Ultrasound image reconstruction and image-guided acquisition methods, devices, systems and terminals

Abstract

This invention provides a method, apparatus, system, and terminal for ultrasound image reconstruction and image-guided acquisition. First, a transducer is excited to generate a single-angle plane wave ultrasound irradiation of the prostate to acquire ultrasound RF signals. Then, based on medical images of the prostate and these ultrasound RF signals, a static flow ultrasound simulation image and a real-time ultrasound image are reconstructed, and precise guidance control commands are generated accordingly. These commands guide the transducer to the optimal imaging position, and then a pulsed laser is released to irradiate the prostate, thereby capturing photoacoustic RF signals. Based on the acquired photoacoustic RF signals, a photoacoustic image is further reconstructed, and these signals are properly stored. This invention achieves visualized conformal ultrasound irradiation of the prostate through a designed real-time image-guided function, ensuring accurate acquisition of ultrasound and photoacoustic RF signals, thus significantly improving the accuracy of ultrasound and photoacoustic image reconstruction. It also helps improve the accuracy of intelligent assessment of the degree of prostate inflammation in patients, greatly improving treatment efficiency.

Description

Technical Field

[0001] This invention relates to the field of imaging technology, and in particular to a method, apparatus, system and terminal for ultrasound image reconstruction and image-guided acquisition. Background Technology

[0002] Chronic prostatitis is the most common urogenital disease in men, and it can easily lead to infertility in young and middle-aged men and prostate cancer in older men. Furthermore, the recurrent pelvic pain, difficulty urinating, and sexual dysfunction caused by chronic prostatitis severely impact patients' quality of life and can even trigger mental health issues.

[0003] Antibiotics are the main treatment for chronic prostatitis. However, the blood-prostate barrier structure in the prostate tissue prevents microorganisms in the prostate ducts from entering the bloodstream, and also prevents antibiotics from reaching the prostate ducts via the bloodstream to exert their therapeutic effect. Studies have reported that the concentration of antibiotics in the prostate ducts is only 12%-29% of that in the blood. Therefore, even with high-dose, long-term antibiotic treatment, only 47%-56% of patients can improve their symptoms, and about 50% of patients relapse shortly after stopping the medication because the microorganisms in the ducts cannot be completely eliminated. This places a heavy burden on patients and the medical system.

[0004] Current research indicates that low-dose ultrasound irradiation can improve the permeability of the prostatic ducts, potentially increasing drug concentrations within them. Currently used continuous wave and pulsed wave ultrasound therapy devices irradiate the entire prostate region to enhance antibiotic concentrations within the ducts, achieving therapeutic goals. However, clinical studies have revealed uneven distribution of inflamed tissue in chronic prostatitis, with varying degrees of inflammation. This coexistence of normal prostate tissue and tissues with varying degrees of inflammation presents significant challenges to controlling the ultrasound irradiation dose. Excessive doses can damage or even destroy the normal blood-prostate barrier, rendering it ineffective. Insufficient doses, on the other hand, fail to open this barrier, hindering antibiotic concentration and impacting treatment efficacy, especially in moderate to severe inflammation, as the robustness of the blood-prostate barrier is directly proportional to the degree of inflammation. Existing technologies lack real-time image guidance for opening the prostatic barrier or performing ultrasound therapy for prostatitis. This lack of real-time image guidance prevents accurate real-time prostate structural imaging, resulting in low accuracy of photoacoustic imaging and photoacoustic RF signals. Consequently, the accuracy of assessing the degree of prostate inflammation is compromised, leading to low treatment efficiency. Summary of the Invention

[0005] In view of the shortcomings of the prior art described above, the purpose of this invention is to provide an ultrasound image reconstruction and image-guided acquisition method, device, system and terminal to solve the technical problems of the lack of real-time image guidance function in the prior art, which leads to the inability to obtain accurate real-time prostate structure, resulting in low accuracy of photoacoustic imaging and photoacoustic RF signals, which in turn affects the accuracy of judging the degree of prostate inflammation in patients and leads to low treatment efficiency.

[0006] To achieve the above and other related objectives, the present invention provides an ultrasound image reconstruction and image-guided acquisition method, the method comprising: exciting a transducer to generate a single-angle plane wave ultrasound to irradiate the prostate, and acquiring an ultrasound RF signal based on the echo signal received by the transducer; reconstructing a static flow ultrasound simulation image and a real-time ultrasound image based on a prostate medical image and the ultrasound RF signal, and generating a guidance control command to guide the transducer to the optimal imaging position; when the transducer is positioned at the optimal imaging position, generating a pulsed laser to irradiate the prostate, and acquiring a photoacoustic RF signal based on the echo signal received by the transducer; reconstructing a photoacoustic image based on the acquired photoacoustic RF signal, and storing the photoacoustic RF signal.

[0007] In one embodiment of the present invention, the step of reconstructing a static flow ultrasound simulation image and a real-time ultrasound image based on prostate medical images and the ultrasound RF signal, and generating guidance control commands to guide the transducer to the optimal imaging position includes: extracting structural features of the prostate and surrounding tissues from the prostate medical images, and reconstructing the static flow ultrasound simulation image based on the extracted structural features using a domain finite difference method; based on the reconstruction guidance network, performing real-time ultrasound image reconstruction according to the ultrasound RF signal, and generating guidance control commands based on the reconstructed static flow ultrasound simulation image and the real-time ultrasound image to control the transducer to reach the optimal imaging position after one or more position adjustments.

