98 results about "Cardiac Ultrasound" patented technology

A method for real-time fusion of a 2D cardiac ultrasound image with a 2D cardiac fluoroscopic image includes acquiring real time synchronized US and fluoroscopic images, detecting a surface contour of an aortic valve in the 2D cardiac ultrasound (US) image relative to an US probe, detecting a pose of the US probe in the 2D cardiac fluoroscopic image, and using pose parameters of the US probe to transform the surface contour of the aortic valve from the 2D cardiac US image to the 2D cardiac fluoroscopic image.

The invention discloses a heart disease risk prediction system, comprising a computer vision pipeline for processing cardiac ultrasound, wherein the computer vision pipeline for processing cardiac ultrasound comprises a view identification classification, a U-Net convolution neural network for cardiac structure identification, cardiac muscle shape tracking, cardiac muscle shape feature vector extraction, electrocardiogram feature data extraction, clinical feature data extraction, depth learning network architecture and data acquisition and training to predict the probability; Through artificial intelligence to assist automatic ultrasound image recognition and diagnosis, Multidimensional myocardial speckle tracking and prediction of ischemic heart failure were calculated, The combination of medical history, clinical data and biomarkers realizes disease prediction on the machine learning platform, and establishes the first artificial intelligence-assisted accurate, sensitive, efficient,automated and scalable cardiovascular screening system, which realizes low-cost, high-accuracy heart disease prediction and early diagnosis system.

A system and method for limiting a temperature induced in a body by an ultrasound imaging catheter are provided. The method includes receiving, at an isolation box, an imaging signal from an imaging catheter, receiving, at an isolation box, a signal indicative of a temperature of tissue adjacent to the imaging catheter, removing power to the imaging catheter at the isolation box if the signal indicates the temperature of tissue adjacent to the imaging catheter exceeds a known value, and sending the imaging signal from the catheter to a processor if the signal indicates the temperature of tissue adjacent to the imaging catheter is less than the limit.

The invention relates to a method and device for calculating ultrasonic cardiogram cardiac parameters and measuring myocardial strain. A trained neural network is employed for executing the processingof the method, and the processing at least comprises: the classification of a cardiac ultrasonic video to obtain a section classification result; image segmentation of the section classification result to obtain a segmentation result; and acquisition of cardiac parameters and myocardial strain according to the segmentation result. In embodiments of the invention, automatic section classificationprocessing and image segmentation are carried out on the cardiac ultrasonic video through the trained neural network, and the measurement results of the cardiac parameters and the myocardial strain are further automatically obtained, so the workload of doctors is effectively reduced, and working efficiency is improved.

An ultrasound image acquisition device initiates acquisition of anatomical images of a portion of patient anatomy in response to a heart rate related synchronization signal. The ultrasound image acquisition device includes multiple ultrasound transducers for generating sound waves. The ultrasound transducers are arranged in different transducer groups oriented to enable acquisition of different ultrasound imaging information used in generating a single composite ultrasound image. A synchronization processor derives the heart rate related synchronization signal from a patient cardiac function blood flow related parameter. The synchronization signal enables adaptive activation of a particular group of the different transducer groups for acquisition of ultrasound imaging information used in generating the single composite ultrasound image. A display processor presents the single composite ultrasound image, acquired by the ultrasound image acquisition device, to a user on a reproduction device.

The invention provides a method for constructing a three-dimensional heart model based on ultrasonic imaging. Firstly, an ultrasonic image is preprocessed; and then an improved full convolutional neural network learning algorithm is adopted to perform image segmentation and edge contour feature extraction on the data set, a PTAM algorithm is adopted to perform detection and matching of cardiac ultrasonic image feature points and construct a three-dimensional model of the heart, and finally visualization of the three-dimensional heart model is realized. According to the method, the image segmentation effect is fine, the feature extraction precision is high, the model reconstruction speed is high, and the accuracy of the constructed three-dimensional heart model is high. The three-dimensional heart ultrasonic model constructed by the invention can move, rotate and zoom randomly in a three-dimensional space, so that the spatial position relationship of each tissue structure of the heart is observed, more diagnostic information than a heart ultrasonic two-dimensional image is obtained, and the three-dimensional heart ultrasonic model has huge medical application value.

