Method and system for visualizing cardiac electrical conduction

Abstract

Various methods and systems for medical imaging systems are provided. In one embodiment, a method includes generating a cardiac ultrasound image from ultrasound imaging data of a heart, generating a spatiotemporal map of electrical impulses in the heart based on contractions and elongations of heart muscle depicted in the cardiac ultrasound image, and outputting the spatiotemporal map of electrical impulses in the heart to a display device. In this way, the spatiotemporal map of electrical impulses in the heart can visually indicate electrical conduction pathways through the heart.

Description

Technical Field

[0001] The implementation scheme of the subject matter disclosed herein relates to ultrasound imaging. Background Technology

[0002] An ultrasound imaging system typically includes an ultrasound probe applied to a patient's body and a workstation or device operatively coupled to that probe. During a scan, the probe can be controlled by the system operator and is configured to transmit and receive ultrasound signals processed into ultrasound images by the workstation or device. The workstation or device can display the ultrasound images and multiple user-selectable inputs via a display device. The operator or other user can interact with the workstation or device to analyze the images displayed on and / or select from the multiple user-selectable inputs. Summary of the Invention

[0003] In one aspect, a method includes generating a cardiac ultrasound image from cardiac ultrasound imaging data, generating a spatiotemporal map of electrical impulses in the heart based on the contraction and elongation of cardiac muscle depicted in the cardiac ultrasound image, and outputting the spatiotemporal map of electrical impulses in the heart to a display device.

[0004] The advantages, other advantages, and features of this specification will become apparent from the following detailed description, either alone or in connection with the accompanying drawings. It should be understood that the above summary is provided to present a simplified version of the selected concepts further described in the detailed description. This is not intended to identify key or essential features of the claimed subject matter, the scope of which is uniquely defined by the claims following the detailed description. Furthermore, the claimed subject matter is not limited to embodiments that address any of the disadvantages mentioned above or in any part of this disclosure. Attached Figure Description

[0005] A better understanding of the various aspects of this disclosure can be achieved by reading the following detailed description and referring to the accompanying drawings, in which:

[0006] Figure 1 A block diagram of an ultrasound imaging system according to one embodiment is shown;

[0007] Figure 2 This is a schematic diagram illustrating an image processing system for segmenting myocardium in medical images according to an embodiment.

[0008] Figure 3 A flowchart is shown of an exemplary method for outputting cardiac electrical conduction pathways during ultrasound imaging of the heart, according to one embodiment;

[0009] Figure 4 An exemplary myocardial segmentation according to one implementation scheme is shown;

[0010] Figure 5This is a graph illustrating an exemplary relationship between strain values ​​and electrical pulse intensity; and

[0011] Figure 6 An exemplary cardiac electrical conduction pathway display output is shown. Detailed Implementation

[0012] Now, we will use examples to refer to... Figures 1 to 6 To describe the implementation scheme of this disclosure, Figures 1 to 6 Various implementation schemes for cardiac ultrasound imaging are disclosed. In particular, systems and methods for visualizing electrical conduction pathways through a patient's heart are provided. Contraction and relaxation of the heart muscle are caused by muscle depolarization and repolarization triggered by electrical impulses. Contraction and relaxation of the heart muscle result in longitudinal, circumferential, and radial strain values, which can be calculated via strain tools used in cardiac ultrasound imaging (e.g., speckle-tracking echocardiography). Such strain values ​​can provide information about cardiac regions with impaired heart muscle function. However, users may find it difficult to interpret strain values, especially because these three strain values ​​may be difficult to combine to assess the health of the muscle in a given region. For example, contraction may be weakened in only one direction (e.g., only one of the longitudinal, circumferential, and radial strain values ​​may show weakening), and this weakening can be masked by successive contractions in the other two directions. As a result, areas of impaired muscle function may go unidentified.

[0013] Therefore, according to the implementation scheme described herein, images of the heart can be acquired by an ultrasound imaging system, such as... Figure 1 The ultrasound imaging system shown in the figure. Figure 2 An exemplary image processing system for segmenting cardiac muscle (e.g., myocardium) is illustrated. The image processing system can employ image processing and deep learning algorithms to segment myocardium within ultrasound images; an example is shown in [the document / example]. Figure 4 As shown in the figure, the segmented ultrasound images can be further analyzed via speckle-tracking echocardiography to determine the contraction of the myocardium over time. Because myocardial contraction is caused by electrical impulses passing through the heart, the strain values ​​determined from speckle-tracking echocardiography can be used, for example, according to… Figure 3 The method generates a spatiotemporal map showing the channels of electrical impulses passing through the heart. An example relationship between strain values ​​and electrical impulse intensity is shown in... Figure 5 As shown in the figure. In some implementations, the image processing system may also employ deep learning algorithms to directly calculate the electrical conduction path from ultrasound images, without first calculating strain values ​​via speckle-tracking echocardiography. Figure 6 The example output is shown in the figure, which illustrates a spatiotemporal diagram of the pathway of electrical impulses through the heart (also referred to herein as the cardiac electrical conduction pathway).

[0014] One advantage achievable in practice with some implementations of the aforementioned systems and techniques is the easier identification of areas of impaired muscle function. For example, generating a visualization of the cardiac electrical conduction pathway can reveal areas of impaired cardiac muscle function because electrical impulses do not travel through the infarcted muscle. Therefore, visualization of the cardiac electrical conduction pathway simultaneously summarizes strain values ​​in all directions in a simple and intuitive way, without relying on additional user interpretation. In this way, areas of impaired cardiac function can be more easily identified, leading to more accurate and timely diagnoses.

[0015] While the systems and methods for evaluating medical images described below are discussed with reference to ultrasound imaging systems, it should be noted that the methods described herein can be applied to a variety of imaging systems. Because the processes described herein can be applied to pre-processed imaging data and / or processed images, the term "image" is generally used throughout this disclosure to refer to pre-processed and partially processed image data (e.g., pre-beamformed RF or in-phase / quadrature data, pre-scan-converted RF data) and fully processed images (e.g., scan-converted and filtered images ready for display).

[0016] See Figure 1 A schematic diagram of an ultrasound imaging system 100 according to an embodiment of the present disclosure is shown. However, it will be understood that the embodiments described herein can be implemented using other types of medical imaging modalities (e.g., magnetic resonance imaging, computed tomography, positron emission tomography, etc.). The ultrasound imaging system 100 includes a transmit beamformer 101 and a transmitter 102 that drives elements (e.g., transducer elements) 104 within a transducer array (referred to herein as probe 106) to transmit pulsed ultrasound signals (referred to herein as transmit pulses) into a body (not shown). According to one embodiment, probe 106 may be a one-dimensional transducer array probe. However, in some embodiments, probe 106 may be a two-dimensional matrix transducer array probe. Transducer element 104 may be made of a piezoelectric material. When a voltage is applied to the piezoelectric material, the piezoelectric material physically expands and contracts, thereby emitting ultrasonic spherical waves. In this way, transducer element 104 can convert an electronic emission signal into an acoustic emission beam.