[0008] In one embodiment of the present invention, the reconstruction guidance network includes: an RF signal preprocessing module for initially aggregating the input ultrasound RF signal to align the initially aggregated signal with the dimension of the input static flow ultrasound simulation image; a B-Mode imaging module connected to the RF signal preprocessing module for envelope detection and denoising of the initially aggregated signal, and obtaining a high-quality B-Mode ultrasound image as the current real-time ultrasound image output; a mixed-flow image matching module connected to the B-Mode imaging module for calculating the position probability vector between the current real-time ultrasound image and each ultrasound simulation image of the static flow; and a guidance command generation module connected to the mixed-flow image matching module for determining the maximum position probability output by the mixed-flow image matching module, and generating a guidance control command for a single position adjustment based on the position setpoint of the ultrasound simulation image corresponding to the maximum position probability.

[0009] In one embodiment of the present invention, calculating the position probability vector between the current real-time ultrasound image and each simulated ultrasound image in the static flow includes: calculating the similarity vector between the current real-time ultrasound image and each simulated ultrasound image in the static flow in real time using a similarity attention mechanism; and obtaining the position probability vector between the current real-time ultrasound image and each simulated ultrasound image in the static flow based on the similarity vector between the current real-time ultrasound image and each simulated ultrasound image in the static flow using a Softmax activation function.

[0010] In one embodiment of the present invention, the reconstruction of the photoacoustic image based on the acquired photoacoustic RF signal includes: reconstructing the photoacoustic image according to the acquired photoacoustic RF signal by delay superposition DAS or time inversion TR method, so as to display the currently reconstructed photoacoustic image through a display device.

[0011] In one embodiment of the present invention, an electrical pulse signal is generated to excite a transducer to generate a single-angle plane wave ultrasound to irradiate the prostate, and the echo signal received by the transducer is converted from analog to digital to obtain the corresponding RF signal.

[0012] In one embodiment of the present invention, the guidance control command is sent to the robotic arm so that the robotic arm can guide the transducer to adjust its position.

[0013] To achieve the above and other related objectives, the present invention provides an ultrasound image reconstruction and image-guided acquisition device, comprising: an ultrasound RF signal acquisition module for exciting a transducer to generate a single-angle plane wave ultrasound to irradiate the prostate, and acquiring an ultrasound RF signal based on the echo signal received by the transducer; an image reconstruction and guidance control module connected to the ultrasound RF signal acquisition module for reconstructing a static flow ultrasound simulation image and a real-time ultrasound image based on a prostate medical image and the ultrasound RF signal, and generating guidance control commands to guide the transducer to the optimal imaging position; a photoacoustic RF signal module connected to the image reconstruction and guidance control module for generating a pulsed laser to irradiate the prostate when the transducer is positioned at the optimal imaging position, and acquiring a photoacoustic RF signal based on the echo signal received by the transducer; and a photoacoustic image reconstruction and signal storage module connected to the photoacoustic RF signal module for reconstructing a photoacoustic image based on the acquired photoacoustic RF signal and storing the photoacoustic RF signal.

[0014] To achieve the above and other related objectives, the present invention provides an electronic terminal, comprising: one or more memories and one or more processors; the one or more memories are used to store a computer program; the one or more processors are connected to the memories and are used to run the computer program to execute the ultrasound image reconstruction and image-guided acquisition method.

[0015] To achieve the above and other related objectives, the present invention provides an ultrasound image reconstruction and image-guided acquisition system. The system includes: a transducer, a robotic arm, an ultrasound image reconstruction and image-guided acquisition device, and a display device. The transducer is mounted at the end of the robotic arm. The ultrasound image reconstruction and image-guided acquisition device is communicatively connected to the transducer, the robotic arm, and the display device. The ultrasound image reconstruction and image-guided acquisition device is used to excite the transducer to generate a single-angle plane wave ultrasound to irradiate the prostate, and to acquire an ultrasound RF signal based on the echo signal received by the transducer. It reconstructs a static flow ultrasound simulation image and a real-time ultrasound image based on the prostate medical image and the ultrasound RF signal, and generates a guidance control command to be sent to the robotic arm so that the robotic arm can guide the transducer to the optimal imaging position. When the transducer is positioned at the optimal imaging position, it generates a pulsed laser to irradiate the prostate, and acquires a photoacoustic RF signal based on the echo signal received by the transducer. It reconstructs a photoacoustic image based on the acquired photoacoustic RF signal and sends it to the display device for display, and also stores the photoacoustic RF signal.

[0016] As described above, this invention provides a method, apparatus, system, and terminal for ultrasound image reconstruction and image-guided acquisition, offering the following advantages: First, the invention excites a transducer to generate a single-angle plane wave ultrasound irradiation of the prostate to acquire ultrasound RF signals. Subsequently, based on medical images of the prostate and these ultrasound RF signals, a static flow ultrasound simulation image and a real-time ultrasound image are reconstructed, generating precise guidance control commands. These commands guide the transducer to the optimal imaging position, followed by the release of a pulsed laser to irradiate the prostate, thereby capturing photoacoustic RF signals. Based on the acquired photoacoustic RF signals, a photoacoustic image is further reconstructed, and these signals are properly stored. This invention, through its designed real-time image-guided function, achieves visualized conformal ultrasound irradiation of the prostate, ensuring accurate acquisition of ultrasound and photoacoustic RF signals, thus significantly improving the accuracy of ultrasound and photoacoustic image reconstruction. It also assists in improving the accuracy of intelligently assessing the degree of prostate inflammation in patients, greatly enhancing treatment efficiency. Attached Figure Description

[0017] Figure 1 The diagram shown is a flowchart of an ultrasound image reconstruction and image-guided acquisition method according to an embodiment of the present invention.

