35 results about "Doppler imaging" patented technology

The embodiment of the invention provides an angiography method, system and device based on ultrasonic positioning and a storage medium, and belongs to the technical field of ultrasonic medical detection. Firstly, an ultrasonic probe is adopted to scan a current area to obtain ultrasonic data, a Doppler imaging technology is adopted to process the ultrasonic data to obtain a Doppler blood vessel image of the current area, then whether the current area is a target area or not is rapidly judged according to the Doppler blood vessel image, and after the target area is rapidly determined, the target area is determined. And performing microbubble contrast operation on the blood vessel of the target area, and scanning the target area after the microbubble contrast operation by adopting an ultrasonic positioning microscope technology, so as to obtain a high-precision blood vessel image of the target area. The target area is rapidly positioned through the Doppler imaging technology, then the blood vessel image is collected in the target area through the ultrasonic positioning microscope technology based on microbubble radiography, the efficiency of the blood vessel image collection process of the target area is improved, and meanwhile the blood vessel image precision is improved.

The invention discloses a 3D human body posture estimation method based on a millimeter wave radar, and relates to the technical field of 3D human body postures. The invention provides a symbol perception energy separation mechanism by introducing a SignAware module and aiming at the problem of information annihilation caused by mixing of positive and negative Doppler components in the prior art, and according to the design, inductive bias consistent with a Doppler imaging physical mechanism is injected into a network structure, so that the model is constrained to follow the dynamic law of a speed symbol, and the model is more accurate and reliable. And separable positive and negative subspaces are formed in the representation space. Therefore, cross-symbol interference is reduced, the alignability and interpretability of specific joint movement are improved, and the sensitivity to speed polarity is kept in a complex multi-joint scene; a PhaseFilm module is provided, aiming at the defect that an existing method lacks periodic and sequential modeling, a phase conditional feature re-calibration mechanism is introduced, the two modules are put into an attitude network, then a feature extraction mechanism combining a time domain and a frequency domain is introduced, and a final SPTFormer network is obtained.

The application discloses a micro blood flow imaging method based on adaptive density filtering and a related device, and relates to the technical field of ultrasonic imaging. The method comprises the following steps: extracting a static frame in original ultrasonic data, screening a high-quality static frame through correlation analysis to eliminate motion interference; performing SVD clutter filtering, and cutting off high spatiotemporal coherence singular values to separate tissue clutter and microbubble signals; performing adaptive density filtering and subtracting a preliminary filtering result to realize noise suppression and overlapping microbubble decoupling; and enhancing microbubble motion signals through time-lag autocorrelation processing, and finally completing power Doppler imaging and ultrasonic localization microscope reconstruction. The scheme effectively solves the problem that the prior art cannot simultaneously consider PDI noise suppression and ULM microbubble decoupling, significantly improves image signal-to-noise ratio and super-resolution, avoids problems such as signal distortion, artifacts and loss of low-speed blood flow, and provides more reliable imaging support for clinical diagnosis such as blood vessel lesion detection and tumor blood flow evaluation.

The invention relates to the field of biomedical ultrasonic imaging, and discloses a pulse wave detection method and system based on ultrafast Doppler imaging, and the method comprises the steps: firstly obtaining a dynamic power Doppler image of the blood flow of a biological tissue; performing spectral analysis on the Doppler signal of each pixel point in the image to obtain a function that the frequency spectrum changes along with time; and on the basis, calculating a blood flow speed time sequence, an impedance index and a pulsation index of each pixel point, and finally obtaining an impedance index distribution diagram and a pulsation index distribution diagram of the whole blood vessel network. According to the method, ultrafast imaging and spectral analysis technologies are ingeniously combined, the structure and the function of the vascular network can be comprehensively evaluated, a new technical means is provided for hemodynamic research and disease diagnosis of organs such as spinal cords, hearts and brains, and the method has a wide application prospect.

The invention discloses a micro blood flow imaging method based on adaptive density filtering and a related device, and relates to the technical field of ultrasonic imaging, the method comprises the following steps: extracting static frames in original ultrasonic data, and screening high-quality static frames through correlation analysis to eliminate motion interference; sVD clutter filtering is carried out, and the high space-time coherence singular value is cut off to separate tissue clutters and microbubble signals; noise suppression and overlapped microbubble decoupling are realized through adaptive density filtering and subtraction with a preliminary filtering result; and enhancing a microbubble motion signal through time-delay self-correlation processing, and finally completing power Doppler imaging and ultrasonic positioning microscope reconstruction. According to the scheme, the problem that PDI noise suppression and ULM microbubble decoupling cannot be considered at the same time in the prior art is effectively solved, the image signal-to-noise ratio and super-resolution are remarkably improved, the problems of signal distortion, artifacts, low-speed blood flow loss and the like are avoided, and more reliable imaging support is provided for clinical diagnosis such as vasculopathy detection and tumor blood flow evaluation.

