk marker values to obtain the variance, coefficient of variation, and fluctuation frequency of the corresponding physiological state risk marker values, and generate a stability index and a fluctuation trend graph based on them; outlier detection uses a time series anomaly detection algorithm and combines the fluctuation trend graph to identify the peaks, mutation points, and intervals continuously deviating from the baseline in the time series of physiological state risk marker values, and conducts classification and risk level division; Feature extraction is carried out on the obtained historical contrast examination records to obtain the corresponding historical contrast feature set, and the historical contrast feature set includes the contrast agent dosage, adverse reaction records, and examination completion quality; Based on the historical contrast agent feature set, perform contrast agent tolerance analysis and sensitivity prediction to obtain a historical risk score. Contrast agent tolerance analysis refers to mining the dose-response relationship pattern in the patient's historical contrast agent examination records and constructing an individualized tolerance model based on it. The individualized tolerance model integrates key features such as the previous contrast agent dosage, adverse reaction type and severity, occurrence time point, and duration. Sensitivity prediction is based on performing time series analysis on historical response data using machine learning algorithms, identifying potential sensitivity trend changes, and combining with a Bayesian network to predict the risk probability distribution corresponding to the corresponding contrast agent examination process. The historical risk score is a standardized risk quantification index generated by comparing the predicted risk probability distribution with the clinically preset threshold, and the historical risk score can be used to reflect the specific risk level of the patient individual to the contrast agent inferred from the historical contrast agent examination records. Establish a three-source data feature space, perform feature extraction and dimensionality reduction processing on the pressure safety score, physiological risk score, and historical risk score to obtain a fused feature vector. The establishment of the three-source data feature space refers to constructing a high-dimensional feature representation framework including three dimensions of pressure, physiology, and history, and the establishment process uses tensor decomposition technology and multi-view learning methods. Construct a multi-level safety assessment model based on the fused feature vector to obtain a preliminary safety assessment result. The construction of the multi-level safety assessment model refers to designing a hierarchical safety risk assessment architecture based on the fused feature vector, and the construction process is realized by using machine learning technologies such as deep neural networks, decision tree ensembles, and probabilistic graphical models. Input the obtained fused feature vector into the constructed multi-level safety assessment model to generate a multi-dimensional preliminary safety assessment result including safety level, confidence interval, and risk distribution. Adopt transfer learning methods and introduce a clinical expert knowledge base to calibrate and optimize the preliminary safety assessment result to obtain the contrast agent safety degree corresponding to the template patient in the corresponding vascular sub-region.

[0024] It should be further noted that in the specific implementation process, the process of obtaining the optimal parameter path for contrast agent injection includes: Obtain the contrast agent safety degree data of each vascular sub-region and the pre-set imaging quality requirement parameters, and construct corresponding optimization target constraint conditions based on them. The imaging quality requirement parameters include contrast requirement, spatial resolution requirement, time resolution requirement, etc. The optimization target constraint conditions define the objective function and constraint conditions for contrast agent injection parameter optimization, and the constraint conditions include safety constraints and quality requirement constraints. Based on the optimization target constraint conditions, establish the mapping relationship between injection parameters, safety degree, and imaging quality, and construct the corresponding parameter-effect response surface based on it. The parameter-effect response surface can be used to reflect the comprehensive impact of injection parameter adjustment on safety degree and imaging quality. Construct a corresponding parameter state space based on the contrast agent injection parameters corresponding to the corresponding contrast agent injection process. The parameter state space includes all possible parameter combinations and their evolution paths during the injection of a contrast agent. The contrast agent injection parameters include injection rate, pressure, total amount, time, pulse mode, etc. Define an action set and a state transition function in the parameter space to obtain an injection control Markov decision process model. The action set includes basic operations such as increasing / decreasing the rate, increasing / decreasing the pressure, etc. The definition of the action set means precisely quantifying the operations that can be performed by the high-pressure injection device into discrete actions, including basic operations such as increasing / decreasing the rate, increasing / decreasing the pressure, etc., to form a complete control instruction library. The state transition function establishes a probability mapping relationship for the high-pressure injection device to transfer from the current parameter state to the next state after executing a control action, and obtains a state evolution equation set through fitting with hydrodynamic and historical patient physiological data information. Furthermore, based on the parameter state space, action set, and state transition function, construct a complete model of the Markov decision process represented by the quadruple (S, A, P, R). Comprehensively consider factors such as contrast agent safety, imaging quality satisfaction, contrast agent dosage, and operation time to design a deep reinforcement learning reward function, and train a deep Q-network or policy gradient network based on it to obtain a corresponding injection strategy model. Perform real-time adjustment and optimization on the injection strategy model through an online learning method to obtain an adaptive injection control strategy. Online learning can continuously optimize the strategy according to real-time feedback, enabling the high-pressure injection device to adapt to patient individual differences and environmental changes. Based on the adaptive injection control strategy, perform path planning and trajectory optimization in the parameter state space to obtain an injection parameter time series. Path planning refers to searching for the optimal parameter change path in the parameter state space to ensure that the contrast agent injection not only meets the imaging requirements but also ensures patient safety. The trajectory optimization process considers key factors such as the dynamic change of blood vessel pressure bearing, the real-time physiological state of the patient, the distribution kinetics of the contrast agent, and the anatomical characteristics of the target blood vessel, and combines the injection strategy model to predict the optimal injection parameter settings at each time point, and finally generates an injection parameter time series that precisely changes parameters such as injection rate, pressure, and pulse mode over time.

