Ultrasonic imaging method and ultrasonic imaging system

Abstract

The invention discloses an ultrasonic imaging method and an ultrasonic imaging system, and the method comprises the steps: transmitting a plurality of groups of ultrasonic waves to a target tissue, and receiving ultrasonic echoes returned from the target tissue, so as to obtain a plurality of groups of first echo signals; generating a first ultrasonic image data sequence according to the multiple groups of first echo signals, wherein the first ultrasonic image data sequence comprises multiple frames of first ultrasonic image data; the first ultrasonic image data sequence is input into a trained neural network to obtain a second ultrasonic image data sequence, and the frame rate of the second ultrasonic image data sequence is higher than that of the first ultrasonic image data sequence; and outputting the second ultrasonic image data sequence. According to the invention, the frame rate of ultrasonic imaging can be improved while the quality of ultrasonic image data is ensured.

Description

Technical Field

[0001] The present invention relates to the field of ultrasonic imaging technology, and more particularly to an ultrasonic imaging method and an ultrasonic imaging system. Background Art

[0002] Ultrasonic imaging is a medical imaging method that uses ultrasonic waves as an information carrier to detect, display, and diagnose human tissues and organs. Ultrasonic imaging is often used to determine the position, size, and shape of organs, determine the scope and physical properties of lesions, provide anatomical diagrams of some glands, and distinguish the normality and abnormality of fetuses. It has a wide range of applications in ophthalmology, obstetrics and gynecology, as well as the cardiovascular system, digestive system, urinary system, etc.

[0003] The quality of ultrasonic images is crucial for doctors' diagnosis. On the premise of ensuring the quality of ultrasonic images, the temporal resolution of ultrasonic images has become an increasingly important issue to consider. Improving the temporal resolution of ultrasonic images is particularly important in imaging tissues with obvious movement such as cardiac ultrasound. Since the heart is a beating tissue that beats about 60 times per second, if the frame rate is too low, phenomena such as motion artifacts in its images will be very obvious. That is to say, to obtain the structural information of the heart, a high frame rate is an inevitable requirement.

[0004] Currently, in cardiac ultrasound, the temporal resolution is mainly improved by sacrificing a certain image quality and reducing the number of transmissions. Obviously, the cost of this sacrifice is huge. Therefore, how to achieve high-image-quality imaging without sacrificing the temporal resolution has become an urgent problem to be solved. Summary of the Invention

[0005] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further elaborated in the Detailed Description section. The Summary of the Invention section of the present invention does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the protection scope of the claimed technical solution.

[0006] An embodiment of the present invention provides an ultrasonic imaging method, the method comprising:

[0007] Transmitting multiple groups of first ultrasonic waves to a target tissue, and receiving ultrasonic echoes returned from the target tissue to obtain multiple groups of first echo signals;

[0008] Generating a first ultrasonic image data sequence according to the multiple groups of first echo signals, the first ultrasonic image data sequence including multiple frames of first ultrasonic image data;

[0009] Input the first ultrasonic image data sequence into a trained neural network to obtain a second ultrasonic image data sequence, where the frame rate of the second ultrasonic image data sequence is higher than that of the first ultrasonic image data sequence;

[0010] Wherein, the neural network is trained with a third ultrasonic image data sequence as the input data set and a fourth ultrasonic image data sequence as the target data set, and the frame rate of the fourth ultrasonic image data sequence is higher than that of the third ultrasonic image data sequence;

[0011] Output the second ultrasonic image data sequence.

[0012] In one embodiment, the third ultrasonic image data sequence is constructed by extracting part of the ultrasonic image data from the fourth ultrasonic image data sequence.

[0013] In one embodiment, the third ultrasonic image data sequence is constructed by interpolating the fourth ultrasonic image data sequence, or the fourth ultrasonic image data sequence is constructed by interpolating the third ultrasonic image data sequence.

[0014] In one embodiment, the number of emission positions of the first ultrasonic wave is greater than the number of emission positions specified by the Nyquist spatial sampling law, and the receiving line density of the first echo signal is greater than the receiving line density specified by the Nyquist spatial sampling law.

[0015] In one embodiment, generating multiple frames of first ultrasonic image data according to the multiple groups of first echo signals includes:

[0016] Processing the first echo signal by using at least one of the following algorithms to obtain the first ultrasonic image data: delay summation algorithm, adaptive algorithm, and iterative algorithm.

[0017] Another aspect of the embodiments of the present invention provides an ultrasonic imaging method, and the method includes:

[0018] Transmit multiple groups of first ultrasonic waves to a target tissue, and receive ultrasonic echoes returned from the target tissue to obtain a first echo signal sequence, where the first echo signal sequence includes multiple groups of first echo signals, and each group of first echo signals corresponds to one frame of ultrasonic image data;

[0019] Input the first echo signal sequence into a trained neural network to obtain a second echo signal sequence, where the frame rate of the ultrasonic image data sequence corresponding to the second echo signal sequence is higher than that of the ultrasonic image data sequence corresponding to the first echo signal sequence,

[0020] Among them, the neural network is trained with the third echo signal sequence as the input data set and the fourth echo signal sequence as the target data set. The frame rate of the ultrasonic image data sequence corresponding to the fourth echo signal sequence is higher than that of the ultrasonic image data sequence corresponding to the third echo signal;

[0021] Generate an ultrasonic image data sequence according to the second echo signal sequence and output the ultrasonic image data sequence.

