1510 results about "Blood flow" patented technology

The invention relates to the technical field of blood pressure measurement, in particular to a cuff-free blood pressure continuous monitoring method based on ICG, PPG and ECG multi-mode physiological signals. According to the method, deep mining and fusion are carried out based on multi-modal physiological signals such as a chest impedance signal ICG, a photoelectric volume pulse wave signal PPG and an electrocardiosignal ECG of a tested object synchronously collected by multi-modal hemodynamics monitoring equipment, and a richer multi-modal feature matrix related to blood pressure changes is constructed; after deep learning fusion training is carried out on the constructed cuff-free blood pressure prediction model, prediction output of a cuff-free blood pressure prediction result can be directly carried out according to ICG, PPG and ECG multi-mode physiological signals of a to-be-detected tested object by means of the cuff-free blood pressure prediction model, the generalization ability and monitoring precision of continuous monitoring of the cuff-free blood pressure can be effectively improved, and the accuracy of continuous monitoring of the cuff-free blood pressure can be improved. The continuous, non-invasive and high-precision blood pressure monitoring requirements are met, and the clinical application value is more remarkable.

The invention relates to the field of medical image analysis, in particular to a deep learning prediction system and method based on multi-modal thyroid cancer lymph node metastasis, and the system comprises a data collection module, a preprocessing module, a nodule segmentation module, a feature extraction module, a feature fusion module, a metastasis prediction module, an interpretability analysis module and a result display module. An ultrasonic image, an elastic imaging image, an ultra-micro blood flow image and clinical index data of a patient are integrated, an improved U-Net algorithm is used for precise segmentation of a thyroid nodule region, a multi-branch deep network is used for extracting multi-modal features, a dynamic weight fusion algorithm is used for integrating the features, and the accuracy of the thyroid nodule region is improved. According to the method, the thyroid cancer lymph node metastasis state (non-metastasis, central region metastasis or lateral neck metastasis) is predicted, meanwhile, a two-dimensional interpretability framework of Grad-CAM activation diagram and SHAP value contribution degree analysis is introduced, an intuitive prediction basis is provided for doctors, and the thyroid cancer lymph node metastasis prediction accuracy is remarkably improved.

The invention belongs to the technical field of medical informatization, and provides an anesthesia medication management system with biological recognition, comprising: a biological recognition module verifies the identities of medical staff and patients through a vein recognition technology; the multi-source data acquisition module acquires vital sign data and equipment parameters of a patient in real time to obtain multi-source data; the intelligent drug management module authorizes to store and take drugs according to the biological recognition result and generates an electronic anesthesia prescription; the processing decision module receives the multi-source data and generates a medicine adjusting instruction through a preset rule and an algorithm in combination with an electronic anesthesia prescription; the execution control module carries out secondary confirmation on the medicine adjusting instruction through biological recognition and then sends the medicine adjusting instruction to anesthetic infusion equipment to be executed; according to the method, through the electroencephalogram double-frequency index, the entropy index and the hemodynamic parameters, in combination with the anesthesia depth evaluation result and the personalized drug metabolism and effect model, the medication scheme is dynamically adjusted, the optimal infusion rate is generated, the anesthesia depth control is more accurate, and the fluctuation range is narrowed.

This disclosure relates to systems, methods, and devices for plaque analysis, vessel and fluid flow analysis, and / or risk determination or prediction thereof. Some embodiments relate to determining fractional flow reserve (FFR) values. Some embodiments relate to determining FFR values using 3D-printed models. Some embodiments relate to identifying thin cap fibroatheroma based on analysis of computed tomography (CT) imaging. Some embodiments relate adjusting calcified plaque thresholds for CT images to address effects of calcium blooming.

The invention relates to the technical field of intelligent anesthesia precise regulation and control, and discloses an anesthetic dosage optimization method based on artificial intelligence. According to the method, a dynamic treatment interval is constructed, and the boundary of the dynamic treatment interval is adaptively adjusted according to the real-time sedation depth and the nociceptive stimulation level. And in the interval, performing pattern recognition on the continuous electroencephalogram signals and the hemodynamic parameters, and marking abnormal events deviating from a standard anesthesia state. And establishing a correlation network of the drug effect chamber concentration and the abnormal events, and generating a virtual drug response curve for predicting the trend of the abnormal events under different doses. Whether dose strategy reconstruction is started or not is determined by comparing the goodness of fit between the prediction curve and the actual physiological trajectory. During reconstruction, contribution weights of historical drug infusion points to abnormal events are backtracked and analyzed, and adjustment coefficients are distributed and integrated into a new infusion sequence. According to the invention, individualization and self-adaptive optimization of anesthesia administration are realized, and the accuracy and safety of anesthesia depth control are improved.

