35 results about "End diastole" patented technology

The invention discloses an aortic valve function evaluation device which comprises a processor and a memory, and the memory stores programs or instructions capable of running on the processor. When the program or the instruction is executed by the processor, the following steps are realized: acquiring a first echocardiogram of a target object corresponding to a final systole and a second echocardiogram of a target object corresponding to a final diastole in a cardiac cycle, and acquiring medical record data of the target object; determining a first mask pattern corresponding to the first echocardiogram and a second mask pattern corresponding to the second echocardiogram according to the first echocardiogram, the second echocardiogram and an aortic valve segmentation model; determining an aortic valve morphological index of the target object according to the first mask pattern and the second mask pattern; determining aortic valve functional indexes of the target object according to the medical record data of the target object; and determining and outputting an aortic valve function evaluation result of the target object according to the first mask pattern, the second mask pattern, the aortic valve morphological index and the aortic valve functional index.

Existing techniques fail to propose a method for improving model parameters optimization and seamless integration of clinical data with computational model required for personalized cardiac hemodynamic model development. This disclosure relates to a system and method, which receives one or more model parameters comprising height, active pressure components and passive pressure components specific to left ventricle from cardiac hemodynamic model. The first set of values corresponding to one or more input parameters comprising end systolic diameter and end diastole diameter are received from subject specific Echo data. The second set of values corresponding to one or more model parameters are estimated using one or more input parameters. The estimated second set of values are optimized using a Particle swarm optimization to obtain one or more optimized values. Select at least a subset of optimized one or more values corresponding to one or more model parameters for personalization.

A system for monitoring right ventricular systolic dysfunction includes a hemodynamic sensor that produces a hemodynamic sensor signal representative of a right ventricular pressure waveform of the patient, a display, one or more processors, and computer-readable memory. The computer-readable memory is encoded with instructions that, when executed by the one or more processors, cause the system to receive the hemodynamic sensor signal representative of the right ventricular pressure waveform of the patient, extract right ventricular peak systolic pressure and right ventricular end diastolic pressure from the right ventricular pressure waveform of the patient, determine a ratio of right ventricular peak systolic pressure over right ventricular end diastolic pressure, and output the ratio of right ventricular peak systolic pressure over right ventricular end diastolic pressure to the display for monitoring the presence of right ventricular systolic dysfunction based on the ratio of peak systolic pressure over end diastolic pressure.

The present application relates to a kind of cardiac magnetic resonance longitudinal relaxation time measurement method, medium and equipment.The measurement method includes the following steps: S1 uses MOLLI sequence respectively before and after scanning contrast;Specifically, in the before and after scanning contrast, by setting different initial inversion time TI, setting 3 groups of LL experiment LL1, LL2, LL3 triggered by continuous ECG, enough relaxation curve sampling points are obtained after fusion;And data is collected at the end of diastole of cardiac cycle, and 1 image is obtained per heartbeat;S2 image processing.This measurement method can realize single-pixel high-resolution T1 mapping under the breath holding of selection data acquisition and multi-LL experiment data fusion, give consideration to high accuracy, high resolution and high efficiency, and have good compatibility and practicality, provide new scheme for early diagnosis of heart disease, lesion quantification and prognosis evaluation, have wide clinical application prospect.

The invention belongs to the technical field of medical treatment, particularly discloses an application of allicin in preparation of a medicine for improving right heart dysfunction caused by pulmonary arterial hypertension, and discloses an effect of the allicin in treatment of the right heart dysfunction caused by the pulmonary arterial hypertension. Compared with existing medicines (mainly for reducing pulmonary arterial pressure) for treating pulmonary arterial hypertension, allicin not only can reduce the pulmonary arterial pressure and relieve the symptoms of pulmonary arterial hypertension, but also can remarkably improve right heart dysfunction caused by pulmonary arterial hypertension, and the allicin is specifically shown as follows: (a) average pulmonary arterial pressure, pulmonary artery ejection time and pulmonary artery end diastolic inner diameter are reduced; the pulmonary artery acceleration time is prolonged; (b) the right ventricular systolic pressure, the right ventricular end-of-systolic free wall thickness, the right ventricular end-of-systolic free wall thickness, the right ventricular end-of-systolic inner diameter and the right heart hypertrophy index are reduced, and tricuspid valve displacement, stroke output and right heart discharge are increased; and (c) improving right ventricular and pulmonary vascular remodeling.