[0022] In one embodiment, the third echo signal sequence is constructed by extracting some echo signals from the fourth echo signal sequence.

[0023] In one embodiment, the third echo signal sequence is constructed by interpolating the fourth echo signal sequence, or the fourth echo signal sequence is constructed by interpolating the third echo signal sequence.

[0024] In one embodiment, the number of emission positions of the first ultrasonic wave is greater than the number of emission positions specified by the Nyquist spatial sampling law, and the receiving line density of the first echo signal is greater than the receiving line density specified by the Nyquist spatial sampling law.

[0025] Another aspect of the embodiments of the present invention provides an ultrasonic imaging system, including:

[0026] An ultrasonic probe;

[0027] A transmitting circuit for exciting the ultrasonic probe to emit ultrasonic waves towards a target tissue;

[0028] A receiving circuit for controlling the ultrasonic probe to receive the echo signal of the ultrasonic wave;

[0029] A processor for executing the ultrasonic imaging method as described above to generate an ultrasonic image;

[0030] A display for displaying the ultrasonic image.

[0031] The ultrasonic imaging method and the ultrasonic imaging system of the embodiments of the present invention input the actually collected first ultrasonic image data sequence into a neural network, and increase the frame rate of the ultrasonic image data sequence through the neural network, which can avoid reducing the quality of the ultrasonic image while improving the imaging frame rate. Description of the Drawings

[0032] The embodiments of the present invention will be described in more detail by combining the accompanying drawings. The above and other objects, features, and advantages of the present invention will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0033] Figure 1 A structural block diagram of an ultrasonic imaging system according to an embodiment of the present invention is shown;

[0034] Figure 2 A schematic flow chart of an ultrasonic imaging method according to an embodiment of the present invention is shown;

[0035] Figure 3 A schematic principle diagram of an ultrasonic imaging method according to an embodiment of the present invention is shown;

[0036] Figure 4 A schematic flow chart of an ultrasonic imaging method according to another embodiment of the present invention is shown. Detailed implementation manners

[0037] In order to make the objectives, technical solutions, and advantages of the present invention more obvious, exemplary embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited by the exemplary embodiments described herein. Based on the embodiments of the present invention described in the present invention, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present invention.

[0038] In the following description, numerous specific details are given to provide a more thorough understanding of the present invention. However, it is obvious to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features well known to those skilled in the art are not described.

[0039] It should be understood that the present invention can be implemented in different forms and should not be construed as limited to the embodiments presented herein. On the contrary, providing these embodiments will make the disclosure thorough and complete, and will fully convey the scope of the present invention to those skilled in the art.

[0040] The purpose of the terms used herein is only to describe specific embodiments and is not a limitation of the present invention. As used herein, the singular forms "a", "an" and "the" are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms "comprising" and / or "including", when used in this specification, determine the presence of the stated features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups. As used herein, the term "and / or" includes any and all combinations of the related listed items.

[0041] To thoroughly understand the present invention, detailed structures will be presented in the following description to illustrate the technical solutions proposed by the present invention. The alternative embodiments of the present invention are described in detail below. However, in addition to these detailed descriptions, the present invention may also have other embodiments.

[0042] Next, first refer to Figure 1 Describe an ultrasonic imaging system according to an embodiment of the present invention. Figure 1 Fig. 100 shows a schematic structural block diagram of an ultrasonic imaging system 100 according to an embodiment of the present invention.

[0043] As Figure 1 shown, the ultrasonic imaging system 100 includes an ultrasonic probe 110, a transmitting circuit 112, a receiving circuit 114, a processor 116, and a display 118. Further, the ultrasonic imaging system may also include a transmit / receive selection switch 120 and a beam synthesis module 122. The transmitting circuit 112 and the receiving circuit 114 may be connected to the ultrasonic probe 110 through the transmit / receive selection switch 120.

[0044] The ultrasonic probe 110 includes a plurality of transducer array elements. The plurality of transducer array elements may be arranged in a row to form a linear array, or arranged in a two-dimensional matrix to form a planar array. The plurality of transducer array elements may also form a convex array. The transducer array elements are used to emit ultrasonic waves according to the excitation electrical signals, or convert the received ultrasonic waves into electrical signals. Therefore, each transducer array element can be used to realize the mutual conversion between electrical pulse signals and ultrasonic waves, so as to emit ultrasonic waves to the tissue in the target area of the object to be measured, and can also be used to receive the ultrasonic echoes reflected by the tissue.

[0045] During ultrasonic imaging, it is possible to control which transducer array elements are used to emit ultrasonic waves and which transducer array elements are used to receive ultrasonic waves through the transmit sequence and the receive sequence, or control the transducer array elements to be used to emit ultrasonic waves or receive the echoes of ultrasonic waves in time slots. The transducer array elements participating in the ultrasonic wave emission can be simultaneously excited by electrical signals to emit ultrasonic waves simultaneously; or, the transducer array elements participating in the ultrasonic beam emission can also be excited by several electrical signals with a certain time interval to continuously emit ultrasonic waves with a certain time interval.