The invention relates to the technical field of medical image processing, in particular to an automatic blood vessel extraction method and system based on a CT image, and the method comprises the steps: 1, constructing a blood vessel local coordinate system, and carrying out the double-domain separation; 2, dynamic double-domain fusion, wherein contrast self-adaptive weighted fusion is carried out on the spatial domain enhanced image and the fundamental frequency blood vessel image; 3, direction constraint morphological reconstruction: constructing a structural element with a long axis parallel to the direction of the blood vessel according to the main direction vector v of the blood vessel; sequentially executing directional opening operation and directional closing operation along the direction of the main direction vector v of the blood vessel; and 4, anatomically-driven blood vessel repair and correction: tracking contours of adjacent slices along the direction of the main direction vector v of the blood vessel and fitting a repair path on the basis of a generated calcified region mask Mcal marked region, and correcting a topological structure at a bifurcation point according to a branching angle and hemodynamic constraint. The vascular structure can be accurately and stably extracted from the CT image by comprehensively utilizing restoration technologies such as spatial domain enhancement and frequency domain separation.

The invention discloses a non-invasive hemodynamics monitoring method and system based on deep learning, and relates to the technical field of medical instruments, and the method comprises the steps: obtaining invasive blood flow data and non-invasive radial artery waveform data of a corresponding time point; time reference alignment is carried out on invasive blood flow data and non-invasive radial artery waveform data through time points, time drift errors between invasive and non-invasive equipment are eliminated, an initial non-invasive detection model is constructed, the method better fits the actual state of non-invasive detection, non-invasive feature vectors are used as input features after vascular elasticity compensation processing, and the non-invasive detection accuracy is improved. The initial non-invasive detection model is trained by taking blood flow parameters in the invasive data set as supervision annotation data, so that the consistency of model output and real invasive blood flow parameters is improved, 'waveform fragment-blood flow parameter 'space-time mapping is established, the running dynamic state of the non-invasive detection model is evaluated and analyzed, and the detection accuracy is improved. The performance change of the model in the training and running process can be monitored in real time, and convergence, over-fitting and under-fitting problems can be found in time.

The invention discloses a hypertensive heart disease early screening system fusing ultrasonic multiple parameters, which comprises the following steps: acquiring ultrasonic image data and physiological index monitoring parameters of a patient at different time points, performing difference comparison on heart structure parameters to generate time sequence change data, and establishing a multi-dimensional data fusion scheme based on the time sequence change data and physiological indexes; according to the fusion scheme, acute risk trigger factors are identified, blood flow abnormal parameters are generated, and emergency threshold comparison is carried out to generate acute risk early warning signals; extracting a myocardial strain degradation rate to determine a chronic degradation acceleration time point, carrying out disease progress stage association to generate a chronic risk layering curve, and establishing a clinical index comparison table; carrying out double-layer correlation on the acute risk early warning signal and the chronic risk layering curve, and carrying out calibration judgment to generate a comprehensive risk judgment sequence; the sequence is decomposed into an acute judgment layer and a chronic judgment layer, a risk threshold value is configured to generate an instant early warning signal, a layered screening report is formed, and technical support is provided for early discovery of the hypertensive heart disease.

The invention relates to the technical field of electric acupuncture apparatuses, and discloses a method and a system for automatically adjusting stimulation parameters of an electric acupuncture apparatus. According to the method, body surface electromyographic signals, skin impedance and capillary hemodynamic parameters of a user are collected in real time through a sensor set, feature extraction and analysis are conducted through a time sequence prediction model of a Transform architecture, and physiological feature data are generated. And then, constructing a user physiological state characterization model by adopting a multi-modal neural perception fusion algorithm, and carrying out collaborative optimization on the electrical stimulation parameters through an adaptive quantum particle swarm optimization algorithm to generate a stimulation parameter combination matched with the real-time neuromuscular response characteristics of the user. The system drives electrical stimulation output according to the parameter combination, monitors physiological data changes in real time, realizes closed-loop dynamic balance of stimulation parameters and biological feedback signals through the dynamic parameter compensation module, and improves the treatment effect and safety.

