Ultrasonic imaging method, system and equipment and readable storage medium

Abstract

The invention discloses an ultrasonic imaging method, system and device and a readable storage medium, and the method comprises the steps: synchronously and continuously collecting B-mode ultrasonic data and Doppler ultrasonic data of a myocardial region of an evaluated object; when the B-mode ultrasonic data and the Doppler ultrasonic data are continuously acquired, synchronously acquiring electrocardiogram data of the evaluated object; determining a time window of the maximum diastole of the heart according to the electrocardiogram data; and in the time window, generating a myocardial structure diagram according to the B-mode ultrasonic data, generating a blood perfusion diagram according to the Doppler ultrasonic data, and overlapping the blood perfusion diagram on the myocardial structure diagram for synchronous display. The ultrasonic imaging method disclosed by the invention can realize clear imaging of blood perfusion in the myocardial tissue.

Description

Technical Field

[0001] This invention relates to the field of ultrasonic equipment technology, and specifically to an ultrasonic imaging method, system, device, and readable storage medium. Background Technology

[0002] Accurate assessment of myocardial blood perfusion status is crucial for the clinical diagnosis, treatment planning, and prognosis of cardiovascular diseases such as coronary heart disease and cardiomyopathy. Currently, myocardial perfusion imaging (MPI) mainly relies on imaging techniques such as X-ray computed tomography (X-CT) and magnetic resonance imaging (MRI). Although these methods offer excellent spatial resolution and tissue contrast, their clinical application still has significant limitations: high equipment purchase and maintenance costs, lengthy examination procedures, complex operational techniques, and contraindications for some patients due to factors such as implanted metal devices, renal insufficiency, or claustrophobia.

[0003] With the evolution of medical imaging technology, ultrasound imaging has become an important tool for the diagnosis and assessment of cardiovascular diseases due to its advantages such as non-invasiveness, ease of operation, real-time performance, and low cost. However, traditional ultrasound techniques, such as conventional grayscale and Doppler ultrasound, are difficult to clearly present the morphology and structure of the microvascular network and the blood perfusion dynamics characteristics within myocardial tissue, and lack effective visualization capabilities for the perfusion status at the myocardial microcirculation level, which greatly limits its application in myocardial perfusion assessment.

[0004] Therefore, there is an urgent need for an ultrasound imaging method that can display the myocardial blood perfusion status in real time and clearly. Summary of the Invention

[0005] The technical problem to be solved by this invention is that existing ultrasound technology cannot achieve clear imaging of blood perfusion in myocardial tissue.

[0006] To address the aforementioned technical problems, this invention provides an ultrasound imaging method, comprising: Simultaneously and continuously acquire B-mode ultrasound data and Doppler ultrasound data of the myocardial region of the evaluated subject; While continuously acquiring the B-mode ultrasound data and the Doppler ultrasound data, the electrocardiogram data of the evaluated object are acquired simultaneously. The time window for the maximum diastolic phase of the heart is determined based on the electrocardiogram data. Within the time window, a myocardial structure map is generated based on the B-mode ultrasound data, and a blood flow perfusion map is generated based on the Doppler ultrasound data. The blood flow perfusion map is then superimposed on the myocardial structure map and displayed synchronously.

[0007] Preferably, the blood perfusion map is generated based on microvascular imaging of the Doppler ultrasound data and is used to indicate blood flow density distribution or blood flow velocity.

[0008] Furthermore, the blood flow perfusion map uses color-coded levels, wherein: a highly saturated first color represents a region of high-speed blood flow or high red blood cell density; a low-saturation first color represents a region of low-speed blood flow or low red blood cell density; and the background of the color-coded levels is a second color, which is not used for the first color.

[0009] Optionally, the method further includes: using a pre-trained blood perfusion map annotation model to annotate the location of the newly generated blood perfusion map within a pre-acquired MRI cardiovascular imaging data volume.