The invention discloses a cardiac ultrasound imaging method, and aims at solving the problem of automatically segmenting of a left ventricle contour during a cardiac measurement process, and preventing the situation of inaccurate volume calculation which might be caused by manually specifying left ventricular segmentation points in the measurement process. Compared with a traditional left ventricular segmentation algorithm, a large number of images of the position of a left ventricle manually marked by a doctor are used to train a deep convolutional neural network, the position of the left ventricle can be accurately identified by the acquired detection network, and a level set algorithm can be performed within a detection position area to obtain a segmentation curve of a left ventricularendocardium; compared with a traditional algorithm, acquired results are more robust, the operation efficiency is higher. According to the cardiac ultrasound imaging method, a manual enhancement manner is adopted to enhance edge areas to improve a segmentation effect aiming at the situation of poor image quality of ultrasound mapping.

A system for improving sensor-based decision making provides for the automatic submission of data obtained locally from instrumentation (such as image data) together with the interpretation of that data, which can be the output of some software which has been checked and possibly corrected by a user according to his / her expertise, to a remote database via an internetwork. The submission to the remote database is preferably automatic so that the remote database grows over time. The local site can access the remote database to retrieve information to assist in interpretation of the locally produced data (for example similar images and their corresponding interpretations), or can retrieve updated or improved software or parameters improving the software used for processing the data. The information on the remote database can also be reprocessed by software agents to provide statistical information based on information from a variety of such local sites. The system is particularly useful in improving the interpretation of data which is difficult to interpret such as medical image data (e.g. mammographic or cardiac ultrasound data).

The invention discloses a three-dimensional myocardial deformation strain calculation method. The invention divides the myocardium into a plurality of local (sub) regions according to the time and space coordinates on the basis of completing the segmentation processing of the marked cardiac magnetic resonance image sequence, a feed forward neural network (BPNN) and a polynomial or support vector machine (SVM) are used for fitting a local displacement field, the calculation of the established local continuous displacement field is done by the Newton iterative method, the motion parameters of the myocardial particle are calculated and the non-linear interpolation technology is used for calculating the myocardial strain parameters. The invention has clear physical significance and simple and effective algorithm, a model is applicable to parallel calculation, which can calculate the forward and backward motion of arbitrary myocardial particle; and the strain calculation results can be used as the judgment criteria of the three-dimensional cardiac ultrasound strain measurement results.

A system and method for limiting a temperature induced in a body by an ultrasound imaging catheter are provided. The method includes receiving, at an isolation box, an imaging signal from an imaging catheter, receiving, at an isolation box, a signal indicative of a temperature of tissue adjacent to the imaging catheter, removing power to the imaging catheter at the isolation box if the signal indicates the temperature of tissue adjacent to the imaging catheter exceeds a known value, and sending the imaging signal from the catheter to a processor if the signal indicates the temperature of tissue adjacent to the imaging catheter is less than the limit.

A method and an apparatus for diagnosing cardiac diseases based on a cardiac motion modeling are provided. The method may include applying physical characteristics of a cardiac motion to a 3D heart shape model, deriving a boundary condition by fusing the 3D heart shape model to which the physical characteristics are applied and a plurality of cardiac ultrasound images according to a temporal change, obtained to acquire a dynamic image, and diagnosing the cardiac diseases using a result of modeling that models the cardiac motion of the user using the boundary condition.