The invention discloses a cerebral apoplexy high risk group positioning evaluation system based on multi-modal data, and relates to the technical field of medical information science, the cerebral apoplexy high risk group positioning evaluation system comprises a cerebral apoplexy prevention and control management platform, and the cerebral apoplexy prevention and control management platform is in communication connection with the following modules: a multi-modal data acquisition and integration module, the multi-modal data collection module is used for collecting multi-modal data related to cerebral apoplexy from multiple channels and carrying out preprocessing operation on the collected multi-modal data. By integrating clinical data, image data, omics data and terminal health data, multi-dimensional information related to the cerebral apoplexy can be comprehensively captured, particularly, cerebral vessel digital twin is utilized to simulate hemodynamic characteristics, a plurality of data sources are fused in combination with a graph neural network, high-risk groups can be recognized more accurately, and the accuracy of cerebral apoplexy recognition is improved. The accuracy and reliability of risk prediction are remarkably improved, the problem of missing detection caused by dependence on a single data source in a traditional method is solved, and more powerful support is provided for early intervention.

A prosthetic heart valve for treatment of a diseased heart valve having native anterior and posterior leaflets that move between an open configuration and a closed position to regulate blood flow through the heart valve during a cardiac cycle of a heart. The prosthetic heart valve having a crescent shaped stent, at least one prosthetic leaflet mounted on an inner surface of the stent, and at least one prong structure coupling a portion of the at least one prosthetic leaflet to a lower ventricular portion of the stent frame. The prosthetic heart valve further having systems for anchoring the upper flared portion of the stent to a posterior portion of the native valve annulus.

The invention discloses an artificial intelligence-based periodontal state evaluation method, which comprises the following steps of: acquiring multi-modal tooth data which comprises a tooth surface image and a local blood vessel network image of an oral cavity; preprocessing the multi-modal tooth data, and performing cross-modal registration by using a registration module to obtain a registered tooth surface image and a registered blood vessel network image; extracting multi-dimensional features of the registered blood vessel network image through a first feature extraction module, wherein the multi-dimensional features comprise spatial morphological features, topological connectivity features and hemodynamic features of blood vessels; extracting macroscopic morphological features and lesion local features of the registered tooth surface image through a second feature extraction module; performing cross-modal fusion on the multi-dimensional features, the macroscopic morphological features, the local lesion features and the clinical data to obtain fusion features; and outputting a periodontal state evaluation result based on the fusion features, thereby facilitating improvement of periodontal state evaluation accuracy and periodontal disease early warning capability.

The invention relates to the technical field of medical image analysis, and discloses a cardiovascular disease detection method based on image analysis. The method comprises the steps of obtaining a medical image sequence of a target patient, and extracting a blood vessel region contour to generate an initial blood vessel topological graph; the initial topological graph is registered with a standard cardiovascular model, the curvature deviation degree and the pipe diameter variation coefficient of each blood vessel branch are calculated, and a blood vessel elastic characteristic matrix is generated in combination with abnormal displacement nodes; and performing multi-scale fusion on the curvature deviation degree, the pipe diameter variation coefficient and the elastic characteristic matrix, outputting a vascular structure anomaly index, and generating a hemodynamic parameter set. Dividing risk areas according to gradient distribution of the parameter set on the three-dimensional model, performing texture co-occurrence matrix analysis on pixel clusters in the high-risk areas, and extracting texture fingerprints of calcified plaques and lipid deposition. And determining the type and severity level of the cardiovascular disease according to the peak value distribution. According to the invention, accurate and objective detection and risk assessment of cardiovascular diseases are realized.

The invention discloses a retina image unsupervised anomaly detection method for early screening of diabetes mellitus. The method comprises the following steps: carrying out registration and multi-scale attention-guided blood vessel segmentation on a longitudinal time sequence retina image of a patient; extracting a vascular skeleton and constructing a time sequence vascular topological graph, calculating geometric morphology and hemodynamic attributes of each vascular segment, identifying vascular morphology evolution characteristics by comparing topological graphs of adjacent time points, and calculating hemodynamic characteristics such as wall shear stress through simulation; the evolution and hemodynamic characteristics are jointly input into a time sequence encoder for unsupervised learning, and an early diabetes risk score is comprehensively generated by analyzing a reconstruction error, an abnormal score based on density estimation and a time sequence trajectory deviation degree of a potential space; the scheme of the invention does not depend on lesion labels, and can sensitively detect the tiny anomalies at the early stage of pathology from multi-dimensional dynamic changes, thereby providing an objective and quantitative new way for early screening and intervention of diabetes.