[0010] Furthermore, the blood perfusion map annotation model is obtained by the following method: preprocessing the blood perfusion map to obtain ultrasound feature vectors; comparing the similarity between the ultrasound feature vectors and the feature vectors of MRI data, wherein the MRI data is data in the MRI cardiovascular imaging data volume; labeling the blood perfusion map corresponding to the ultrasound feature vector with the position of the MRI data with the highest similarity; training the labeled blood perfusion map and MRI data using a convolutional neural network to obtain the blood perfusion map annotation model.

[0011] Preferably, the continuous acquisition of B-mode ultrasound data and Doppler ultrasound data of the myocardial region includes: generating and displaying a myocardial structure map of the entire target myocardial tissue region; receiving a user's selection operation on the myocardial structure map to obtain the myocardial region; adjusting the B-mode ultrasound data acquisition parameters and Doppler ultrasound data acquisition parameters according to the myocardial region; and continuously acquiring B-mode ultrasound data and Doppler ultrasound data of the myocardial region according to the B-mode ultrasound data acquisition parameters and Doppler ultrasound data acquisition parameters, respectively.

[0012] Furthermore, the continuous acquisition of B-mode ultrasound data and Doppler ultrasound data of the myocardial region includes: continuously acquiring B-mode ultrasound data of the myocardial region at a first frame frequency; and continuously acquiring Doppler ultrasound data of the myocardial region at a second frame frequency, wherein the second frame frequency is less than the first frame frequency.

[0013] Optionally, the type of acoustic beam used for data acquisition can be one of the following: focused wave, plane wave, divergent wave, V wave, C wave, and incompletely focused wave.

[0014] Furthermore, the emission frequency of the acoustic beam used for data acquisition is determined based on the current maximum depth of the target myocardial tissue.

[0015] Preferably, obtaining the maximum diastolic period of the heart based on the electrocardiogram data includes: classifying and labeling the electrocardiogram data within a single heartbeat cycle according to different stages; training the classified electrocardiograms and corresponding labels using a convolutional neural network to obtain a diastolic period recognition model; and using the diastolic period recognition model to identify the maximum diastolic period of the heart.

[0016] The present invention also provides an ultrasound imaging system, the system comprising: an ultrasound device for simultaneously and continuously acquiring B-mode ultrasound data and Doppler ultrasound data of the myocardial region of the subject being evaluated; an electrocardiogram (ECG) measuring instrument for simultaneously acquiring ECG data of the subject being evaluated while continuously acquiring the B-mode ultrasound data and Doppler ultrasound data; a computer for determining a time window of the maximum diastolic period of the heart based on the ECG data, and generating a myocardial structure diagram based on the B-mode ultrasound data and a blood flow perfusion diagram based on the Doppler ultrasound data within the time window; and a display screen for simultaneously displaying the blood flow perfusion diagram superimposed on the myocardial structure diagram within the time window.

[0017] The beneficial effects of this invention are as follows: This invention can clearly display myocardial blood flow perfusion with high sensitivity and clarity, thereby enabling real-time ultrasound assessment of myocardial blood flow perfusion and expanding the clinical application scenarios of ultrasound.

[0018] The Doppler data acquisition of this invention is simple, not controlled by trigger signals, and does not require mid-process changes to acquisition and processing parameters. By simultaneously displaying B-ultrasound images and Doppler microvascular images during the maximum diastolic phase of the heart, it effectively improves the imaging quality of myocardial blood flow perfusion.

[0019] This invention uses artificial intelligence to automatically select the diastolic phase of the heart, and coordinates with the localization and analysis of MRI cardiovascular imaging data, which facilitates the analysis and evaluation of ultrasound myocardial blood flow perfusion images by clinicians, thereby improving diagnostic efficiency and accuracy. Attached Figure Description

[0020] Figure 1 A flowchart illustrating an ultrasound imaging method according to an embodiment of the present invention is shown; Figure 2 A blood perfusion diagram is shown in a preferred embodiment of the present invention; Figure 3 A flowchart illustrating another ultrasound imaging method according to an embodiment of the present invention is shown; Figure 4 A schematic diagram of the structure of an ultrasound imaging system according to an embodiment of the present invention is shown. Detailed Implementation

[0021] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. Example 1

[0022] This ultrasound imaging method can achieve real-time and clear display of myocardial blood flow perfusion, thereby enabling doctors to more accurately and efficiently assess the myocardial blood flow perfusion status of the assessed subject.