The present disclosure discloses a remote heart three-dimensional ultrasonic imaging system and method based on deep learning. The system includes a user client, a cloud server and a doctor client; the user client is used to control an ultrasonic transmitter and transmit a strobe signal instruction to a flexible wearable multi-array element imaging transducer worn on a chest wall of a human body surface during use, at the same time, the user client is used to control a ultrasonic receiver to receive an ultrasonic signal fed back by an array element corresponding to the strobe signal instruction and upload the fedback ultrasonic signal to the cloud server; the cloud server processes the ultrasonic signal uploaded by the user client and uses a pre-trained individual three-dimensional heart model to process a heart two-dimensional ultrasonic image of a subject to obtain real-time heart contour key points of the subject and obtains real-time heart three-dimensional ultrasonic imaging of the subject based on the real-time heart contour key points; and the doctor client receives the heart contour key points of the subject selected by a doctor, sends the heart contour key points of the subject to the user client through the cloud server, and instructs the user client to send the strobe signal instruction.

An arrhythmia detection device, comprising: an ultrasound probe (22) fastened on the body surface of an object under test, and used to conduct ultrasound scan monitoring on the heart of the object under test; a monitoring probe (20) for probing ECG parameters of the object under test; an ultrasound function module (12) for receiving a cardiac ultrasound signal obtained by the ultrasound probe (22); a monitoring function module (10) for acquiring the ECG parameters of the object under test; an ultrasound information display unit (32) for displaying cardiac ultrasound parameters; a monitoring information display unit (30) for displaying the ECG parameters; and an arrhythmia trigger module (17) for triggering the ultrasound function module (12) to conduct ultrasound scan monitoring via the ultrasound probe (22) on the heart of the object under test.

The invention provides a method and device for identifying a cardiac anatomy structure. The method comprises the steps that of acquiring cardiac ultrasound image to be identified; inputting the cardiac ultrasound image into a pre-trained anatomical structure recognition model to obtain an anatomical structure recognition result, wherein the anatomical structure recognition result comprises pixel values of all pixel points in the cardiac ultrasound image, and the pixel values represent the probability that the pixel points belong to anatomical structure pixels or image background pixels; and determining the position of each anatomical structure key point in the cardiac ultrasound image according to the anatomical structure identification result. According to the processing process of the technical scheme, automatic identification of the anatomical structure in the cardiac ultrasound image is achieved, the method is applied to identification of the cardiac anatomical structure, the identification speed can be increased, and meanwhile the manual labor of doctors can be saved.

A method for real-time fusion of a 2D cardiac ultrasound image with a 2D cardiac fluoroscopic image includes acquiring real time synchronized US and fluoroscopic images, detecting a surface contour of an aortic valve in the 2D cardiac ultrasound (US) image relative to an US probe, detecting a pose of the US probe in the 2D cardiac fluoroscopic image, and using pose parameters of the US probe to transform the surface contour of the aortic valve from the 2D cardiac US image to the 2D cardiac fluoroscopic image.

The present invention provides a congenital heart ultrasonic diagnosis auxiliary device and relates to the field of medical devices. The congenital heart ultrasonic diagnosis auxiliary device comprises a support plate, both sides of a bottom end surface of the support plate are both fixedly connected with three support rods, a reinforcement connecting plate fixedly sleeves middle end rod bodies ofthe six support rods, a rear bed plate and a front bed plate are arranged on an upper end surface, close to a front sides, of the support plate, the rear bed plate is fixedly connected with the upperend surface of the support plate, the rear bed plate and the front bed plate are rotatably connected through a hinge, a soft pad is fixedly connected on an upper end surface of the rear bed plate andthe front bed plate, and two vertical plates are fixedly connected with an upper end surface of the reinforcement connecting plate right at a lower end of the front bed plate. A use of the congenitalheart ultrasonic diagnosis auxiliary device can heat a couplant used during examination, prevents patients from feeling uncomfortable, enables applying of the couplant to be more convenient, and helps patients to get up simultaneously.