[0018] Figure 2 The diagram shown is a structural schematic of the reconstruction guidance network in one embodiment of the present invention.

[0019] Figure 3 The diagram shown is a structural schematic of an ultrasound image reconstruction and image-guided acquisition device according to an embodiment of the present invention.

[0020] Figure 4 The diagram shown is a structural schematic of an electronic terminal according to an embodiment of the present invention.

[0021] Figure 5 The diagram shown is a structural schematic of an ultrasound image reconstruction and image-guided acquisition system according to an embodiment of the present invention.

[0022] Figure 6 The diagram shown is a structural schematic of an ultrasound image reconstruction and image-guided acquisition system according to an embodiment of the present invention. Detailed Implementation

[0023] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0024] It should be noted that in the following description, reference is made to the accompanying drawings, which illustrate several embodiments of the invention. It should be understood that other embodiments may also be used, and changes in mechanical composition, structure, electrical system, and operation may be made without departing from the spirit and scope of the invention. The following detailed description should not be considered limiting, and the scope of the embodiments of the invention is defined only by the claims of the published patents. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. Spatially related terms, such as “upper,” “lower,” “left,” “right,” “below,” “below,” “lower part,” “above,” “upper part,” etc., may be used herein to illustrate the relationship between one element or feature shown in the figures and another element or feature.

[0025] Throughout this specification, when it is said that a part is "connected" to another part, this includes not only "direct connection" but also "indirect connection" by placing other elements in between. Furthermore, when it is said that a part "includes" a certain constituent element, unless otherwise stated otherwise, this does not exclude other constituent elements, but rather means that other constituent elements may also be included.

[0026] The terms "first," "second," and "third," etc., used herein are for the purpose of describing various parts, components, regions, layers, and / or segments, but are not limiting. These terms are used only to distinguish one part, component, region, layer, or segment from others. Therefore, the "first part," "component," "region," "layer," or "segment" described below may refer to a "second part," "component," "region," "layer," or "segment" without departing from the scope of this invention.

[0027] Furthermore, as used herein, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context indicates otherwise. It should be further understood that the terms “comprising,” “including,” indicate the presence of the stated feature, operation, element, component, item, kind, and / or group, but do not preclude the presence, occurrence, or addition of one or more other features, operations, elements, components, items, kinds, and / or groups. The terms “or” and “and / or” as used herein are interpreted as inclusive, or mean any one or any combination thereof. Thus, “A, B, or C” or “A, B, and / or C” means “any one of: A; B; C; A and B; A and C; B and C; A, B, and C.” Exceptions to this definition arise only when combinations of elements, functions, or operations are inherently mutually exclusive in some manner.

[0028] This invention provides a method for ultrasound image reconstruction and image-guided acquisition. First, a transducer is excited to generate a single-angle plane wave ultrasound irradiation of the prostate to acquire ultrasound RF signals. Then, based on medical images of the prostate and these ultrasound RF signals, a static flow ultrasound simulation image and a real-time ultrasound image are reconstructed, and precise guidance control commands are generated accordingly. These commands guide the transducer to the optimal imaging position, and then a pulsed laser is released to irradiate the prostate, thereby capturing photoacoustic RF signals. Based on the acquired photoacoustic RF signals, a photoacoustic image is further reconstructed, and these signals are properly stored. This invention achieves visualized conformal ultrasound irradiation of the prostate through a designed real-time image-guided function, ensuring accurate acquisition of ultrasound and photoacoustic RF signals, thus significantly improving the accuracy of ultrasound and photoacoustic image reconstruction. It also helps improve the accuracy of intelligent assessment of the degree of prostate inflammation in patients, greatly improving treatment efficiency.

[0029] The present invention will now be described in detail with reference to the accompanying drawings, so that those skilled in the art can readily implement it. The present invention can be embodied in many different forms and is not limited to the embodiments described herein.

[0030] like Figure 1 This is a flowchart illustrating an ultrasound image reconstruction and image-guided acquisition method according to an embodiment of the present invention.

[0031] The method includes:

[0032] Step S1: Excite the transducer to generate a single-angle plane wave ultrasound to irradiate the prostate, and obtain the ultrasound RF signal based on the echo signal received by the transducer.

[0033] In one embodiment, an electrical pulse signal is first generated to excite a transducer to produce a single-angle plane wave ultrasound irradiation of the prostate. When the transducer emits ultrasound waves, they encounter the prostate tissue, and some of the sound waves are reflected back, forming echoes. These echo signals are received and captured by the transducer. These echo signals contain information about the internal structure of the prostate and are crucial data for subsequent image reconstruction. The echo signals are then converted from analog-to-digital signals (ADCs) into digital single-angle ultrasound RF signals. Specifically, the echo signals can be converted from analog to digital using an ADC device.

[0034] The design of the electrical pulse signal needs to ensure that the transducer can generate a high-quality ultrasonic beam; the given signal expression is as shown in equation (1):

[0035] S(t)=(-t)·sin(2πf0t)exp(-4β 2 t 2 (1)

[0036] Where f0 is the center frequency of the transducer, and β is a parameter related to the signal bandwidth. This signal is a modulated sine wave, where the (-t) factor is used to produce a chirp effect, and exp(-4β) 2 t 2 The factor is used to limit the duration of the signal, ensuring that the signal is finite in the time domain.

[0037] For example, the center frequency f0 of the transmitting and receiving transducers is set to 1MHz to 10MHz. The electrical pulse signal is converted into an ultrasonic beam by the transducer, and the transducer diameter is set to 7.4 mm. The total area size is 26mm × 14mm.

[0038] Step S2: Based on the prostate medical image and the ultrasound RF signal, reconstruct the static flow ultrasound simulation image and the real-time ultrasound image, and generate guidance control commands to guide the transducer to the optimal imaging position.

