Ultrasonic temperature measurement method and device, computer device, storage medium and program product
By combining ultrasonic image target detection and signal filtering with temperature regression algorithm, the problems of insufficient accuracy and real-time performance in ultrasonic temperature measurement methods are solved, and efficient and accurate temperature measurement is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHANGHAI YINGTAI PURUN MEDICAL INSTR CO LTD
- Filing Date
- 2026-04-15
- Publication Date
- 2026-07-21
AI Technical Summary
Existing ultrasonic temperature measurement methods rely on a single physical parameter, resulting in large temperature inversion errors, low accuracy, and complex and time-consuming calculations with poor real-time performance.
By acquiring orthogonal ultrasonic signals, generating ultrasonic images, performing target detection to determine the target area of the region to be measured, filtering orthogonal ultrasonic signals based on the target area, and finally performing temperature regression processing, the accuracy and efficiency of temperature measurement are improved.
It improves the accuracy and efficiency of ultrasonic temperature measurement, reduces the amount of computation, ensures real-time performance, avoids interference from signals from other locations, and simplifies multiple iterative calculations.
Smart Images
Figure CN122429945A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of ultrasonic signal processing technology, specifically to ultrasonic temperature measurement methods, devices, computer equipment, storage media, and program products. Background Technology
[0002] With the widespread adoption of minimally invasive surgeries such as high-intensity focused ultrasound (HIFU) and laser ablation, real-time temperature monitoring has become a clinical necessity. Ultrasound imaging, with its advantages of being radiation-free, easy to operate, and providing real-time imaging, has been extensively studied for intraoperative temperature measurement. Related techniques primarily rely on analyzing changes in the velocity of sound, echo frequency shift, or tissue elasticity to indirectly estimate temperature, such as temperature-dependent sound velocity models or time-shift estimation algorithms.
[0003] However, the above method relies on a single physical parameter, which leads to large temperature inversion errors, low accuracy, and requires multiple iterative calculations, making the calculations complex, time-consuming, and lacking in real-time performance. Summary of the Invention
[0004] In view of this, the purpose of the present invention is to provide an ultrasonic temperature measurement method, device, computer equipment, storage medium and program product to solve the problems of low accuracy and poor real-time performance in ultrasonic temperature measurement.
[0005] In a first aspect, the present invention provides an ultrasonic temperature measurement method, the method comprising: Acquire orthogonal ultrasonic signals from the region to be tested; An ultrasound image is generated based on the aforementioned orthogonal ultrasound signals; Target detection is performed on the ultrasound image to obtain the target area of the region to be tested; Based on the target area of the region to be tested, the ultrasonic orthogonal signals are filtered to obtain the target ultrasonic orthogonal signals; Temperature regression processing is performed on the target ultrasonic orthogonal signal to perform ultrasonic temperature measurement on the target area.
[0006] In one optional implementation, the temperature regression processing of the target ultrasonic orthogonal signal includes: Extract the time-domain and frequency-domain features of the target ultrasonic orthogonal signal, respectively; The time-domain features and frequency-domain features are fused to obtain ultrasound fusion features; Temperature prediction is performed based on the aforementioned ultrasonic fusion characteristics.
[0007] In one optional implementation, the extraction of the time-domain and frequency-domain features of the target ultrasound orthogonal signal includes: The real part of the target ultrasonic orthogonal signal is extracted to obtain the first time-domain features; The imaginary part of the target ultrasonic orthogonal signal is extracted to obtain the second time-domain features; The target ultrasound orthogonal signal is converted into a target ultrasound real signal, and feature extraction is performed to obtain frequency domain features.
[0008] In one optional implementation, converting the target ultrasound orthogonal signal into a target ultrasound real signal includes: The target ultrasonic orthogonal signal is subjected to Fourier transform to obtain the target ultrasonic frequency domain signal; The target ultrasonic frequency domain signal is subjected to a modulus extraction operation to generate a target ultrasonic real number signal.
[0009] In one optional implementation, the feature fusion of the time-domain features and frequency-domain features to obtain ultrasound fusion features includes: The first time-domain feature, the second time-domain feature, and the frequency-domain feature are concatenated to obtain the ultrasound fusion feature; The temperature prediction based on the ultrasound fusion features includes: The ultrasonic fusion features are mapped to temperature values for temperature prediction.
[0010] In one optional implementation, the step of performing target detection on the ultrasound image to obtain the target region of the area to be tested includes: The ultrasound image is subjected to target detection using a target detection model to obtain the target area of the region to be tested; the target detection model is pre-trained based on ultrasound sample images with the target area marked.