[0025] Conduct safety verification and robustness testing on the injection parameter time series to obtain the optimal parameter path for the corresponding contrast agent injection; and generate corresponding injection control instructions based on it and transmit them to the high-pressure injection device for execution.

[0026] In the embodiments of the present application, through the collaborative action of multiple modules and the application of deep learning algorithms, precise personalized control of contrast agent injection parameters is achieved, which not only significantly improves the safety of contrast examinations but also ensures the effectiveness of imaging quality. By obtaining the patient's multi-dimensional physiological data and historical examination records through the API interface and comprehensively analyzing them in combination with the characteristics of the contrast agent, precise calculation of individualized injection parameter coefficients is realized, taking into account both the patient's physical differences and the organ function status; through the acquisition of vascular anatomical structure information and hydrodynamic analysis, the bearing capacity and pressure sensitivity of each vascular sub-region can be accurately evaluated, providing an accurate anatomical basis for safe injection. The physiological state assessment model constructed based on real-time physiological monitoring data realizes a dynamic risk marking and warning mechanism, improving the examination efficiency while ensuring the safety of patients. Through the multi-source data fusion of injection pressure adjustment factors, physiological state risk marking values, and historical contrast records, a contrast safety degree that comprehensively reflects the vascular safety state is constructed, providing a reliable decision-making basis for injection control. With the help of the deep reinforcement learning algorithm to optimize the injection parameter path, real-time dynamic adjustment and adaptive control of the parameters are achieved, maximizing the imaging effect while minimizing the safety risk. Through continuous evaluation and parameter optimization mechanisms, it can continuously adapt to patient individual differences and clinical examination needs, providing strong support for precision medicine.

[0027] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

[0028] It should be noted that in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or device. Without further limitations, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or device including the said element.

[0029] In the description of the present invention, it should be understood that the terms "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0030] In the description of the present invention, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0031] In the description of the present invention, "several" means one or more, and "a large number" means two or more.

[0032] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0033] For the formulas in this specification, the dimensional quantities are removed and the numerical values are calculated. The formula is obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters and threshold selections in the formula are set by those skilled in the art according to the actual situation.

[0034] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and purposes of the present invention. The scope of the present invention is defined by the claims and their equivalents.