[0039] In one embodiment, step S2 includes:

[0040] Step S21: Extract the structural features of the prostate and surrounding tissues from the prostate medical image, and reconstruct the static flow ultrasound simulation image based on the extracted structural features using the domain finite difference method.

[0041] Specifically, the static flow ultrasonic simulation image is reconstructed using the ultrasonic motion equation and the finite-difference time-domain numerical solution, following these steps:

[0042] The wave equation can be written as a second-order partial differential form of displacement, then decomposed into a system of first-order partial differential equations in velocity-stress form, and further discretized into elastodynamic difference equations to simulate the dynamics of ultrasound, as represented by equations (2)-(5). Finite-difference time-domain numerical solution discretizes the computational space and connects the differential particle and its surrounding particles through the system of difference equations. It calculates the velocity and stress values ​​of the differential particle as it iterates over time (a total of 9 variables: particle velocity, normal stress, and shear stress in the x, y, and z directions), thereby realizing the solution of the propagation of ultrasound in tissues for individual particles.

[0043]

[0044] In the second-order ultrasonic motion equations, ρ is the material density, and w is the displacement vector. The first and second Lamé constants are λ and μ, respectively, and the first viscosity coefficient η and the second viscosity coefficient Φ characterize the absorption properties of sound waves in the material. In the first-order partial differential equations, α, β, and γ can cyclically correspond to three-dimensional coordinates; the normal stress and shear stress at a certain location are tαα and tαβ, respectively; εL and εT are the positive impedance coefficient and shear impedance coefficient that control the attenuation of longitudinal waves and transverse waves, respectively.

[0045] The dynamics of ultrasound in the prostate can be obtained by numerically solving the above differential equation using the finite difference method. The conditions for the finite difference time-domain numerical solution include initial conditions, boundary conditions, and excitation conditions. For the initial conditions, the particle velocity and stress in the ultrasound-guided region of the prostate are both zero, indicating that the tissue layers are in a static state before ultrasound excitation.

[0046] It should be noted that the material density ρ of fat and prostate, the first Lamé coefficient λ, the second Lamé coefficient μ, the first viscosity coefficient η, the second viscosity coefficient Φ, the positive acoustic impedance coefficient εL, and the shear acoustic impedance coefficient εT are used as input imaging parameters for the prostate. Ultrasound waves propagate to the prostate through multiple layers of the human body. The prostate imaging parameters are shown in Table 1, and these parameters are used for ultrasound image guidance and photoacoustic imaging.

[0047] Table 1 Prostate imaging parameters

[0048]

[0049] Step S22: Based on the reconstruction guidance network, real-time ultrasound image reconstruction is performed according to the ultrasound RF signal, and guidance control commands are generated based on the reconstructed static flow ultrasound simulation image and real-time ultrasound image to control the transducer to reach the optimal imaging position through one or more position adjustments.

[0050] Specifically, the current ultrasound RF signal and the static flow ultrasound simulation image reconstructed in the previous step are input into the reconstruction guidance network. Real-time ultrasound image reconstruction is performed based on the current ultrasound RF signal, and guidance control commands are generated based on the reconstructed static flow ultrasound simulation image and real-time ultrasound image. The reconstruction guidance network outputs the current real-time ultrasound image and guidance control commands. The guidance control commands are used to guide the transducer to perform corresponding position adjustments. After the position is adjusted, the prostate is irradiated. The ultrasound RF signal is then obtained based on the echo signal received by the transducer. This ultrasound RF signal is used as the current signal and the static flow ultrasound simulation image and input into the reconstruction guidance network again. Real-time ultrasound image reconstruction and guidance control commands are generated again to realize a closed-loop feedback system until the transducer is guided to the optimal imaging position and stops.

[0051] The guidance control command is represented in the form of command code and is used to specify a fixed distance of movement in a direction. For example, an output command of 01 indicates that it needs to move forward, an output command of 10 indicates that it needs to move backward, and an output command of 00 indicates that the position has been reached.

[0052] In one embodiment, the transducer is mounted at the end of a robotic arm, which acts as a drive actuator responsible for adjusting the position of the transducer (i.e., the ultrasonic probe) according to the received and transmitted guidance and control commands.

[0053] In one embodiment, the reconstruction guidance network is designed as a multi-task deep neural network based on mixed-stream image matching. The network has two main functions: first, it can reconstruct high-quality B-mode ultrasound images using single-angle plane wave ultrasound RF signals; second, it uses dynamic and static mixed image stream data for matching, senses the deviation between the current position of the transducer and the given position, and generates guidance control commands based on the deviation vector.

[0054] The network takes RF signals from the transducer and simulated ultrasound images as input, and outputs reconstructed high-quality B-mode ultrasound images and guidance control commands. Utilizing the parallel computing capabilities of neural networks, the network achieves real-time, high-speed B-mode imaging, meeting the system's real-time guidance control requirements.

[0055] like Figure 2 As shown, the reconstruction guidance network includes:

[0056] The RF signal preprocessing module is used to perform preliminary aggregation on the input ultrasound RF signal so that the pre-aggregated signal is aligned with the dimension of the input static flow ultrasound simulation image.

[0057] Specifically, the RF signal preprocessing module mainly consists of three signal aggregation layers. Aggregation layers 1 and 2 have the same basic structure but perform different operations. Aggregation layer 3, compared to the first two layers, lacks the intermediate column interpolation transformation layer. The module input is a single-angle RF signal, and the output is the aggregated signal. The purpose of this module is to perform preliminary signal aggregation on the acquired single-angle RF signal, and secondly, to align the aggregated signal with the dimensions of the ultrasound simulation image, facilitating the mixed-stream image matching module to obtain the position probability vector.