[0011] Secondly, the present invention provides an ultrasonic temperature measuring device, the device comprising: The acquisition module is used to acquire the ultrasonic orthogonal signals of the area to be tested; An image generation module is used to generate an ultrasound image based on the ultrasound orthogonal signal; The target detection module is used to perform target detection on the ultrasound image to obtain the target area of the region to be tested; The filtering module is used to filter the ultrasonic orthogonal signals based on the target area of the region to be tested, so as to obtain the target ultrasonic orthogonal signals; The temperature regression module is used to perform temperature regression processing on the target ultrasonic orthogonal signal in order to perform ultrasonic temperature measurement on the target area.
[0012] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the ultrasonic temperature measurement method of the first aspect or any corresponding embodiment described above.
[0013] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the ultrasonic temperature measurement method of the first aspect or any corresponding embodiment described above.
[0014] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the ultrasonic temperature measurement method of the first aspect or any corresponding embodiment described above.
[0015] The technical solution provided by this invention may include the following beneficial effects: The ultrasonic temperature measurement method provided by this invention first acquires the ultrasonic orthogonal signal of the area to be measured, then generates an ultrasonic image based on the ultrasonic orthogonal signal, next performs target detection on the ultrasonic image to obtain the target area of the area to be measured, then filters the ultrasonic orthogonal signal based on the target area of the area to be measured to obtain the target ultrasonic orthogonal signal, and finally performs temperature regression processing on the target ultrasonic orthogonal signal to perform ultrasonic temperature measurement on the target area. By performing target detection on the ultrasonic image to obtain the target area of the area to be measured, and then filtering the ultrasonic orthogonal signal based on the target area of the area to be measured, only the ultrasonic orthogonal signal corresponding to the target area is retained. This allows subsequent temperature regression to be performed only on the target area, avoiding interference caused by ultrasonic orthogonal signals corresponding to other locations, improving the accuracy of ultrasonic temperature measurement, reducing the computational load of subsequent temperature regression processing, improving the efficiency of ultrasonic temperature measurement, and ensuring the real-time performance of ultrasonic temperature measurement. By performing temperature regression processing on the target ultrasonic orthogonal signal, the correspondence between the target ultrasonic orthogonal signal and the temperature value is analyzed to predict the temperature value corresponding to the target ultrasonic orthogonal signal. This eliminates the multiple loop calculations in the algorithm of related technologies, reduces the amount of computation, and improves the efficiency of ultrasonic temperature measurement. Attached Figure Description
[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0017] Figure 1 This is a schematic flowchart of an ultrasonic temperature measurement method according to an embodiment of the present invention; Figure 2 This is a schematic flowchart of another ultrasonic temperature measurement method according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a multi-view complex neural network according to an embodiment of the present invention; Figure 4 This is a structural block diagram of an ultrasonic temperature measuring device according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0019] With the widespread adoption of minimally invasive surgeries such as high-intensity focused ultrasound (HIFU), laser ablation, and radiofrequency ablation, real-time temperature monitoring has become a clinical necessity. Ultrasound imaging, with its advantages of being radiation-free, easy to operate, and providing real-time imaging, has been extensively studied for intraoperative temperature measurement. Related techniques primarily rely on analyzing changes in the velocity of sound, echo frequency shift, or tissue elasticity to indirectly estimate temperature, such as temperature-dependent sound velocity models or time-shift estimation algorithms.
[0020] However, the above method relies on a single physical parameter, resulting in large temperature inversion errors, low accuracy, and requires multiple iterative calculations, which are computationally complex and have poor real-time performance.
[0021] Therefore, this invention provides an ultrasonic temperature measurement method that improves the efficiency and accuracy of ultrasonic temperature measurement by detecting the target area of the area to be measured, filtering the ultrasonic orthogonal signals based on the target area, and then performing temperature regression.
[0022] According to an embodiment of the present invention, an ultrasonic temperature measurement method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0023] This embodiment provides an ultrasonic temperature measurement method that can be used in desktop computers, laptops, servers, etc. Figure 1 This is a flowchart of an ultrasonic temperature measurement method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps: Step S101: Obtain the ultrasonic orthogonal signal of the area to be tested.
