24 results about "Cardiac phase" patented technology

The invention provides a registration method and device in a cardiac surgery and computer equipment, which are used for improving the safety and accuracy of the surgery. The registration method comprises the following steps: acquiring an electrocardiosignal and multi-modal physiological data of a surgical patient, and performing cardiac time phase division on a cardiac cycle based on the electrocardiosignal and the multi-modal physiological data; collecting multi-angle image data of the heart under each cardiac time phase, and synchronously collecting physiological parameter data; performing three-dimensional reconstruction based on the multi-angle image data corresponding to each cardiac time, and mapping the physiological parameter data corresponding to each cardiac time to a corresponding three-dimensional reconstruction result to obtain a multi-temporal three-dimensional heart model library; the method comprises the following steps: acquiring real-time electrocardiosignals and real-time multi-modal physiological data of a surgical patient in a surgical process to identify a current cardiac time phase, selecting a current time phase three-dimensional heart model from a multi-time phase three-dimensional heart model library according to the current cardiac time phase, and performing surgical registration by using the current time phase three-dimensional heart model.

The application discloses an old person free breathing coronary artery scanning image lesion analysis system and relates to the technical field of scanning image lesion analysis. In order to solve the problem that the accurate condition of a patient cannot be obtained according to a scanning image. The application adopts a diameter method, an area method and a contrast agent filling condition to judge the stenosis degree and the hemodynamic change, analyzes the lesion from the morphological and functional double angles, provides comprehensive information for clinical decision-making, identifies the R wave peak value and divides the cardiac phase, matches the respiratory signal and the projection data in time, can accurately capture the characteristics of the heart in different motion states and the respiratory stage, effectively avoids the interference of the artifacts caused by the heart beat and the respiratory motion, makes the reconstructed image clearer and more accurate, sets the CT and the injector parameters in sequence from the scanning type confirmation, each link is closely related and the target is clear, improves the work efficiency, and is convenient for quality control and process management.

The application discloses a heart soft tissue model correction method and device based on a physical information neural network, and comprises the following steps: acquiring preoperative images to construct a personalized heart biomechanical model and an active motion priori library; constructing a double-flow coupled physical information neural network, which comprises an active deformation prediction branch for predicting heart autonomous beats and a passive residual correction branch for correcting deformations caused by external contact forces; defining a loss function comprising a data matching loss and a biomechanical control equation loss, and training the network; receiving in-surgery collected cardiac phase data and sparse surface displacement data, inputting the data into the trained network, and outputting a global three-dimensional deformation field to update a preoperative three-dimensional model. The application effectively decouples the active and passive mixed deformation of the heart through a double-flow coupled architecture, and can infer the full-field volume deformation by only using sparse surface observation points by embedding physical control equations as strong constraints, thereby overcoming the data sparsity problem.

The application provides a cardiac phase judgment device, method, medium and electronic equipment. The device comprises: a medical image acquisition module, configured to acquire a plurality of three-dimensional medical images of a target object in at least one cardiac cycle; a myocardial wall thickness acquisition module, configured to acquire the thickness of a left ventricular myocardial wall in each frame of the three-dimensional medical images; and a cardiac phase judgment module, configured to acquire the cardiac phase of the target object according to the thickness of the left ventricular myocardial wall in each frame of the three-dimensional medical images. The cardiac phase judgment device only needs to acquire the cardiac phase of the target object according to the three-dimensional medical images of the target object, and is simpler to implement.

The present application aims to improve the data acquisition efficiency in the imaging using both ECG synchronization and respiratory motion synchronization. During the imaging, the respiratory motion is monitored to detect the start of the respiratory stable period (exhalation). After detecting the R wave, it is confirmed that the respiratory motion immediately before the R wave has transitioned to the respiratory stable period, and the formal measurement is performed at the time when the cardiac phase and the respiratory phase of the subject coincide, and the image data is acquired. The cardiac phase at which the image data is acquired is fixed, and the slice position for the formal measurement is adjusted using the respiratory motion displacement acquired immediately before. Thus, it is possible to acquire image data of two heart rate quantities within the respiratory cycle after entering the stable period while suppressing the influence of motion.