The invention relates to a brain small vessel blood flow monitoring method and system based on ultrasonic imaging, and the method comprises the steps: setting pulse Doppler ultrasonic imaging devices at different positions, and carrying out the color pulse Doppler imaging of the artery and vein in a brain small vessel through the pulse Doppler ultrasonic imaging devices, arranging according to spatial positions corresponding to different positions to obtain three-dimensional color pulse Doppler imaging; in the process of color pulse Doppler imaging, comparing and analyzing a current frame of color pulse Doppler image and a previous frame of color pulse Doppler image to obtain an analysis result for optimizing a subsequent color pulse Doppler image; blood flow power information is extracted from the three-dimensional color pulse Doppler imaging, and the blood flow change condition of the small cerebral vessels is obtained based on the blood flow power information. The brain small vessel blood flow monitoring system can realize real-time and dynamic monitoring of brain small vessel blood flow, has high clinical application value, and provides a new technical means for prevention and treatment work of brain small vessel diseases.

Dynamic mode decomposition technique for doppler-based imaging of cavitation bubbles in pulsed high intensity focused ultrasound is described. A method for imaging transient cavitation bubbles in a tissue of a patient using ultrasound imaging includes: generating a burst of therapy ultrasound waves by a focused therapy transducer; and generating cavitation bubbles by the burst of therapy ultrasound waves at a target region that is a focal region of the tissue. After generating a plurality of the gas bubbles at the target region and within a time period of the dissolving process, imaging ultrasound pulses are generated by an imaging probe. Generating ultrasound images as B-scan images based on returning ultrasound signals. The filtering is configured for isolating representations of dissolving gas bubbles from representations of surrounding tissue, and determining spatial and temporal attributes of the sub-mm scale gas bubbles.

The application provides a kind of space target ISAR image component intelligent segmentation and attitude estimation method, through inverse synthetic aperture radar to space target is continuously observed, and utilize distance-Doppler imaging algorithm to the echo is sequentially imaged, obtain the ISAR image sequence of space target;Utilize deep learning network Pix2pixGAN to the ISAR image sequence is segmented, and the segmentation accuracy is higher;After removing the invalid connected region in each component segmentation result, obtain the final segmentation image of each component;Linear structure extraction is carried out to the final each component segmentation image using the minimum circumscribed rectangle method, and the method is lower to the image component segmentation accuracy requirement, and the robustness is stronger;Finally, according to the imaging principle of radar observation and ISAR image, an unconstrained optimization problem for solving three-dimensional attitude is constructed, and a particle swarm optimization algorithm is used for solving, and the solving efficiency is higher, to realize the attitude inversion of space target key component.

The present application discloses an ultrasonic Doppler imaging method, comprising extracting features from an acquired raw blood flow image to obtain vascular features; determining illumination processing parameters for each vascular location based on the vascular features; adjusting the original illumination model using the illumination processing parameters to obtain an illumination model; processing the corresponding vascular locations using the illumination model to obtain reflection results; and fusing each reflection result with a pseudo-color blood flow image corresponding to the raw blood flow image to generate an ultrasonic Doppler image. The ultrasonic Doppler imaging method can effectively reduce the dependence of different blood flow feature processing on illumination model parameters, thereby improving the ultrasonic Doppler blood flow imaging effect. The present application also discloses an ultrasonic Doppler imaging device, apparatus, and computer-readable storage medium, all of which have the aforementioned beneficial effects.

The invention discloses a method for improving the color Doppler signal-to-noise ratio of deep peripheral pancreatic vessels, and relates to the technical field of medical ultrasonic imaging. According to the method, the signal penetrating power is enhanced and the original data quality is optimized by combining coding excitation and matched filtering with self-adaptive space composite imaging at the front end, and blood flow signals are intelligently extracted through self-adaptive clutter suppression and a deep learning model in sequence at the rear end and are finally fused and displayed with a B-mode image. According to the method, the problem of extremely low signal-to-noise ratio of deep peripancreatic vessel color Doppler imaging caused by serious signal attenuation and background noise interference is systematically solved. According to the method, the detection capability of deep low-speed blood flow signals can be effectively enhanced within a safety limit value, clearer and more accurate blood flow images are obtained, dependence on experience of an operator is reduced, and the diagnosis reliability is improved.