Claims

1. An angiography high-pressure injection system, characterized in that, Including: A data acquisition module for acquiring physiological data and medical records of a target patient to obtain corresponding patient physiological data information; The patient physiological data information includes standardized patient information, physiological monitoring data, renal function assessment data, and historical contrast examination records; A parameter calculation module for obtaining corresponding individualized contrast agent injection parameter coefficients based on the standardized patient information and renal function assessment data, and in combination with the contrast agent type; A vascular analysis module for obtaining vascular anatomical structure information corresponding to the vascular region of the target patient, and performing pressure assessment based on hemodynamic characteristics to obtain the vascular bearing capacity corresponding to each vascular sub-region within the corresponding vascular region; and obtaining an injection pressure adjustment factor corresponding to each vascular sub-region in combination with the patient physiological data information; A physiological assessment module for assessing the physiological state of the vascular region of the target patient based on the patient physiological data information to obtain corresponding physiological state influencing factors, and performing risk marking in combination with a pre-constructed physiological state safety threshold to obtain corresponding physiological state risk marking values at different times; A safety construction module for performing multi-source data fusion based on the obtained injection pressure adjustment factor, physiological state risk marking value, and historical contrast examination records, and constructing a corresponding contrast safety degree for each vascular sub-region based on the above; An injection control module for obtaining an optimal parameter path for contrast agent injection corresponding to the target patient based on the obtained contrast safety degree, and in combination with a deep reinforcement learning algorithm, and controlling a high-pressure injection device to perform an injection operation based on the above; 2. The angiography high-pressure injection system according to claim 1, characterized in that, The process of obtaining the patient physiological data information includes: Setting up a data acquisition unit to perform data crawling based on the data acquisition unit to obtain corresponding basic file information and historical contrast examination records; Performing digital processing and standardized storage on the collected basic file information to obtain corresponding standardized patient information; Setting up a data monitoring unit to perform real-time acquisition of the physiological parameters of the patient based on the data monitoring unit; obtaining corresponding physiological parameter data; and performing data filtering and noise elimination processing on the collected physiological parameters to obtain smooth physiological monitoring data; The data monitoring unit is further used to acquire data on renal function-related indicators of the patient to obtain corresponding renal function assessment data; Summarizing the obtained standardized patient information, physiological monitoring data, renal function assessment data, and historical contrast examination records to obtain corresponding patient physiological data information.

3. The angiography high-pressure injection system according to claim 2, wherein The process of obtaining the individualized contrast agent injection parameter coefficients includes: Obtaining the corresponding physical health index of the target patient based on the standardized information; and obtaining the corresponding weight range of the target patient based on the physical health index; Performing benchmark dose mapping based on the weight range of the target patient to obtain a benchmark dose value corresponding to the weight of the target patient; and performing unit body weight injection amount adjustment and upper limit control on the obtained benchmark dose value to obtain a corresponding weight adjustment coefficient; Obtaining the corresponding age grouping result of the patient based on the standardized patient information; and performing physiological function attenuation estimation and compensation factor calculation based on the age grouping result to obtain a corresponding age correction coefficient; Classify the collected renal function assessment data into renal function grades and evaluate the risks to obtain the corresponding renal function status index; Construct a corresponding kidney load assessment model based on the obtained renal function status index, and classify the renal function of the corresponding patients according to the renal function assessment data to obtain the corresponding renal function risk level; Predict the contrast agent clearance rate and set the safety threshold according to the renal function risk level corresponding to the patient; obtain the corresponding renal function protection coefficient; Obtain the contrast agent type information; perform hydrodynamic analysis and injection characteristic simulation based on the contrast agent type information to obtain the corresponding contrast agent characteristic correction factor; Use the body weight adjustment coefficient, age correction coefficient, renal function protection coefficient, and contrast agent characteristic correction factor as input variables; and assign weights to each input variable; integrate each input variable by applying a weighted fusion algorithm to obtain the corresponding individualized contrast agent injection parameter coefficient.

4. The angiography high-pressure injection system according to claim 1, wherein The process of obtaining the vascular anatomical structure information corresponding to the vascular region of the target patient includes: Collect initial images of the patient's vascular region based on a pre-selected angiography device to obtain the corresponding original vascular images; Perform digital enhancement and noise suppression on the obtained original vascular images to obtain the corresponding optimized vascular images; Perform edge detection and contour extraction on the obtained optimized vascular images to obtain the corresponding vascular contour data; Obtain the blood vessel diameters corresponding to each blood vessel in the target vascular region based on the extracted vascular contour data; and generate the corresponding blood vessel diameter distribution map based on it; Perform three-dimensional reconstruction based on the obtained blood vessel diameter distribution map and the blood vessel diameter distribution map to obtain the corresponding spatial structure model of the vascular region; Perform curvature quantization calculation and bend point identification based on the spatial structure model to obtain the corresponding blood vessel curvature index set; Identify the branch points in the corresponding spatial structure model by applying a topological analysis algorithm, and measure the angle between the branch blood vessels and the main blood vessel at the corresponding branch points; at the same time, record the three-dimensional coordinates corresponding to the branch points; and construct the corresponding blood vessel branch topological structure based on the three-dimensional coordinates and angles of the branch points; Based on the obtained blood vessel branch topological structure, evaluate the importance based on the supply tissue range of the branch blood vessels corresponding to the branch points, and estimate the blood flow ratio in the corresponding branch blood vessels by applying a pre-constructed hydrodynamic model; summarize the obtained blood flow ratio and importance evaluation results to obtain the corresponding branch characteristic data; Identify and extract the anatomical feature points corresponding to the target vascular region based on the obtained blood vessel diameter distribution map, blood vessel curvature index set, and branch characteristic data; and divide the corresponding vascular region into several continuous vascular sub-regions based on the anatomical feature points; Establish an anatomical indexing structure for the corresponding vascular sub-regions to form complete vascular anatomical structure information.

