An AI-enabled ultrasound temperature measurement method for deep organ HIFU treatment

Abstract

The present invention discloses an AI-enabled ultrasonic temperature measurement method for HIFU treatment of deep organs. First, the ultrasonic echo signals and temperature change data of deep organs during the treatment process are collected through the HIFU system, and a breathing-guided multimodal teacher-student model is proposed. The quasi-periodic respiratory phase curve is established through the normalized cross-correlation coefficient of the radio frequency data and the gated threshold strategy, and then the six respiratory phases are extracted using phase analysis technology. Subsequently, starting from the energy parameters of the high-intensity focused ultrasound probe, a multi-layer perceptual mapping of acoustic parameters is constructed in the multimodal teacher knowledge integration module based on intensity normalization and stage feature fusion strategy. The student knowledge module then uses KL divergence as an optimization operator to establish a probabilistic relationship between feature latent variables, and temperature prediction is achieved through entropy reduction strategy and loss function minimization strategy. The temperature distribution of deep organs is effectively monitored in real time during high-intensity focused ultrasound treatment, laying the foundation for clinical high-intensity focused ultrasound applications.

Description

Technical Field

[0001] The present invention relates to the field of medical diagnosis technology, and in particular to an AI-enabled ultrasonic temperature measurement method for HIFU treatment of deep organs. Background Art

[0002] High-intensity focused ultrasound (HIFU) tumor ablation technology is a non-invasive treatment method. Its basic principle is to use thermal and cavitation effects to rapidly increase the temperature of the focal area, thereby causing coagulative necrosis of tumor tissue, which is subsequently absorbed and cleared by the body. HIFU has the advantages of being radiation-free, non-invasive, and providing real-time treatment, making it widely used in tumor treatment. Although HIFU technology has made significant progress in clinical practice, real-time and accurate monitoring of the acoustic energy absorption distribution within the focal area, that is, the temperature field, remains a fundamental scientific challenge. During HIFU treatment, biological tissue absorbs acoustic energy and converts it into heat. Therefore, measuring and controlling the tissue temperature in the HIFU focal area is crucial to improving the therapeutic effect of HIFU.

[0003] Compared with traditional temperature measurement techniques such as thermocouples and magnetic resonance imaging, ultrasound offers several advantages, including high temporal resolution, lack of radiation, low cost, strong immunity to electromagnetic interference, and ease of integration with high-intensity focused ultrasound (HIFU) systems. These advantages make ultrasound an ideal choice for monitoring the temperature field in lesions. In our previous work, we proposed a lightweight neural network algorithm, the Deep Multimodal Teacher-Student Model, which establishes a nonlinear mapping relationship between ultrasound signals and temperature fields by leveraging ultrasound B-mode images, hemodynamics, and stress changes. This method successfully established a physical model of temperature distribution and enabled real-time monitoring of the two-dimensional temperature field of animal muscle in vivo (0.3 seconds per frame, maximum error less than 3°C, and average error less than 2.5°C). Although the Deep Multimodal Teacher-Student Model performs well in detecting the temperature field of muscle tissue, it remains challenging to reconstruct the temperature field of complex deep organs, which are susceptible to physiological motion (such as respiration and heartbeat) under ultrasound guidance.

[0004] Ultrasound artifacts and errors caused by physiological motion often interfere with the reconstruction of the temperature field in the focal region of high-intensity focused ultrasound (HIFU). To address this issue, researchers have proposed gating strategies that utilize electrocardiogram (ECG) signals or image correlation coefficients to capture images during the same physiological motion phase and established motion compensation strategies to correct for deformed images. However, gating strategies require additional hardware and algorithmic support, increasing system complexity and cost and introducing time delays that affect the efficiency of real-time monitoring. Another research approach is adaptive filters, such as least mean square (LMS), recursive least squares (RLS), and Kalman filters. Researchers have improved the robustness of these filters in complex environments by optimizing algorithms and improving filter design. However, adaptive filters require dynamic adjustment of filter parameters, increasing computational burden and processing time. Furthermore, they are ineffective when dealing with large, rapidly varying noise. Therefore, researchers have explored fast artifact removal methods, such as regularization algorithms. These algorithms stabilize the computation by introducing constraints in the optimization process and utilize global and local information to suppress local noise in the displacement estimate. However, excessive regularization can lead to oversmoothing, resulting in the loss of important details and compromising measurement accuracy. In summary, these methods have limitations and cannot fully meet the requirements of end-to-end high-intensity focused ultrasound temperature field detection. Typically, motion correction is first achieved through a motion compensation algorithm, and then the temperature field is reconstructed using a temperature inversion algorithm. This two-step approach hinders rapid clinical temperature detection. Summary of the Invention