[0046] During the ultrasonic imaging process, the transmitting circuit 112 generates a transmission sequence according to the control of the processor 116. The transmission sequence is used to control some or all of the multiple transducer elements to transmit ultrasonic waves to the target tissue. The transmission sequence parameters include the number of transducer element positions for transmission and the ultrasonic beam transmission parameters, such as amplitude, frequency, number of transmissions, transmission interval, transmission angle, waveform, focusing position, etc. In some cases, the transmitting circuit 112 is also used to perform phase delay on the transmitted beam so that different transducer elements transmit ultrasonic waves at different times, so that each transmitted ultrasonic beam can be focused in a predetermined region of interest. The transmission sequence parameters corresponding to different imaging modes may be different. After the echo signal is received by the receiving circuit 114 and processed by subsequent modules and corresponding algorithms, ultrasonic images of different imaging modes can be generated.

[0047] The receiving circuit 114 may include one or more amplifiers, analog-to-digital converters, etc. The amplifier is used to amplify the received echo signal after appropriate gain compensation, and the analog-to-digital converter is used to sample the analog echo signal at a predetermined time interval, thereby converting it into a digital signal. The digitized echo signal still retains amplitude information, frequency information, and phase information. The receiving circuit 114 sends the echo signal to the beam synthesis module 122 for processing.

[0048] The beam synthesis module 122 performs processing such as focusing delay, weighting, and channel summation on the echo signal, and then sends it to the processor 116. The processor 116 performs processing such as signal detection, signal enhancement, data conversion, and logarithmic compression on the echo signal to form an ultrasonic image. The ultrasonic image obtained by the processor 116 can be displayed on the display 118 or stored in the memory 124.

[0049] Optionally, the processor 116 can be implemented as software, hardware, firmware, or any combination thereof, and can use a single or multiple application specific integrated circuits (ASICs), a single or multiple general integrated circuits, a single or multiple microprocessors, a single or multiple programmable logic devices, or any combination of the foregoing circuits and / or devices, or other suitable circuits or devices. Moreover, the processor 116 can control other components in the ultrasonic imaging system 100 to perform the corresponding steps of the methods in the various embodiments of this specification.

[0050] The display 118 is connected to the processor 116. The display 118 can be a touch display screen, a liquid crystal display screen, etc.; or, the display 118 can be an independent display such as a liquid crystal display or a television outside the ultrasonic imaging system 100; or, the display 118 can be the display screen of an electronic device such as a smart phone or a tablet computer, etc. Among them, the number of displays 118 can be one or more.

[0051] The display 118 can display the ultrasonic image obtained by the processor 116. In addition, while displaying the ultrasonic image, the display 118 can also provide a graphical interface for the user to perform human-computer interaction. One or more controlled objects are set on the graphical interface, and the user is provided with a human-computer interaction device to input operation instructions to control these controlled objects, so as to execute corresponding control operations. For example, an icon is displayed on the graphical interface, and the icon can be operated by using the human-computer interaction device to perform a specific function, such as drawing a region of interest box on the ultrasonic image, etc.

[0052] Optionally, the ultrasonic imaging system 100 can also include other human-computer interaction devices other than the display 118, which are connected to the processor 116. For example, the processor 116 can be connected to the human-computer interaction device through an external input / output port. The external input / output port can be a wireless communication module, a wired communication module, or a combination of both. The external input / output port can also be implemented based on USB, bus protocols such as CAN, and / or wired network protocols, etc.

[0053] Among them, the human-computer interaction device can include an input device for detecting the input information of the user. The input information can be, for example, a control instruction for the ultrasonic emission / reception timing, an operation input instruction for drawing points, lines or boxes on the ultrasonic image, or other instruction types can also be included. The input device can include one or a combination of multiple of a keyboard, a mouse, a roller, a trackball, a mobile input device (such as a mobile device with a touch display screen, a mobile phone, etc.), a multi-functional knob, etc. The human-computer interaction device can also include an output device such as a printer.

[0054] The ultrasonic imaging system 100 can also include a memory 124 for storing instructions executed by the processor, storing received ultrasonic echoes, storing ultrasonic images, etc. The memory can be a flash memory card, a solid-state memory, a hard disk, etc. It can be a volatile memory and / or a non-volatile memory, a removable memory and / or a non-removable memory, etc.

[0055] It should be understood that Figure 1 The components included in the illustrated ultrasonic imaging system 100 are only schematic, and it can include more or fewer components. The present invention is not limited thereto.

[0056] Next, reference will be made to Figure 2 describe an ultrasonic imaging method according to an embodiment of the present invention. Figure 2 FIG. 200 is a schematic flowchart of an ultrasonic imaging method according to an embodiment of the present invention.

[0057] As Figure 2 shown, the ultrasonic imaging method 200 according to an embodiment of the present invention includes the following steps:

[0058] In step S210, a plurality of groups of ultrasonic waves are emitted to a target tissue, and ultrasonic echoes returned from the target tissue are received to obtain a plurality of groups of first echo signals;

[0059] In step S220, a first ultrasonic image data sequence is generated according to the plurality of groups of first echo signals, and the first ultrasonic image data sequence includes a plurality of frames of first ultrasonic image data;

[0060] In step S230, the first ultrasonic image data sequence is input into a trained neural network to obtain a second ultrasonic image data sequence, and the frame rate of the second ultrasonic image data sequence is higher than the frame rate of the first ultrasonic image data sequence.