[0017] After the transducer element 104 of probe 106 transmits a pulsed ultrasound signal into the patient's body, the pulsed ultrasound signal is backscattered from internal structures such as blood cells and muscle tissue to generate an echo returning to element 104. The echo is converted into an electrical signal or ultrasound data by element 104, and the electrical signal is received by receiver 108. The electrical signal representing the received echo passes through a receiving beamformer 110 that performs beamforming and outputs ultrasound data, which may be in the form of a radio frequency (RF) signal. Additionally, transducer element 104 may generate one or more ultrasound pulses based on the received echo to form one or more transmit beams.

[0018] According to some embodiments, probe 106 may include electronic circuitry to perform all or part of transmit beamforming and / or receive beamforming. For example, all or part of transmit beamformer 101, transmitter 102, receiver 108, and receive beamformer 110 may be located within probe 106. In this disclosure, the terms “scanning” or “under scanning” may also be used to refer to the process of acquiring data by transmitting and receiving ultrasound signals. In this disclosure, the term “data” may be used to refer to one or more datasets acquired using an ultrasound imaging system. In one embodiment, data acquired via ultrasound imaging system 100 may be processed via an imaging processing system, as will be described below relative to… Figure 2 Detailed description.

[0019] User interface 115 can be used to control the operation of ultrasound imaging system 100, including for controlling the input of patient data (e.g., patient history), for changing scan or display parameters, for initiating probe repolarization sequences, etc. User interface 115 may include one or more of the following: a rotary element, a mouse, a keyboard, a trackball, hard keys linked to specific actions, soft keys configurable to control different functions, and a graphical user interface displayed on display device 118. In some embodiments, display device 118 may include a touch-sensitive display, and therefore display device 118 may be included in user interface 115.

[0020] The ultrasound imaging system 100 also includes a processor 116 for controlling the transmitting beamformer 101, the transmitter 102, the receiver 108, and the receiving beamformer 110. The processor 116 communicates electronically (e.g., is communicatively connected) with the probe 106. As used herein, the term "electronic communication" can be defined to include both wired and wireless communication. The processor 116 can control the probe 106 to acquire data according to instructions stored in the processor's memory and / or memory 120. As an example, the processor 116 controls which of the elements 104 are active and the shape of the beam emitted from the probe 106. The processor 116 also communicates electronically with a display device 118, and the processor 116 can process data (e.g., ultrasound data) into images for display on the display device 118. According to one embodiment, the processor 116 may include a central processing unit (CPU). According to other embodiments, the processor 116 may include other electronic components capable of performing processing functions, such as a digital signal processor, a field-programmable gate array (FPGA), or a graphics board. According to other embodiments, processor 116 may include multiple electronic components capable of performing processing functions. For example, processor 116 may include two or more electronic components selected from a list of electronic components, including: a central processing unit, a digital signal processor, a field-programmable gate array, and a graphics board. According to another embodiment, processor 116 may also include a composite demodulator (not shown) that demodulates RF data and generates raw data. In yet another embodiment, demodulation may be performed earlier in the processing chain.

[0021] Processor 116 is adapted to perform one or more processing operations based on multiple selectable ultrasound modalities on the data. In one example, data can be processed in real time during a scanning session because echo signals are received by receiver 108 and transmitted to processor 116. For the purposes of this disclosure, the term "real time" is defined as including processes performed without any intentional delay (e.g., substantially as they occur). For example, embodiments may acquire images at a real-time rate of 7 frames / second to 20 frames / second. Ultrasound imaging system 100 is capable of acquiring two-dimensional (2D) data of one or more planes at significantly faster rates. However, it should be understood that the real-time frame rate can depend on the length of time (e.g., duration) spent acquiring and / or processing each frame of data used for display. Therefore, the real-time frame rate may be slower when acquiring relatively large amounts of data. Thus, some embodiments may have a real-time frame rate significantly faster than 20 frames / second, while other embodiments may have a real-time frame rate less than 7 frames / second.

[0022] In some implementations, data may be temporarily stored in a buffer (not shown) during a scanning session and processed in a less real-time manner during real-time or offline operation. Some implementations of this disclosure may include multiple processors (not shown) to handle processing tasks handled by processor 116 according to the exemplary implementation described above. For example, a first processor may be used to demodulate and extract RF signals before displaying an image, while a second processor may be used to further process the data (e.g., by augmenting the data as further described herein). It should be understood that other implementations may use different processor arrangements.

[0023] The ultrasound imaging system 100 can continuously acquire data at frame rates, for example, from 10 Hz to 30 Hz (e.g., 10 frames / second to 30 frames / second). Images generated from the data can be refreshed on a display device 118 at a similar frame rate. Other embodiments are capable of acquiring and displaying data at different rates. For example, depending on the frame size and the intended application, some embodiments may acquire data at frame rates less than 10 Hz or greater than 30 Hz. The memory 120 can store processed frames of acquired data. In an exemplary embodiment, the memory 120 has sufficient capacity to store at least several seconds of ultrasound data frames. The data frames are stored in a manner that facilitates retrieval based on their acquisition order or time. The memory 120 may include any known data storage medium.

[0024] In various embodiments of this disclosure, data may be processed by processor 116 using different mode-related modules (e.g., B-mode, color Doppler, M-mode, color M-mode, spectral Doppler, elastography, tissue velocity imaging (TVI), strain, strain rate, etc.) to form 2D or three-dimensional (3D) images. When multiple images are acquired, processor 116 may also be configured to stabilize or register images. For example, one or more modules may generate B-mode, color Doppler, M-mode, color M-mode, color flow imaging, spectral Doppler, elastography, tissue velocity imaging (TVI), strain (e.g., speckle tracking echocardiography), strain rate, etc., and combinations thereof. As an example, the one or more modules may process B-mode data, which may include 2D or 3D B-mode data, etc. Image lines and / or frames are stored in memory and may include timing information indicating the time during which image lines and / or frames are stored in memory. These modules may include, for example, a scan transformation module to perform a scan transformation operation to convert the acquired images from beamspace coordinates to display space coordinates. A video processor module may be provided that reads acquired images from memory and displays image playback (e.g., movie playback) in real time while procedures are performed on a patient (e.g., ultrasound imaging). The video processor module may include a separate image memory, and ultrasound images may be written to the image memory for reading and display by the display device 118.

[0025] Furthermore, the components of the ultrasound imaging system 100 may be coupled to each other to form a single structure, may be separate but located in a common room, or may be geographically distant from each other. For example, one or more modules described herein may operate in a data server that has a different and remote location relative to other components of the ultrasound imaging system 100, such as probe 106 and user interface 115. Optionally, the ultrasound imaging system 100 may be a single system capable of being moved from one room (e.g., portable) to another. For example, the ultrasound imaging system 100 may include wheels or be transportable on a trolley, or may include a handheld device.