[0005] In order to solve the technical problems existing in the background technology, the present invention aims to provide an AI-enabled ultrasound temperature measurement method for HIFU treatment of deep organs, which can effectively monitor the temperature distribution of deep organs in real time during high-intensity focused ultrasound treatment, lay the foundation for the clinical application of high-intensity focused ultrasound, provide a scientific and accurate dose planning solution, and provide effective guidance for non-invasive cancer treatment.

[0006] In order to solve the technical problem, the technical solution of the present invention is:

[0007] An AI-enabled ultrasound temperature measurement method for deep-seated organ HIFU treatment, comprising: acquiring ultrasound echo signals and temperature data, constructing a breathing-guided multimodal teacher-student model, and reconstructing the deep-seated organ temperature field;

[0008] The multimodal teacher-student model of breathing guidance includes: a breathing prediction module, a multimodal teacher knowledge integration module and a student knowledge permission module.

[0009] Furthermore, the multimodal teacher-student model of breathing guidance is constructed, including:

[0010] A quasi-periodic respiratory phase curve is established through the normalized cross-correlation coefficient of RF data and the gating threshold strategy, and then the phase analysis technology is used to extract the six respiratory phases. Subsequently, starting from the energy parameters of the high-intensity focused ultrasound probe, a multi-layer perceptual mapping of acoustic parameters is constructed in the multimodal teacher knowledge integration module based on intensity normalization and stage feature fusion strategy; then the student knowledge licensing module uses KL divergence as the optimization operator to establish a probabilistic relationship between feature latent variables, and realizes temperature prediction through entropy reduction strategy and loss function minimization strategy.

[0011] Furthermore, a high-intensity focused ultrasound system was used to conduct in vivo experiments to collect ultrasound echo signals and temperature data.

[0012] Furthermore, the respiration prediction module is used to demodulate the radio frequency data into a quasi-periodic respiration curve and establish a relationship between the ultrasound signal and the respiration phase through phase analysis, thereby capturing the displacement caused by the physiological movement of deep organs;

[0013] The multimodal teacher knowledge integration module is used to reconstruct the ultrasound signal into a temperature representation by combining high-intensity focused ultrasound acoustic parameters and an intensity normalization strategy and a stage feature fusion strategy;

[0014] The student knowledge licensing module is used to fit the probability distribution matrix in the latent space of the multimodal teacher knowledge integration module, reduce the matrix calculation load in the neural network and improve the reasoning speed.

[0015] Furthermore, the respiratory prediction module specifically includes: first calculating the normalized cross-correlation coefficient of the radiofrequency data to extract the animal's respiratory phase; then setting the normalized cross-correlation coefficient threshold based on the amplitude gating principle to preliminarily filter the radiofrequency data; finally, establishing a small area around the thermocouple and using a gradient update strategy to map the relationship between the small area and the respiratory phase, wherein the normalized cross-correlation coefficient formula of the radiofrequency data is as follows:

[0016]

[0017] Where γ(m)∈R 1×M ,COV(X,X m ) is the RF reference data X and the i-th frame data X m The covariance of X and σ X,m X and X respectively m The standard deviation of

[0018] Taking the six breathing stages as labels, multi-class cross entropy is used to update the weights, and the formula is as follows:

[0019]

[0020] Where S is the total number of samples, C=6 is the respiratory stage category, represents the actual label of the i-th sample, It represents the probability distribution of the model predicting that the i-th sample belongs to each respiratory stage category;

[0021] Furthermore, the multimodal teacher knowledge integration module incorporates high-intensity focused ultrasound acoustic parameters and treatment duration as prior knowledge into the neural network. represents the high-intensity focused ultrasound acoustic parameters and treatment duration, where H f is the high-intensity focused ultrasound frequency, H p Indicates the high-intensity focused ultrasound power, The duration of the high-intensity focused ultrasound pulse is H t Duration of high-intensity focused ultrasound treatment; the intensity normalization strategy introduced by the multimodal teacher knowledge integration module is to h ∈R S×m Normalize, which represents the feature map output of H, and then use the affine transformation of the trainable parameters, that is, rescaling parameter α h and bias parameter β h , the formula is as follows:

[0022]

[0023] in is the output of the intensity normalization strategy, μ h and σ h They are x h The mean and standard deviation of , ε is used for stability.