[0061] wherein, the neural network is trained with a third ultrasonic image data sequence as an input data set and a fourth ultrasonic image data sequence as a target data set, and the frame rate of the fourth ultrasonic image data sequence is higher than the frame rate of the third ultrasonic image data sequence;

[0062] In step S240, the second ultrasonic image data sequence is output.

[0063] The ultrasonic imaging method 200 according to an embodiment of the present invention inputs the actually acquired first ultrasonic image data sequence into a neural network, and the neural network increases the frame rate of the ultrasonic image data sequence, which can improve the imaging frame rate and avoid reducing the quality of the ultrasonic image at the same time.

[0064] Specifically, in step S210, a plurality of groups of ultrasonic waves are emitted to a target tissue, and ultrasonic echoes returned from the target tissue are received to obtain a plurality of groups of first echo signals. Among them, each group of first echo signals is used to generate a frame of ultrasonic image, and the plurality of groups of ultrasonic waves are used for real-time ultrasonic imaging of the target tissue. The target tissue includes but is not limited to the heart.

[0065] Referring to Figure 1 the ultrasonic imaging system, the transmitting circuit generates a transmitting waveform, which is applied to one or more elements in the ultrasonic probe to form a transmitting beam. The transmit / receive selection switch controls the element to switch between transmit and receive. After the transmission is completed, it is switched to the receive state. After the ultrasonic wave propagates to the imaging area, it is scattered by the target tissue. At the same time, the element is switched to the receive state and receives the first echo signal returned from the target tissue.

[0066] Next, in step S220, signal processing is performed on the first echo signal to obtain a first ultrasonic image data sequence. The first ultrasonic image data sequence includes multiple frames of first ultrasonic image data, and each group of first echo signals is used to generate one frame of first ultrasonic image data. Generally, front-end processing includes links such as signal amplification, analog-to-digital conversion, and reception coherent synthesis. Then, back-end signal processing is performed, which generally includes envelope detection, logarithmic compression, spatial smoothing, and other signal processing links. As the transmitting line and receiving line change, the above processing is repeated multiple times to complete the scanning of one frame of the image, thereby obtaining one frame of ultrasonic image data. The ultrasonic imaging method according to the embodiment of the present invention can be used for tissue imaging, and can also be applied to the Doppler imaging mode and other imaging modes; it can be applied to conventional two-dimensional ultrasonic imaging, and can also be applied to three-dimensional ultrasonic imaging.

[0067] Usually, when performing ultrasonic imaging at positions such as the heart, it is necessary to balance image quality and resolution. However, since the frame rate will be increased by a neural network in the embodiment of the present invention, therefore, an imaging method with high quality and low frame rate can be adopted to generate the first ultrasonic image. Among them, methods such as increasing the number of transmitting positions, increasing the receiving line density, increasing the number of transmissions, harmonic imaging, and adopting complex imaging algorithms can be used to improve the image quality of the first ultrasonic image.

[0068] Exemplarily, increasing the number of transmitting positions and the receiving line density includes: making the number of transmitting positions of the first echo signal greater than the number of transmitting positions specified by the Nyquist spatial sampling law, and making the receiving line density of the first echo signal greater than the receiving line density specified by the Nyquist spatial sampling law.

[0069] Among them, the Nyquist spatial sampling law describes the minimum sampling frequency required for sampling a continuous signal in the spatial domain. The core idea of the Nyquist spatial sampling law is that the spectrum of the signal is limited. If sampling is performed at a sampling frequency lower than twice its highest frequency, aliasing will occur, resulting in the signal being unable to be accurately reconstructed. Therefore, for an image, in order to avoid aliasing and meet the resolution requirements, it is necessary to satisfy the repetition pitch 1 / x > 2fx, where x is the point pitch, that is, the receiving line pitch, and (-fx, fx) is the image horizontal frequency range.

[0070] Exemplarily, generating multiple frames of first ultrasonic image data using a complex imaging algorithm includes: processing the first echo signal using at least one of an adaptive algorithm and an iterative algorithm to obtain the first ultrasonic image data. Among them, the adaptive imaging method, namely the adaptive beamforming method, taking the minimum variance (MV) method as an example, mainly considers the ratio of noise and useful signals in the signal, and then calculates different weights to achieve the purpose of suppressing noise and interference. The weight calculation amount of this algorithm is very large and time-consuming, and it is usually not applicable to real-time ultrasonic imaging. The iterative algorithm usually calculates the image data by inversely solving the wave equation. It takes into account physical processes such as refraction and reflection of ultrasonic propagation, and has a relatively high accuracy, but also has problems of large calculation amount and serious time consumption. Since the embodiment of the present invention reduces the requirement for the frame rate of the first ultrasonic image data, complex imaging algorithms such as the above-mentioned adaptive algorithm and iterative algorithm can be used to generate the first ultrasonic image data to improve the quality of the first ultrasonic image data.