The invention discloses an ultrasonic measurement method and an ultrasonic imaging device, and the method comprises the steps: obtaining a carotid artery ultrasonic image of a target object, and carrying out the image recognition, thereby obtaining a recognition result; displaying the measurement items in all the imaging modes corresponding to the recognition result on the same display interface; when any measurement item is selected, measurement of the measurement item is executed in the imaging mode corresponding to the selected measurement item, and a measurement result is displayed; wherein the identification result comprises a section type of a blood vessel section corresponding to a carotid artery blood vessel region in the carotid artery ultrasonic image; when the image is a cross section, displaying a measurement item in a two-dimensional gray-scale imaging mode; when the section is a longitudinal section, identifying a corresponding section type; displaying a measurement item in a two-dimensional gray-scale imaging mode when the carotid artery is the globe part of the carotid artery; and when the arteries are common carotid arteries, internal carotid arteries or external carotid arteries, respective measurement items in a two-dimensional gray-scale imaging mode, a color Doppler imaging mode and a pulse Doppler imaging mode are displayed. The method can reduce user operations.

Disclosed is an ultrasound imaging approach employing a transmission scheme, termed "StaBle", to increase the Nyquist limit, through dealiasing, of conventional sequential angle, ultrafast (high-frame-rate) ultrasound imaging (e.g., plane-wave Doppler imaging or diverging wave imaging). The dealiased multi-angle Doppler estimates facilitate accurate least-squares estimates of flow magnitude and direction for vector Doppler imaging (VDI). "StaBle" combines the Nyquist velocity limit extension of staggered, multiple pulse repetition frequencies (PRFs) with a double transmission scheme. With 3 transmit angles and 2 PRFs, for example, the disclosed "StaBle" technique can achieve a 6-12 times higher velocity limit compared to sequential-angle VDI. The robustness of "StaBle" can be observed in derived measures from the VDI results, such as vorticity, kinetic energy, and energy loss obtained from the resolved vector field, which show consistent beat-to-beat variation.

The invention discloses a precession target scattering center separation method based on a three-dimensional radar data cube, and the method comprises the steps: carrying out the processing of a radar echo pulse signal of a conical precession target, and building a precession model of the target, so as to distinguish the different signal characteristics of a local scattering center and a sliding scattering center; carrying out two-dimensional distance-Doppler imaging on the radar echo signal, arranging multiple frames of obtained distance-Doppler images according to a time sequence within a preset imaging time, and constructing a distance-Doppler image sequence; based on a feature enhancement method of a binary mask, automatically separating data of a local scattering center and a sliding scattering center from the distance-Doppler image sequence, extracting coordinate information of each scattering center, and generating a three-dimensional radar data cube containing distance, frequency and time dimensions; and performing trajectory tracking and separation on the sliding scattering center signal in the three-dimensional radar data cube by using a three-dimensional optimal path selection method.

The present invention belongs to the technical field of ultrasonic Doppler blood flow imaging, specifically a three-dimensional ultrasonic vector Doppler imaging method based on a row-column addressing array. The present invention combines a high-frame-rate two-dimensional non-focused wave transmission sequence and a row-column addressing array (RCA) of a least square multi-angle Doppler velocity estimator to achieve three-dimensional ultrasonic vector Doppler imaging; specifically, it includes: acquiring radio frequency data from each tilted non-focused wave transmission, and then performing IQ demodulation, beamforming, and clutter filtering; performing high-frame-rate multi-angle vector Doppler analysis and velocity estimation on the results through RCA; and performing dual-wavelength anti-aliasing processing. The present invention can achieve an imaging speed of more than one thousand frames, significantly improve the sensitivity to low-speed flow and the measurement accuracy of high-speed flow, and has been verified by clinical environment experiments; it is suitable for clinical applications, especially in the dynamic monitoring of blood flow in large blood vessels, and can provide important support for hemodynamic research and clinical diagnosis.