[0024] Furthermore, the student knowledge licensing module makes full use of multimodal data to explore the temperature prediction of the high-intensity focused ultrasound focal area based on ultrasound signals. Specifically, a lightweight ResNet18 is determined as E s , where x and H are E s Input, z s ∈R S×S It is E s The extracted feature map, the feature map in the latent space represents the probability distribution of the neural network output, so KL divergence is used to establish z s and x hifu The probability relationship between them is as follows:

[0025]

[0026] By minimizing the KL divergence loss function, z can be reduced s and Bx hifu The relative entropy between them makes z in the latent space sThe distribution gradually approaches x hifu ;

[0027] The multimodal teacher knowledge integration module and the student knowledge licensing module both use the mean square error loss function, which is formulated as follows:

[0028] where y h is the prediction result, y t For label.

[0029] Furthermore, the multimodal data includes: acoustic parameters, treatment duration, respiratory stage category and ultrasound signal.

[0030] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements any of the above-mentioned AI-enabled ultrasonic temperature measurement methods for deep organ HIFU treatment.

[0031] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned AI-enabled ultrasonic temperature measurement methods for deep organ HIFU treatment.

[0032] Compared with the prior art, the advantages of the present invention are:

[0033] First, a high-intensity focused ultrasound (HIFU) system was used to collect ultrasound echo signals and temperature change data from deep-seated organs during treatment. An artificial intelligence (AI) algorithm, a respiration-guided multimodal teacher-student model, was proposed. This model established a quasi-periodic respiratory phase curve using the normalized cross-correlation coefficient of radiofrequency data and a gated threshold strategy. Six respiratory phases were then extracted using phase analysis techniques. Subsequently, based on the HIFU probe energy parameters, a multi-layer perceptual mapping of acoustic parameters was constructed within the multimodal teacher knowledge integration module using intensity normalization and phase feature fusion. The student knowledge module then used KL divergence as an optimization operator to establish probabilistic relationships between feature latent variables. Temperature prediction was achieved through entropy reduction and loss function minimization. This method effectively monitors temperature distribution in deep organs in real time during HIFU treatment, laying the foundation for clinical HIFU applications, providing a scientifically accurate dose planning solution, and offering effective guidance for non-invasive cancer treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 , the main flow chart of the AI-enabled ultrasonic temperature measurement method for HIFU treatment of deep organs of the present invention. DETAILED DESCRIPTION

[0035] The specific implementation of the present invention is described below in conjunction with examples:

[0036] It should be noted that the structures, proportions, sizes, etc. shown in this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the conditions under which the present invention can be implemented. Any structural modification, change in proportional relationship or adjustment of size should still fall within the scope of the technical content disclosed in the present invention without affecting the efficacy and purpose that can be achieved by the present invention.

[0037] At the same time, the terms such as "upper", "lower", "left", "right", "middle" and "one" quoted in this specification are only for the convenience of description and are not used to limit the scope of implementation of the present invention. Changes or adjustments to their relative relationships should be regarded as the scope of implementation of the present invention without substantially changing the technical content.

[0038] HIFU: High-intensity focused ultrasound.

[0039] Example 1:

[0040] Power ultrasound transmits energy through high-intensity sound waves and has great potential in clinical applications. A classic example is high-intensity focused ultrasound (HIFU), which is widely used for non-invasive tumor ablation in deep organs. During HIFU treatment, biological tissue absorbs the sound wave energy and converts it into heat. The temperature of the HIFU focal area then rises rapidly, leading to coagulative necrosis of the tumor tissue. Therefore, controlling tissue temperature is crucial to improving the treatment effect. Although HIFU technology has made significant progress in clinical practice, non-invasive and accurate real-time temperature monitoring within the HIFU focal area remains a fundamental scientific challenge.