[0026] For example, in various embodiments of this disclosure, one or more components of the ultrasound imaging system 100 may be included in a portable handheld ultrasound imaging device. For example, a display device 118 and a user interface 115 may be integrated into the external surface of the handheld ultrasound imaging device, which may also include a processor 116 and a memory 120. A probe 106 may include a handheld probe that electronically communicates with the handheld ultrasound imaging device to collect raw ultrasound data. Transmit beamformer 101, transmitter 102, receiver 108, and receive beamformer 110 may be included in the same or different parts of the ultrasound imaging system 100. For example, transmit beamformer 101, transmitter 102, receiver 108, and receive beamformer 110 may be included in the handheld ultrasound imaging device, the probe, and combinations thereof.

[0027] See now Figure 2 An example medical image processing system 200 is shown. In some embodiments, the medical image processing system 200 is incorporated into a medical imaging system, such as an ultrasound imaging system (e.g., Figure 1 The medical image processing system 200 includes ultrasound imaging systems 100, magnetic resonance imaging (MRI) systems, computed tomography (CT) systems, single-photon emission computed tomography (SPECT) systems, etc. In some embodiments, at least a portion of the medical image processing system 200 is located at a device (e.g., an edge device or server) communicatively coupled to the medical imaging system via a wired and / or wireless connection. In some embodiments, the medical image processing system 200 is located at a separate device (e.g., a workstation) that can receive images from the medical imaging system or from a storage device storing images generated by the medical imaging system. The medical image processing system 200 may include an image processor 231, a user input device 232, and a display device 233. For example, the image processor 231 may be operatively / communically coupled to the user input device 232 and the display device 233.

[0028] The image processor 231 includes a processor 204 configured to execute machine-readable instructions stored in non-transitory memory 206. The processor 204 may be single-core or multi-core, and the program executed by the processor 204 may be configured for parallel or distributed processing. In some embodiments, the processor 204 may optionally include individual components distributed across two or more devices, which may be remotely located and / or configured for collaborative processing. In some embodiments, one or more aspects of the processor 204 may be virtualized and executed by a remotely accessible networked computing device configured in a cloud computing configuration. In some embodiments, the processor 204 may include other electronic components capable of performing processing functions, such as a digital signal processor, an FPGA, or a graphics board. In some embodiments, the processor 204 may include multiple electronic components capable of performing processing functions. For example, the processor 204 may include two or more electronic components selected from a plurality of possible electronic components including: a central processing unit, a digital signal processor, a field-programmable gate array, and a graphics board. In still other embodiments, the processor 204 may be configured as a graphics processing unit (GPU), including a parallel computing architecture and parallel processing capabilities.

[0029] exist Figure 2 In the illustrated embodiment, non-transitory memory 206 stores myocardial analysis module 212 and medical image data 214. Myocardial analysis module 212 includes one or more algorithms, including machine learning models, to process input medical images from medical image data 214. Specifically, myocardial analysis module 212 can provide an artificial intelligence system for identifying heart muscle in medical image data 214. For example, myocardial analysis module 212 may include one or more deep learning networks, including multiple weights and biases, activation functions, loss functions, gradient descent algorithms, and instructions for implementing the one or more deep learning networks to process the input medical images. Additionally or alternatively, myocardial analysis module 212 may store instructions for implementing neural networks, such as convolutional neural networks, to identify heart muscle captured in medical image data 214. Myocardial analysis module 212 may include trained and / or untrained neural networks and may also include training routines or parameters (e.g., weights and biases) associated with one or more neural network models stored therein. Additionally or alternatively, myocardial analysis module 212 may include image recognition algorithms, shape or edge detection algorithms, etc., for identifying heart muscle. In some implementations, the myocardial analysis module 212 can evaluate the medical image data 214 during real-time acquisition. Alternatively or additionally, the myocardial analysis module 212 can evaluate the medical image data 214 offline rather than in real-time.

[0030] In some implementations, the myocardial analysis module 212 may further include a trained and / or untrained neural network for determining cardiac electrical conduction pathways of the heart muscle identified in the medical image data 214. For example, the neural network can be trained using cardiac medical images (e.g., B-mode echocardiography images) and associated electrical conduction pathways generated via speckle-tracking echocardiography. After training, the electrical conduction pathways can be generated directly from the cardiac medical images by the neural network without first performing speckle-tracking echocardiography analysis.

[0031] Image processor 231 is communicatively coupled to training module 210, which includes instructions for training one or more machine learning models stored in cardiac analysis module 212. Training module 210 may include instructions that, when executed by a processor, cause the processor to build a model (e.g., a mathematical model) based on sample data to make predictions or decisions about electrical conduction pathways through the heart, without explicitly programming conventional algorithms that do not utilize machine learning. In one example, training module 210 includes instructions for receiving a training dataset from medical image data 214. The training dataset includes a set of medical images (e.g., B-mode echocardiogram images) for training one or more machine learning models stored in cardiac analysis module 212, associated ground truth labels / images, and associated model outputs (e.g., electrical conduction pathways generated via speckle-tracking echocardiography). Training module 210 may receive medical images, associated ground truth labels / images, and associated model outputs for training one or more machine learning models from sources other than medical image data 214 (such as other image processing systems, the cloud, etc.). In some embodiments, one or more aspects of training module 210 may include a remotely accessible networked storage device configured for cloud computing. Additionally, in some embodiments, training module 210 is included in non-transitory storage 206. Additionally or alternatively, in some embodiments, training module 210 can be used offline and remotely from medical image processing system 200 to generate myocardial analysis module 212. In such embodiments, training module 210 may not be included in medical image processing system 200, but may generate data stored in medical image processing system 200. For example, myocardial analysis module 212 may be pre-trained at the manufacturing site using training module 210.

[0032] The non-transitory memory 206 also stores medical image data 214. Medical image data 214 includes functional and / or anatomical images captured, for example, by imaging modalities such as ultrasound imaging systems, MRI systems, CT systems, etc. As an example, medical image data 214 may include ultrasound images, such as cardiac ultrasound images. Furthermore, medical image data 214 may include one or more of 2D images, 3D images, static single-frame images, and multi-frame image loops (e.g., movies).

[0033] In some implementations, nontransitory storage 206 may include components disposed on two or more devices, which may be remotely located and / or configured for coordinated processing. In some implementations, one or more aspects of nontransitory storage 206 may include a remotely accessible, networked storage device configured for cloud computing. As an example, nontransitory storage 206 may be part of a Picture Archiving and Communication System (PACS) configured to store, for example, patient history, imaging data, test results, diagnostic information, administrative information, and / or scheduling information.

[0034] The medical image processing system 200 may also include a user input device 232. The user input device 232 may include one or more of a touchscreen, keyboard, mouse, touchpad, motion-sensing camera, or other devices configured to enable a user to interact with and manipulate data stored within the image processor 231. As an example, the user input device 232 may enable a user to select images for analysis by the myocardial analysis module 212.