5. The angiography high-pressure injection system according to claim 4, wherein The acquisition of the blood vessel pressure-bearing capacity corresponding to each vascular sub-region includes: Measure the blood flow velocity and blood flow volume corresponding to each vascular sub-region in combination with the obtained anatomical structure information; and perform three-dimensional reconstruction based on the measurement results to obtain the corresponding blood flow velocity vector field; and obtain the Reynolds number corresponding to each sub-region based on the obtained blood flow velocity vector field; obtain the corresponding set of hemodynamic characteristic indexes based on it; Identify the corresponding optimized vascular image to obtain the blood vessel wall thickness within each vascular sub-region; and construct the corresponding wall thickness distribution map based on it; Conduct statistical analysis on the obtained wall thickness distribution map to obtain the corresponding statistical characteristic information; and identify the wall thickness abnormal points by using an anomaly detection algorithm; obtain the corresponding blood vessel wall structure characteristics; apply internal pressure load based on the blood vessel wall structure characteristics to obtain the corresponding stress-strain curve; and calculate the wall tension based on it to obtain the corresponding elastic modulus distribution; Estimate the maximum tolerable pressure according to the obtained elastic modulus distribution to obtain the corresponding theoretical pressure bearing upper limit; Obtain the blood vessel health data of the target patient such as age and blood vessel lesion history based on the standardized patient information; and perform blood vessel wall strength correction and safety factor setting based on the blood vessel health data; obtain the corresponding blood vessel state adjustment factor; Obtain the blood vessel pressure bearing capacity of each vascular sub-region based on the hemodynamic characteristic indexes, blood vessel wall structure characteristics, theoretical pressure bearing upper limit and blood vessel state adjustment factor.

6. The angiography high-pressure injection system according to claim 5, wherein The process of obtaining the injection pressure adjustment factor includes: Obtain the heart rate change curve corresponding to the target patient based on the collected physiological monitoring data, and perform heart rate variability analysis and periodic feature extraction on it to obtain the corresponding heart rate fluctuation pattern; Divide the cardiac systolic and diastolic cycles and identify the time window based on the heart rate fluctuation pattern to obtain the best injection timing index; Extract the statistical characteristics of the systolic and diastolic blood pressure data of the corresponding patient based on the physiological monitoring data to obtain the corresponding blood pressure state characteristics; Obtain the blood vessel pressure bearing capacity of each vascular sub-region, and construct a pressure safety threshold curve based on it; set the upper limit of the injection pressure and divide the risk level based on the pressure safety threshold curve to obtain the sub-region pressure limit table; Construct a three-dimensional relationship model of heart rate-blood pressure-pressure bearing capacity, and perform dynamic simulation analysis and sensitivity test based on it to obtain the parameter sensitivity matrix; Optimize the pressure adjustment strategy and design smooth transition according to the parameter sensitivity matrix to obtain the corresponding pressure adjustment reference value; Generate the corresponding injection pressure adjustment factor according to the best injection timing index, internal pressure fluctuation range, sub-region pressure limit table and pressure adjustment reference value.

7. The angiography high-pressure injection system according to claim 6, characterized in that, The process of obtaining the physiological state influence factor includes: Extract the characteristics of the collected physiological monitoring data to obtain the corresponding respiratory mode characteristics of the patient; Identify the respiratory cycle and estimate the change in intrathoracic pressure based on the respiratory mode characteristics to obtain the respiratory influence coefficient; Obtain the electrocardiogram waveform of the target patient based on the collected physiological monitoring data, and perform waveform feature extraction and abnormal mode recognition on it to obtain the corresponding heart rhythm state evaluation result; predict the change in cardiac output and analyze the hemodynamic influence based on the heart rhythm state evaluation result to obtain the heart function influence coefficient; Perform trend analysis and threshold monitoring on the changes in blood oxygen saturation within physiological monitoring data to obtain corresponding oxygenation status data; perform tissue perfusion assessment and hypoxic risk prediction based on the oxygenation status data to obtain an oxygenation impact coefficient; Obtain a regional feature description corresponding to the target vascular sub-region based on the obtained vascular anatomical structure information; perform risk weight assignment and key point identification based on the regional feature description to obtain a regional sensitivity coefficient; Obtain the physiological state impact factor at each moment by integrating the respiratory impact coefficient, cardiac function impact coefficient, oxygenation impact coefficient, and regional sensitivity coefficient.