The invention relates to the technical field of medical image diagnosis, and discloses a cardiovascular disease diagnosis model construction method based on image processing. The method comprises the steps that cardiac medical image data of a target patient is collected, a standardized data set is generated through preprocessing, and a morphological and hemodynamic feature set is extracted; establishing a heart state evolution characteristic spectrum according to a characteristic dynamic evolution rule, dividing a pathological state space, and calculating the characteristic distribution density of a historically diagnosed case; acquiring real-time image data of a patient to be diagnosed, and constructing a real-time diagnosis feature vector; mapping the vector to a pathological state space, and calculating a space matching degree to generate a pathological association index; and combining the association index and the two types of feature sets to construct a heart pathology probability prediction model, outputting a pathology probability prediction value and generating a hierarchical diagnosis suggestion. According to the method, through multi-dimensional feature analysis and space matching analysis, precise and graded diagnosis of the cardiovascular diseases is realized, and an efficient and feasible technical path is provided for diagnosis of the cardiovascular diseases.

An ultrasound-imaging system includes an ultrasound probe coupled with a console. Operations of the system can include detecting one or more blood vessels within the ultrasound image and identifying each blood vessel as a vein, an artery or other anatomic element using doppler ultrasound functionality of the ultrasound probe. Operations can also include determining a confidence for the blood vessel identification and defining a window for doppler ultrasound operation. Operations can further include assessing a blood flow rate within blood vessels, and superimposing notifications atop the ultrasound image pertaining to the identity of the blood vessel including a confidence for the identity.

The invention provides a heart valve regurgitation detection method and system and a medium. The method comprises the steps that regurgitation area identification caused by heart valve structure or function abnormity is obtained; performing principal component analysis on the regurgitation area, and determining the main extension direction of the regurgitation of the corresponding heart valve; determining at least one morphological characteristic parameter of the reflux region according to the main extension direction; and determining the regurgitation state information of the heart valve according to the morphological characteristic parameters. According to the method, the spatial distribution of a reflux region is subjected to characteristic decomposition through principal component analysis, a complex irregular blood flow form is converted into a main extension direction with definite physical significance, and form characteristic parameters are calculated based on the main extension direction; random errors caused by subjective view angle differences or insufficient experience when valve reflux parameters are manually measured can be eliminated, and valve reflux evaluation results obtained by different operators under different detection conditions have high consistency and repeatability.

A prosthesis assembly includes a stent frame that is expandable and configured for being positioned in the ascending aorta, and a receiving socket positioned within a proximal end of the prosthesis assembly. The receiving socket defines a recess for allowing flowthrough of blood into the stent frame. The receiving socket is further configured for selectively receiving a heart valve assembly for replacing a native heart of a patient or maintaining a mode of operation where the socket is empty and blood flows through the socket into the stent frame.

The invention relates to the technical field of medical data processing, and discloses a non-invasive hemodynamic assessment system for coronary artery stenosis degree, comprising an image acquisition module used for acquiring a coronary artery computed tomography angiography image of a patient; the physiological signal acquisition module is used for synchronously acquiring physiological signals of a patient, and the physiological signals comprise electrocardiosignals and non-invasive arterial blood pressure signals; and the data processing module is used for preprocessing and segmenting the coronary artery computed tomography angiography image. Electrocardiogram and non-invasive arterial blood pressure signals are collected through the sensor, risks and complications caused by invasive examination of traditional coronary artery radiography are avoided, the problem that patients unsuitable for invasive examination such as contrast agent allergy and renal insufficiency are difficult to evaluate is solved, the pain of the patients is relieved, and the acceptability of the patients is improved.