This invention discloses a refined ISAR imaging method based on frequency-modulated plane fitting, belonging to the field of radar signal processing and target imaging technology. This invention can automatically identify and eliminate outliers generated by noise during feature extraction, using only interior points conforming to rigid body motion laws for parameter calculation. Through the established planar constraints, this invention can simultaneously decouple and accurately estimate rotational angular velocity and angular acceleration, solving the problem of inaccurate parameter estimation caused by neglecting geometric constraints between scattering points in traditional methods. Combining the estimated accurate motion parameters, this invention uses the PFA algorithm to replace the traditional range-Doppler imaging algorithm. This not only eliminates azimuth defocus caused by angular acceleration but also effectively corrects cross-range cell movement and image geometric distortion caused by large rotation angles or long accumulation times, significantly improving the spatial resolution and geometric fidelity of the imaging.

The present invention belongs to the technical field of radar detection, and discloses a human action recognition method based on deep learning and ultra-wideband radar, including: obtaining a human action information data set through an ultra-wideband radar module, and performing feature extraction to extract the action features of the target; successively performing range-Doppler imaging, adaptive threshold detection and multi-target segmentation processing on the data of the human action information data set, constructing a three-dimensional feature data set including time, range and velocity, and performing label marking according to the actual occurrence time of each action; dividing the three-dimensional feature data set into a training set and a test set, building a PointNet network model to train and test the network; extracting human action features from the real-time collected radar signals and constructing three-dimensional feature data, and inputting the trained PointNet network model to recognize the action types. The present invention can realize human action classification and recognition with a higher recognition rate, and can be applied in aspects such as physical security and intelligent detection.

The application discloses a kind of based on differential evolution optimization SPWVD's unmanned plane ISAR instantaneous imaging method, it includes the following steps: the received echo signal is carried out distance compression, envelope alignment and phase compensation and obtains the data after processing;The data after processing is replaced by the fast Fourier transform (FFT) in the azimuth direction in distance Doppler algorithm by the time-frequency analysis method such as smooth pseudo-winer distribution (SPWVD), and the initial distance-instantaneous Doppler imaging is obtained, and then the two smooth windows of SPWVD are optimized by differential evolution (DE) algorithm, and imaging again.The inverse synthetic aperture radar algorithm of the present application is improved by introducing the optimization process of differential evolution algorithm SPWVD, and the imaging quality of the mobile target inverse synthetic aperture radar can be effectively improved, so that the target imaging result is clearer, and the entropy value of the imaging diagram is smaller.

The application provides a signal-to-noise ratio robust ISAR imaging method and device based on an HSNet. The method comprises the following steps: obtaining ISAR echo data to be imaged; performing motion compensation and range-Doppler imaging processing on the ISAR echo data to be imaged to obtain a range-Doppler image of original echo; inputting the range-Doppler image of the original echo into a pre-trained HSNet network to output parameter information of a reconstructed ISAR image; obtaining an ISAR imaging result based on the parameter information of the reconstructed ISAR image; and setting a preset loss function of the pre-trained HSNet network as a negative variational lower bound. In the application, the parameter information of the reconstructed ISAR image is obtained through the pre-trained HSNet network, so that the calculation complexity of the existing ISAR imaging problem is reduced; in addition, by setting the preset loss function as the negative variational lower bound, the imaging quality is improved, and the network interpretability is greatly improved.

The ultrasonic imaging device comprises an ultrasonic probe and an operating handle, the ultrasonic probe comprises a sheathing canal, an energy converter arranged in the sheathing canal, a torsion piece at least partially located in the sheathing canal and a connecting piece connecting the torsion piece and the energy converter, and the energy converter comprises a plurality of array elements. The operating handle is connected with the torsion part and used for manually driving the torsion part to twist, and when the torsion part twists, the transducer can be driven to rotate through the connecting part. When the ultrasonic probe is used, the transducer only needs to be manually driven by the operating handle to rotate so as to find the optimal scanning direction, high-speed rotation is not needed, the ultrasonic probe can carry out Doppler imaging, especially Doppler blood flow can be observed, a doctor can carry out clinical diagnosis conveniently, and the cost of a patient can be saved.