[0058] The B-Mode imaging module, connected to the RF signal preprocessing module, is used to perform envelope detection and noise reduction on the initially aggregated signal and obtain a high-quality B-Mode ultrasound image as the current real-time ultrasound image output.

[0059] Specifically, the B-Mode imaging module primarily employs a deep neural network model with an encoding and decoding structure. Its main function is to further perform envelope detection and denoising on the preliminary aggregated signal obtained from the RF signal preprocessing module, enabling the network to process the preliminary aggregated signal into a high-quality B-Mode ultrasound image. The network takes the preliminary aggregated signal as input and outputs a high-quality B-Mode image.

[0060] A mixed-flow image matching module, connected to the B-Mode imaging module, is used to calculate the position probability vector between the current real-time ultrasound image and each ultrasound simulation image of the static flow;

[0061] Specifically, the mixed-stream image matching module receives high-quality B-Mode ultrasound images from the B-Mode imaging module as input, while simultaneously accessing multiple ultrasound simulation images stored in the static stream. Using a specific image similarity algorithm, this module calculates the similarity between the current real-time ultrasound image and each ultrasound simulation image in the static stream. Based on the similarity results, a positional probability vector is generated for each ultrasound simulation image and the real-time ultrasound image.

[0062] The guidance instruction generation module, connected to the mixed-flow image matching module, is used to determine the maximum position probability output by the mixed-flow image matching module, and generate a guidance control instruction for a single position adjustment based on the position setpoint of the ultrasound simulation image corresponding to the maximum position probability.

[0063] Specifically, the guidance command generation module adopts an MLP (Multilayer Perceptron) structure. Its main function is to evaluate the position probability vector output by the mixed-flow image matching module, find the maximum position probability, and compare it with the position given value of the ultrasonic simulation image corresponding to the maximum position vector to generate a definite guidance control command.

[0064] In one specific embodiment, the mixed-flow image matching module calculates the positional probability vector between the current real-time ultrasound image and each simulated ultrasound image of the static flow, including:

[0065] A similarity attention mechanism is used to calculate the similarity vector between the current real-time ultrasound image and each simulated ultrasound image in the static flow in real time. Each element in the similarity vector represents the similarity score between the current real-time ultrasound image and a simulated ultrasound image in the static flow.

[0066] Using the Softmax activation function, each element in the similarity vector between the current real-time ultrasound image and each simulated ultrasound image in the static flow is converted into a probability value between 0 and 1, and the sum of all probability values ​​is 1. The position probability vector is composed of the probability values ​​between the current real-time ultrasound image and each simulated ultrasound image in the static flow, which can indirectly determine the position of the ultrasound probe. The simulated ultrasound image corresponding to the element with the highest probability value in the position probability vector is likely to be the actual position of the current real-time ultrasound image.

[0067] Step S3: When the transducer is positioned at the optimal imaging location, a pulsed laser is generated to irradiate the prostate, and a photoacoustic RF signal is acquired based on the echo signal received by the transducer.

[0068] In one embodiment, when it is determined that the transducer has reached the optimal imaging position, a pulsed laser is generated to irradiate the prostate, and the echo signal is received through the transducer. Then, the photoacoustic RF signal is obtained through analog-to-digital conversion in the system.

[0069] Step S4: Reconstruct the photoacoustic image based on the acquired photoacoustic RF signal and store the photoacoustic RF signal.

[0070] In one embodiment, reconstructing a photoacoustic image based on the acquired photoacoustic RF signal includes:

[0071] The photoacoustic image is reconstructed based on the acquired photoacoustic RF signal using delay superposition DAS or time inversion TR methods, so that the reconstructed photoacoustic image can be displayed on a display device.

[0072] The time-delay superposition (DAS) algorithm is a commonly used image reconstruction technique in photoacoustic imaging. Its basic principle is to delay and superimpose the received photoacoustic RF signals based on the time difference in the propagation of ultrasound waves from different locations within the tissue to the transducer, thereby reconstructing an image of the tissue's light absorption distribution. The time-reversal (TR) method is a more advanced image reconstruction technique. It utilizes the reversibility of sound wave propagation to reconstruct the location and intensity distribution of the sound source by reversing the propagation of the received sound wave signal.

[0073] Similar to the above embodiments, the present invention provides an ultrasound image reconstruction and image-guided acquisition device.

[0074] The following specific embodiments are provided in conjunction with the accompanying drawings:

[0075] like Figure 3 This invention presents a schematic diagram of the structure of an ultrasound image reconstruction and image-guided acquisition device according to an embodiment of the present invention.

[0076] The device includes:

[0077] The ultrasound RF signal acquisition module 1 is used to excite the transducer to generate a single-angle plane wave ultrasound to irradiate the prostate, and to acquire the ultrasound RF signal based on the echo signal received by the transducer.

[0078] The image reconstruction and guidance control module 2 is connected to the ultrasound RF signal acquisition module 1. It is used to reconstruct static flow ultrasound simulation images and real-time ultrasound images based on prostate medical images and ultrasound RF signals, and generate guidance control commands to control the transducer to be guided to the optimal imaging position.

[0079] The photoacoustic RF signal module 3 is connected to the image reconstruction and guidance control module 2. It is used to generate pulsed laser to irradiate the prostate when the transducer is inserted into the optimal imaging position, and to obtain photoacoustic RF signals based on the echo signals received by the transducer.