The embodiment of the invention provides a color Doppler ultrasonic hemodynamic analysis method for an artery in a semi-open mouth meninx, which comprises the following steps of: taking a semi-open mouth of a patient, and maintaining an acoustic window through an occlusion object to enlarge a subtemporal fossa; a linear array or convex array probe is selected according to the body type of a subject, and ultrasonic equipment parameters are set; scanning in the subtemporal fossa to identify the trunk of the maxillary artery (MXA) and the branch of the middle meninx artery (MMA); measuring inner diameters and hemodynamic parameters of the MXA and the MMA, wherein the parameters comprise a systolic peak flow rate (PSV), an end-diastolic flow rate (EDV), a resistance index (RI) and a pulsation index (PI); compared with the prior art, the subtemporal fossa is expanded by 5-10 mm through the medical silica gel occlusion object with the occlusion thickness of 3-8 mm, the anterior-posterior diameter of the subtemporal fossa is expanded to 25-35 mm, the upper-lower diameter of the subtemporal fossa is expanded to 18-28 mm, and bone shielding of the condylar process on the initial section of the middle meninx artery (MMA) is thoroughly relieved.

The invention discloses a cardiac magnetic resonance T1mapping image synthesis method, which comprises the following steps of: acquiring a plurality of groups of samples, each group comprising native T1mapping images and movie imaging sequence images, determining a heart region corresponding to each native T1mapping image, identifying initial associated image pairs of end diastole and end systole from the same group of movie images according to the heart region corresponding to each native T1mapping image, and synthesizing the initial associated image pairs of the end diastole and end systole according to the initial associated image pairs of the end diastole and end systole. Obtaining a target associated image pair corresponding to the heart preset region after segmentation, and training the constructed initial diffusion model to obtain a target model; respectively extracting myocardial tissue texture features and heart morphological dynamic features in a specific period from each film imaging sequence image; and inputting the tissue texture features and the heart morphological dynamic features into a target model, and performing inverse diffusion denoising on random noise randomly sampled from Gaussian distribution to obtain a synthesized T1mapping image. According to the method, rapid, efficient and high-quality T1mapping image synthesis can be realized.

The invention provides a method for measuring the left ventricular ejection fraction of a dynamic echocardiography. The method comprises the following steps: inputting a to-be-identified echocardiogram sequence into a neural network segmentation model based on multi-frame feature aggregation, then performing spatial feature coding on each frame of image of the to-be-identified echocardiogram sequence through a spatial feature encoder structure to obtain a spatial feature map corresponding to each frame of image, and finally, identifying the to-be-identified echocardiogram sequence according to the spatial feature map. Performing cross-frame and cross-section spatio-temporal feature aggregation on the spatial feature pattern through a spatio-temporal feature aggregation structure to obtain global spatio-temporal features including time sequence information of a heart apex two-cavity section and a heart apex four-cavity section; the left ventricular ejection fraction determining method comprises the steps of generating a left ventricular membrane segmentation mask of a terminal diastole frame and a terminal systole frame on the basis of global spatial-temporal characteristics and spatial shallow layer characteristics corresponding to the terminal diastole frame and the terminal systole frame, and finally determining the left ventricular ejection fraction on the basis of the left ventricular membrane segmentation mask of the terminal diastole frame and the terminal systole frame.

The invention discloses a method and a system for removing breathing artifacts of an animal micro-CT image. The method comprises the following steps: preprocessing projection data of an animal to obtain label information; training label information by using a depth target detection network to obtain thoracic cavity diaphragm positions, classifying the thoracic cavity diaphragm positions, extracting target limiting projections at the end of diastole and the end of systole, and performing unequal interval filtering back projection reconstruction on the target limiting projections to obtain a breathing artifact-removed image; correcting the breathing artifact-removed image by using an improved deep noise reduction network to obtain a breathing and stripe artifact-removed image; in-phase projection is extracted in a projection domain and is reconstructed, so that respiratory artifacts are effectively removed from the source; and the improved deep noise reduction network is used to enhance the quality of the sparse reconstruction image, so that the image quality is remarkably improved, and a clearer and more accurate image basis is provided.

The present invention provides an image processing device for evaluating cardiac images and a method for identifying ventricular states. In this method, regions of interest are identified from multiple target images, grayscale value changes of multiple pixels in the regions of interest in those target images are determined, and one or more representative images are obtained based on the grayscale value changes. The target images are pixels within the endocardial contour of the left ventricle, with the boundaries of the region of interest roughly located on both sides of the bottom of the endocardial contour, and the region of interest corresponds to the mitral valve. Grayscale value changes are related to the movement of the mitral valve. The representative images are used to evaluate the state of the left ventricle. In this way, the end-systole and end-diastole of the heart can be quickly and accurately identified.