[0071] In addition, the traditional delay-and-sum algorithm can also be used to generate the first ultrasonic image data. The delay-and-sum algorithm delays the echo signals received by each array element and then superimposes them to obtain the echo signal of each imaging point, thereby achieving the focusing effect. This algorithm makes a linear approximation of ultrasonic propagation and does not consider physical processes such as refraction and reflection, and has the advantage of fast calculation speed.

[0072] In step S230, as Figure 3 shown, input the first ultrasonic image data sequence into the trained neural network to obtain a second ultrasonic image data sequence, and the frame rate of the second ultrasonic image data sequence is higher than that of the first ultrasonic image data sequence. Exemplarily, the second ultrasonic image data sequence includes multiple frames of second ultrasonic image data, and the number of frames of the second ultrasonic image data is greater than that of the first ultrasonic image data.

[0073] The neural network of the embodiment of the present invention is used to increase the number of frames of ultrasonic image data and improve the frame rate of ultrasonic image data. The ultrasonic imaging system obtains multiple frames of first ultrasonic image data using low-frame-rate and high-quality imaging parameters. Although the actually obtained first ultrasonic image data sequence has relatively high image quality, its frame rate is low, which cannot meet the requirement for time resolution in application scenarios such as cardiac ultrasound where tissue movement speed is relatively fast. After increasing the number of frames of ultrasonic image data through the neural network, the finally obtained second ultrasonic image data sequence not only has relatively high image quality but also has a relatively high frame rate. Moreover, compared with estimating the images between frames by interpolation, using the neural network to obtain the second ultrasonic image sequence has a faster calculation speed, higher accuracy, and a wider applicable range.

[0074] In one embodiment, the second ultrasonic image data includes multiple frames of the first ultrasonic image data and includes multiple frames of newly created ultrasonic image data. In Figure 3 the example, the first ultrasonic image data sequence includes F1, F2, and F3, and the second ultrasonic image data sequence includes F1, F1.5, F2, F2.5, and F3. Among them, F1, F2, and F3 are the first ultrasonic image data, and F1.5 and F2.5 are the newly created ultrasonic image data. The neural network adds one frame of ultrasonic image data between every two adjacent frames of the first ultrasonic image data, thereby increasing the frame rate of the second ultrasonic image data sequence.

[0075] Specifically, the neural network can add at least one frame of newly created ultrasonic image data between every two adjacent frames of the first ultrasonic image data. The newly created ultrasonic image data has an image quality similar to that of the first ultrasonic image data. The number of frames of the newly created ultrasonic image data between every two adjacent frames of the first ultrasonic image data can be the same. For example, the neural network can add two frames of newly created ultrasonic image data between every two adjacent frames of the first ultrasonic image data, or add one frame of newly created ultrasonic image data between every two adjacent frames of the first ultrasonic image data. Or, the number of frames of the newly created ultrasonic image data between every two frames of the first ultrasonic image data can be different. For example, when the tissue movement is fast, the number of frames of the newly created ultrasonic image data between every two adjacent frames of the first ultrasonic image data can be adaptively increased, thereby improving the time resolution of the ultrasonic image data sequence. The number of frames of the newly created ultrasonic image data between every two adjacent frames of the first ultrasonic image data can be determined according to the gap between the frame rate of the first ultrasonic image and the required frame rate.

[0076] In another embodiment, there may also be no inclusion relationship between the second ultrasonic image data and the first ultrasonic image data, that is, each frame of the second ultrasonic image data is data reconstructed by the neural network according to the first ultrasonic image data. For example, the first ultrasonic image data sequence includes F1, F2, and F3, and the second ultrasonic image data sequence includes F4, F5, F6, F7, and F8. The neural network integrates and reconstructs multiple frames of the first ultrasonic image data to obtain more frames of the second ultrasonic image data, thereby increasing the frame rate of the second ultrasonic image data sequence. Obtaining multiple frames of the second ultrasonic image data through reconstruction can make the distribution of the multiple frames of the second ultrasonic image data more uniform and closer to the real imaging effect.

[0077] The neural network according to the embodiments of the present invention is trained with the third ultrasonic image data sequence as the input data set and the fourth ultrasonic image data sequence as the target data set, and the frame rate of the fourth ultrasonic image data sequence is higher than that of the third ultrasonic image data sequence. Exemplarily, the third ultrasonic image data sequence includes multiple frames of third ultrasonic image data, the fourth ultrasonic image data sequence includes multiple frames of fourth ultrasonic image data, and the number of frames of the fourth ultrasonic image data is greater than that of the third ultrasonic image data. By selecting a suitable neural network architecture and through continuous iteration, after the data in the third ultrasonic image data sequence is input into the neural network, the data output by the neural network continuously approaches the corresponding data in the fourth ultrasonic image data sequence. When the error is less than the set value, the training is completed. The finally trained neural network can output a second ultrasonic image data sequence with a higher frame rate after obtaining the first ultrasonic image sequence, thereby improving the frame rate without sacrificing image quality. Exemplarily, the neural network includes, but is not limited to, convolutional neural network, recurrent neural network, adversarial neural network, and attention neural network, etc.

[0078] In one embodiment, the third ultrasonic image data sequence for training the neural network is constructed by extracting some ultrasonic image data from the fourth ultrasonic image data sequence. That is, first, ultrasonic imaging is performed by using a low frame rate and high-quality imaging method to obtain the fourth ultrasonic image data sequence, and the fourth ultrasonic image data sequence includes multiple frames of fourth ultrasonic image data.