[0023] Figure 1 An ultrasound imaging method according to an embodiment of the present invention is illustrated. See also Figure 1 As shown, the ultrasound imaging method may include: Step S100: Simultaneously and continuously acquire B-mode ultrasound data and Doppler ultrasound data of the myocardial region of the evaluated subject. This step can be implemented using an ultrasound device equipped with an ultrasound probe featuring a time-alternating duplex mode. After locating the myocardial region, the synchronization control module triggers alternating scans of B-mode and Doppler modes: B-mode scanning is used to acquire B-mode ultrasound data, and Doppler mode is used to acquire Doppler ultrasound data. The synchronization control module generates a clock source based on a crystal oscillator clock, which controls the data acquisition for both modes. The raw signals are converted into digital signals by a radio frequency signal analog-to-digital converter and stored as a time-series array, ensuring spatiotemporal alignment between the B-mode ultrasound data and the Doppler ultrasound data. The synchronization control module can use an FPGA to generate dual trigger pulses: B-mode scanning is triggered by the rising edge, and Doppler mode by the falling edge, with adjustable pulse intervals.

[0024] Before data acquisition, a myocardial structure map of the entire target myocardial tissue region can be pre-generated and displayed. The user then selects a region on the map using a bounding box, identifying the area to be evaluated. Based on the user-selected region, the B-mode ultrasound and Doppler ultrasound acquisition parameters are adjusted to ensure data quality. After parameter adjustment, B-mode and Doppler ultrasound data for the selected myocardial region are continuously acquired using the appropriate parameters.

[0025] During data acquisition, B-mode ultrasound data of the myocardial region can be continuously acquired at a first frame frequency, while Doppler ultrasound data of the myocardial region can be continuously acquired at a second frame frequency, where the second frame frequency is lower than the first frame frequency. The first frame frequency, which meets the spatial resolution requirements of myocardial motion, can be 100–200 Hz. The second frame frequency, which meets the rate of change of hemodynamic parameters, can be 20–50 Hz. For example only, the first frame frequency can be 150 Hz, and the second frame frequency can be 30 Hz. This acquisition method can balance system resource usage and data quality requirements.

[0026] The acoustic beamforming methods used for data acquisition include, but are not limited to, focused beamforming, plane wave composite imaging, or divergent beamforming aperture technology, depending on the penetration depth and resolution requirements of the target tissue. For example, the acoustic beam type used for data acquisition can be one of focused wave, plane wave, divergent wave, V wave, C wave, or incompletely focused wave, with the specific choice depending on clinical needs and equipment configuration.

[0027] The transmission frequency of the acoustic beam used for data acquisition is determined based on the current maximum depth of the target myocardial tissue. Specifically, when the maximum depth is >8cm, a transmission frequency of ≤2.5MHz can be used; when the maximum depth is ≤8cm, a transmission frequency of 5MHz can be used. This ensures that the acoustic waves can effectively penetrate to the target depth and acquire a valid signal.