[0024] The area to be measured can be a diseased tissue area that requires ultrasound temperature measurement. Optionally, a high-frequency sound wave (e.g., 2-15MHz) is emitted into the area to be measured by an ultrasound probe, and the echo signal reflected by the tissue is received. The received echo signal is decomposed into in-phase (I) and quadrature (Q) signals by the quadrature demodulator in the ultrasound probe to obtain the ultrasound quadrature signal (ultrasound IQ signal).
[0025] Step S102: Generate an ultrasound image based on the ultrasound orthogonal signal.
[0026] Optionally, the ultrasound orthogonal signal can be preprocessed, such as by time gain compensation (TGC) and dynamic filtering, to eliminate noise and depth attenuation effects. Then, beamforming can be performed, for example by aligning the phases of the multi-element ultrasound orthogonal signal using a time-delay superposition algorithm to achieve dynamic focusing. Next, envelope detection can be performed, and finally, image optimization can be performed, such as spatial composite noise reduction and edge enhancement, to obtain the ultrasound image.
[0027] Step S103: Target detection is performed on the ultrasound image to obtain the target area of the region to be tested.
[0028] The target area refers to a specific anatomical region or lesion tissue that requires targeted intervention in medical treatment; it is the core target area in the treatment plan. Since the target area's location may change due to the patient's breathing or movement during treatment, target detection can be used to track and locate the target area within the treatment region. Optionally, a target detection algorithm with automatic target area identification capability can be used to perform target detection on ultrasound images to identify the target area within the treatment region. This target detection algorithm is pre-trained using a sample image set labeled with target areas.
[0029] Step S104: Based on the target area of the region to be tested, the ultrasonic orthogonal signals are screened to obtain the target ultrasonic orthogonal signals.
[0030] After the target area is detected, the ultrasonic orthogonal signals are filtered based on the target area, and only the corresponding ultrasonic orthogonal signals within the target area are retained, which improves accuracy and reduces the amount of calculation required for subsequent temperature regression processing, thereby improving efficiency and real-time performance.
[0031] Step S105: Perform temperature regression processing on the target ultrasonic orthogonal signal to perform ultrasonic temperature measurement on the target area.
[0032] When the temperature in the target area increases, leading to local protein denaturation, some acoustic properties of the ultrasound signal (such as echo intensity or propagation speed) change, affecting the orthogonal ultrasound signal received by the ultrasound equipment and thus altering the reconstructed ultrasound image. Therefore, a temperature regression algorithm with ultrasound thermometry capabilities can be used to obtain the time and frequency domain characteristics of the target orthogonal ultrasound signal, analyze the relationship between the target orthogonal ultrasound signal and temperature, and thus predict the temperature corresponding to the target orthogonal ultrasound signal, obtaining the temperature measurement result of the target target area. This temperature regression algorithm is pre-trained using ultrasound orthogonal signal samples with known corresponding temperatures.
[0033] The ultrasonic temperature measurement method provided in this embodiment first acquires the ultrasonic orthogonal signal of the area to be measured, then generates an ultrasonic image based on the ultrasonic orthogonal signal, next performs target detection on the ultrasonic image to obtain the target area of the area to be measured, then filters the ultrasonic orthogonal signal based on the target area of the area to be measured to obtain the target ultrasonic orthogonal signal, and finally performs temperature regression processing on the target ultrasonic orthogonal signal to perform ultrasonic temperature measurement on the target area. By performing target detection on the ultrasonic image to obtain the target area of the area to be measured, and then filtering the ultrasonic orthogonal signal based on the target area of the area to be measured, only the ultrasonic orthogonal signal corresponding to the target area is retained. This allows subsequent temperature regression to be performed only on the target area, avoiding interference caused by ultrasonic orthogonal signals corresponding to other locations, improving the accuracy of ultrasonic temperature measurement, reducing the computational load of subsequent temperature regression processing, improving the efficiency of ultrasonic temperature measurement, and ensuring the real-time performance of ultrasonic temperature measurement. By performing temperature regression processing on the target ultrasonic orthogonal signal, the correspondence between the target ultrasonic orthogonal signal and the temperature value is analyzed to predict the temperature value corresponding to the target ultrasonic orthogonal signal. This eliminates the multiple loop calculations in the algorithm of related technologies, reduces the amount of computation, and improves the efficiency of ultrasonic temperature measurement.
[0034] This embodiment provides an ultrasonic temperature measurement method that can be used in desktop computers, laptops, servers, etc. Figure 2 This is a flowchart of an ultrasonic temperature measurement method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Train the target detection model to be trained to obtain the target detection model.