[0079] Since the role of the fourth ultrasonic image data sequence is to train the neural network rather than to perform clinical diagnosis in real time, methods such as increasing the number of emission positions, the number of emissions, harmonics, and using complex imaging algorithms can be adopted to improve the image quality of the fourth ultrasonic image data without considering the imaging frame rate. Exemplarily, the number of emission positions corresponding to the fourth ultrasonic image data is greater than the number of emission positions specified by the Nyquist spatial sampling law, and the receiving line density is greater than the receiving line density specified by the Nyquist spatial sampling law. The imaging algorithms corresponding to the fourth ultrasonic image data include delay summation algorithms, adaptive algorithms, and iterative algorithms, etc. Then, a part of the ultrasonic image data is extracted from the fourth ultrasonic image data sequence to obtain a third ultrasonic image data sequence, and the ultrasonic image data extracted from the fourth ultrasonic image data sequence can be referred to as the third ultrasonic image data. When extracting the third ultrasonic image data, frame extraction can be performed at equal intervals. For example, one frame is extracted every two frames or one frame is extracted every three frames, etc.; alternatively, frame extraction can also be performed at unequal intervals. During the process of training the neural network using the third ultrasonic image data sequence and the fourth ultrasonic image data sequence, after inputting multiple frames of the third image data into the neural network, the image data output by the neural network continuously approaches the actually collected fourth ultrasonic image data. Since the third ultrasonic image data and the fourth ultrasonic image data are continuously collected ultrasonic image data, therefore, when actually applying the neural network to improve the frame rate, the second ultrasonic image data sequence output by the neural network is also closer to the actually collected ultrasonic image data.

[0080] In another embodiment, the fourth ultrasonic image data sequence can be constructed by interpolating the third ultrasonic image data sequence. For example, after collecting multiple frames of the third ultrasonic image data to form a third ultrasonic image sequence, at least one frame of ultrasonic image data is newly created by image interpolation between every two frames of the third ultrasonic image data. The third ultrasonic image data and the newly created ultrasonic image data by interpolation together constitute the fourth ultrasonic image data. Or, if the number of frames of the newly created ultrasonic image data by interpolation is greater than the number of frames of the third ultrasonic image data, the fourth ultrasonic image data can also only include the newly created ultrasonic image data and not include the original third ultrasonic image data.

[0081] Optionally, the third ultrasonic image data sequence can also be constructed by interpolating the fourth ultrasonic image data sequence. For example, newly created ultrasonic image data is obtained by interpolating based on every two frames of the fourth ultrasonic image data sequence, and the newly created ultrasonic image data is used as the third ultrasonic image data, so that the number of frames of the third ultrasonic image data is less than the number of frames of the fourth ultrasonic image data.

[0082] Finally, in step S240, the second ultrasonic image data sequence is output. Specifically, a dynamic ultrasonic image is displayed in real time on the display of the ultrasonic imaging system according to the second ultrasonic image data sequence.

[0083] The ultrasonic imaging method 200 according to the embodiment of the present invention acquires multiple frames of first ultrasonic image data in a high-quality and low-frame-rate manner, and inputs the actually acquired multiple frames of first ultrasonic image data into a neural network. The neural network increases the number of frames of the ultrasonic image data, and can avoid reducing the quality of the ultrasonic image while increasing the frame rate of the ultrasonic image.

[0084] On the other hand, an embodiment of the present invention provides an ultrasonic imaging method, referring to Figure 4 , the ultrasonic imaging method 400 includes the following steps:

[0085] In step S410, multiple groups of ultrasonic waves are emitted to a target tissue, and ultrasonic echoes returned from the target tissue are received to obtain a first echo signal sequence. The first echo signal sequence includes multiple groups of first echo signals, and each group of first echo signals corresponds to a frame of ultrasonic image data;

[0086] In step S420, the first echo signal sequence is input into a trained neural network to obtain a second echo signal sequence. The frame rate of the ultrasonic image data sequence corresponding to the second echo signal sequence is higher than the frame rate of the ultrasonic image data sequence corresponding to the first echo signal sequence.

[0087] Wherein, the neural network is trained with a third ultrasonic image data sequence as an input data set and a fourth ultrasonic image data sequence as a target data set. The frame rate of the ultrasonic image data sequence corresponding to the fourth echo signal sequence is higher than the frame rate of the ultrasonic image data sequence corresponding to the third echo signal.

[0088] In step S430, an ultrasonic image data sequence is generated according to the second echo signal sequence, and the ultrasonic image data sequence is output.

[0089] The ultrasonic imaging method 400 according to the embodiments of the present invention is similar to the ultrasonic imaging method 200 described above. It also performs ultrasonic imaging in a high-quality and low-frame-rate manner to ensure the quality of ultrasonic images, and improves the imaging frame rate through a neural network. The difference is that the neural network in this embodiment acts on the first echo signal sequence in the signal domain and outputs a second echo signal sequence, and the second echo signal sequence includes multiple groups of second echo signals. The first echo signal or the second echo signal can be an RF (radio frequency) signal or an IQ signal (i.e., a baseband signal). Briefly, the RF signal is the echo signal before quadrature demodulation, and the IQ signal is the echo signal after quadrature demodulation. After quadrature demodulation, the echo signal is divided into two mutually orthogonal I and Q signals, where I and Q represent in-phase and quadrature respectively, and the two signals mainly retain the low-frequency part of the original signal. In contrast, the first ultrasonic image data in the above text is data in the image domain, which can be data after envelope detection or data after logarithmic compression, etc.