[0080] The photoacoustic image reconstruction and signal storage module 4 is connected to the photoacoustic RF signal module 3 and is used to reconstruct photoacoustic images based on the acquired photoacoustic RF signals and store the photoacoustic RF signals.

[0081] It should be noted that, as should be understood Figure 3 The division of modules in the embodiments is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these units can be implemented entirely in software through processing element calls; they can be implemented entirely in hardware; or some units can be implemented by processing element calls to software, while others are implemented in hardware.

[0082] Since the implementation principle of the ultrasound image reconstruction and image-guided acquisition device has been described in the foregoing embodiments, it will not be repeated here.

[0083] The ultrasound image reconstruction and image-guided acquisition method provided in this invention can be implemented on the terminal side or the server side. Regarding the hardware structure of the electronic terminal, please refer to [link to relevant documentation]. Figure 4 This is a schematic diagram of an optional hardware structure of an electronic terminal 1000 provided in an embodiment of the present invention. The terminal 1000 can be a mobile phone, computer device, tablet device, personal digital processing device, factory back-end processing device, etc. The terminal 1000 includes: at least one processor 1001, a memory 1002, at least one network interface 10010, and a user interface 10010. The various components in the device are coupled together through a bus system 1005. It is understood that the bus system 1005 is used to realize the connection and communication between these components. In addition to a data bus, the bus system 1005 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 4 The general will label all buses as bus systems.

[0084] The user interface 10010 may include a monitor, keyboard, mouse, trackball, clicker, button, touchpad, or touch screen.

[0085] It is understood that memory 1002 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM) or programmable read-only memory (PROM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memories described in the embodiments of this invention are intended to include, but are not limited to, these and any other suitable categories of memory.

[0086] In this embodiment of the invention, the memory 1002 is used to store various types of data to support the operation of the terminal 1000. Examples of this data include: any executable program for operation on the terminal 1000, such as the operating system 10021 and application program 10022; the operating system 10021 contains various system programs, such as the framework layer, core library layer, driver layer, etc., for implementing various basic services and handling hardware-based tasks. The application program 10022 may contain various applications, such as a media player, browser, etc., for implementing various application services. The ultrasound image reconstruction and image-guided acquisition method provided in this embodiment of the invention can be included in the application program 10022.

[0087] The methods disclosed in the above embodiments of the present invention can be applied to or implemented by the processor 1001. The processor 1001 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 1001 or by instructions in the form of software. The processor 1001 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 1001 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor 1001 may be a microprocessor or any conventional processor, etc. The steps of the accessory optimization method provided in the embodiments of the present invention can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium, which is located in a memory. The processor reads the information in the memory and combines it with its hardware to complete the steps of the aforementioned method.

[0088] In an exemplary embodiment, the terminal 1000 may be used to execute the aforementioned method by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), or complex programmable logic devices (CPLDs).

[0089] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented using computer program-related hardware. The aforementioned computer program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0090] In the embodiments provided in this application, the computer-readable and writable storage medium may include read-only memory, random access memory, EEPROM, CD-ROM or other optical disc storage devices, disk storage devices or other magnetic storage devices, flash memory, USB flash drive, portable hard drive, or any other medium capable of storing desired program code in the form of instructions or data structures and accessible by a computer. Additionally, any connection may be appropriately referred to as a computer-readable medium. For example, if instructions are transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of the medium. However, it should be understood that computer-readable and writable storage media and data storage media do not include connections, carrier waves, signals, or other transient media, but are intended for non-transient, tangible storage media. The disks and optical discs used in the application include compact discs (CDs), laser discs, optical discs, digital multifunction discs (DVDs), floppy disks, and Blu-ray discs, where disks typically copy data magnetically, while optical discs use lasers to copy data optically.

[0091] like Figure 5 This invention presents a schematic diagram of the structure of an ultrasound image reconstruction and image-guided acquisition system according to an embodiment of the present invention.

[0092] The system includes:

[0093] Transducer 101, robotic arm 102, ultrasonic image reconstruction and image-guided acquisition device 103, and display device 104;

[0094] The transducer 101 is installed at the end of the robotic arm 102 and serves as a device for transmitting and receiving ultrasonic signals.

[0095] The robotic arm 102 controls the position and orientation of the transducer 101 to ensure that the transducer 101 can irradiate the prostate and collect RF signals at the optimal imaging position.

[0096] The ultrasound image reconstruction and image-guided acquisition device 103, communicatively connected to the transducer 101, robotic arm 102, and display device 104, is the core control and processing module of the entire system. It excites the transducer 101 to generate a single-angle plane wave ultrasound to irradiate the prostate, and acquires an ultrasound RF signal based on the echo signal received by the transducer 101. Based on the prostate medical image and the ultrasound RF signal, it reconstructs a static flow ultrasound simulation image and a real-time ultrasound image, and generates a guidance control command which is sent to the robotic arm 102 to guide the transducer 101 to the optimal imaging position. When the transducer 101 reaches the optimal imaging position, it generates a pulsed laser to irradiate the prostate, and acquires a photoacoustic RF signal based on the echo signal received by the transducer 101. Based on the acquired photoacoustic RF signal, it reconstructs a photoacoustic image and sends it to the display device 104 for display, and also stores the photoacoustic RF signal.