[0035] Display device 233 may include one or more display devices utilizing any type of display technology. In some embodiments, display device 233 may include a computer monitor and may display unprocessed images, processed images, parameter mapping diagrams, and / or examination reports. Display device 233 may be combined with processor 204, non-transitory memory 206, and / or user input device 232 in a shared housing, or it may be a peripheral display device. Display device 233 may include a monitor, touchscreen, projector, or another type of display device that enables a user to view medical images and / or interact with various data stored in non-transitory memory 206. In some embodiments, display device 233 may be included in a smartphone, tablet, smartwatch, etc.

[0036] Understandable. Figure 2 The illustrated medical image processing system 200 is one non-limiting embodiment of an image processing system, and other imaging processing systems may include more, fewer, or different components without departing from the scope of this disclosure. Furthermore, in some embodiments, at least a portion of the medical image processing system 200 may be included in… Figure 1In the ultrasound imaging system 100, or vice versa (e.g., at least a portion of the ultrasound imaging system 100 may be included in the medical image processing system 200).

[0037] As used herein, the terms "system" and "module" can include hardware and / or software systems that operate to perform one or more functions. For example, a module or system may include, or be included therein, a computer processor, controller, or other logic-based device that performs operations based on instructions stored on a tangible, non-transitory computer-readable storage medium, such as computer memory. Alternatively, a module or system may include a hardwired device that performs operations based on device-based hardwired logic. The various modules or systems illustrated in the figures may represent hardware that operates based on software or hardwired instructions, software that instructs the hardware to perform operations, or a combination thereof.

[0038] The term "system" or "module" may include or represent hardware and associated instructions (e.g., software stored on a tangible, non-transitory computer-readable storage medium, such as a computer hard disk drive, ROM, RAM, etc.) that perform one or more of the operations described herein. Hardware may include electronic circuitry that includes and / or is connected to one or more logic-based devices, such as microprocessors, processors, controllers, etc. These devices may be readily available devices that are appropriately programmed or instructed to perform the operations described herein according to the instructions described above. Alternatively or additionally, one or more of these devices may be hardwired to logic circuitry to perform these operations.

[0039] Figure 3 An example method 300 for generating a visual depiction of the electrical conduction pathways of a patient's heart during cardiac ultrasound imaging is shown. This will be applied to systems using ultrasound imaging such as... Figure 1 Method 300 is described using ultrasound images acquired by ultrasound imaging system 100, but other ultrasound imaging systems may also be used. Furthermore, method 300 is applicable to other imaging modalities. Method 300 may be implemented by one or more of the aforementioned systems, including... Figure 1 Ultrasound imaging system 100 and Figure 2 The medical image processing system 200. Therefore, method 300 can be stored as executable instructions in non-transitory memory such as... Figure 1 The memory 120 and / or Figure 2 In the non-transitory memory 206, and by the processor such as Figure 1 Processor 116 and / or Figure 2The processor 204 executes the method. Furthermore, in some embodiments, method 300 is executed in real time during ultrasound image acquisition, while in other embodiments, at least a portion of method 300 is executed offline after ultrasound image acquisition. For example, the processor can evaluate ultrasound images stored in memory even when the ultrasound system is not actively operated to acquire images. Moreover, at least a portion of method 300 can be executed in parallel. For example, ultrasound data for a second image can be acquired while a first ultrasound image is being generated, ultrasound data for a third image can be acquired while a second ultrasound image is being generated, and so on.

[0040] At 302, method 300 includes acquiring ultrasound imaging data of the heart. The ultrasound imaging data can be acquired according to an ultrasound protocol, which can be selected by an operator (e.g., a user) of the ultrasound imaging system via a user interface (e.g., user interface 115). As an example, the operator can select an ultrasound protocol from several possible protocols using a drop-down menu or by selecting a virtual button. Alternatively, the system can automatically select a protocol based on data received from an electronic health record (EHR) associated with the patient. For example, the EHR may include previously performed examinations, diagnoses, and current treatments that can be used to select an ultrasound protocol. Furthermore, in some examples, the operator can manually enter and / or update parameters for the ultrasound protocol. The ultrasound protocol can be a system-guided protocol, where the system guides the operator step-by-step through the protocol, or it can be a user-guided protocol, where the operator follows a laboratory-defined or custom-defined protocol without the system enforcing a specific protocol or knowing the protocol steps in advance.

[0041] Furthermore, the ultrasound protocol may include multiple views and / or imaging modes executed sequentially. Using cardiac ultrasound imaging as an example, the ultrasound protocol may include a four-ventricle view of the left ventricle with B-mode and a four-ventricle view focused on the right ventricle with B-mode. It is understood that in some examples, partial views of the heart may be acquired, such as a biventricular view of the left ventricle and left atrium or a single-ventricle view (e.g., left ventricle only). In some examples, additional imaging modes, such as color flow imaging (CFI), may be used. Additionally, the ultrasound protocol may specify the frame rate used to acquire ultrasound imaging data. When acquiring regional, local views of the heart, the frame rate used for acquisition can be increased compared to full acquisition because the field of view is smaller. A higher frame rate can result in a more accurate mapping of strain values ​​to electrical activity, as will be described in detail below. However, strain and electrical activity mapping may not be performed in areas outside the field of view. Therefore, in some examples, multiple regional views of the heart may be acquired, each of which obtains a different partial view of the heart, in order to obtain a more accurate mapping of strain and electrical activity in each region.

[0042] Ultrasound imaging data can be acquired by transmitting and receiving ultrasound signals using an ultrasound probe according to an ultrasound protocol. In the cardiac ultrasound imaging example described above, executing the ultrasound protocol includes acquiring some or all of the ultrasound data in the views and imaging modes described above. Acquiring ultrasound data according to the ultrasound protocol may include the system displaying instructions on the user interface and / or display, for example, to guide the operator to complete the acquisition of a specified view. Additionally or alternatively, the ultrasound protocol may include instructions for the ultrasound system to automatically acquire some or all of the data or perform other functions. For example, the ultrasound protocol may include instructions for the user to move, rotate, and / or tilt the ultrasound probe, as well as to automatically start and / or terminate the scanning process and / or adjust the imaging parameters of the ultrasound probe, such as ultrasound signal transmission parameters, ultrasound signal reception parameters, ultrasound signal processing parameters, or display parameters. Furthermore, the acquired ultrasound data may include one or more image parameters calculated for each pixel or group of pixels to be displayed (e.g., a group of pixels assigned the same parameter values), wherein the one or more calculated image parameters include, for example, one or more of intensity, texture, graininess, contractility, deformation, and deformation rate values.

[0043] At 304, method 300 includes generating an ultrasound image of the heart from the acquired ultrasound imaging data. The ultrasound image of the heart may also be referred to herein as a cardiac ultrasound image. At least one ultrasound image may be generated for each view of the ultrasound protocol. For example, signal data acquired during the method at 302 is processed and analyzed by a processor to generate an ultrasound image. The processor may include an image processing module that receives the signal data (e.g., image data) acquired at 302 and processes the received image data. For example, the image processing module may process the ultrasound signals to generate slices or frames of ultrasound information (e.g., ultrasound images) for display to an operator. In one example, generating the image may include determining the intensity value of each pixel to be displayed based on the received image data (e.g., 2D or 3D ultrasound data). Therefore, the generated ultrasound image may be 2D or 3D, depending on the ultrasound mode being used (e.g., CFI, acoustic radiation force imaging, B-mode, A-mode, M-mode, spectral Doppler, acoustic flow, tissue Doppler module, C-scan, or elastography).