An ultrasound image acquisition device initiates acquisition of anatomical images of a portion of patient anatomy in response to a heart rate related synchronization signal. The ultrasound image acquisition device includes multiple ultrasound transducers for generating sound waves. The ultrasound transducers are arranged in different transducer groups oriented to enable acquisition of different ultrasound imaging information used in generating a single composite ultrasound image. A synchronization processor derives the heart rate related synchronization signal from a patient cardiac function blood flow related parameter. The synchronization signal enables adaptive activation of a particular group of the different transducer groups for acquisition of ultrasound imaging information used in generating the single composite ultrasound image. A display processor presents the single composite ultrasound image, acquired by the ultrasound image acquisition device, to a user on a reproduction device.

The invention relates to the technical field of image treatment, in particular to a determination method of cardiac cycles and ultrasonic equipment. The determination method comprises the steps that cardiac ultrasonic videos are obtained; the cardiac ultrasonic videos are classified by using a section-type recognition model to determine the section types of the cardiac ultrasonic videos; and the cardiac ultrasonic videos are processed by adopting systolic and diastolic period recognition models corresponding to the section types, and the cardiac cycles corresponding to the cardiac ultrasonic videos are obtained. Models are adopted to process the cardiac ultrasonic videos to detect the corresponding cardiac cycles. Through a mode of model detection, the use of an electrocardiograph can be avoided, and the detection of the cardiac cycles can be simplified; and furthermore, the real-time detection of the cardiac cycles in the process of cardiac ultrasound can be achieved.

The invention discloses a cardiovascular department detector.The cardiovascular department detector comprises a blood oxygen saturation collecting module, an electrocardio collecting module, a body temperature collecting module, a non-invasive blood pressure collecting module, a cardiac ultrasound detecting module, an other related cardiovascular data collecting module, a man-machine operating module, a central processor, a three-dimension generating module, an expert evaluating module and an artificial expert evaluating module.According to the cardiovascular department detector, detection results of multiple instruments and symptoms dictated by a patient are perfectly integrated, the cardiovascular conditions can be realistically presented through the three-dimension generating module, therefore, a doctor can be immersed to observe and feel the cardiovascular change condition, and the precision of the detection results is further improved; through diagnosis of the expert evaluating module and the artificial expert evaluating module, the detection precision on the symptoms of the patient is improved; meanwhile, data can be shared in real time, and therefore convenience is brought to management and timely treatment of the patient.

The invention discloses an ultrasonic cadiogram system and the realizing method through the esophagus virtually, wherein the system includes a display, a main frame connected to the display and a virtual probe connected to the main frame; a virtual multiple plane ultrasonic cadiogram system module via the esophagus is arranged in the main frame, wherein the system module includes a multiple plane ultrasonic cadiogram data base via the esophagus and a virtual reality environment for the heart ultrasonic operation; the system is applied in the clinic and the practical work, for solving the a plurality of problems which are not identified by the esophagus ultrasonic cadiogram image and are hard to popularize and master by the esophagus ultrasonic cadiogram, in addition, the clinicians and the medicos can grasp the anatomical structure of different esophagus depth and the angle via the ultrasonic cadiogram image on said system, which is favorable for the popularization of the ultrasonic cadiogram via the esophagus and advances the accuracy for diagnosing the heart disease via the esophagus ultrasonic cadiogram, thereby avoiding from adding the pain to the sufferer and reducing the incidence rate of the complication.

The invention discloses a ultrasonic report post-structured analysis method and system, electronic equipment and a computer readable storage medium, and the method comprises the steps: obtaining a to-be-analyzed cardiac ultrasonic reporting file, and recognizing all levels of indexes and corresponding index values in the to-be-analyzed cardiac ultrasonic reporting file through a named entity recognition model based on deep learning; verifying the accuracy of each level of index in combination with a pre-constructed cardiac ultrasound post-structured knowledge graph; if the verification is passed, combining all levels of indexes and index values to obtain cardiac ultrasound post-structured data; and storing the cardiac ultrasound post-structured data into a cardiac ultrasound post-structured knowledge graph so as to display a post-structural result by utilizing the updated knowledge graph. The named entity recognition model is trained in advance based on deep learning, the named entityrecognition model is used for recognizing the ultrasonic report; and compared with a template recognition method, the analysis method based on deep learning has better generalization capacity, and theaccuracy and comprehensiveness of the recognition result can be improved.