[0035] This target detection model has target detection capabilities, used to detect targets in ultrasound images and obtain the target area of the region to be measured. For example, since the ultrasound imaging environment is relatively simple, YOLO V4 is used as the network framework for the target detection model. YOLO V4 has high processing speed and relatively sufficient accuracy, making it very suitable for real-time applications requiring rapid response.
[0036] Optionally, different ultrasound images are first acquired in various target application scenarios, covering different patients, target locations, and respiratory states. Experts then use professional annotation tools (such as Labellmg) to annotate the target areas in the ultrasound sample images, generating corresponding bounding boxes and category labels to form an ultrasound sample image set. This set is then divided into training, validation, and test sets, with settings such as learning rate, batch size, and number of training epochs. The target detection model is then trained using this ultrasound sample dataset to obtain the target detection model. During training, mixed precision training can be used to accelerate the process and reduce memory usage; an early stopping mechanism can be introduced to terminate training prematurely when validation set performance no longer improves, thus avoiding overfitting.
[0037] Step S202: Train the multi-view complex neural network to be trained to obtain the multi-view complex neural network.
[0038] Figure 3 This is a schematic diagram of the structure of a multi-view complex neural network according to an embodiment of the present invention. This multi-view complex neural network has an ultrasonic temperature measurement function, used to perform temperature regression processing on the target ultrasonic orthogonal signal to perform ultrasonic temperature measurement on the target area. For example, a convolutional neural network (CNN) is used as the basic framework of the multi-view complex neural network to process the time shift of the ultrasonic orthogonal signal. Based on the ultrasonic temperature measurement scenario, input layers, convolutional layers, and activation layers are respectively set for the real part of the time domain, the imaginary part of the time domain, and the frequency domain corresponding to the ultrasonic orthogonal signal. Corresponding features are extracted, and a fully connected layer is set to perform multi-view fusion of the features of the output in the real part of the time domain, the imaginary part of the time domain, and the frequency domain. The relationship between the ultrasonic orthogonal signal and temperature is analyzed, mapping the ultrasonic orthogonal signal to temperature values to achieve accurate temperature estimation and obtain the ultrasonic temperature measurement result. In signal processing of related technologies, the real and imaginary parts are often treated as two completely independent parts, and the results are simply superimposed. However, the multi-view complex neural network provided in this embodiment adopts an advanced complex signal processing technology. By establishing a coupled learning mechanism for the real and imaginary parts, independent trainable weights are assigned to the real and imaginary parts, which captures the details and features in the signal more meticulously. This is beneficial for considering the time-shift amplitude of the signal, improving the accuracy of feature extraction, and thus improving the accuracy of temperature regression.
[0039] Optionally, the activation layer uses the ReLU activation function.
[0040] Step S203: Obtain the ultrasonic orthogonal signal of the area to be tested.
[0041] Optionally, a high-pass filter can be used to remove low-frequency noise (such as equipment noise), and a low-pass filter can be used to remove high-frequency interference (such as electromagnetic interference); wavelet transform technology can be combined to extract the effective components in the signal and retain the features related to temperature changes.
[0042] Optionally, data augmentation can be performed on the orthogonal ultrasound signals, such as by rotation, scaling, and translation, to increase data diversity, add random noise to simulate interference in the real environment, and improve robustness.
[0043] Step S204: Generate an ultrasound image based on the ultrasound orthogonal signal.
[0044] Please see details Figure 1 Step S102 of the illustrated embodiment will not be described again here.
[0045] Step S205: Target detection is performed on the ultrasound image to obtain the target area of the region to be tested.
[0046] Optionally, a target detection model is used to perform real-time target detection on the ultrasound image. The region of interest (ROI) is dynamically adjusted according to the real-time state of the area to be detected to ensure the continuity and accuracy of target detection. The bounding box and confidence score of the target area are output to obtain the target area of the area to be detected. Low-quality detection results are filtered according to the confidence score threshold to ensure the reliability of the detection. This target detection model is pre-trained based on ultrasound sample images with labeled target areas. The training process is detailed in step S201 and will not be repeated here.
[0047] Optionally, before target detection, the ultrasound images can be preprocessed, such as normalizing the real-time acquired ultrasound images to ensure the uniformity of the input data; histogram equalization can be used to enhance the contrast of the ultrasound images to improve the subsequent detection effect.
[0048] Optionally, the Kalman filter algorithm can be combined to predict the motion trajectory of the target area and adjust the position of the region of interest in advance; optical flow can be used to analyze the motion pattern of the target area to improve prediction accuracy.