[0044] At 306, method 300 includes identifying and segmenting myocardium in ultrasound images of the heart. For example, each ultrasound image can be input into one or more image analysis algorithms substantially in real time as it is acquired. Alternatively, each ultrasound image can be processed offline by one or more image analysis algorithms after ultrasound imaging data acquisition is complete. In some embodiments, one or more image analysis algorithms may be included in a myocardial analysis module, such as those described above. Figure 2The described myocardial analysis module 212. One or more image analysis algorithms may include image recognition algorithms, shape detection algorithms, and / or edge detection algorithms for identifying cardiac muscle. The one or more image analysis algorithms may further include one or more machine learning algorithms and / or conventional programming algorithms for identifying and segmenting myocardium. Furthermore, the myocardium can be divided into right ventricular, right atrial, left ventricular, and left atrial portions of cardiac muscle surrounding each chamber of the heart. For example, chambers can be identified based on their relative location in ultrasound images and the pixel contrast between brighter (e.g., higher intensity) pixels of cardiac tissue and darker (e.g., lower intensity) pixels of blood-filled chambers.

[0045] At 308, method 300 includes performing speckle-tracking echocardiography to track strain values ​​in the myocardium over time. For example, once identified, the myocardium can be tracked at various points throughout the cardiac cycle to determine how each part of the myocardium contracts and relaxes throughout the entire cardiac cycle. Each cardiac cycle consists of one heartbeat, which includes two periods called diastole and systole. During diastole, the myocardium relaxes and the heart is refilled with blood. During systole, the myocardium contracts to pump blood out of the heart. Contraction and relaxation, respectively, cause shortening and elongation of the myocardium, which can be quantified via speckle-tracking echocardiography.

[0046] Speckled-tracking echocardiography can include pre-programmed analysis tools that calculate the strain at a given location of the heart muscle as a change in the length of the heart muscle at that location between two time points. Thus, the strain at a given location can change throughout the cardiac cycle as the muscle expands and contracts. Furthermore, strain values ​​can be determined in multiple directions (e.g., longitudinal, circumferential, and radial), each corresponding to a change in length in that direction. For example, a longitudinal strain value could represent the change in length of the heart muscle along its long axis, a circumferential strain value could represent the circumferential change of an associated chamber (e.g., a ventricle) during cardiac circulation, and a radial strain value could represent the change in length (e.g., thickness) of the muscle wall along its radius. Each strain value can be given as a percentage change (e.g., negative or positive) between an initial time point (e.g., before the electrical pulse passes through the heart) and a final time point (e.g., after the electrical pulse passes through the heart).

[0047] As an example, speckle tracking echocardiography can include brighter pixel "spots" of myocardium defined by the scattering of an ultrasound beam by tissue. The identified spots can be tracked frame-by-frame to determine their positional variations in different dimensions (e.g., longitudinal, circumferential, and radial). As an illustrative example, speckle tracking echocardiography can use an absolute difference sum algorithm. Speckle tracking echocardiography can further determine the amplitude of myocardial deformation corresponding to the mechanical movement of the heart in these different directions within the cardiac cycle to generate strain values. In some examples, speckle tracking echocardiography can further generate strain rate curves corresponding to the rate of change of strain values ​​over time (e.g., within the cardiac cycle).

[0048] At 310, method 300 includes performing strain-electrical impulse mapping to generate a spatiotemporal map of electrical impulses in the heart. Cardiac muscle contraction is triggered by an electrical impulse generated within the heart at the sinoatrial (SA) node, located in the superior wall of the right atrium. The atrioventricular (AV) node, located in the right atrial wall between the atria and ventricles, is electrically connected to the SA node to coordinate the beating of the atria and ventricles. The electrical impulse travels through the cardiac muscle and causes a series of contractions as it travels spatiotemporally. As described above, speckle-tracking echocardiography quantifies the contraction patterns at different time locations. Because contraction is a direct effect of the passage of the electrical impulse, a spatiotemporal map showing the passage of the electrical impulse can be generated directly from a given strain value. For example, the stronger the electrical impulse, the greater the resulting contraction / expansion (and therefore, the larger the measured strain value). Furthermore, the electrical impulse may not travel through dead cardiac tissue. Thus, the force (e.g., intensity) and location of an electrical impulse at a given location in the heart at a given time can be directly determined from the strain value at that location at that time. That is, the parts of the myocardium with channels of electrical impulses at a given time point can be identified based on strain values ​​indicating the contraction of those parts of the myocardium at a given time point. Thus, electrical impulses are mapped to regions of the heart in a spatiotemporally specific manner so that the channels of electrical impulses are synchronized with the mechanical movement of specific regions, as indicated by the strain values.

[0049] As an example, the strength of an electrical pulse at a given location can be determined based on one or more functions stored in non-transient memory. For instance, strain values ​​can be input into one or more functions that output the corresponding electrical pulse strength. For example, when the strain value indicates that the heart muscle is not contracting at that location, the resulting strength could be zero, indicating the absence of an electrical pulse. In some embodiments, each strain value can be input into a different function, and the resulting strength values ​​can be combined (e.g., summed). In other embodiments, strain values ​​can be combined, and the combined strain values ​​can be input into a single function. An example relationship relating strain values ​​to the strength of an electrical pulse is shown in... Figure 5 The above is illustrated graphically, as will be described in detail below.

[0050] At 312, method 300 includes displaying a spatiotemporal map of electrical impulses in the heart. As an example, the spatiotemporal map of electrical impulses in the heart can be generated by superimposing electrical impulses onto an ultrasound image of the heart such that the conduction path of the electrical impulses is synchronized with the mechanical movement of the heart muscle depicted in the ultrasound image. Alternatively or additionally, the spatiotemporal map of electrical impulses in the heart can be generated by superimposing electrical impulses onto an animation of the heart in a manner that synchronizes the mechanical movement of the heart with the conduction path of the electrical impulses. For example, the animation of the heart can be generated by adjusting a pre-made heart animation based on strain values ​​and heart rate observed in the ultrasound image, such that the heart animation provides a simplified model of the imaged heart. Displaying the spatiotemporal map of electrical impulses in the heart may include outputting the spatiotemporal map to one or more display devices, such as… Figure 1 The display device 118. Furthermore, the pixel brightness of the electrical pulse can be directly related to the intensity of the electrical pulse at that location (as determined above), allowing the user or another clinician to easily observe areas of weak conduction. Method 300 can then be terminated.