[0097] In one specific embodiment, such as Figure 2 As shown, the specific process of the system includes:

[0098] The system first generates an electrical pulse signal to excite the transducer to emit a single-angle plane wave ultrasound signal to the prostate. It then receives and processes the echo signal as an RF signal. During the ultrasound image reconstruction stage, the system processes the data in two parallel paths: first, it constructs a simulated ultrasound image based on the structural features of medical images (CT / MRI) using the finite-difference time-domain method; second, it uses a reconstruction-guided network to reconstruct a high-quality real-time ultrasound image using the single-angle RF signal, and compares it with the simulated image through a similarity attention mechanism to calculate and optimize the probe position in real time. Finally, at the optimal imaging position, the system initiates photoacoustic RF signal acquisition, irradiating the prostate with a pulsed laser and receiving the echo signal, converting it into a photoacoustic RF signal. Subsequently, it reconstructs the photoacoustic image using a time-delayed superposition DAS or time-reversal TR algorithm, instantly displaying the imaging results and saving the photoacoustic RF data to a hard drive for subsequent analysis.

[0099] In summary, the ultrasound image reconstruction and image-guided acquisition method, apparatus, system, and terminal of the present invention first excite a transducer to generate a single-angle plane wave ultrasound irradiation of the prostate to acquire ultrasound RF signals. Subsequently, based on the medical image of the prostate and these ultrasound RF signals, a static flow ultrasound simulation image and a real-time ultrasound image are reconstructed, and precise guidance control commands are generated accordingly. These commands guide the transducer to move to the optimal imaging position, and then a pulsed laser is released to irradiate the prostate, thereby capturing photoacoustic RF signals. Based on the acquired photoacoustic RF signals, a photoacoustic image is further reconstructed, and these signals are properly stored. The present invention achieves visualized conformal ultrasound irradiation of the prostate through a designed real-time image guidance function, ensuring the accurate acquisition of ultrasound and photoacoustic RF signals, thereby significantly improving the accuracy of ultrasound and photoacoustic image reconstruction, and also assisting in improving the accuracy of intelligent assessment of the degree of prostate inflammation in patients, greatly improving treatment efficiency. Therefore, the present invention effectively overcomes the various shortcomings of the prior art and has high industrial application value.

[0100] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A method for ultrasound image reconstruction and image-guided acquisition, characterized in that, The ultrasound image reconstruction and image-guided acquisition method includes: The transducer is excited to generate a single-angle ultrasonic plane wave to irradiate the prostate, and the ultrasonic RF signal is obtained based on the echo signal received by the transducer. Based on prostate medical images and the ultrasound RF signals, a static flow ultrasound simulation image and a real-time ultrasound image are reconstructed, and guidance control commands are generated to guide the transducer to the optimal imaging position. Specifically, this includes: extracting structural features of the prostate and surrounding tissues from the prostate medical images, and reconstructing the static flow ultrasound simulation image using a finite-difference time-domain method based on the extracted structural features; reconstructing a real-time ultrasound image based on the ultrasound RF signals using a reconstruction guidance network, and generating guidance control commands based on the reconstructed static flow ultrasound simulation image and the real-time ultrasound image to guide the transducer to the optimal imaging position after one or more position adjustments; the reconstruction guidance network includes: an RF signal preprocessing module for initially aggregating the input ultrasound RF signals to align the dimensions of the initially aggregated signals with those of the input static flow ultrasound simulation image; and a B-Mode imaging module connected to the RF signal preprocessing module for envelope detection of the initially aggregated signals. The system denoises and obtains a high-quality B-Mode ultrasound image as the current real-time ultrasound image output; a mixed-flow image matching module, connected to the B-Mode imaging module, is used to calculate the position probability vector between the current real-time ultrasound image and each static flow ultrasound simulation image; a guidance command generation module, connected to the mixed-flow image matching module, is used to determine the maximum position probability output by the mixed-flow image matching module, and generate a guidance control command for a position adjustment based on the position setpoint of the static flow ultrasound simulation image corresponding to the maximum position probability; calculating the position probability vector between the current real-time ultrasound image and each static flow ultrasound simulation image includes: calculating the similarity vector between the current real-time ultrasound image and each static flow ultrasound simulation image in real time through a similarity attention mechanism; and using the Softmax activation function to obtain the position probability vector between the current real-time ultrasound image and each static flow ultrasound simulation image based on the similarity vector between the current real-time ultrasound image and each static flow ultrasound simulation image. When the transducer is guided to the optimal imaging position, a pulsed laser is generated to irradiate the prostate, and a photoacoustic RF signal is obtained based on the echo signal received by the transducer. Reconstructing an optical-acoustic image based on the acquired optical-acoustic RF signal specifically includes: reconstructing the optical-acoustic image using a delay-overlay DAS or time-reversal TR method based on the acquired optical-acoustic RF signal, displaying the currently reconstructed optical-acoustic image through a display device, and storing the optical-acoustic RF signal.

2. The ultrasound image reconstruction and image-guided acquisition method according to claim 1, characterized in that, An electrical pulse signal is generated to excite a transducer to produce a single-angle ultrasonic plane wave that irradiates the prostate. The echo signal received by the transducer is then converted from analog to digital to obtain the corresponding ultrasonic RF signal.

3. The ultrasound image reconstruction and image-guided acquisition method according to claim 1, characterized in that, The guidance control command is sent to the robotic arm to control the robotic arm to guide the transducer to adjust its position.