[0049] Optionally, the parameters of the target detection model can be dynamically calibrated based on feedback information to optimize detection performance. An anomaly handling mechanism can also be set up; when an anomaly is detected in the target area (such as exceeding a preset range), an alarm function is triggered. Machine learning algorithms are then used to analyze the cause of the anomaly and provide handling suggestions to remind relevant technical personnel to correct it promptly.
[0050] Step S206: Based on the target area of the region to be tested, the ultrasonic orthogonal signals are screened to obtain the target ultrasonic orthogonal signals.
[0051] Optionally, the ultrasound image is cropped according to the target area of the region to be tested, removing the part outside the target area, and the cropped ultrasound image is converted into a complex signal to obtain the target ultrasound orthogonal signal, which is used as the input for temperature regression.
[0052] Step S207: Perform temperature regression processing on the target ultrasonic orthogonal signal to perform ultrasonic temperature measurement on the target area.
[0053] Specifically, step S207 includes: Step S2071: Extract the time domain features and frequency domain features of the target ultrasonic orthogonal signal, respectively.
[0054] Specifically, the input layer, convolutional layer, and activation layer corresponding to the real part of the time domain of the multi-view complex neural network are used to extract features from the real part of the target ultrasonic orthogonal signal to obtain the first time domain features; the input layer, convolutional layer, and activation layer corresponding to the imaginary part of the time domain of the multi-view complex neural network are used to extract features from the imaginary part of the target ultrasonic orthogonal signal to obtain the second time domain features.
[0055] Simultaneously, the target ultrasound orthogonal signal is converted into a target ultrasound real-valued signal, and feature extraction is performed using the input layer, convolutional layer, and activation layer corresponding to the frequency domain of the multi-view complex neural network to obtain frequency domain features. Specifically, in converting the target ultrasound orthogonal signal into a target ultrasound real-valued signal, a Fourier transform is first performed on the target ultrasound orthogonal signal to obtain the target ultrasound frequency domain signal, and then a modulo operation is performed on the target ultrasound frequency domain signal to generate the target ultrasound real-valued signal. This Fourier transform can convert complex time-domain signals into the frequency domain, thereby providing more information about the signal characteristics.
[0056] Step S2072: The time domain features and frequency domain features are fused to obtain the ultrasound fusion features.
[0057] To ensure maximum information extraction from each signal, this multi-view complex neural network employs a multi-view fusion strategy. This means that the network not only observes the signal from a fixed perspective but also attempts to observe and analyze it from multiple different angles, ensuring that no important information is missed. The design of this neural network fully considers all characteristics of complex signals and uses various strategies to ensure maximum information extraction. This multi-view fusion and independent real and imaginary part processing strategy gives the network higher accuracy and robustness when processing complex signals. Specifically, through the fully connected layer of this multi-view complex neural network, the first time-domain features, the second time-domain features, and the frequency-domain features are concatenated to obtain the ultrasound fusion features.
[0058] Step S2073: Temperature prediction is performed based on the ultrasonic fusion feature.
[0059] The ultrasound fusion features are mapped to temperature values through the fully connected layer of the multi-view complex neural network for temperature prediction.
[0060] Furthermore, in practical application scenarios, by repeating steps S203 to S207, real-time ultrasonic temperature measurement of the area to be measured can be achieved. Compared with related technologies, multiple loop calculations are not required, which reduces the amount of calculation, improves efficiency, and ensures real-time performance.
[0061] The ultrasonic temperature measurement method provided in this embodiment first acquires the ultrasonic orthogonal signal of the area to be measured, then generates an ultrasonic image based on the ultrasonic orthogonal signal, next performs target detection on the ultrasonic image to obtain the target area of the area to be measured, then filters the ultrasonic orthogonal signal based on the target area of the area to be measured to obtain the target ultrasonic orthogonal signal, and finally performs temperature regression processing on the target ultrasonic orthogonal signal to perform ultrasonic temperature measurement on the target area. By performing target detection on the ultrasonic image to obtain the target area of the area to be measured, and then filtering the ultrasonic orthogonal signal based on the target area of the area to be measured, only the ultrasonic orthogonal signal corresponding to the target area is retained. This allows subsequent temperature regression to be performed only on the target area, avoiding interference caused by ultrasonic orthogonal signals corresponding to other locations, improving the accuracy of ultrasonic temperature measurement, reducing the computational load of subsequent temperature regression processing, improving the efficiency of ultrasonic temperature measurement, and ensuring the real-time performance of ultrasonic temperature measurement. By performing temperature regression processing on the target ultrasonic orthogonal signal, the correspondence between the target ultrasonic orthogonal signal and the temperature value is analyzed to predict the temperature value corresponding to the target ultrasonic orthogonal signal. This eliminates the multiple loop calculations in the algorithm of related technologies, reduces the amount of computation, and improves the efficiency of ultrasonic temperature measurement.