[0051] It is understood that, in alternative implementations, a neural network can be used instead of performing speckle-tracking echocardiography. In such implementations, ultrasound images generated from ultrasound imaging data can be directly input into the neural network, and the neural network can output a spatiotemporal map of electrical impulses in the heart without performing speckle-tracking echocardiography and strain-to-electrical-pulse mapping. The neural network can be trained using previously acquired cardiac ultrasound images and the associated spatiotemporal map of electrical impulses in the heart generated via speckle-tracking echocardiography, such as according to method 300 described above.

[0052] Now transferred to Figure 4 An example segmented cardiac ultrasound image 400 is shown. The segmented cardiac ultrasound image 400 is a B-mode grayscale image and shows a four-ventricle view of the heart 402. The heart 402 is segmented into the right atrium 404, right ventricle 406, left atrium 408, and left ventricle 410. Furthermore, brighter pixel specks 412 are visible in the segmented cardiac ultrasound image 400, which can be used for speckle-tracking echocardiography, as described above. Figure 4 As described. For example, tracking the displacement of the spot 412 between image frames in the right ventricle 406 can provide a strain value specific to the right ventricle, while tracking the spot 412 in the left atrium 408 can provide a different strain value specific to the left atrium.

[0053] Segmenting the myocardium allows speckle tracking algorithms to distinguish between contracting cardiac tissue (e.g., myocardium) and non-contracting cardiac tissue (e.g., pericardium), determining strain values ​​specifically for contracting tissue. Because the pericardium does not contract, including it in strain calculations can lead to underestimation of both regional and global strain values. Furthermore, electrical impulses do not travel through non-contracting tissue. Therefore, segmenting the myocardium before performing speckle tracking echocardiography increases the accuracy of strain calculations and the resulting electrical impulse mappings.

[0054] then, Figure 5 Graph 500 illustrates an example relationship between the magnitude of the strain value (horizontal axis) and the intensity of the electrical pulse (vertical axis). First curve 502 shows a first relationship between the strain value and the electrical pulse intensity, second curve 504 shows a second relationship, and third curve 506 shows a third relationship. From each of the first curve 502, second curve 504, and third curve 506, it can be seen that, generally, the electrical pulse intensity increases with increasing strain value. However, this relationship can be linear (e.g., second curve 504) or non-linear (e.g., first curve 502 and third curve 506). In some examples, first curve 502, second curve 504, and third curve 506 describe the relationship between the strain value and the electrical pulse intensity for different types of strain. For example, first curve 502 may correspond to circumferential strain, second curve 504 may correspond to longitudinal strain, and third curve 506 may correspond to radial strain. In some examples, the example relationship may be adjusted based, for example, the rate of change of the strain value over time. For example, the slopes of the first curve 502, the second curve 504, and / or the third curve 506 can be adjusted based on the rate of change of the strain values. In other examples, more or fewer than three relationships can be used to map strain values ​​to electrical pulse intensities. Furthermore, in some examples, instead of electrical pulse intensity, strain values ​​can be directly correlated with pixel intensity to display a spatiotemporal map of electrical pulses passing through the heart.

[0055] As shown in each of the first curve 502, the second curve 504, and the third curve 506, the electrical pulse intensity is zero when the strain value is zero. That is, if a part of the heart muscle dies (e.g., does not contract), the strain value is zero, and the corresponding electrical pulse intensity is also zero. If the strain value is high, the electrical pulse travels rapidly through the muscle. Conversely, if the strain value is low, the electrical pulse travels more slowly through the muscle. Therefore, the strain value and the electrical pulse are positively correlated. Furthermore, it can be understood that the electrical pulse is a closed loop in one direction and does not travel backward.

[0056] Figure 6An example sequence 600 of display outputs that may occur when acquiring echocardiographic images and generating a spatiotemporal map of the electrical conduction pathway through the heart is shown. Sequence 600 shows a series of image frames about time axis 620, including first image frame 601, second image frame 603, third image frame 605, fourth image frame 607, fifth image frame 609, and sixth image frame 611. The first to sixth image frames together depict a cardiac cycle. First image frame 601 is the earliest frame, and sixth image frame 611 is the latest time frame, as shown on time axis 620. It is understood that additional image frames may exist between consecutive image frames in sequence 600, and the spacing between each consecutive image frame is intended to represent the relative arrangement of each image frame with respect to time rather than a specific duration between each image frame. Each image frame depicts a single snapshot of the animation of electrical impulses in the heart 602 over time. Figure 6 A two-dimensional cross-sectional view of the heart 602 is shown. However, in other examples, a three-dimensional representation of the heart 602 can be depicted. In particular, this cross-sectional view makes it easy to observe the right atrium 604, right ventricle 606, left atrium 608, left ventricle 610, SA node 612, and AV node 614 in each image frame.

[0057] Electrical pulse 616 initiates at SA junction 612 and travels via the atrial pathway to left atrium 608 in the first image frame 601, causing both right atrium 604 and left atrium 608 to contract and associated valves to open. The first image frame 601 is output to a display at a first time point t1 (e.g., [missing information]). Figure 1 (Display device 118). For example, when acquiring echocardiogram images, a first image frame 601 can be output to the display substantially in real time. Shaded areas 618 indicate display areas that can have greater pixel brightness to indicate the intensity of electrical pulses 616 in those areas of the heart 602. The electrical pulses 616 travel via the atrial pathway to the AV junction 614 and cease to travel to the left atrium 608 in the second image frame 603. As a result, the left atrium 608 relaxes in the second image frame 603. The second image frame 603 is output to the display at a second time point t2.

[0058] Electrical pulse 616 travels downwards from AV segment 614 along bundle branches in the third image frame 605, output to the display at the third time point t3, and the fourth image frame 607, output to the display at the fourth time point t4. Electrical pulse 616 continues to reach the Purkinje fibers in the inner walls of the right ventricle 606 and left ventricle 610, located in the fifth image frame 609, causing both ventricles to contract. The fifth image frame 609, visually indicating the electrical pulse 616 causing the contraction of the right ventricle 606 and left ventricle 610, is output to the display at the fifth time point t5. Electrical pulse 616 terminates at the Purkinje fibers, thus allowing the heart (specifically the right ventricle 606 and left ventricle 610) to relax. This is visually indicated in the sixth image frame 611, which depicts the absence of electrical pulse 616 and the dilation of the ventricles. The sixth image frame 611 is output to the display at the sixth time point t6. Sequence 600 can be repeated for additional cardiac cycles. Thus, sequence 600 maps the position of electrical pulse 616 at a given time point in the cardiac cycle to the region of myocardial deformation at that given time point.

[0059] In this way, a spatiotemporal map of the electrical conduction pathway through the heart can be generated and displayed to the user. For example, a spatiotemporal map of the electrical conduction pathway can be interpreted more easily than a strain value map. For instance, a spatiotemporal map of the electrical conduction pathway can combine strain values ​​reported in different directions into a single dynamic visual representation. As a result, areas of weak heart muscle or dead tissue can be more easily identified. By more easily identifying areas of weak heart muscle or dead tissue, diagnostic time can be reduced, enabling faster patient intervention and more positive patient outcomes.