Some disclosed methods involve monitoring a heart rate waveform associated with a subject to detect cardiac cycle markers, determining a cardiac phase transition window based on the cardiac cycle markers, and activating a photoacoustic sampling system at a start of the cardiac phase transition window, the photoacoustic sampling system including a piezoelectric receiver and a light source system. Such methods may involve, during the cardiac phase transition window, controlling the light source system to emit a plurality of light pulses into biological tissue of the subject, receiving, from the piezoelectric receiver, signals corresponding to acoustic waves emitted from portions of the biological tissue, and obtaining plethysmography data based on the signals. Such methods may involve deactivating the photoacoustic sampling system by an end of the cardiac phase transition window.

The invention discloses a heart CTA image group registration template construction method based on deep learning, and aims to solve the problems of fuzzy template, low construction efficiency and unstable alignment caused by significant deformation and intensity difference of the heart under different cardiac phases and scanning conditions. The method comprises the following steps: acquiring and preprocessing a heart CTA image; grouping is carried out based on feature similarity and topology persistent coherence; a multi-resolution three-dimensional registration network is adopted in each level to carry out coarse-to-fine registration estimation; differential deformation is realized through a space converter, and end-to-end and symmetric training is carried out by adopting combined loss of multi-scale reconstruction similarity and displacement field smooth regularization; clear sub-templates are obtained through iteration of a registration-averaging-updating strategy in the sub-groups, and finally, the sub-templates are converged step by step to obtain a global heart template, so that efficient and stable heart template construction is realized.

This invention discloses a preoperative risk prediction method for cerebral aneurysms based on multimodal deep learning. To address the problems of time-consuming computational fluid dynamics simulations and difficulty in quickly obtaining individualized hemodynamic indicators, this invention reconstructs vascular geometry and a tree diagram by aligning computed tomography angiography, magnetic resonance angiography, and blood pressure and heart rate time series. It employs a graph network that satisfies Kirchhoff conservation and connects differentiable Wendt-Kessel impedance learning boundary conditions. Combining physical constraints of cardiac phase conditional neural operators, Helmholtz projection, and signed distance function boundary embedding, it approximates the flow field, calculates and closes the loop to correct wall shear stress, oscillatory shear exponent, and pressure gradient. Then, it fuses the risk features of the imaging branch, clinical branch, and text branch through expert product to output lesion-level and patient-level risks and confidence levels. This achieves the technical effect of rapidly estimating hemodynamics and performing interpretable preoperative risk assessment under physically consistent constraints.

The present disclosure provides a cardiac phase recognition method, device, equipment and storage medium, to realize multi-frame automatic segmentation and accurate cardiac phase recognition. The cardiac phase recognition method comprises: selecting an initial segmentation frame in the ventricular contrast sequence image data; performing ventricular boundary recognition based on the feature points marked in the initial segmentation frame to determine the ventricular boundary contour; for the image frame adjacent to the initial segmentation frame, taking the ventricular boundary contour of the initial segmentation frame as the starting contour, emitting a ray in a narrow band range to search for a boundary point in a polar coordinate manner, connecting the boundary points and performing region-driven segmentation to obtain the ventricular boundary contour; taking the image frame as a new initial segmentation frame, repeating the above steps for the next image frame to obtain the full sequence ventricular boundary contour; determining the ventricular cavity area sequence corresponding to the ventricular contrast sequence image data based on the full sequence ventricular boundary contour, and dividing the cardiac phase according to the ventricular cavity area sequence.