The embodiment of the invention relates to a method and device for screening diastolic and systolic images based on a cardiac ultrasound video. The method comprises the following steps: acquiring the cardiac ultrasound video; performing video image framing to generate a plurality of framed images; performing left ventricle semantic segmentation on each framed image to obtain a corresponding left ventricle segmented image; performing image area statistics to generate corresponding left ventricular area parameters; performing area-time curve conversion to generate a first area-time curve; performing significance threshold confirmation to generate a first significance threshold; carrying out saliency peak and valley value point identification on the existing peak and valley value points of the first area-time curve; performing effective peak and valley value point screening on the significant peak and valley value points; and taking the framed image corresponding to the effective valley point as a screening image at the end of a contraction period, taking the framed image corresponding to the effective peak point as a screening image at the end of a relaxation period, and sorting all the screening images to generate a screening image sequence. According to the invention, the image screening quality stability can be ensured.

A method for processing echocardiography data to enable automatic functional measurements based on cardiac ultrasound images as an input, including (i) classification of the cardiac ultrasound images to ensure that relevant images are passed on to the next steps, optionally utilising a first neural network, such as a convolutional neural network, (ii) segmentation and semantic partitioning of the left ventricle (LV) myocardium to extract relevant parts of the image, optionally by using a second neural network, (iii) regional motion estimates to determine a mapping of displacements in the extracted parts of the image and to output estimated tissue motion vectors for the extracted parts of the image, optionally using a third neural network, and (iv) fusion of measurements via state estimation applied to the tissue motion vectors and thereby incorporating a temporal domain to produce data showing variation of the estimated measurements over time.

A cardiac ultrasound image display to analyze a heart wall motion, and a method and apparatus for displaying a cardiac ultrasound image. A method of displaying a medical image includes obtaining a characteristic value for each of one or more segments included in an object, generating an image of the object indicating the segment of which the characteristic value is a predetermined value, and displaying the image.

A method and an apparatus for diagnosing cardiac diseases based on a cardiac motion modeling are provided. The method may include applying physical characteristics of a cardiac motion to a 3D heart shape model, deriving a boundary condition by fusing the 3D heart shape model to which the physical characteristics are applied and a plurality of cardiac ultrasound images according to a temporal change, obtained to acquire a dynamic image, and diagnosing the cardiac diseases using a result of modeling that models the cardiac motion of the user using the boundary condition.

The invention provides an automatic ventricular region segmentation method and device for a cardiac ultrasound image and a storage medium, and relates to the technical field of image processing. According to the method, a ventricular region automatic segmentation model is utilized to obtain a segmentation result of each pixel in a to-be-segmented ultrasonic image. According to the ventricular region automatic segmentation model, compared with a traditional UNet method, the network structure of the model is improved, an up-sampling deconvolution layer of a decoder of the model is a multi-dimensional splicing type deconvolution up-sampling layer, the decoder can better obtain image information from multiple dimensions, and then the segmentation accuracy is improved. According to the automatic ventricular region segmentation model, the model training speed and accuracy can be effectively improved, and then the speed and accuracy of automatically segmenting the left ventricular region in the echocardiogram are improved.