The present application relates to an ultrasonic diagnostic apparatus and an electrocardiogram waveform processing method. A setter (42) sets a plurality of heart rate intervals for an electrocardiogram waveform. A primary determiner (44) determines an interval satisfying a primary determination condition as a temporary stable interval within the plurality of heart rate intervals. A secondary determiner (46) determines the temporary stable interval as a stable interval in a case where the temporary stable interval satisfies a secondary determination condition. An end-diastole detector (48) and an end-systole detector (50) detect an end-diastole and an end-systole within a focus interval. A selection control section (33) controls selection of the focus interval at a time of change of the focus interval so that the changed focus interval becomes the stable interval.

The invention provides an in-aorta balloon counterpulsation system control method based on hemodynamics, and relates to the technical field of medical system control. According to the method provided by the invention, hemodynamic monitoring signals of a target user are obtained in real time, wherein the hemodynamic monitoring signals comprise the total heart end diastole volume, the rate of variation per stroke, extravascular lung water and the heart index; the basic counterpulsation blood volume of the target user is determined according to the volume of the full heart diastole; optimizing the basic counterpulsation blood volume according to the variation rate per stroke, the extravascular lung water and the heart index to obtain a target counterpulsation blood volume of the target user; according to the target counterpulsation blood volume of the target user, the balloon inflation volume of the balloon counterpulsation system in the aorta is determined. According to the method, accurate determination of the balloon inflation volume of the balloon counterpulsation system in the aorta can be achieved, the processing efficiency and accuracy are improved, and the use requirements of different users are met.

This application provides an ultrasound cardiac dynamic monitoring system and method, relating to the field of ultrasound cardiac function dynamic monitoring technology. The system includes: a patch-type ultrasound probe, a hydrogel patch, a wearable hardware module, and a cardiac function analysis module. The cardiac function analysis module is configured to: receive the ultrasound image; determine a target sampling line in the ultrasound image based on a reinforcement learning model; control the wearable hardware module to acquire M-mode images along the target sampling line; input the M-mode images into a deep learning model to output the key point positions of the left ventricular septum and the left ventricular posterior wall at end-diastole and end-systole based on the deep learning model; calculate the left ventricular ejection fraction (LVEF) based on the LVEF and the key point positions; the LVEF represents the dynamic monitoring and detection results of cardiac function. This system can improve the effectiveness and accuracy of dynamic cardiac monitoring.

A control circuit for a sensorless implantable blood pump configured to determine mitral valve regurgitation includes processing circuitry configured to generate an estimated blood flow waveform from the sensorless implanted blood pump and generate an alert if between an end period of diastole and a beginning period of systole a measured amplitude of the estimated blood flow waveform does not include an inflection point.

An ultrasonic measurement method and an ultrasonic imaging system for cardiac parameters, the method comprising: under the condition that an ultrasonic probe is guided into a cavity of a patient, controlling the ultrasonic probe to emit ultrasonic waves to the heart of the patient to obtain a first cardiac section; controlling the ultrasonic probe to obtain a first imaging angle of the first heart section to emit ultrasonic waves so as to obtain a first end diastole ultrasonic image and a first end systole ultrasonic image; controlling the driving mechanism to enable the ultrasonic probe to rotate from the first imaging angle to a second imaging angle for acquiring a second heart section, wherein the angle difference between the second imaging angle and the first imaging angle is a preset angle; controlling the ultrasonic probe to emit ultrasonic waves at a second imaging angle to obtain a second end diastole ultrasonic image and a second end systole ultrasonic image; and calculating the cardiac ejection fraction according to the first end-diastolic ultrasound image, the first end-systolic ultrasound image, the second end-diastolic ultrasound image and the second end-systolic ultrasound image.