[0028] In step S200, while continuously acquiring the B-mode ultrasound data and the Doppler ultrasound data, the electrocardiogram (ECG) data of the evaluated subject is acquired simultaneously. ECG is a general abbreviation for electrocardiogram. The acquisition of ECG data and the acquisition of ultrasound data (B-mode ultrasound data and Doppler ultrasound data) in step S100 are both controlled by the same clock source generated by the synchronization control module. The synchronization control module sends synchronization signals to the ultrasound equipment and the ECG measuring instrument to ensure that the data acquisition timestamp error between the two types of equipment is less than 100 μs. During data acquisition, the ultrasound equipment executes B-mode and Doppler modes in an alternating scanning manner. Simultaneously, the ECG measuring instrument continuously acquires ECG signals (i.e., ECG data) and suppresses electromyographic interference and baseline drift through a 1–40 Hz bandpass filter, recording the R-wave peak value and ST segment characteristics in real time. Each time the ultrasound device completes a scan frame, it sends an interrupt request to the synchronization control module. The electrocardiogram (ECG) meter responds to the interrupt and records the ECG data at the corresponding timestamp, thus ensuring that the ultrasound data frame and the ECG data points are precisely aligned in the same cardiac cycle in the time dimension. The synchronization control module can directly trigger the ECG meter to sample via a hardware interrupt circuit, ensuring a timestamp synchronization error ≤100μs. The clock source phase noise is ≤-100dBc / Hz, and the synchronization control module can utilize an FPGA to implement the hardware interrupt response.

[0029] Step S300: Determine the time window for the maximum diastolic period of the heart based on the electrocardiogram (ECG) data. The specific steps for determining the maximum diastolic period include: first, classifying and labeling the ECG data within a single heartbeat cycle according to different stages; then, training the classified ECGs and corresponding labels using a convolutional neural network to obtain a diastolic recognition model; and finally, using this diastolic recognition model to identify the maximum diastolic period of the heart. A single heartbeat cycle is one heartbeat period. Before training, baseline correction, R-wave alignment, and z-score normalization can be performed on the ECG data. The input data is the complete ECG signal within a single heartbeat cycle. Continuous ECG signals are segmented based on a sliding window, single-cycle samples are extracted, and the start and end times of the diastolic period are labeled. The output of the diastolic recognition model can be a time window [t1, t2], where t1 is the start time of the diastolic period after the R-wave peak, and t2 is the end time. This machine learning-based method can improve the accuracy and automation of diastolic recognition. Preferably, the classified ECGs and corresponding labels can be trained using a BiLSTM network to obtain the diastolic recognition model.

[0030] In step S400, within the determined maximum diastolic time window, a myocardial structure map is generated based on the B-mode ultrasound data, and a blood flow perfusion map is generated based on the Doppler ultrasound data. Then, the blood flow perfusion map is superimposed on the myocardial structure map and displayed synchronously.

[0031] A blood flow perfusion map is generated by microvascular imaging based on Doppler ultrasound data and is used to indicate the distribution of blood flow density or blood flow velocity, wherein the blood flow velocity can be vertical blood flow velocity or horizontal blood flow velocity.

[0032] Blood flow perfusion maps can be encoded using color gradation, where a highly saturated first color represents areas of high-velocity blood flow or high red blood cell density, and a less saturated first color represents areas of low-velocity blood flow or low red blood cell density. The background of the color-coded map is a second color, which is different from the first color. For example only, the first color can be red or another color, and the second color can be blue or another color different from the first color.

[0033] Figure 2 A blood perfusion diagram is shown in a preferred embodiment of the present invention. See also Figure 2 As shown, this blood flow perfusion map uses color-coded levels. High-saturation red indicates areas of high-velocity blood flow or high red blood cell density, while low-saturation red indicates areas of low-velocity blood flow or low red blood cell density. The background for this color-coded level is blue. Specifically, the higher the blood flow velocity or red blood cell density, the higher the red saturation; conversely, the lower the blood flow velocity or red blood cell density, the lower the red saturation.

[0034] It should be noted that red blood cells are also called erythrocytes, and red blood cell density is the density of red blood cells.

[0035] This color-coded system allows doctors to visually identify areas with different blood flow states, facilitating clinical diagnosis.

[0036] In other implementations, the blood perfusion map can be overlaid on a grayscale myocardial structure map using a pseudo-color mapping, employing a transparency blending algorithm. RGB_mix=α·RGB_B-mode+(1-α)·RGB_Doppler Wherein, α is the transparency weight, which is fixed at 0.7; or it can be dynamically adjusted according to the blood flow velocity: the higher the flow velocity, the smaller the value of α.

[0037] It is important to note that before overlaying the data, the timestamps of the B-mode frame data must be checked to ensure they fall entirely within the [t1,t2] interval; otherwise, the frame data should be discarded.