The invention relates to the technical field of medical artificial intelligence, in particular to a vascular embolism risk prediction method based on big data analysis, and the method comprises the steps: collecting a pulse pressure fluctuation rate, a microcirculation resistance index and a platelet adhesion gradient through a multi-source sensor, and extracting dynamic physiological parameter time sequence features; constructing a hemodynamic finite element model based on CTA and VFI image data, and obtaining a vascular mechanical feature vector; deep coupling of the pulse pressure spectrum and the circumferential stress is achieved through dynamic time warping and convolution mapping, and a multi-modal risk feature set is generated; and performing cross-modal coding by using the double-branch graph neural network, and outputting an acute embolism probability and a three-dimensional risk thermodynamic diagram. According to the method, physiological, image and mechanical multi-dimensional information is fused, and the method has the advantages of being high in real-time performance, accurate in positioning and good in interpretability and is suitable for risk prediction and auxiliary diagnosis of clinical cardiovascular and cerebrovascular events.

The invention discloses an infrared thermal image enhanced real-time rectal blood vessel blood flow detection method. The method comprises the following steps that S1, a thermal image of an operation area is collected through an infrared thermal imager to serve as a to-be-processed medical purpose image; s2, adopting a double-branch collaborative network architecture, adopting an improved U-Net structure for a deep denoising priori network DDPNet, introducing a detail sensing unit DAU, and separating noise and organizational structure features through residual learning; and S3, obtaining a supervision signal in the image, and processing each supervision model to obtain a processed image. The method can effectively improve the accuracy and comprehensiveness of information obtained after image processing in the operation and improve the effectiveness of information acquisition in the operation process.

The invention relates to a traditional Chinese medicine composition for treating haemorrhoids and a preparation method and application thereof.The traditional Chinese medicine composition is prepared from, by weight, 20-60 parts of sargentgloryvine stem, 15-45 parts of moutan bark, 20-40 parts of dandelion, 20-40 parts of rheum officinale, 20-40 parts of radix paeoniae rubra and 10-30 parts of lithospermum erythrorhizon. The traditional Chinese medicine composition has the effects of cooling blood and detoxifying, promoting blood circulation to remove blood stasis and relieving swelling and pain through combination of all the medicines, can remarkably relieve inflammation and pain of haemorrhoids through test verification, and has the potential of industrial production and popularization.

The invention discloses a TAVR postoperative blood flow parameter complementing method based on CT-MRI fusion, and belongs to the technical field of crossing of medical image processing and computational fluid mechanics. A CT valve frame registration technology is adopted, an invisible artificial valve leaflet three-dimensional structure is reconstructed through valve frame information in a CT image and is coupled with a dynamic heart model, a complete valve mechanical and functional simulation platform is constructed, the problem of an imaging blind area is solved, hemodynamic parameters of an inlet and an outlet of a postoperative area are further collected in combination with 4D Flow MRI, and the artificial valve leaflet three-dimensional structure is obtained. The blood flow conditions of the upstream and the downstream of the artificial valve area at each stage of contraction and relaxation of the TAVR postoperative part are comprehensively restored, the temporal-spatial resolution and the physical authenticity of the boundary condition in fluid-solid coupling simulation are greatly improved, and the more real passive response of the valve leaflet under the action of the blood flow is obtained; and a reliable basis is provided for quantitative and mechanical risk analysis of postoperative complications such as thrombosis, perivalvular leakage and valve leaflet fatigue.

Aspects of the present disclosure describe systems and methods for predicting an intra-aortic pressure of a patient receiving hemodynamic support from a transvalvular micro-axial heart pump. In some implementations, an intra-aortic pressure time series is derived from measurements of a pressure sensor of the transvalvular micro-axial heart pump and a motor speed time series is derived from a measured back electromotive force of a motor of the transvalvular micro-axial heart pump. Furthermore, in some implementations, machine learning algorithms, such as deep learning, are applied to the intra-aortic pressure and motor speed time series to accurately predict an intra-aortic pressure of the patient. In some implementations, the prediction is short-term (e.g., approximately 5 minutes in advance).

The invention discloses a blood vessel OCT image training method, a blood vessel OCT image generating method and a blood vessel OCT image training device based on a DCN cross-modal fusion network and structure-blood flow coupling modeling. The method comprises the following steps: acquiring image data marked with a blood vessel segmentation result and a plaque position; acquiring the preprocessed OCT image data; registering the image data marked with the blood vessel segmentation result and the plaque position and the OCT image data so as to obtain registered image data; acquiring hemodynamic parameters; inputting the coronary artery CTA image, the image marked with the blood vessel segmentation result and the plaque position and hemodynamic parameters into a cross-modal fusion network based on deformable convolution so as to obtain CTA features of the cross-modal fusion network; and inputting the CTA features of the cross-modal fusion network into a trained OCT generation network so as to obtain a cross-section OCT image containing blood vessel wall and plaque information. The method can replace part of invasive OCT examination, assist doctors in assessing plaque vulnerability and guide interventional therapy.