[0041] Unlike other temperature measurement techniques, such as thermocouples and magnetic resonance imaging, ultrasound offers the advantages of real-time, non-invasiveness, and ease of integration with high-intensity radiated ultrasonography (HIFU) treatment systems. These advantages make ultrasound an ideal choice for monitoring the temperature field within the lesion. Traditional ultrasound monitoring of the temperature field within the HIFU focal region relies primarily on echo signals, as tissue acoustic parameters, such as ultrasound attenuation, velocity of sound, density, and thermal expansion, typically exhibit linear functions of temperature within the range of 37°C to 50°C. However, nonlinear relationships emerge above 50°C, limiting its application. Indeed, during HIFU treatment, controlling the focal region temperature above 60°C is crucial to ensure effective coagulative necrosis. Therefore, to address the conflict between existing technologies and clinical needs, exploring new ultrasound temperature measurement technologies and expanding the measurement range are essential.

[0042] Artificial intelligence (AI) has recently shown significant potential in solving clinical medical problems, ranging from image recognition and segmentation to treatment planning. Therefore, it is worth investigating whether AI-driven ultrasound technology can address the challenge of monitoring hyperthermia (T > 50°C) in the HIFU focal area. However, to our knowledge, such studies remain relatively scarce.

[0043] Here, an AI-based ultrasound temperature measurement technique is proposed, which adopts an end-to-end deep neural network model called breathing-guided multimodal teacher-student network (BMTS). The BMTS model is proven to be able to elucidate the interaction between HIFU and complex heterogeneous biological media. After removing physiological noise, the two-dimensional temperature distribution of the HIFU focal area in the rabbit liver can be accurately reconstructed with an average error of 0.8°C and a frame rate of 0.37 seconds. Most importantly, the temperature measurement range of the ultrasound technology has been successfully extended from 37°C-50°C to 37°C-67°C. This breakthrough shows that AI-based ultrasound temperature measurement technology is a promising solution for monitoring temperature changes in deep organs during HIFU ablation.

[0044] like Figure 1 As shown, the present invention provides a technical solution: a method for real-time reconstruction of the focal temperature field of deep organs during high-intensity focused ultrasound (HIFU). This method first uses an HIFU system to collect ultrasound echo signals and temperature change data from deep organs during treatment. Furthermore, a breathing-guided multimodal teacher-student model is proposed. This model establishes a quasi-periodic respiratory phase curve using the normalized cross-correlation coefficient of radiofrequency data and a gated threshold strategy. Six respiratory phases are then extracted using phase analysis techniques. Subsequently, based on the HIFU probe energy parameters, a multi-layer perceptual mapping of acoustic parameters is constructed in the multimodal teacher knowledge integration module using intensity normalization and phase feature fusion strategies. The student knowledge module then uses KL divergence as an optimization operator to establish probabilistic relationships between feature latent variables. Temperature prediction is achieved through entropy reduction and loss function minimization strategies. This method effectively monitors the temperature distribution of deep organs in real time during HIFU treatment, laying the foundation for clinical HIFU applications, providing a scientifically accurate dose planning solution, and offering effective guidance for non-invasive cancer treatment.

[0045] A method for real-time reconstruction of the focal temperature field of deep organs using high-intensity focused ultrasound (HIFU) is described. The method comprises the following steps: Step 1: Conducting in vivo animal experiments to collect ultrasound echo signals and temperature change data. Step 2: Processing the data and feeding it into a breathing-guided multimodal teacher-student model for training. Step 3: Fixing the model parameters. Step 4: Using the trained model to reconstruct the deep organ temperature field.

[0046] For the in vivo animal experiments, five New Zealand rabbits (weight: 4.5±1 kg) were selected. Anesthesia was induced by intramuscular injection of 1.3 ml of ketamine. After establishing intravenous access in the rabbit's marginal ear vein, 2-3 ml of vecuronium bromide was injected intravenously to achieve muscle relaxation. After anesthesia induction, the rabbit was intubated and connected to a ventilator to replace spontaneous breathing. Anesthesia was maintained using isoflurane at a rate of 0.6 ml / min. The inspiratory to expiratory time ratio was set to approximately 0.5, and the respiratory rate was maintained at 30 times per minute. Both parameters were adjusted to keep the oxygen saturation above 95%. The rabbit was placed supine on a board with its forelimbs crossed. The hair on the chest and upper abdomen was shaved using a trimmer and depilatory cream to expose the skin for high-intensity focused ultrasound treatment.