[0038] Figure 3 Another ultrasound imaging method according to an embodiment of the present invention is illustrated. See also Figure 3 As shown, the ultrasound imaging method may further include: In step S500, during the non-maximal diastolic period, a myocardial structure map is generated and displayed separately based solely on B-mode ultrasound data.

[0039] Specifically, when the R wave of the ECG is detected but does not enter the [t1,t2] time window, it is determined to be the systolic phase, i.e., the non-maximum diastolic period. In this case, only the myocardial structure map is generated and displayed. This reduces the amount of computation and improves the response speed.

[0040] To further improve diagnostic accuracy, a pre-trained blood perfusion map annotation model was used to mark the location of the newly generated blood perfusion map within the pre-acquired MRI cardiovascular imaging data. This annotation allows for comparison and fusion of ultrasound and MRI imaging results, providing more comprehensive diagnostic information.

[0041] The method for obtaining the blood perfusion icon annotation model may include the following steps: First, preprocess the blood perfusion map to obtain ultrasound feature vectors; then, compare the similarity between the ultrasound feature vectors and the feature vectors of MRI data, where the MRI data refers to data from the MRI cardiovascular imaging data volume; next, annotate the blood perfusion map corresponding to the ultrasound feature vector with the location of the MRI data with the highest similarity; finally, train the annotated blood perfusion map and MRI data using a convolutional neural network to obtain the blood perfusion icon annotation model. Specifically, the similarity is calculated as follows: the coordinate system of the ultrasound feature vectors is mapped to the space of the feature vectors of the MRI data through an affine transformation, and the Euclidean distance similarity of the feature vectors is calculated.

[0042] Using the methods described above, doctors can obtain blood perfusion information during diastole and continuously observe changes in myocardial structure throughout the entire cardiac cycle, thereby comprehensively assessing myocardial blood perfusion status and providing important evidence for the diagnosis and treatment of heart diseases. Example 2

[0043] Figure 4 An ultrasound imaging system according to an embodiment of the present invention is illustrated. See also Figure 4 As shown, the ultrasound imaging system may include an ultrasound device 100, an electrocardiogram measuring instrument 200, a computer 300, and a display screen 400.

[0044] Ultrasound device 100 is used to simultaneously and continuously acquire B-mode ultrasound data and Doppler ultrasound data of the myocardial region of the subject being evaluated. Ultrasound device 100 includes an ultrasound probe 110 and an ultrasound host 120. The ultrasound probe includes a piezoelectric crystal array capable of emitting ultrasound waves and receiving reflected echoes. The ultrasound host includes a signal amplifier, an analog-to-digital converter, and signal processing circuitry, capable of converting the received ultrasound echo signals into digital signals and processing them. The ultrasound device is equipped with dual-mode acquisition capabilities and can quickly switch between B-mode and Doppler modes to achieve simultaneous acquisition of both types of data. B-mode ultrasound data primarily reflects the acoustic impedance differences of tissue structures and is used to display the anatomical structure of the myocardium; Doppler ultrasound data, based on the Doppler frequency shift principle, is used to detect blood flow velocity and direction, reflecting the blood perfusion status in the myocardium.

[0045] The electrocardiogram (ECG) measuring instrument 200 is used to simultaneously acquire ECG data of the subject being evaluated while continuously acquiring B-mode ultrasound data and Doppler ultrasound data. The ECG measuring instrument includes multiple electrodes, a signal amplification circuit, and a filtering circuit. The electrodes are connected via wires to specific locations on the chest and limbs of the subject being evaluated to acquire weak electrical signals generated by cardiac electrical activity. The signal amplification circuit amplifies the weak ECG signals to a detectable level. The filtering circuit is used to eliminate environmental and electromechanical interference, improving signal quality. The ECG measuring instrument is connected to ultrasound equipment and a computer via a data interface to achieve synchronous data acquisition and transmission. The ECG data acquired by the ECG measuring instrument includes key waveforms such as the P wave, QRS complex, and T wave, used to accurately identify various stages of cardiac electrical activity.