The invention relates to a cardiac ultrasound training model comprising a main model body being a model made of a simulated human heart. The main model body consists of a plurality of model assembliesand an acoustic window board assembly. The model assemblies are connected successively from the heart bottom of the main model body to the heat tip; the connection plane between each two adjacent model assemblies is a cardiac ultrasound standard section; and mirror image structures are formed at the connection parts. The acoustic window board assembly has a foldable sector structure; and the multiple model assemblies are connected with the acoustic window board assembly. According to the cardiac ultrasound training model, the main model body is based on the design of the simulated human heartand is formed by successive connection of multiple model assemblies; and with cooperation of adjustment by the acoustic window board assembly, the whole standard section is displayed, so that interpretation transformation from the cardiac anatomy to the ultrasonic image is realized conveniently. Therefore, students are assisted in understand the corresponding relationship of the ultrasound anatomy quickly and thus the teaching goal is achieved quickly. Moreover, the model has advantages of reasonable price, first-rate quality, high portability, high repeatability, and good economic efficiency.

The invention provides a method of noninvasively calculating personalized coronary artery branch blood flow reserve capacity, and belongs to the field of biomedical engineering. The method includes the steps: cardiac ultrasound data is adopted to obtain the flow of a coronary artery at a resting state; on the basis of coronary artery CT image files, a coronary artery three-dimensional model is rebuilt, and the length, volume and opening cross-section area of a coronary artery branch are measured; then, according to coronary artery fractal coefficients and allometry laws, a flow distribution method based on the opening cross-section area of the coronary artery branch is built, in combination with resistance mathematical models corresponding to coronary artery stenosis segments and coronaryartery non-stenosis segments, the pressure of a coronary artery distal outlet is obtained, and through hydrodynamics, coronary artery distal outlet flow taking stenosis effects into account is calculated; and finally, according to the relationship that the flow of the coronary artery at a maximum congestion state is 3 times that of the coronary artery at the resting state, coronary artery distal outlet flow at the maximum congestion state is obtained, and by comparing a threshold value of 3 with the ratio of the coronary artery blood flow at the maximum congestion state and the coronary arteryblood flow at the resting state, the coronary artery branch blood flow reserve capacity is determined.

The invention provides a cardiac ultrasound real-time imaging method. The method comprises the following steps: S1, when ultrasonic equipment is in a real-time scanning state, detecting and storing amovie triggering request signal in real time; S2, responding to the detected triggering request signal, and automatically executing timing operation; S3, acquiescently, automatically generating a freezing control instruction when timekeeping time is equal to time T of a waited movie; S4, responding to the freezing control instruction, and freezing a real-time ultrasonic image of the ultrasonic equipment, wherein time of the frozen real-time ultrasonic image is corresponding to the timekeeping time; S5, automatically storing the frozen real-time ultrasonic image; S6, detecting progress that theultrasonic equipment stores the real-time ultrasonic image, and generating an unfreezing control instruction after a save action is completed; and S7, responding to the unfreezing control instruction, automatically unfreezing, and entering the real-time scanning state. The invention also provides a corresponding imaging system, and the operation is simplified, so that a doctor can concentrate ona cardiac ultrasound real-time image.

The invention discloses a percutaneous left heart drainage tube, which comprises a ventricular segment positioned in a left ventricle and an artery segment (1) positioned in an external artery of theleft ventricle, wherein the included angle between the ventricular segment and the artery segment (1) is 160-175 degrees; the ventricular segment consists of an inhalation segment (3) and a non-inhalation segment (2); the inhalation segment (3) is positioned at the tail end; a plurality of inhalation side holes (4) are formed in the wall of the inhalation segment (3); a plastic spring ring (7) sleeves outside the non-inhalation segment (2) and the artery segment (1); the percutaneous left heart drainage tube can be inserted through the axillary artery or the carotid artery, the operation flowis simplified, and the ventricular assist device can be coordinated to achieve left heart drainage. The drainage catheter is directly arranged in the left ventricle under the guidance of cardiac ultrasound or DSA through the peripheral vessel, and high-risk invasive operations such as atrial septum puncture or ventricular opening and the like are not needed; in addition, the percutaneous left heart drainage tube can effectively drain left ventricle blood, and the ventricular load is reduced through the catheter in ventricular assistance.