4. An ultrasound image reconstruction and image-guided acquisition device, characterized in that, The ultrasound image reconstruction and image-guided acquisition device includes: An ultrasound RF signal acquisition module is used to excite a transducer to generate a single-angle ultrasound plane wave to irradiate the prostate, and to acquire ultrasound RF signals based on the echo signals received by the transducer. The image reconstruction and guidance control module, connected to the ultrasound RF signal acquisition module, is used to reconstruct a static flow ultrasound simulation image and a real-time ultrasound image based on the prostate medical image and the ultrasound RF signal, and generate guidance control commands to guide the transducer to the optimal imaging position. Specifically, this includes: extracting structural features of the prostate and surrounding tissues from the prostate medical image, and reconstructing the static flow ultrasound simulation image using a finite-difference time-domain method based on the extracted structural features; reconstructing a real-time ultrasound image based on the ultrasound RF signal using a reconstruction guidance network, and generating guidance control commands based on the reconstructed static flow ultrasound simulation image and the real-time ultrasound image to guide the transducer to the optimal imaging position after one or more position adjustments; the reconstruction guidance network includes: an RF signal preprocessing module, used to initially aggregate the input ultrasound RF signal to align the dimension of the initially aggregated signal with that of the input static flow ultrasound simulation image; and a B-Mode imaging module, connected to the RF signal preprocessing module, used to... The initially aggregated signals undergo envelope detection and denoising to obtain a high-quality B-Mode ultrasound image as the current real-time ultrasound image output. A mixed-flow image matching module, connected to the B-Mode imaging module, is used to calculate the position probability vector between the current real-time ultrasound image and each static flow ultrasound simulation image. A guidance command generation module, connected to the mixed-flow image matching module, is used to determine the maximum position probability output by the mixed-flow image matching module and generate a guidance control command for a single position adjustment based on the position setpoint of the static flow ultrasound simulation image corresponding to this maximum position probability. Calculating the position probability vector between the current real-time ultrasound image and each static flow ultrasound simulation image includes: calculating the similarity vector between the current real-time ultrasound image and each static flow ultrasound simulation image in real-time using a similarity attention mechanism; and using the Softmax activation function to obtain the position probability vector between the current real-time ultrasound image and each static flow ultrasound simulation image based on the similarity vector between the current real-time ultrasound image and each static flow ultrasound simulation image. The photoacoustic RF signal module is connected to the image reconstruction and guidance control module. It is used to generate pulsed laser to irradiate the prostate when the transducer is guided to the optimal imaging position, and to obtain photoacoustic RF signals based on the echo signals received by the transducer. The photoacoustic image reconstruction and signal storage module is connected to the photoacoustic RF signal module and is used to reconstruct photoacoustic images based on the acquired photoacoustic RF signals. Specifically, it includes: reconstructing photoacoustic images based on the acquired photoacoustic RF signals using delay superposition DAS or time inversion TR methods, displaying the currently reconstructed photoacoustic images through a display device, and storing the photoacoustic RF signals.

5. An electronic terminal, characterized in that, include: Memory and processor; The memory is used to store computer programs; The processor, connected to the memory, is used to run the computer program to perform the ultrasound image reconstruction and image-guided acquisition method as described in any one of claims 1 to 3.

6. An ultrasound image reconstruction and image-guided acquisition system, characterized in that, The ultrasound image reconstruction and image-guided acquisition system includes: a transducer, a robotic arm, an ultrasound image reconstruction and image-guided acquisition device, and a display device; The transducer is mounted at the end of the robotic arm; the ultrasonic image reconstruction and image-guided acquisition device is communicatively connected to the transducer, the robotic arm, and the display device. The ultrasound image reconstruction and image-guided acquisition device is used to excite the transducer to generate a single-angle ultrasound plane wave to irradiate the prostate, and to acquire ultrasound RF signals based on the echo signals received by the transducer; it reconstructs static flow ultrasound simulation images and real-time ultrasound images based on the prostate medical images and the ultrasound RF signals, and generates guidance control commands to guide the transducer to the optimal imaging position. Specifically, this includes: extracting the structural features of the prostate and surrounding tissues from the prostate medical images, and reconstructing the static flow ultrasound simulation image based on the extracted structural features using the finite-difference time-domain method; and reconstructing real-time ultrasound images based on the ultrasound RF signals using a reconstruction guidance network. The system generates acoustic images and, based on the reconstructed static flow ultrasound simulation image and real-time ultrasound image, generates guiding control commands to guide the transducer to the optimal imaging position through one or more position adjustments. The reconstruction guiding network includes: an RF signal preprocessing module for initially aggregating the input ultrasound RF signals to align the dimensions of the pre-aggregated signals with those of the input static flow ultrasound simulation image; a B-Mode imaging module, connected to the RF signal preprocessing module, for performing envelope detection and denoising on the pre-aggregated signals to obtain a high-quality B-Mode ultrasound image as the current real-time ultrasound image output; and mixed-flow image matching. The module, connected to the B-Mode imaging module, is used to calculate the position probability vector between the current real-time ultrasound image and each static flow ultrasound simulation image; the guidance command generation module, connected to the mixed-flow image matching module, is used to determine the maximum position probability output by the mixed-flow image matching module, and generate a guidance control command for a single position adjustment based on the position setpoint of the static flow ultrasound simulation image corresponding to the maximum position probability; calculating the position probability vector between the current real-time ultrasound image and each static flow ultrasound simulation image includes: calculating the similarity vector between the current real-time ultrasound image and each static flow ultrasound simulation image in real time through a similarity attention mechanism; Using the Softmax activation function, a positional probability vector between the current real-time ultrasound image and each static flow ultrasound simulation image is obtained based on the similarity vector between the current real-time ultrasound image and each static flow ultrasound simulation image. When the transducer is guided to the optimal imaging position, a pulsed laser is generated to irradiate the prostate, and a photoacoustic RF signal is acquired based on the echo signal received by the transducer. The photoacoustic image is reconstructed based on the acquired photoacoustic RF signal, specifically including: reconstructing the photoacoustic image using a time-delay superposition DAS or time-reversal TR method based on the acquired photoacoustic RF signal, displaying the currently reconstructed photoacoustic image through a display device, and storing the photoacoustic RF signal.

Images