The present invention provides a method, device, and ultrasonic imaging device for determining left ventricular parameters. The method comprises: collecting two-dimensional ultrasonic cardiac data of a target subject over a continuous period of time, the continuous period being greater than one cardiac cycle, the two-dimensional ultrasonic cardiac data comprising multiple frames of two-dimensional ultrasonic cardiac images; determining multiple target frame images from the multiple frames of two-dimensional ultrasonic cardiac images, the target frame images comprising multiple frames of end-diastolic images corresponding to the end-diastolic phase and multiple frames of end-systolic images corresponding to the end-systolic phase; performing image segmentation on the target frame images to determine the left ventricular contour of the target frame images; determining the apex point, the junction point between the left ventricular septum and the mitral valve, and the junction point between the left ventricular wall and the mitral valve in the left ventricular contour; and determining left ventricular parameters based on the left ventricular contour, the apex point, the junction point between the left ventricular septum and the mitral valve, and the junction point between the left ventricular wall and the mitral valve. The present invention balances the efficiency and accuracy of left ventricular measurement.

The application provides a kind of magnetic resonance image myocardial strain determination method and system based on group registration algorithm, comprising: step S1: left ventricular myocardium is segmented from diastolic end image of cardiac magnetic resonance movie image, and the image sequence is preprocessed according to the segmentation result, and the direction field is calculated;Step S2: using group registration algorithm based on global or local low rank difference measure to register image sequence, and estimate displacement field;Step S3: left ventricular myocardial strain related parameters are calculated using direction field and displacement field.The application uses group registration based method to eliminate cumulative error, so that myocardial strain can be more accurately determined, especially the strain in the later diastolic phase.The global or local low rank difference used in the method can more accurately measure the motion change between multiple movie images, and is more robust to artifacts.In addition, the joint use of spatial regularization term and cycle time regularization term further improves the accuracy of the method.

A cardiac assist device (10) for acting on a heart (11) having an actual end-diastolic conformation in vivo and an ideal end-diastolic conformation that would cause the heart (11) to pump more efficiently. The cardiac assist device (10) has a shell configuration (13) with a top opening (24), a base (21), and a maximum interior diameter (MD) between the top opening (24) and the base (21). The shell configuration (13) has a total long axis length (TL). The shell configuration (13) has a major axis that follows a curvature rotated about a major axis. At last one inflatable membrane (26) extends from said shell configuration (13), wherein said shell configuration (13) and said at least one inflatable membrane (26) act upon said heart (11) to alter said actual end-diastolic conformation toward said ideal end-diastolic conformation.

The invention discloses a heart ultrasound video left ventricle segmentation and ejection fraction calculation method based on a DeepLabv3 + and R (2 + 1) D network, and belongs to the field of medical artificial intelligence. The method aims at solving the problems that in the prior art, left ventricle function evaluation time sequence information is insufficient in utilization, the key frame recognition automation degree is low, and the segmentation precision and the overall process automation degree are not high. According to the technical scheme, the method comprises the following steps: preprocessing an original cardiac ultrasound video, including frame extraction, intelligent cutting of a region of interest and data enhancement; performing time sequence modeling on a video sequence by using an R (2 + 1) D network, and automatically identifying key frames of the end of diastole (ED) and the end of systole (ES); performing high-precision pixel-level left ventricle region segmentation on the identified key frame by adopting a DeepLabv3 + network; estimating a left ventricular end diastolic volume (LVEDV) and a left ventricular end systolic volume (LVESV) by combining an improved Simpson method on the basis of a segmentation result and image physical size calibration information; and finally, calculating a left ventricular ejection fraction (LVEF) according to a standard formula, and outputting a structured report and a visual image. Through multi-network collaboration and full-process automation, the accuracy, efficiency, objectivity and consistency of LVEF evaluation are remarkably improved, and the method has a good clinical application prospect.

The invention provides an in-aorta balloon counterpulsation system control method based on hemodynamics, and relates to the technical field of medical system control. According to the method provided by the invention, hemodynamic monitoring signals of a target user are obtained in real time, wherein the hemodynamic monitoring signals comprise the total heart end diastole volume, the rate of variation per stroke, extravascular lung water, the heart index and the cardiac output; based on a pre-trained neural network model, determining heart indexes corresponding to multiple moments of the target user in a future time period according to the hemodynamic monitoring signal; and under the condition that the heart index corresponding to the first moment of the target user is smaller than a first threshold value, generating a first request, and in response to an input confirmation operation on the first request, starting the intra-aortic balloon counterpulsation system at the first moment. According to the method provided by the invention, the start and stop of the balloon counterpulsation system in the aorta can be accurately controlled, and the processing efficiency and accuracy are improved.