[0060] The advantage of using strain values ​​determined from echocardiogram images to map electrical impulses passing through the heart is that it allows for accurate visualization of the relationship between electrical and mechanical activity within the heart.

[0061] This disclosure also provides support for a method comprising: generating an echocardiogram from echocardiogram imaging data of the heart; generating a spatiotemporal map of electrical impulses in the heart based on contraction and elongation of cardiac muscle depicted in the echocardiogram; and outputting the spatiotemporal map of the electrical impulses in the heart to a display device. In a first example of the method, generating the spatiotemporal map of electrical impulses in the heart based on contraction and elongation of cardiac muscle depicted in the echocardiogram includes: identifying and segmenting the cardiac muscle; determining strain values ​​in the identified and segmented cardiac muscle via speckle-tracking echocardiography; and determining the intensity and location of the electrical impulses at each segment of the identified and segmented cardiac muscle based on the strain values ​​at a given segment. In a second example of the method, optionally including a first example, the intensity of the electrical impulses at the given segment increases with the magnitude of the strain value, and wherein the intensity of the electrical impulses corresponds to the brightness of a pixel of the display device. In a third example of the method, optionally including one or both of the first and second examples, determining the strain value includes determining the length change of a given segment of the identified and segmented cardiac muscle between an initial time point and a final time point. In a fourth example of the method, one or more of the first to third examples may be optionally included, and the strain values ​​include longitudinal strain values, circumferential strain values, and radial strain values. In a fifth example of the method, one or more of the first to fourth examples may be optionally included, and generating the spatiotemporal map of the electrical pulses in the heart based on the contraction and elongation of the cardiac muscle includes: inputting the cardiac ultrasound image generated from the ultrasound imaging data into a neural network, and receiving the spatiotemporal map of the electrical pulses in the heart as the output of the neural network. In a sixth example of the method, one or more of the first to fifth examples may be optionally included, and the neural network is trained using previously acquired cardiac ultrasound images and associated electrical conduction pathways generated via speckle-tracking echocardiography. In a seventh example of the method, one or more of the first to sixth examples may be optionally included, and outputting the spatiotemporal map of the electrical pulses in the heart to the display device includes superimposing the electrical pulses in the heart onto the cardiac ultrasound image, wherein the position of the electrical pulses is synchronized with the mechanical movement of the cardiac muscle depicted in the cardiac ultrasound image. In an eighth example of the method, one or more of the first to seventh examples may be optionally included, and outputting the spatiotemporal map of the electrical pulses in the heart to the display device includes: generating an animation of the heart, and superimposing the electrical pulses in the heart onto the animation of the heart, wherein the position of the electrical pulses is synchronized with the mechanical movement of the heart at a given time point in the animation.

[0062] This disclosure also provides support for a method comprising: acquiring ultrasound imaging data of the heart; identifying myocardium in an image generated from the ultrasound imaging data; determining strain values ​​at each portion of the myocardium in the image; and outputting an electrical conduction pathway through the heart based on the determined strain values. In a first example of the method, identifying the myocardium in the image generated from the ultrasound imaging data includes analyzing the image via at least one of an image recognition algorithm, a shape detection algorithm, and an edge detection algorithm. In a second example of the method, optionally including the first example, determining strain values ​​at each portion of the myocardium in the image includes performing speckle-tracking echocardiography on the image. In a third example of the method, optionally including one or both of the first and second examples, the strain values ​​include longitudinal strain values ​​corresponding to changes in length in a given portion of the myocardium during cardiac circulation, circumferential strain values ​​corresponding to changes in the circumference of an associated chamber of the given portion of the myocardium during cardiac circulation, and radial strain values ​​corresponding to changes in thickness along the radius of the given portion of the myocardium. In a fourth example of the method, optionally including one or more of the first to third examples, the output of an electrical conduction pathway through the heart generated based on the determined strain value includes: spatiotemporally mapping the channel of the electrical pulse through the heart to the strain value. In a fifth example of the method, optionally including one or more of the first to fourth examples, the output of a channel of the electrical pulse through the heart to the strain value includes: identifying the myocardial portion having the channel of the electrical pulse at a given time point based on the strain value indicating contraction of the myocardial portion at a given time point.

[0063] This disclosure also provides support for a system comprising: an ultrasound probe, a display device, and a processor configured to execute instructions stored in a non-transitory memory, the instructions, when executed, causing the processor to: acquire ultrasound imaging data of the heart via the ultrasound probe; generate a cardiac ultrasound image from the acquired cardiac ultrasound imaging data; determine the cardiac electrical conduction pathway during cardiac circulation based on myocardial deformation in the heart during cardiac circulation; and output an animation of the electrical conduction pathway on the display device. In a first example of the system, to determine the cardiac electrical conduction pathway during cardiac circulation based on myocardial deformation in the heart during cardiac circulation, the processor is configured to execute additional instructions stored in the non-transitory memory, the additional instructions, when executed, causing the processor to: perform speckle-tracking echocardiography on the generated cardiac ultrasound image to calculate strain values ​​quantified by myocardial deformation in the heart during cardiac circulation; and map the position of an electrical pulse at a given time point in cardiac circulation to the region experiencing myocardial deformation at the given time point. In a second example of the system, the first example may be optionally included, wherein the animation of the electrical conduction pathway comprises the superposition of the electrical conduction pathway on the echocardiogram image, and wherein the pixel brightness of the electrical conduction pathway increases with the magnitude of myocardial deformation in the heart. In a third example of the system, one or both of the first and second examples may be optionally included, wherein, in order to determine the electrical conduction pathway of the heart during cardiac circulation based on myocardial deformation in the heart during cardiac circulation, the processor is configured to execute additional instructions stored in non-transitory memory, which, when executed, cause the processor to: input the generated echocardiogram image into a neural network, and receive the animation of the electrical conduction pathway as the output of the neural network. In a fourth example of the system, one or more of the first to third examples may be optionally included, wherein the neural network is trained using previously acquired echocardiogram images and associated electrical conduction pathways generated by mapping strain values ​​to the location of electrical impulses in the heart in a spatiotemporally specific manner.

[0064] As used herein, elements or steps listed in the singular and beginning with the word "a" or "an" should be understood to not exclude a plurality of said elements or steps unless such exclusion is explicitly stated. Furthermore, references to "one embodiment" of the invention are not intended to be construed as excluding the existence of additional embodiments that also include the referenced features. Moreover, unless explicitly stated to the contrary, embodiments that "comprise," "include," or "have" elements or multiple elements having a particular characteristic may include additional such elements that do not have that characteristic. The terms "comprise" and "in..." are used as concise linguistic equivalents to the corresponding terms "comprising" and "wherein". Furthermore, the terms "first," "second," and "third," etc., are used merely as notations and are not intended to impose numerical requirements or a particular order of position on their objects.

[0065] This written description uses examples to disclose the invention, including the best mode, and also enables those skilled in the art to practice the invention, including making and using any device or system and performing any included methods. The scope of patentability of the invention is defined by the claims and may include other examples that would occur to those skilled in the art. Such other examples are intended to fall within the scope of the claims if they have structural elements that are not indistinguishable from the literal language of the claims, or if they include equivalent structural elements that have minor differences from the literal language of the claims.