A medical system may include a pump disposed along a longitudinal axis of a blood flow assist system and including an impeller disposed in a pump housing; a power lead coupled with the first end portion of the pump; and a tether coupled with a second end portion of the pump opposite the first end portion. During operation of the blood flow assist system with the pump disposed within the blood vessel, the power lead may be configured to extend from within the blood vessel within which the pump is disposed to outside the first vascular access site to couple to the control system, and the tether may be configured to extend from within a blood vessel within which the pump is disposed to an anchoring position disposed away from the second end portion.

The invention provides a heart transplantation post-operation continuous physiological monitoring and anomaly recognition method and system based on wearable equipment, and relates to the technical field of physiological monitoring. According to the method, an individualized dynamic reference interval and a multi-index correlation coefficient matrix are constructed by collecting baseline data such as electrocardio, blood pressure and blood oxygen, abnormal state detection is achieved in combination with the Mahalanobis distance of a unified feature vector and a multi-task recognition model, and then a multi-physics field digital twin model is called to simulate hemodynamic evolution. And high-confidence abnormity is judged according to a coupling rule, so that the intellectualization and response efficiency of postoperative monitoring are improved.

The invention relates to the technical field of disease course trend modeling, in particular to a subarachnoid hemorrhage disease course trend modeling system fusing multi-source data. Four kinds of signals of intracranial pressure, blood flow velocity, cerebrospinal fluid pressure and electroencephalogram of a monitored object are synchronously collected, an instantaneous phase is extracted through Hilbert transform, a time window is adaptively adjusted according to the brain blood vessel conduction delay characteristic of an individual, and phase locking indexes among three pairs of signals are calculated. A multivariate coupled oscillator model is established, phase track topology invariant features are extracted, and comprehensive trend indexes are generated through tensor fusion. An individualized four-dimensional phase entropy baseline mode is established, and a double-layer early warning mechanism is adopted: when second derivative continuous symbol overturning occurs in all three phase locking indexes, early warning is directly performed, and when any two phase locking indexes are overturned, a trend index needs to be synthesized for confirmation. And predicting a state level, a trend level and an expected evolution trajectory based on a support vector regression model. According to the invention, precise disease course prediction and early warning are realized, and a basis is provided for clinical decision making.

The invention relates to the technical field of medical monitoring and intelligent decision making, and particularly discloses an intraoperative noninvasive real-time blood flow monitoring and medication intervention analysis system. Pulse wave oscillation harmonic component characteristics and diastolic attenuation characteristic characteristics are extracted by using variational mode decomposition and a polynomial fitting algorithm; the multi-dimensional features are fused and then input into a deep learning classification model, and accurate recognition of insufficient heart pump efficiency, abnormal peripheral vascular tension and circulation capacity imbalance states is achieved; time sequence prediction and grading early warning are carried out based on the hidden Markov model and the individualized baseline safety interval, and finally a targeted medication scheme is output through the intervention strategy knowledge base.

The invention discloses an information processing method and device for intracranial aneurysm hemodynamic prediction, equipment and a medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: receiving a three-dimensional medical image containing an intracranial aneurysm, inputting the three-dimensional medical image into a target hemodynamic prediction model, and capturing the comprehensive morphological characteristics of the intracranial aneurysm from the three-dimensional medical image; inputting the blood flow boundary condition into the target hemodynamics prediction model, and performing low-dimensional mapping on the blood flow boundary condition to obtain a first low-dimensional feature vector; receiving a spatial point coordinate and a directional distance corresponding to each sampling point in the CFD model formed in the intracranial aneurysm area, and performing low-dimensional mapping on the spatial point coordinate and the directional distance to obtain a second low-dimensional feature vector; and performing feature fusion on the comprehensive morphological features, the first low-dimensional feature vectors and the second low-dimensional feature vectors through a feature fusion module to predict hemodynamic parameters. And end-to-end hemodynamic parameter prediction is realized.