[0047] To accurately locate the temperature measurement site and install the temperature measurement device, the following procedure was performed: First, under ultrasound guidance, the middle lobe of the liver was located. A flat area with significant tissue thickness and no major blood vessels was selected as the focal point and thermocouple placement location. The shaved area was disinfected with 75% alcohol, and three acupuncture points were marked on the skin with a marker, each at a depth of 1-3 cm and in the same plane. The skin was incised with the tip of a scalpel (approximately 0.3 cm). Under ultrasound guidance, a 15G puncture needle and cannula were inserted at the marked points. After ensuring a puncture depth of 3-5 cm, the needle was removed, and the thermocouples were inserted through the cannula. During the experiment, the three thermocouples were used to record the spatiotemporal temperature distribution perpendicular to the heating beam axis. The treatment head was adjusted so that the focal point and the tips of the three thermocouples were in the same plane and visible on the ultrasound image. The thermocouples were connected to the temperature detection system and numbered TC1, TC2, and TC3, with each thermocouple positioned progressively farther away from the heating zone. TC1 was located at the focal point, and adjacent thermocouples were spaced 2 mm apart. At the end of the experiment, the rabbits were euthanized by injecting air (20–40 ml) through the marginal ear vein. All animal experiments were performed according to protocols approved by the Animal Welfare and Ethics Group of the Department of Laboratory Animal Science, Fudan University (202310034S).

[0048] During the experiment, HIFU therapeutic waves were used to heat the focal area. Simultaneously with treatment, temperature was recorded in real time using thermocouples, and radiofrequency data were collected and exported. Thermocouple and radiofrequency data were sampled at 10 Hz and 24 MHz, respectively, and ultrasound images were captured at a fixed frame rate of 9 FPS. Each ultrasound image covered a depth range of 0–12 cm, with a frame size of 128 (horizontally) × 2078 (vertically) pixels.

[0049] The respiration prediction module first calculates the normalized cross-correlation coefficient of the RF data to extract the animal's respiratory phase. It then sets a normalized cross-correlation coefficient threshold based on the amplitude gating principle to initially filter the RF data. Finally, it creates small regions around the thermocouples and uses a gradient update strategy to map the relationship between these small regions and the respiratory phase. The formula for the normalized cross-correlation coefficient of the RF data is as follows:

[0050]

[0051] Where γ(m)∈R 1×M ,COV(X,X m ) is the RF reference data X and the i-th frame data X m The covariance of X and σ X,m X and X respectively m The standard deviation of .

[0052] The breathing prediction module uses the six breathing stages as labels and uses multi-class cross entropy to update the weights. The formula is as follows:

[0053]

[0054] Where S is the total number of samples, C=6 is the respiratory stage category, represents the actual label of the i-th sample, Represents the probability distribution of the model predicting that the i-th sample belongs to each respiratory stage category.

[0055] The multimodal teacher knowledge integration module incorporates high-intensity focused ultrasound acoustic parameters and treatment duration as prior knowledge into the neural network. represents the high-intensity focused ultrasound acoustic parameters and treatment duration, where H f is the high-intensity focused ultrasound frequency, H p Indicates the high-intensity focused ultrasound power, The duration of the high-intensity focused ultrasound pulse is H t Duration of high-intensity focused ultrasound treatment. The intensity normalization strategy introduced by the multimodal teacher knowledge integration module is to h ∈R S×m Normalize, which represents the feature map output of H, and then use the affine transformation of the trainable parameters, that is, rescaling parameter α h and bias parameter β h , the formula is as follows:

[0056]

[0057] in is the output of the intensity normalization strategy. h and σh They are x h The mean and standard deviation of , ε is used for stability.