The embodiment of the invention provides a Doppler spectrum signal acquisition method and device, electronic equipment and a storage medium. The method is applied to an ultrasonic imaging system, the ultrasonic imaging system comprises an ultrasonic probe, and the method comprises the following steps: determining a target three-dimensional sampling volume; based on the determined target three-dimensional sampling volume, at least three ultrasonic beams received by the ultrasonic probe at the target receiving moment in the Doppler imaging mode are obtained, the at least three ultrasonic beams are ultrasonic beams having intersection with the target three-dimensional sampling volume, and the at least three ultrasonic beams are distributed in a three-dimensional space; and according to an echo signal of at least one sampling point on an effective beam segment of each of the at least three ultrasonic beams, determining a target Doppler spectrum signal at the target receiving moment, the effective beam segment being a beam segment of the corresponding ultrasonic beam located in the target three-dimensional sampling volume. According to the scheme, the target Doppler spectrum signal with a high signal-to-noise ratio and good exclusive OR performance can be obtained.

The present application discloses a non-invasive ultrasonic blood viscosity imaging method, apparatus, device, medium, and product, relating to the field of blood viscosity technology. The method uses a cross-beam-based vector Doppler imaging method to acquire a two-dimensional blood flow velocity vector of the blood vessel to be measured; establishes an incompressible Navier-Stokes equation for describing blood flow and encodes it as a loss function; combines the loss function with a physical information neural network to construct a blood viscosity measurement model; the blood viscosity measurement model includes a first physical information neural network and a second physical information neural network; the two-dimensional spatial coordinates and acquisition time of the two-dimensional blood flow velocity vector are used as the first input data, the two-dimensional spatial coordinates are used as the second input data, and the two-dimensional blood flow velocity in the two-dimensional blood flow velocity vector is used as a label. These are input into the blood viscosity measurement model together, and the blood viscosity is output to form a blood viscosity image of the blood vessel to be measured. The present application can non-invasively image the blood viscosity of the blood vessel.

Methodology of various imaging modalities and engineering features are provided for multispectral soft tissue imaging architecture. The architectural designs comprise hardware of multiple ranges of wavelength for illumination and camera sensing and software for image acquisition, processing, feature abstraction, artificial intelligence-machine learning (AI-ML) analysis, visualization, and reporting. Embodiments of imaging hardware in a medical device can include a light source of multiple bands of wavelength of noncoherent and coherent light for broadband, narrowband, fluorescence, autofluorescence, Laser Speckle Imaging (LSI), Laser Doppler Imaging (LDI), tissue oxygenation imaging, and other variation of soft tissue imaging modalities. The imaging software can include temporally and spatially synchronized acquisition of multiple imaging channels, image processing based on physics principle and mathematical equations of each imaging modality, feature engineering to abstract key parameters, AI-ML training and predictive analysis, image fusion-based visualization and report. The system is designed to be either an addon to smart phones, tablets or independent handheld equipment based on embedded System On Module (SOM).

Various motion artifact reduction and correction methods are provided within multispectral soft tissue imaging architecture. A motion amplitude indication and monitoring strategy is useful before reducing motion and this can be achieved through hardware sensors such as accelerometers, gyroscopes, or software analysis such as image registration, optics flow. Large and medium level motion such as device shaking, and target breathing can be resolved through image stabilization and snapshot approach by only using a time interval where motion is minimum. Small and micro motion such as device vibration can be resolved through motion correction by identifying the mathematical correlation between velocity magnitude and signal to noise ratio (SNR) or baseline normalization by using a standard reflection marker. Sources of the motion need to be taken into consideration such as intrinsic motion from the target or extrinsic motion from the device. The present inventive concept can apply to broadband, narrowband, fluorescence, autofluorescence, Laser Speckle Imaging (LSI), Laser Doppler Imaging (LDI), tissue oxygenation imaging, and other variation of soft tissue imaging modalities. The imaging software includes temporally and spatially synchronized acquisition of motion amplitude, multiple imaging channels, image processing based on physics principle and mathematical equations of each imaging modality, motion reduction and correction, image fusion-based visualization and report. The system is designed to be an addon to smart phones, tablets, and other mobile devices as portable equipment.

The invention provides a living body detection technical method and system based on multi-channel MIMO radar near-field three-dimensional Doppler imaging and a storage medium. The system collects multiple frames of echoes and performs near-field imaging, constructs a cross-frame time sequence for the same pixel position and performs time direction FFT to obtain a pixel-level Doppler spectrum; and determining a living body area and outputting an alarm by taking the zero frequency point amplitude of the Doppler spectrum and the joint relationship between the maximum value and the mean value in the frequency band after the zero frequency point is removed as a criterion. According to the scheme, the motility replaces the shape to serve as the main criterion, parallel processing is combined with the MIMO virtual aperture and the assembly line, high resolution, low false alarm and real-time alarm are achieved, and the method is suitable for scenes such as security check, post check and logistics.