Claims

1. A method for visualizing cardiac electrical conduction, the method comprising: Generate cardiac ultrasound images from cardiac ultrasound imaging data; Determine the strain value at each part of the myocardium in the cardiac ultrasound image, the strain value representing the contraction and elongation of the cardiac muscle depicted in the cardiac ultrasound image; A spatiotemporal map of electrical impulses in the heart is generated based on the contraction and elongation of the heart muscle depicted in the cardiac ultrasound images. as well as The spatiotemporal diagram of the electrical impulses in the heart is output to a display device, wherein the spatiotemporal diagram represents the electrical conduction pathway through the heart generated based on the strain values. The spatiotemporal graph described therein is an animation of the heart generated by adjusting a pre-made cardiac animation based on the strain values ​​and heart rate observed in the ultrasound imaging data of the heart.

2. The method according to claim 1, wherein, The spatiotemporal map for generating the electrical impulses in the heart based on the contraction and elongation of the heart muscle depicted in the echocardiogram includes: Identify and segment the heart muscle; Strain values ​​in the identified and segmented cardiac muscle were determined via speckle-tracking echocardiography; and The strength and location of the electrical pulses at each segment of the identified and segmented heart muscle are determined based on the strain values ​​at a given segment.

3. The method of claim 2, wherein the intensity of the electrical pulse at the given portion increases with the magnitude of the strain value, and wherein the intensity of the electrical pulse corresponds to the brightness of a pixel of the display device.

4. The method of claim 2, wherein determining the strain value comprises determining the length change of a given portion of the identified and segmented cardiac muscle between an initial time point and a final time point.

5. The method according to claim 2, wherein the strain value includes a longitudinal strain value, a circumferential strain value, and a radial strain value.

6. The method of claim 1, wherein generating the spatiotemporal map of the electrical impulses in the heart based on the contraction and elongation of the cardiac muscle comprises: The cardiac ultrasound image generated from the ultrasound imaging data is input into the neural network; as well as The spatiotemporal graph of the electrical pulses received in the heart is used as the output of the neural network.

7. The method of claim 6, wherein the neural network is trained using previously acquired cardiac ultrasound images and associated electrical conduction pathways generated via speckle-tracking echocardiography.

8. The method of claim 1, wherein outputting the spatiotemporal map of the electrical pulses in the heart to the display device comprises superimposing the electrical pulses in the heart onto the echocardiogram, wherein the position of the electrical pulses is synchronized with the mechanical movement of the heart muscle depicted in the echocardiogram.

9. The method of claim 1, wherein outputting the spatiotemporal map of the electrical impulses in the heart to the display device comprises: Generate an animation of the heart; as well as The electrical pulses in the heart are superimposed onto the animation of the heart, wherein the position of the electrical pulses is synchronized with the mechanical movement of the heart at a given point in time in the animation.

10. A method for visualizing cardiac electrical conduction, the method comprising: Acquire ultrasound imaging data of the heart; Identify the myocardium in images generated from the ultrasound imaging data; Determine the strain value at each portion of the myocardium in the image; as well as A spatiotemporal diagram of electrical impulses in the heart is generated from the determined strain values; Output the spatiotemporal diagram, wherein the spatiotemporal diagram represents the electrical conduction pathway through the heart generated based on the determined strain values. The spatiotemporal graph described therein is an animation of the heart generated by adjusting a pre-made cardiac animation based on the strain values ​​and heart rate observed in the ultrasound imaging data of the heart.

11. The method of claim 10, wherein identifying the myocardium in the image generated from the ultrasound imaging data comprises analyzing the image via at least one of an image recognition algorithm, a shape detection algorithm, and an edge detection algorithm.

12. The method of claim 10, wherein determining the strain value at each portion of the myocardium in the image comprises performing speckle-tracking echocardiography on the image.

13. The method of claim 10, wherein the strain values ​​include longitudinal strain values ​​corresponding to length changes in a given portion of the myocardium during cardiac circulation, circumferential strain values ​​corresponding to circumferential changes in the associated chamber of the given portion of the myocardium during cardiac circulation, and radial strain values ​​corresponding to thickness changes along the radius of the given portion of the myocardium.

14. The method of claim 10, wherein outputting the electrical conduction pathway through the heart generated based on the determined strain value comprises: The strain value is mapped to the channels of electrical pulses passing through the heart in a spatiotemporal manner.

15. The method of claim 14, wherein the channel of the electrical pulse passing through the heart is mapped to the strain value in the spatiotemporal manner: Based on strain values ​​indicating the contraction of a myocardial portion at a given time point, the myocardial portion having the electrical pulse at that given time point is identified.

16. A system for visualizing cardiac electrical conduction, the system comprising: Ultrasonic probe; Display devices; and A processor configured to execute instructions stored in non-transitory memory, the instructions causing the processor, when executed, to: Ultrasound imaging data of the heart are acquired via the ultrasound probe; Generate cardiac ultrasound images from the acquired cardiac ultrasound imaging data; Generate a spatiotemporal diagram, wherein the spatiotemporal diagram represents the electrical conduction pathway of the heart during the cardiac cycle, determined based on myocardial deformation in the heart during the cardiac cycle; as well as Based on the spatiotemporal diagram, an animation of the electrical conduction path is output on the display device. The spatiotemporal graph described therein is an animation of the heart generated by adjusting a pre-made cardiac animation based on strain values ​​and heart rate observed in the ultrasound imaging data of the heart.

17. The system of claim 16, wherein, in order to determine the electrical conduction pathway of the heart during the cardiac cycle based on the myocardial deformation in the heart during the cardiac cycle, the processor is configured to execute additional instructions stored in the non-transitory memory, the additional instructions causing the processor, when executed, to: Perform speckle-tracking echocardiography on the generated cardiac ultrasound images to calculate strain values ​​that quantify the myocardial deformation in the heart during the cardiac cycle; and The location of the electrical pulse at a given time point in the cardiac cycle is mapped to the region of myocardial deformation at that given time point.

18. The system of claim 16, wherein the animation of the electrical conduction pathway comprises superimposing the electrical conduction pathway onto the cardiac ultrasound image, and wherein the pixel brightness of the electrical conduction pathway increases with the magnitude of the myocardial deformation in the heart.

19. The system of claim 16, wherein, in order to determine the electrical conduction pathway of the heart during the cardiac cycle based on the myocardial deformation in the heart during the cardiac cycle, the processor is configured to execute additional instructions stored in the non-transitory memory, the additional instructions causing the processor, when executed, to: The generated echocardiogram images are input into a neural network; and The animation of the electrical conduction path is received as the output of the neural network.

20. The system of claim 19, wherein the neural network is trained using previously acquired cardiac ultrasound images and associated electrical conduction pathways generated by mapping strain values ​​to the location of electrical pulses in the heart in a spatiotemporal manner.

Images