A cardiac phase selection method and an imaging method are described. The cardiac phase selection method includes: obtaining coronary image quality index data of a coronary image dataset, wherein the coronary image quality index data quantifies the medical image quality of coronary medical images of a subject under examination at a plurality of cardiac phases; selecting a first cardiac phase from the plurality of cardiac phases based on the coronary image quality index data, wherein the first cardiac phase is within a first phase range; and selecting a second cardiac phase based on the coronary image quality index data, wherein the second cardiac phase is within a second phase range different from the first phase range. In examples described herein, a plurality of cardiac phases can be selected, thereby facilitating the acquisition of medical images of the plurality of cardiac phases.

The invention provides a CT cardiac stationary period detection and imaging triggering method and device based on millimeter wave radar, and the method comprises the steps: carrying out the self-adaptive offset through a chest wall micro-motion signal collected in a non-contact manner and a reference channel signal, and separating breathing and heartbeat components; obtaining a high-precision instantaneous cardiac phase and the uncertainty thereof; generating a trigger availability score in combination with the multi-dimensional features, and adaptively selecting a trigger strategy; and system delay is calibrated on line, an RR interval is predicted, an advanced triggering moment is calculated based on a target phase proportion, and accurate imaging triggering is realized in combination with a safety guard condition. According to the method, non-contact and self-adaptive accurate cardiac stationary phase detection and imaging triggering can be realized in a strong interference environment of a CT machine room, multiple challenges such as metal scattering, cardiac respiration coupling, individual difference and system delay are overcome, CT environment interference and individual difference can be effectively overcome, and the cardiac CT image quality and the scanning success rate are remarkably improved.

The disclosure relates to a method for generating MR images of a heart of a patient. The method may include selecting first 3D MR datasets acquired at a first breath hold of the patient over a plurality of cardiac phases and selecting second 3D MR datasets acquired at a second breath hold over several cardiac phases. A first combined MR dataset may be generated based on the first 3D MR datasets at the first breath hold, and a second combined MR dataset may be generated based on the second 3D MR datasets at the second breath hold. Motion information for the heart between the first and second breath hold may be determined based on the first and second combined MR datasets. For the plurality of cardiac phases, MR images of the heart may be reconstructed based on the first 3D MR datasets, motion information, and second 3D MR datasets.

The invention provides for a medical system, a method of operating thereof and a computer program. The system comprises a magnetic resonance system (200) and a cardiac monitoring system (110) capturing cardiac phase data. A memory (320) holds machine executable instructions (330) and pulse sequence commands (340) causing magnetic resonance system (200) to acquire myocardial k- space data. The commands comprise at least one preparatory pulse portion (130) and multiple k-space acquisition portions (140). Executing instructions (330), computational system (302) processes cardiac phase data, identifies trigger signals (150) and causes data collection. A first preparatory pulse portion (131) follows a first k-space acquisition portion (141) after a first trigger signal (151) which occurs at a fixed acquisition delay (160) after the trigger. A second k-space acquisition portion (142) follows the pulse and a second trigger signal (152), the preparatory delay (170) between pulse and second acquisition exceeds the fixed acquisition delay.

This invention discloses a patient vital signs detection system based on millimeter-wave radar, belonging to the field of vital signs monitoring technology. The system includes: acquiring multi-range-unit echo phase data using millimeter-wave radar; calculating the phase difference between adjacent range units to identify and delete static scatterer data; and outputting a dynamic phase sequence. Spectral analysis is performed on the dynamic phase sequence to identify overlapping energy frequency bands, establishing a time-frequency distribution matrix, and separating the phase into respiratory and cardiac phase components based on temporal envelope differences. The trough positions of the respiratory phase components are detected, and the cardiac phase components are divided into multiple respiratory cycle segments according to the trough positions. Phase jump variables at the boundaries are calculated for cumulative phase compensation, and a continuous phase heartbeat signal is output. The phase offset angle between the peak of the heartbeat signal and the trough of the respiratory signal is detected, and the cross-cycle change amplitude is calculated. An intervention command is triggered when the value exceeds a threshold. This invention improves the accuracy and reliability of vital signs monitoring.