This application provides a radar space target echo processing method based on interferometric imaging and beamforming, comprising: performing interferometric imaging on the space target to obtain the position of the space target in the radar field of view; adjusting the digital beamforming direction to obtain narrow-beam high signal-to-noise ratio echo data; using a range-Doppler algorithm to obtain an image map of a partial area of ​​the space target surface at this time; adjusting the beam direction according to the interferometric imaging map to complete the next interferometric imaging and direction adjustment to obtain image maps of the space target surface in other areas; obtaining multiple range-Doppler imaging maps by adjusting the beam direction multiple times; and obtaining a complete high signal-to-noise ratio radar image map of the space target through scattering point fusion. The advantages of this application are: single-detection imaging, low complexity, high reliability, and high signal-to-noise ratio, while also having the advantage of low system operating cost. It can be widely applied to radar detection and imaging where the beamwidth is too narrow to cover large-sized targets.

A marker is localized using ultrasound imaging. Ultrasound video stream data are received with a computer system. The ultrasound video stream data are representative of ultrasound data acquired from a subject using an ultrasound system using Doppler imaging. Color image data are extracted from the ultrasound video stream data based on a color model. Marker position data are determined based on values of a color model component in the color image data. The marker position data are output using the computer system.

The application relates to the technical field of laser radar, in particular to a multi-channel synthetic aperture laser radar imaging method and system based on motion compensation, which comprises the following steps: acquiring echo data of multiple receiving channels; performing distance pre-processing on the echo data to obtain multi-channel echo data focused in the distance direction; setting a tentative speed based on the multi-channel echo data and calculating corresponding azimuth ambiguity signal ratio (AASR); performing MAASR search in a preset speed range to determine a target radial velocity true value; constructing a motion compensation phase factor according to the target radial velocity true value and performing phase correction processing on the multi-channel echo data; performing multi-channel spectrum reconstruction, space-time adaptive processing, full-bandwidth spectrum splicing and distance Doppler imaging processing on the multi-channel echo data after phase correction, and outputting a high-resolution wide-surveying-band image. The application can maintain correct phase relationships among multi-channel echoes in the presence of target motion influence, and realize stable and reliable imaging.

An ultrasonic imaging device and an ultrasonic imaging method, the device comprising a transmitting and receiving circuit, an ultrasonic probe, a processor, and a display, wherein the transmitting and receiving circuit controls the ultrasonic probe to transmit a first ultrasonic wave to a portion of a target object where nerve block is to be performed in a grayscale imaging mode; the processor generates an ultrasonic image of the portion where nerve block is to be performed based on the first ultrasonic echo data, identifies a neurovascular region in the ultrasonic image, and obtains the position of a sampling frame including the neurovascular region; the transmitting and receiving circuit also controls the ultrasonic probe to transmit a second ultrasonic wave to the position of the sampling frame in a Doppler imaging mode; the processor also obtains blood flow information based on the second ultrasonic echo data, obtains a vascular region in the ultrasonic image based on the blood flow information, obtains a nerve region in the ultrasonic image based on the neurovascular region and the vascular region, and controls the display to display the ultrasonic image, wherein the nerve region and the vascular region are highlighted so as to be distinguishable from each other on the ultrasonic image.

The invention discloses a Doppler imaging method and device based on Spearman rank correlation and a medium. The method comprises the following steps: acquiring beam forming radio frequency data generated in a Doppler imaging process of a target area; calculating a signal power diagram and a noise power diagram of the beam forming radio frequency data; and inputting the signal power diagram and the noise power diagram into an optimized and trained noise coefficient adjustment network, outputting a pixel-level noise coefficient to correct the beam synthesis radio frequency data, and obtaining an enhanced image of the target area. The network loss function comprises Spearman rank correlation loss which is used for maximizing the Spearman rank correlation between noise coefficient adjustment network output and 1-gCF; the signal power constraint loss is used for maximizing the original beam forming radio frequency data intensity reserved by the imaging result of the area specified by the gCF; gCF is a generalized coherence factor. According to the method, the noise suppression capability and the signal retention capability during complex tissue Doppler imaging are optimized, and the imaging effect is improved.