The invention discloses a heart finite element model parameter optimization method and system, and the method comprises the steps: adding a boundary condition model and a material attribute model to a ventricular systolic end stage finite element model based on a ventricular finite element model; calculating to obtain a simulated end-diastolic volume of the finite element model under the action of the boundary condition model and the material attribute model, comparing the simulated end-diastolic volume with an end-diastolic volume obtained based on the magnetic resonance image, calculating a volume difference, and constructing a loss function according to the volume difference; a Bayesian optimization framework is introduced and is carried out in an iteration mode, mechanical response is obtained through calculation in combination with a constructed loss function, parameter optimization is carried out, and finally optimal parameter configuration is obtained. According to the method, the finite element model and the Bayesian parameter estimation algorithm are combined, so that the training efficiency of the substitution model is improved, the final model parameters are easier to obtain, and the final heart finite element model can accurately reproduce heart dynamic characteristics.

The application discloses a kind of based on registration point set cardiac deformation field estimation method, system, device and medium, solve the precision of image registration in prior art needs to be improved, method includes: receiving diastolic end and systolic end cardiac image and its segmentation map;The segmentation map of diastolic end and systolic end cardiac image is used to extract the contour of heart, and the registration point set corresponding to the contour of heart image center is obtained using farthest point sampling algorithm;Diastolic end and systolic end cardiac image and the registration point set are input into the variational neural network trained in advance, and the distribution of latent variable is obtained;The distribution of latent variable is input into the radial basis function constructed in advance, and the deformation field of diastolic end image is decoded to obtain, and the deformed diastolic end image is obtained according to the deformation field.This application improves the image registration precision of cardiac deformation field.

The invention provides a coronary angiography image-based end-diastolic recognition method and related equipment, and the method comprises the steps: collecting a plurality of frames of coronary angiography images to construct a coronary angiography sequence which at least comprises coronary angiography images of two cardiac cycles; the coronary angiography sequence is input into a trained recognition model for probability prediction of the end diastole to obtain a probability sequence, and the recognition model is used for extracting spatial features and time sequence features of each frame of image, calculating attention between frames and outputting a probability value of each frame of coronary angiography image belonging to the end diastole, the end-diastole image is an image with most dispersed blood vessels in the cardiac cycle, and the probability value of the end-diastole image is maximum; and extracting a wave crest from the probability sequence output by the recognition model by adopting a wave crest extraction algorithm, wherein the coronary angiography image corresponding to the wave crest is the end-diastole image. According to the method, the end-diastole prediction can be carried out on the coronary angiography sequence image, the accuracy is high, the generalization ability is high, and the robustness is good.

The application discloses a method, system, device, medium and product for evaluating right ventricular function, and relates to the technical field of medical image processing and ultrasonic diagnosis. The method comprises the following steps: acquiring a sequence of multiple two-dimensional ultrasonic images of a right ventricle of a heart and spatial pose information of the sequence, and generating point cloud data; identifying an end-diastolic frame, an end-systolic frame and an anatomical structure point, and acquiring sparse point cloud data of the anatomical structure point; constructing a three-dimensional grid model of the end-diastolic frame and the end-systolic frame; determining multiple tracking points of a tricuspid annulus and acquiring a three-dimensional coordinate trajectory; calculating longitudinal displacement, area change rate and peak time dispersion based on the trajectory, and completing function evaluation. The application overcomes the limitations of angle dependence and point substitution of traditional TAPSE technology, realizes comprehensive evaluation of right ventricular function from three dimensions of longitudinal displacement, area change rate and systolic synchrony, and improves the accuracy and clinical value of evaluation.

The invention discloses a method, a system, equipment, a medium and a product for evaluating a right ventricular function, and relates to the technical field of medical image processing and ultrasonic diagnosis. The method comprises the following steps: acquiring a multi-frame two-dimensional ultrasonic image sequence of a right ventricle of a heart and spatial pose information of the multi-frame two-dimensional ultrasonic image sequence, and generating point cloud data; identifying the last diastole frame, the last systole frame and the anatomical structure point, and obtaining sparse point cloud data of the anatomical structure point; constructing a three-dimensional grid model of the last diastole frame and the last systole frame; determining a plurality of tracking points of the tricuspid valve ring and acquiring a three-dimensional coordinate trajectory; and calculating the longitudinal displacement, the area change rate and the peak arrival time dispersion based on the trajectory to complete the function evaluation. According to the method, the limitation that a traditional TAPSE technology depends on a point instead of a surface is overcome, comprehensive evaluation of the right ventricular function from the three dimensions of longitudinal displacement, the area change rate and contraction synchronism is achieved, and the accuracy and clinical value of evaluation are improved.