A method implemented by a system of one or more computers, wherein the method comprises: accessing an image sequence comprising a plurality of vascular images, the vascular images depicting a portion of a heart from a particular viewpoint and the vascular images being associated with different times within a time range; determining a subset of the vascular images which are associated with a particular cardiac phase, wherein determining comprises computing a forward pass through a machine learning model trained to classify vascular images based on cardiac phase; generating segmentation masks associated with the subset, wherein the segmentation masks segment vessels included in the respective vascular images which form the subset, wherein mask scores are determined for the segmentation masks which are indicative of a size or length associated with a vessel included in a segmentation mask, and wherein the subset is filtered to remove one or more vascular images based on the mask scores; and determining a particular vascular image included in the filtered subset, wherein the determination is based analyzing one or more image quality measures determined for each vascular image included in the filtered subset, wherein the particular vascular image is configured for inclusion in an interactive user interface.

The present disclosure provides a cardiac phase recognition method, device, equipment and storage medium, to realize multi-frame automatic segmentation and accurate cardiac phase recognition. The cardiac phase recognition method comprises: selecting an initial segmentation frame in the ventricular contrast sequence image data; performing ventricular boundary recognition based on the feature points marked in the initial segmentation frame to determine the ventricular boundary contour; for the image frame adjacent to the initial segmentation frame, taking the ventricular boundary contour of the initial segmentation frame as the starting contour, emitting a ray in a narrow band range to search for a boundary point in a polar coordinate manner, connecting the boundary points and performing region-driven segmentation to obtain the ventricular boundary contour; taking the image frame as a new initial segmentation frame, repeating the above steps for the next image frame to obtain the full sequence ventricular boundary contour; determining the ventricular cavity area sequence corresponding to the ventricular contrast sequence image data based on the full sequence ventricular boundary contour, and dividing the cardiac phase according to the ventricular cavity area sequence.

The invention discloses a heart soft tissue model correction method and device based on a physical information neural network. The method comprises the following steps: acquiring a preoperative image to construct a personalized heart biomechanical model and an active movement prior library; constructing a double-flow coupling physical information neural network, wherein the double-flow coupling physical information neural network comprises an active deformation prediction branch used for predicting heart autonomous pulsation and a passive residual error correction branch used for correcting deformation caused by external contact force; defining a loss function including data matching loss and biomechanical control equation loss, and training the network; and receiving cardiac phase data and sparse surface displacement data collected in an operation, inputting the data into the trained network, and outputting a global three-dimensional deformation field to update the preoperative three-dimensional model. According to the method, active and passive mixed deformation of the heart is effectively decoupled through a double-flow coupling architecture, a physical control equation is embedded as a strong constraint, full-field volume deformation can be deduced only by using sparse surface observation points, and the problem of data sparsity is solved.

An apparatus is provided with processing circuitry that receives a phase image acquired at a corresponding cardiac phase, determines, from the received phase image, a mask image of a particular cardiac region, applies both the determined mask image and the phase image to inputs of a trained neural network model to obtain, from outputs of the neural network model, a location probability map. The neural network model is trained with a set of input data and a corresponding set of output data. The input data includes a training mask image and a training phase image, and the output data includes a training location probability map. The processing circuitry calculates, for the cardiac phase, from the determined location probability map output from the trained neural network model, a value of a cardiac motion metric. The determined location probability map specifies a probable location of a cardiac vessel.

The invention discloses an image acquisition and post-processing method and device, electronic equipment, a medium and a product, and belongs to the technical field of medical image acquisition and post-processing. The angiography image set is a set of cardiac angiography images at different angles, which are triggered and acquired when the target object is in a target cardiac phase in a composite rotational motion process of a C-shaped arm on a plane formed from a left front oblique position to a right front oblique position of the target object and a plane formed from a head position to a foot position; or the cardiac angiography image of the target cardiac phase is selected from angiography images of different angles of cardiac blood vessels, which are continuously and rotatably acquired in a plurality of cardiac cycles; selecting a target angiography image from the angiography image set; and performing image post-processing on the target angiography image to obtain the post-processing parameter which corresponds to the target angiography image and is used for generating the operation planning information, thereby improving the accuracy of the generated operation planning information.