[0058] The student knowledge license module makes full use of multimodal data (acoustic parameters, treatment duration, respiratory stage category and ultrasound signal) to explore the temperature prediction of the high-intensity focused ultrasound focal area based on ultrasound signal. Specifically, a lightweight ResNet18 is defined as E s , where x and H are E s Input, z s ∈R S×S It is E s Extracted feature maps. Since the feature maps in the latent space represent the probability distribution of the neural network output, KL divergence can be used to establish z s and x hifu The probability relationship between them is as follows:

[0059]

[0060] By minimizing the KL divergence loss function, z can be reduced s and Bx hifu The relative entropy between them makes z in the latent space s The distribution gradually approaches x hifu .

[0061] The multimodal teacher knowledge integration module and the student knowledge licensing module both use the mean square error loss function, which is formulated as follows:

[0062] where y h is the prediction result, y t For label.

[0063] The present invention's method for real-time reconstruction of the focal temperature field of deep-seated organs during high-intensity focused ultrasound (HIFU) therapy can be applied to deep-seated organ temperature field reconstruction during HIFU therapy. This method achieves a maximum temperature error of approximately 2.6°C and a reconstruction speed of 0.37 seconds per frame. This method lays the foundation for clinical HIFU applications, provides a scientifically accurate dose planning solution, and offers effective guidance for non-invasive cancer treatment.

[0064] Example 2:

[0065] This embodiment provides a terminal device, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for a method for real-time reconstruction of the focal temperature field of deep organs using high-intensity focused ultrasound, comprising the following steps:

[0066] A method for real-time reconstruction of the focal temperature field of deep organs using high-intensity focused ultrasound (HIFU) comprises the following steps: Step 1: Conduct an in vivo experiment, using a high-intensity focused ultrasound system to collect ultrasound echo signals and temperature change data from deep organs during treatment. Step 2: Process the data and feed it into a breathing-guided multimodal teacher-student model for training. Step 3: Fix the model parameters. Step 4: Use the trained model to reconstruct the deep organ temperature field.

[0067] Example 3:

[0068] This embodiment provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It is understandable that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and, of course, the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0069] The processor may load and execute one or more instructions stored in a computer-readable storage medium to implement the corresponding steps of the method for real-time reconstruction of a focal temperature field of a deep-seated organ using high-intensity focused ultrasound in the above-mentioned embodiment. The processor may load and execute the following steps:

[0070] Step 1: Conduct an in vivo experiment, using a high-intensity focused ultrasound system to collect ultrasound echo signals and temperature change data from deep-seated organs during treatment. Step 2: Process this data and feed it into a breathing-guided multimodal teacher-student model for training. Step 3: Fix the model parameters. Step 4: Use the trained model to reconstruct the temperature field of deep-seated organs.

[0071] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0072] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0073] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0075] The preferred embodiments of the present invention are described in detail above, but the present invention is not limited to the above embodiments. Various changes can be made within the knowledge of ordinary technicians in this field without departing from the scope of the present invention.

[0076] Many other changes and modifications can be made without departing from the spirit and scope of the present invention. It should be understood that the present invention is not limited to the specific embodiments, and the scope of the present invention is defined by the appended claims.

Claims

1. An AI-enabled ultrasound temperature measurement method for deep organ HIFU treatment, characterized by: The method comprises: collecting ultrasonic echo signals and temperature data, constructing a respiratory-guided multimodal teacher-student model, and reconstructing a deep organ temperature field; The multimodal teacher-student model for breathing guidance includes: a breathing prediction module, a multimodal teacher knowledge integration module, and a student knowledge permission module; The multimodal teacher-student model for breathing guidance is constructed, including: A quasi-periodic respiratory phase curve is established through the normalized cross-correlation coefficient of RF data and the gating threshold strategy, and then the phase analysis technology is used to extract the six respiratory phases. Subsequently, starting from the energy parameters of the high-intensity focused ultrasound probe, a multi-layer perceptual mapping of acoustic parameters is constructed in the multimodal teacher knowledge integration module based on intensity normalization and stage feature fusion strategy; then the student knowledge licensing module uses KL divergence as the optimization operator to establish a probabilistic relationship between feature latent variables, and realizes temperature prediction through entropy reduction strategy and loss function minimization strategy.