The invention relates to an aortic valve pressure gradient determination method and device and a storage medium, and the method comprises the steps: obtaining a first pressure gradient of a target object, a first cardiac image corresponding to the end systole in a cardiac cycle, a second cardiac image corresponding to the end diastole in the cardiac cycle, and a blood flow velocity time sequence in the cardiac cycle; determining cardiovascular characteristics of the target object according to the first cardiac image, the second cardiac image and the blood flow velocity time sequence; inputting the first pressure gradient and the cardiovascular characteristics into a pressure gradient correction model to obtain a second pressure gradient after the first pressure gradient is corrected; wherein the pressure gradient correction model is used for determining a pressure gradient correction amount according to the cardiovascular characteristics, and correcting the first pressure gradient according to the pressure gradient correction amount.

Embodiments of the present invention provide a system for automatically deriving parameters of a human heart from ultrasound results. The first neural network is arranged to receive a plurality of echocardiography images and to classify the images as one of at least a two-lumen tangent plane and a four-lumen tangent plane. The second neural network is arranged to receive echocardiography images comprising two or four-lumen tangent planes and to identify endocardial boundaries of a left ventricle (LV) for each tangent plane. End systolic and end diastolic images are then identified and parameters such as LV volume, ejection fraction, overall longitudinal strain, and regional longitudinal strain are calculated.

The present application belongs to the field of medical devices and physiological signal detection technology, and relates to a pulse wave analysis method and system based on piezoelectric dynamics characteristics. The present application compensates for the attenuation of the subcutaneous tissue on the pulse wave through active acoustic detection, emits high-frequency mechanical vibration waves at the end of diastole using multi-frequency voltage pulses, and receives reflected echoes to construct an equivalent acoustic impedance transfer function and an acoustic inverse compensation filter. The present application restores the true arterial vessel wall dynamics by performing frequency domain deconvolution operation on the original pulse wave signal, locates key physiological event points, estimates the local pulse wave propagation speed using a single-point piezoelectric sensor without the need for multi-point measurement. In combination with the fluid mechanics equation, the present application separates the forward incident wave and the backward reflected wave, calculates the absolute amplitude ratio to evaluate the vascular compliance, effectively eliminates the interference of subcutaneous fat and muscle tissue, improves the accuracy and reliability of the evaluation, and provides a new tool for cardiovascular function evaluation.

The invention discloses an ultrasonic measurement method and system for the three-dimensional volume and ejection fraction of a cardiac cavity, and relates to the field of ultrasonication.The measurement method comprises the following steps that S1, a low-frequency ultrasonic cardiac cavity image and a high-frequency ultrasonic cardiac cavity image are obtained respectively; s2, suppressing high-frequency image noise, adjusting high-frequency feature weight, screening continuous edge segments, and reserving continuous endocardium boundaries; s3, superposing the low-frequency contour and the high-frequency detail features to generate a fused image; s4, segmenting the endocardium boundary of the fused image; and S5, based on the segmented boundary data, calculating the volume and ejection fraction of the end diastole / end systole. According to the method, the low-frequency and high-frequency ultrasonic images are synchronously collected, the fusion weight is dynamically adjusted by monitoring the signal-to-noise ratio in real time, the low-frequency image provides the overall contour of the cardiac cavity, the high-frequency image focuses endocardium details, excessive superposition of high-frequency features in the noise environment is effectively avoided, the stability of endocardium boundary recognition is further guaranteed, and the recognition accuracy is improved. Therefore, the accuracy of measuring the three-dimensional volume and ejection fraction of the heart cavity is improved.

The invention discloses a heart ultrasonic image automatic measurement and analysis method and system and a medium. The method comprises the following steps: acquiring a heart ultrasonic image; performing ultrasonic section classification on the heart ultrasonic image based on a ResNet deep learning model; performing image segmentation on the classified ultrasonic sections based on a UNet segmentation model; identifying the state of the mitral valve in each frame of segmented section, and selecting a final diastole target frame according to the state of the mitral valve corresponding to each frame; calculating heart parameters in the end diastole target frame, and generating an ultrasonic report according to the heart parameters in the multi-segmented section by using an ultrasonic report generation model; therefore, the cardiac ultrasound image can be automatically segmented and analyzed, and a measurement analysis report can be automatically generated.