[0046] Computer 300 is used to determine the time window of the heart's maximum diastolic period based on electrocardiogram (ECG) data, and within the time window, to generate a myocardial structure map based on B-mode ultrasound data and a blood flow perfusion map based on Doppler ultrasound data. Furthermore, computer 300 can also be used to generate a myocardial structure map based solely on B-mode ultrasound data during non-maximum diastolic periods. Computer 300 may include a processor, memory, and dedicated image processing software. The processor is responsible for executing the ECG analysis algorithm, determining the time window of the heart's maximum diastolic period by identifying the RR interval and the T wave termination point. The memory is used for temporary storage of various acquired data and processing results. The dedicated image processing software has multiple functional modules, including an ECG analysis module, a B-mode image reconstruction module, and a Doppler data processing module. The ECG analysis module accurately locates the time window of the heart's maximum diastolic period by analyzing the relationship between the QRS complex and the T wave. The B-mode image reconstruction module converts the B-mode ultrasound data into a two-dimensional grayscale image, displaying the anatomical structure of the myocardium. The Doppler data processing module converts Doppler frequency shift data into color-coded blood flow perfusion maps, with different colors representing different blood flow velocities and directions. The computer can process the input data in real time and adjust the output according to different stages of the cardiac cycle.

[0047] The display screen 400 is used to simultaneously display the blood perfusion map overlaid on the myocardial structure map within a time window. Furthermore, the display screen 400 can also be used to display only the myocardial structure map during non-maximum diastolic periods. The display screen 400 is a high-resolution medical monitor with excellent contrast and color reproduction capabilities. The display screen is connected to a computer via a video interface, enabling real-time display of computer-processed images. The display screen has a split-screen display function, capable of simultaneously displaying electrocardiogram waveforms and ultrasound images. The display screen employs intelligent display control technology, automatically switching display modes according to different stages of the cardiac cycle. During the maximum diastolic time window, the display screen overlays the color blood perfusion map with the grayscale myocardial structure map, allowing physicians to intuitively assess the myocardial blood perfusion status. Conversely, during non-maximum diastolic periods, the display screen only displays the myocardial structure map, avoiding the impact of Doppler signal distortion caused by cardiac contraction on diagnostic judgment.

[0048] In a preferred embodiment, the ultrasound device 100 uses a phased array probe with an operating frequency range of 2-5 MHz, suitable for imaging deep cardiac tissues. The phased array probe can consist of 64 to 256 independently controlled piezoelectric elements. Preferably, the phased array probe consists of 128 independently controlled piezoelectric elements, enabling electronic control of the direction and focus of the ultrasound beam, improving image resolution and penetration depth. The ultrasound device is also equipped with harmonic imaging capabilities, which can receive second harmonic signals generated by tissue, further improving image quality and contrast.

[0049] In a preferred embodiment, the computer 300 further includes a blood perfusion quantitative analysis module. This module is capable of quantitatively processing Doppler data, calculating parameters such as blood flow velocity, blood flow rate, and perfusion index in different regions of the myocardium, and displaying them in numerical and color-coded form. The blood perfusion quantitative analysis module employs an adaptive threshold algorithm, which can automatically adjust parameters according to the physiological state of different patients, improving the accuracy and reliability of the analysis results.

[0050] In a preferred embodiment, the ultrasound imaging system further includes an image storage device for storing acquired B-mode ultrasound data, Doppler ultrasound data, and electrocardiogram data, as well as processed myocardial structure diagrams and blood perfusion diagrams. The image storage device uses a high-capacity solid-state drive and supports the DICOM standard format, facilitating the archiving and transmission of medical images. The image storage device also features data encryption to protect patient privacy and medical information security.

[0051] In a preferred embodiment, the ultrasound imaging system further includes a network interface for transmitting acquired data and processing results to a hospital information system or a remote consultation platform. The network interface supports both wired and wireless connections, with a transmission rate of up to 1Gbps, ensuring rapid transmission of large volumes of medical image data. The network interface conforms to medical information standards such as HL7 and DICOM, enabling seamless integration with other medical devices and systems.