[0090] Since the neural network in this embodiment acts on the signal domain, therefore, the third ultrasonic image data sequence used to train the neural network contains multiple groups of third echo signals, and the fourth ultrasonic image data sequence contains multiple groups of fourth echo signals. The third echo signal and the fourth echo signal can also be an RF signal or an IQ signal. Exemplarily, the third echo signal sequence is constructed by extracting third echo signals from the fourth echo signal sequence, that is, ultrasonic imaging can be performed on the target tissue to obtain multiple groups of fourth echo signals as the fourth echo signal sequence, and some of the fourth echo signals are extracted as the third echo signal sequence, and the extracted fourth echo signals are the third echo signals. Exemplarily, when extracting the third echo signal, an equally spaced extraction method can be used, that is, the number of groups of echo signals extracted between every two adjacent groups of fourth echo signals is equal. In other embodiments, the third echo signal sequence can also be constructed by interpolating the fourth echo signal sequence, or the fourth echo signal sequence can be constructed by interpolating the third echo signal sequence.

[0091] When obtaining the first echo signal, a high-quality and low-frame-rate imaging method can be adopted, specifically including increasing the number of transmit positions, increasing the receive line density, increasing the number of transmissions, etc. Exemplarily, the number of transmit positions of the first echo signal is greater than the number of transmit positions specified by the Nyquist spatial sampling law, and the receive line density of the first echo signal is greater than the receive line density specified by the Nyquist spatial sampling law. Similarly, the number of transmit positions of the third echo signal and the fourth echo signal is greater than the number of transmit positions specified by the Nyquist spatial sampling law, and the receive line density of the third echo signal and the fourth echo signal is greater than the receive line density specified by the Nyquist spatial sampling law.

[0092] Finally, generate an ultrasonic image data sequence according to the second echo signal sequence and output the ultrasonic image data sequence. Specifically, generate one frame of ultrasonic image data according to each group of second echo signals, and obtain an ultrasonic image data sequence composed of multiple frames of ultrasonic image data and output it.

[0093] The ultrasonic imaging method 400 according to the embodiment of the present invention collects multiple groups of first echo signals in a high-quality and low-frame-rate manner, inputs the actually collected multiple groups of first echo signals into a neural network, and outputs more groups of second echo signals through the neural network, which can avoid reducing the quality of the ultrasonic image while increasing the frame rate of the ultrasonic image.

[0094] The embodiment of the present invention also provides an ultrasonic imaging system for implementing the above ultrasonic imaging method 200 or ultrasonic imaging method 400. Now, referring back to Figure 1 , this ultrasonic imaging system can be implemented as the ultrasonic imaging system 100 shown in Figure 1 . The ultrasonic imaging system 100 may include an ultrasonic probe 110, a transmitting circuit 112, a receiving circuit 114, a processor 116, and a display 118. Optionally, the ultrasonic imaging system 100 may further include a transmit / receive selection switch 120 and a beam synthesis module 122. The transmitting circuit 112 and the receiving circuit 114 may be connected to the ultrasonic probe 110 through the transmit / receive selection switch 120. The relevant descriptions of each component may refer to the relevant descriptions above and will not be elaborated here.

[0095] Among them, the transmitting circuit 112 is used to excite the ultrasonic probe 110 to emit ultrasonic waves to the target tissue; the receiving circuit 114 is used to control the ultrasonic probe 110 to receive the echoes of the ultrasonic waves to obtain echo signals; the processor 116 is used to execute the steps of the above ultrasonic imaging method 200 or ultrasonic imaging method 400. The processor 116 is also used to control the display 118 to display ultrasonic images.

[0096] The above only describes the main functions of the components of the ultrasonic imaging system. For more details, refer to the relevant descriptions of the ultrasonic imaging method 200 and the ultrasonic imaging method 400. The ultrasonic imaging system according to the embodiment of the present invention collects multiple frames of first ultrasonic image data or multiple groups of first echo signals in a high-quality and low-frame-rate manner, and inputs the actually collected multiple frames of first ultrasonic image data or first echo signals into a neural network, and increases the number of frames of ultrasonic image data or the number of groups of first echo signals through the neural network, which can avoid reducing the quality of the ultrasonic image while increasing the frame rate of the ultrasonic image.

[0097] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely exemplary and are not intended to limit the scope of the present invention thereto. Those of ordinary skill in the art can make various changes and modifications therein without departing from the scope and spirit of the present invention. All such changes and modifications are intended to be included within the scope of the present invention as claimed in the appended claims.

[0098] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0099] In several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0100] In the specification provided herein, a large number of specific details are described. However, it can be understood that the embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures, and technologies are not shown in detail so as not to obscure the understanding of this specification.