2. The AI-enabled ultrasonic temperature measurement method for deep organ HIFU treatment according to claim 1, characterized in that: In vivo experiments were conducted using a high-intensity focused ultrasound system to collect ultrasound echo signals and temperature data.

3. The AI-enabled ultrasonic temperature measurement method for deep organ HIFU treatment according to claim 1 is characterized in that: The respiration prediction module is used to demodulate the radio frequency data into a quasi-periodic respiration curve and establish the relationship between the ultrasound signal and the respiration phase through phase analysis, thereby capturing the displacement caused by the physiological movement of deep organs; The multimodal teacher knowledge integration module is used to reconstruct the ultrasound signal into a temperature representation by combining high-intensity focused ultrasound acoustic parameters and an intensity normalization strategy and a stage feature fusion strategy; The student knowledge licensing module is used to fit the probability distribution matrix in the latent space of the multimodal teacher knowledge integration module, reduce the matrix calculation load in the neural network and improve the reasoning speed.

4. The AI-enabled ultrasonic temperature measurement method for deep organ HIFU treatment according to claim 1, characterized in that: The respiratory prediction module specifically includes: first, calculating the normalized cross-correlation coefficient of the radiofrequency data to extract the animal's respiratory phase; then, setting the normalized cross-correlation coefficient threshold based on the amplitude gating principle to preliminarily filter the radiofrequency data; finally, establishing a small area around the thermocouple and using a gradient update strategy to map the relationship between the small area and the respiratory phase. The formula for the normalized cross-correlation coefficient of the radiofrequency data is as follows: Among them, γ(m)∈r 1×M ,COV(X,X m ) is the RF reference data X and the i-th frame data X m The covariance of X and σ X,m X and X respectively m The standard deviation of Taking the six breathing stages as labels, multi-class cross entropy is used to update the weights, and the formula is as follows: Where S is the total number of samples, C=6 is the respiratory stage category, represents the actual label of the i-th sample, Represents the probability distribution of the model predicting that the i-th sample belongs to each respiratory stage category.

5. The AI-enabled ultrasonic temperature measurement method for deep organ HIFU treatment according to claim 1 is characterized in that: The multimodal teacher knowledge integration module incorporates high-intensity focused ultrasound acoustic parameters and treatment duration as prior knowledge into the neural network. represents the high-intensity focused ultrasound acoustic parameters and treatment duration, where H f is the high-intensity focused ultrasound frequency, H p Indicates the high-intensity focused ultrasound power, The duration of the high-intensity focused ultrasound pulse is H t duration of high-intensity focused ultrasound treatment; The strength normalization strategy introduced by the multimodal teacher knowledge integration module is to h ∈R S×m Normalize, which represents the feature map output of H, and then use the affine transformation of the trainable parameters, that is, rescaling parameter α h and bias parameter β h , the formula is as follows: in is the output of the intensity normalization strategy, μ h and σ h They are x h The mean and standard deviation of , ε is used for stability.

6. The AI-enabled ultrasonic temperature measurement method for deep organ HIFU treatment according to claim 1, characterized in that: The student knowledge licensing module makes full use of multimodal data to explore the temperature prediction of the high-intensity focused ultrasound focal area based on ultrasound signals. Specifically, a lightweight ResNet18 is determined as E s , where x and H are E s Input, z s ∈R S ×S It is E s The extracted feature map, the feature map in the latent space represents the probability distribution of the neural network output, so KL divergence is used to establish z s and x hifu The probability relationship between them is as follows: By minimizing the KL divergence loss function, we reduce z s and Bx hifu The relative entropy between them makes z in the latent space s The distribution gradually approaches x hift ; The multimodal teacher knowledge integration module and the student knowledge licensing module both use the mean square error loss function, which is formulated as follows: where y h is the prediction result, y t For label.

7. The AI-enabled ultrasonic temperature measurement method for deep organ HIFU treatment according to claim 6, characterized in that: The multimodal data includes: acoustic parameters, treatment duration, respiratory phase category and ultrasound signal.

8. A computer device, characterized in that: The invention comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, an AI-enabled ultrasonic temperature measurement method for deep organ HIFU treatment according to any one of claims 1 to 7 is implemented.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements an AI-enabled ultrasonic temperature measurement method for deep organ HIFU treatment according to any one of claims 1 to 7.

Images