[0052] The working principle of the ultrasound imaging system is as follows: the ultrasound device emits ultrasound waves towards the myocardial region and receives the reflected echoes, while an electrocardiogram (ECG) scanner acquires the electrocardiogram (ECG) signals of the subject being evaluated. A computer receives this data and analyzes the ECG waveforms to determine the time window of the heart's maximum diastolic phase. Within this time window, the computer processes the B-mode ultrasound data to generate a myocardial structure map and processes the Doppler ultrasound data to generate a blood flow perfusion map. The display screen overlays both images during the maximum diastolic time window; at other times, only the myocardial structure map is displayed. This intelligent display method avoids the distortion problem of Doppler signals during cardiac systole, improving the accuracy and reliability of myocardial blood flow perfusion assessment. Example 3

[0053] This embodiment provides an electronic device including at least one processor and a memory communicatively connected to the processor. The memory stores instructions executable by the processor, which, upon executing these instructions, can perform the ultrasound imaging method described in Embodiment 1.

[0054] The electronic device can be an ultrasound diagnostic instrument, a medical imaging workstation, or other medical device with computing and display capabilities. The processor can be a central processing unit (CPU), graphics processing unit (GPU), or digital signal processor (DSP), etc. The memory can include read-only memory and random access memory, used to store the operating system, applications, and various data.

[0055] The electronic device may also be equipped with a display screen for displaying the myocardial structure diagram and blood perfusion diagram generated in Embodiment 1. Furthermore, the electronic device may include a data acquisition interface for connecting an ultrasound probe and an electrocardiogram (ECG) device to acquire B-mode ultrasound data, Doppler ultrasound data, and ECG data.

[0056] The processor in the electronic device executes instructions stored in the memory, enabling it to perform all the functions of the ultrasound imaging method described in Embodiment 1, including data acquisition, electrocardiogram analysis, image generation, and display. Through this electronic device, doctors can conveniently observe the myocardial blood perfusion status of the subject being evaluated, providing assistance in the diagnosis of heart diseases. Example 4

[0057] This embodiment provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the ultrasound imaging method described in Embodiment 1.

[0058] The non-transient computer-readable storage medium can be a read-only memory (ROM), random access memory (RAM), optical disc, magnetic disk, USB flash drive, or any other medium capable of storing computer programs. When the computer instructions in the storage medium are loaded and executed by the processor, the processor will execute the various steps of the ultrasound imaging method described in Embodiment 1, including simultaneously and continuously acquiring B-mode ultrasound data and Doppler ultrasound data of the myocardial region of the evaluated object, simultaneously acquiring the electrocardiogram data of the evaluated object, determining the time window of the maximum diastolic period of the heart based on the electrocardiogram data, generating and overlaying myocardial structure diagrams and blood flow perfusion diagrams within the time window, and displaying only myocardial structure diagrams during non-maximum diastolic periods.

[0059] In a preferred embodiment, the non-transitory computer-readable storage medium can be integrated into the ultrasound imaging device, enabling the ultrasound imaging device to automatically execute the above-described method. In another preferred embodiment, the non-transitory computer-readable storage medium can also be a stand-alone storage device, connected to the ultrasound imaging device via an interface, providing the ultrasound imaging device with the necessary computer instructions.

[0060] By storing the above methods in the form of computer instructions in a non-transient computer-readable storage medium, the methods can be standardized and automated, improving the efficiency and accuracy of myocardial blood flow perfusion assessment, reducing human error, and facilitating the promotion and application of the methods.

[0061] The above description is merely a preferred embodiment of the present invention, and the present invention is not limited to the above embodiments. It is understood that other improvements and variations that are directly derived or conceived by those skilled in the art without departing from the spirit and concept of the present invention should be considered to be included within the protection scope of the present invention.