Some disclosed methods involve: monitoring a heart rate waveform associated with a subject to detect a cardiac cycle marker; determining a cardiac phase change window based on the cardiac cycle marker; and starting a photoacoustic sampling system at the beginning of the heart phase change window, wherein the photoacoustic sampling system comprises a piezoelectric receiver and a light source system. Such methods may involve, during the cardiac phase change window: controlling the light source system to emit a plurality of light pulses into biological tissue of the subject; receiving, from the piezoelectric receiver, signals corresponding to the acoustic waves emitted from the portions of the biological tissue; and obtaining plethysmographic data based on the signal. Such methods may involve deactivating the photoacoustic sampling system at the end of the cardiac phase change window.

The application provides a non-synchronous dual-view coronary motion compensation reconstruction method. The method constructs a high-dimensional motion model containing a cardiac phase, a respiratory phase and a local region modulation parameter based on three-dimensional coronary prior data, generates a non-synchronous dual-view training sample through reversible differential homeomorphism deformation, trains an implicit motion compensation network by using the sample, corrects cross-view non-rigid mismatch, inputs a compensated three-dimensional intermediate representation into a post-stage reconstruction model, and outputs a coronary three-dimensional result, so that the reconstruction continuity and topological consistency are improved.

This application discloses a plaque segmentation model training method, an information processing method, apparatus, device, and medium for carotid plaque segmentation, relating to the field of information processing technology. The method includes: performing cardiac cycle detection on raw carotid ultrasound video and normalizing the video frame sequence to cardiac phase to obtain a preprocessed carotid ultrasound video; constructing a target training dataset using the preprocessed carotid ultrasound video; including a first training dataset with segmentation annotations and a second training dataset without segmentation annotations; extracting plaque motion features and vessel wall motion features from the first training dataset to construct motion coupling constraints; training a plaque segmentation network model based on the target training dataset, and dynamically adjusting the weights of the loss term in the joint loss function according to the course learning strategy during training, so as to optimize the network parameters based on the joint loss function and motion coupling constraints to train a plaque segmentation model.

Disclosed herein is a medical system (100, 300, 700) comprising a magnetic resonance imaging system (102) configured to acquire lines of k-space (144) data from a thoracic region (122) of a subject (118). Execution of machine executable instructions (140) causes a computational system (132) to: repeatedly (200) acquire the lines of k-space data by controlling the magnetic resonance imaging system with the pulse sequence commands; repeatedly (202) assemble motion resolved k-space data (146) from the lines of k-space data using at least one cardiac phase and one respiratory phase of the subject as the k-space data is acquired; retrieve (204) at least a portion (148) of the motion resolved k-space data during acquisition of the k-space data; and construct (206) a preliminary three-dimensional cardiac image (150) using at least a portion of the motion resolved k-space data before acquisition of the lines of k-space data is finished. The pulse sequence commands are according to a three-dimensional free running cardiac magnetic resonance imaging protocol.

This specification provides a cardiac phase selection method and a medical imaging method. The cardiac phase selection method includes: acquiring coronary artery image quality index data from a coronary artery image dataset, wherein the coronary artery image quality index data quantifies the medical image quality of the coronary arteries of an examined object at multiple cardiac phases; selecting a first cardiac phase from the multiple cardiac phases based on the coronary artery image quality index data, wherein the first cardiac phase is within a first phase range; and selecting a second cardiac phase from the coronary artery image quality index data, wherein the second cardiac phase is within a second phase range different from the first phase range. This specification embodiment can select multiple cardiac phases, thereby facilitating the acquisition of medical images at multiple cardiac phases.