8. The angiography high-pressure injection system according to claim 7, wherein The process of obtaining the physiological state risk marker value includes: Construct a safety reference standard; perform individualized adjustment and special situation correction on the obtained safety reference standard to obtain the corresponding personalized safety threshold set; Obtain the physiological state impact factor corresponding to each moment, and perform component decomposition and parameter mapping based on it to obtain a multi-dimensional physiological index vector; Compare the multi-dimensional physiological index vector with the personalized safety threshold set one by one and calculate the deviation to obtain a parameter deviation list; Quantify the risk level and assign weights based on the parameter deviation list to obtain a weighted risk score; Perform risk level classification and critical state identification based on the weighted risk score to obtain a risk classification result; Perform time-series risk prediction and trend analysis based on the current physiological state impact factor and the time series corresponding to the physiological monitoring parameters to obtain a risk evolution trend graph; Determine the warning level and evaluate the risk cumulative effect based on the risk evolution trend graph to obtain a dynamic risk index; Integrate the risk classification result and the dynamic risk index, generate a comprehensive risk assessment result through a fuzzy logic inference algorithm, and perform defuzzification processing on it to obtain the corresponding physiological state risk marker value.

9. The angiography high-pressure injection system according to claim 8, wherein The process of obtaining the contrast safety degree includes: Obtain the injection pressure adjustment factor corresponding to each vascular sub-region, and perform spatial distribution analysis and key area identification based on it to obtain a pressure-sensitive area map; Perform risk level assessment and safety boundary determination based on the pressure-sensitive area map to obtain a pressure safety score; Organize the physiological state risk marker values at each moment into a time series, and perform time series pattern mining and fluctuation characteristic analysis to obtain risk fluctuation characteristics; Perform stability assessment and outlier detection based on the risk fluctuation characteristic description to obtain a physiological risk score; Extract features from the obtained historical contrast examination records to obtain the corresponding historical contrast feature set; perform contrast tolerance analysis and sensitivity prediction based on the historical contrast feature set to obtain a historical risk score; Establish a three-source data feature space, perform feature extraction and dimensionality reduction processing on the pressure safety score, physiological risk score, and historical risk score to obtain a fused feature vector; the establishment of the three-source data feature space refers to constructing a high-dimensional feature representation framework including three dimensions of pressure, physiology, and history; Construct a multi-level safety assessment model based on the fused feature vector to obtain a preliminary safety degree assessment result; Input the obtained fused feature vector into the constructed multi-level safety assessment model to generate a multi-dimensional preliminary safety degree assessment result; Calibrate and optimize the results of the preliminary safety evaluation to obtain the angiography safety corresponding to the template patient in the corresponding vascular sub-region.

10. The angiography high-pressure injection system according to claim 9, characterized in that, The process of obtaining the optimal parameter path for contrast agent injection includes: Obtain the angiography safety data of each vascular sub-region and the pre-set imaging quality requirement parameters, and construct corresponding optimization objective constraint conditions based on them; Establish the mapping relationship between injection parameters, safety, and imaging quality based on the optimization objective constraint conditions, and construct the corresponding parameter-effect response surface based on it; Construct the corresponding parameter state space based on the contrast agent injection parameters corresponding to the corresponding angiography injection process; Define the action set and state transition function in the parameter space to obtain the injection control Markov decision process model; Based on the parameter state space, action set, and state transition function, construct a complete Markov decision process model represented by a quadruple; Design a deep reinforcement learning reward function, and train a deep Q network or policy gradient network based on it to obtain the corresponding injection policy model; perform real-time adjustment and optimization of the injection policy model through an online learning method to obtain an adaptive injection control policy; Perform path planning and trajectory optimization in the parameter state space based on the adaptive injection control policy to obtain the injection parameter time series; Perform safety verification and robustness testing on the injection parameter time series to obtain the optimal parameter path for contrast agent injection; generate corresponding injection control instructions based on it and transmit them to the high-pressure injection device for execution.

Images