[0101] Similarly, it should be understood that, in order to streamline the present invention and assist in understanding one or more of the various inventive aspects, in the description of the exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, the method of the present invention should not be construed as reflecting the intention that the claimed present invention requires more features than are expressly recited in each claim. Rather, as reflected by the corresponding claims, the inventive point lies in that the technical problem can be solved with features less than all the features of a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into the detailed description, where each claim itself serves as a separate embodiment of the present invention.

[0102] Those skilled in the art will appreciate that, except where features are mutually exclusive, any combination can be employed of all the features disclosed in this specification (including the accompanying claims, abstract, and drawings), as well as of all the processes or units of any method or apparatus so disclosed. Each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by alternative features serving the same, equivalent, or similar purpose, unless expressly stated otherwise.

[0103] In addition, those skilled in the art will understand that, although some embodiments described herein include certain features included in other embodiments but not others, combinations of features of different embodiments are meant to be within the scope of the present invention and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0104] Each component embodiment of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some of the modules according to the embodiments of the present invention. The present invention can also be implemented as a device program (such as a computer program and a computer program product) for performing part or all of the methods described herein. Such a program for implementing the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or in any other form.

[0105] It should be noted that the above embodiments illustrate rather than limit the present invention, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The present invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims listing several devices, several of these devices may be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names.

[0106] As described above, this is only a specific implementation manner or an illustration of the specific implementation manner of the present invention, and the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, and all such changes or substitutions should be covered by the protection scope of the present invention. The protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An ultrasonic imaging method, characterized in that, the method includes: transmitting multiple groups of first ultrasonic waves to a target tissue, and receiving ultrasonic echoes returned from the target tissue to obtain multiple groups of first echo signals; generating a first ultrasonic image data sequence according to the multiple groups of first echo signals, the first ultrasonic image data sequence including multiple frames of first ultrasonic image data; inputting the first ultrasonic image data sequence into a trained neural network to obtain a second ultrasonic image data sequence, the frame rate of the second ultrasonic image data sequence being higher than that of the first ultrasonic image data sequence; wherein, the neural network is trained with a third ultrasonic image sequence as an input data set and a fourth ultrasonic image data sequence as a target data set, and the frame rate of the fourth ultrasonic image data sequence is higher than that of the third ultrasonic image sequence; outputting the second ultrasonic image data sequence.

2. The ultrasonic imaging method according to claim 1, characterized in that, the third ultrasonic image data sequence is constructed by extracting part of the ultrasonic image data from the fourth ultrasonic image data sequence.

3. The ultrasonic imaging method according to claim 1, characterized in that, the third ultrasonic image data sequence is constructed by interpolating the fourth ultrasonic image data sequence, or the fourth ultrasonic image data sequence is constructed by interpolating the third ultrasonic image data sequence.

4. The ultrasonic imaging method according to claim 1, characterized in that, the number of emission positions of the first ultrasonic waves is greater than the number of emission positions specified by the Nyquist spatial sampling law, and the receiving line density of the first echo signals is greater than the receiving line density specified by the Nyquist spatial sampling law.

5. The ultrasonic imaging method according to claim 1, characterized in that, generating multiple frames of first ultrasonic image data according to the multiple groups of first echo signals includes: processing the first echo signals by using at least one of the following algorithms to obtain the first ultrasonic image data: delay summation algorithm, adaptive algorithm, and iterative algorithm.

6. An ultrasonic imaging method, characterized in that, the method includes: transmitting multiple groups of first ultrasonic waves to a target tissue, and receiving ultrasonic echoes returned from the target tissue to obtain a first echo signal sequence, the first echo signal sequence including multiple groups of first echo signals, and each group of first echo signals corresponding to one frame of ultrasonic image data; inputting the first echo signal sequence into a trained neural network to obtain a second echo signal sequence, the frame rate of the ultrasonic image data sequence corresponding to the second echo signal sequence being higher than that of the ultrasonic image data sequence corresponding to the first echo signal sequence, wherein, the neural network is trained with a third echo signal sequence as an input data set and a fourth echo signal sequence as a target data set, and the frame rate of the ultrasonic image data sequence corresponding to the fourth echo signal sequence is higher than that of the ultrasonic image data sequence corresponding to the third echo signal; generating an ultrasonic image data sequence according to the second echo signal sequence, and outputting the ultrasonic image data sequence.

7. The ultrasonic imaging method according to claim 6, wherein, the third echo signal sequence is constructed by extracting partial echo signals from the fourth echo signal sequence.

8. The ultrasonic imaging method according to claim 6, wherein, the third echo signal sequence is constructed by interpolating the fourth echo signal sequence, or the fourth echo signal sequence is constructed by interpolating the third echo signal sequence.

9. The ultrasonic imaging method according to claim 6, wherein, the number of transmission positions of the first ultrasonic wave is greater than the number of transmission positions specified by the Nyquist spatial sampling law, and the receiving line density of the first echo signal is greater than the receiving line density specified by the Nyquist spatial sampling law.

10. An ultrasonic imaging system, wherein, comprising: an ultrasonic probe; a transmitting circuit for exciting the ultrasonic probe to transmit ultrasonic waves to a target tissue; a receiving circuit for controlling the ultrasonic probe to receive echo signals of the ultrasonic waves; a processor for executing the ultrasonic imaging method according to any one of claims 1-9 to generate an ultrasonic image; a display for displaying the ultrasonic image.

Images