Claims

1. An ultrasound imaging method, characterized in that, include: Simultaneously and continuously acquire B-mode ultrasound data and Doppler ultrasound data of the myocardial region of the evaluated subject; While continuously acquiring the B-mode ultrasound data and the Doppler ultrasound data, the electrocardiogram data of the evaluated object are acquired simultaneously. The time window for the maximum diastolic phase of the heart is determined based on the electrocardiogram data. Within the time window, a myocardial structure map is generated based on the B-mode ultrasound data, and a blood flow perfusion map is generated based on the Doppler ultrasound data. The blood flow perfusion map is then superimposed on the myocardial structure map and displayed synchronously.

2. The method according to claim 1, characterized in that, The blood perfusion map is generated based on microvascular imaging of the Doppler ultrasound data and is used to indicate blood flow density distribution or blood flow velocity.

3. The method according to claim 2, characterized in that, The blood perfusion map uses color-coded scales, where: The first color with high saturation indicates areas of high-speed blood flow or high red blood cell density; The first color with low saturation indicates areas of slow blood flow or low red blood cell density; The background of the color-coded scale is a second color, which is different from the first color.

4. The method according to claim 3, characterized in that, The method further includes: Using a pre-trained blood perfusion map annotation model, the location of the newly generated blood perfusion map within the pre-acquired MRI cardiovascular imaging data volume is labeled; The blood perfusion icon annotation model is obtained using the following method: The blood perfusion map is preprocessed to obtain ultrasound feature vectors; The similarity between the ultrasound feature vector and the feature vector of the MRI data is compared, wherein the MRI data is the data in the MRI cardiovascular imaging data volume; The blood perfusion map corresponding to the ultrasound feature vector is labeled with the location of the MRI data with the highest similarity; The labeled blood perfusion maps and MRI data are trained using a convolutional neural network to obtain the blood perfusion map annotation model.

5. The method according to claim 1, characterized in that, The continuous acquisition of B-mode ultrasound data and Doppler ultrasound data of the myocardial region includes: Generate and display a myocardial structure map of the entire target myocardial tissue region; Receive the user's selection operation on the myocardial structure diagram to obtain the myocardial region; Adjust the B-mode ultrasound data acquisition parameters and Doppler ultrasound data acquisition parameters according to the described myocardial region; Based on the B-mode ultrasound data acquisition parameters, B-mode ultrasound data of the myocardial region is continuously acquired at the first frame frequency; Based on the Doppler ultrasound data acquisition parameters, Doppler ultrasound data of the myocardial region is continuously acquired at a second frame frequency, where the second frame frequency is less than the first frame frequency.

6. The method according to claim 5, characterized in that, The type of acoustic beam used for data acquisition is one of focused wave, plane wave, divergent wave, V wave, C wave, and incompletely focused wave, and the emission frequency of the acoustic beam used for data acquisition is determined according to the current maximum depth of the target myocardial tissue.

7. The method according to claim 5 or 6, characterized in that, The step of obtaining the maximum diastolic period of the heart based on the electrocardiogram data includes: The electrocardiogram data within a single heartbeat cycle are classified and labeled according to different stages; The classified electrocardiograms and their corresponding labels are trained using a convolutional neural network to obtain a diastolic recognition model; The diastolic phase recognition model is used to identify the maximum diastolic phase of the heart.

8. An ultrasound imaging system, characterized in that, The system includes: Ultrasound equipment is used to simultaneously and continuously acquire B-mode ultrasound data and Doppler ultrasound data of the myocardial region of the subject being evaluated. An electrocardiogram (ECG) measuring instrument is used to simultaneously acquire the ECG data of the subject being evaluated while continuously acquiring the B-mode ultrasound data and the Doppler ultrasound data. A computer is used to determine a time window of the maximum diastolic period of the heart based on the electrocardiogram data, and within the time window, to generate a myocardial structure map based on the B-mode ultrasound data and a blood flow perfusion map based on the Doppler ultrasound data. A display screen is used to synchronously display the blood perfusion map overlaid on the myocardial structure map within the time window.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7.

Images