[0062] This embodiment also provides an ultrasonic temperature measuring device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0063] This embodiment provides an ultrasonic temperature measuring device, such as... Figure 4 As shown, it includes: Acquisition module 401 is used to acquire the ultrasonic orthogonal signal of the area to be tested; Image generation module 402 is used to generate an ultrasound image based on the ultrasound orthogonal signal; Target detection module 403 is used to perform target detection on the ultrasound image to obtain the target area of the region to be tested; The filtering module 404 is used to filter the ultrasonic orthogonal signal based on the target area of the region to be tested, so as to obtain the target ultrasonic orthogonal signal; The temperature regression module 405 is used to perform temperature regression processing on the ultrasonic orthogonal signal of the target in order to perform ultrasonic temperature measurement on the target area.
[0064] In one alternative implementation, the temperature regression module includes: The feature extraction module is used to extract the time-domain and frequency-domain features of the target ultrasonic orthogonal signal, respectively. The feature fusion module is used to fuse the time-domain features and frequency-domain features to obtain ultrasound fusion features. A temperature prediction module is used to predict temperature based on the ultrasonic fusion characteristics.
[0065] In one optional implementation, the feature extraction module includes: The first extraction module is used to extract features from the real part of the target ultrasonic orthogonal signal to obtain the first time-domain features; The second extraction module is used to extract the imaginary part of the target ultrasonic orthogonal signal to obtain the second time-domain features; The third extraction module is used to convert the target ultrasound orthogonal signal into a target ultrasound real signal and perform feature extraction to obtain frequency domain features.
[0066] In an optional implementation, the third extraction module is further configured to: The target ultrasonic orthogonal signal is subjected to Fourier transform to obtain the target ultrasonic frequency domain signal; The target ultrasonic frequency domain signal is subjected to a modulus extraction operation to generate the target ultrasonic real signal.
[0067] In an optional implementation, the feature fusion module is further configured to: The first time-domain feature, the second time-domain feature, and the frequency-domain feature are spliced together to obtain the ultrasound fusion feature. This temperature prediction module is also used for: The ultrasound fusion feature is mapped to a temperature value for temperature prediction.
[0068] In an optional implementation, the target detection module is further configured to: A target detection model is used to detect targets in the ultrasound image to obtain the target area of the region to be tested; the target detection model is pre-trained based on ultrasound sample images with target areas marked.
[0069] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.
[0070] In this embodiment, the ultrasonic temperature measuring device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.
[0071] This invention also provides a computer device having the above-described features. Figure 4 The ultrasonic temperature measuring device shown.
[0072] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 5 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 5 Take a processor 10 as an example.
[0073] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.
[0074] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.
[0075] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
[0076] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.
[0077] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.
[0078] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.
[0079] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.
[0080] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.
[0081] Although embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and all such modifications and variations fall within the protection scope of the present invention.
Claims
1. An ultrasonic temperature measurement method, characterized in that, The method includes: Acquire orthogonal ultrasonic signals from the region to be tested; An ultrasound image is generated based on the aforementioned orthogonal ultrasound signals; Target detection is performed on the ultrasound image to obtain the target area of the region to be tested; Based on the target area of the region to be tested, the ultrasonic orthogonal signals are filtered to obtain the target ultrasonic orthogonal signals; Temperature regression processing is performed on the target ultrasonic orthogonal signal to perform ultrasonic temperature measurement on the target area.
2. The method according to claim 1, characterized in that, The temperature regression processing of the target ultrasonic orthogonal signal includes: Extract the time-domain and frequency-domain features of the target ultrasonic orthogonal signal, respectively; The time-domain features and frequency-domain features are fused to obtain ultrasound fusion features; Temperature prediction is performed based on the aforementioned ultrasonic fusion characteristics.
3. The method according to claim 2, characterized in that, The extraction of time-domain and frequency-domain features of the target ultrasonic orthogonal signal includes: The real part of the target ultrasonic orthogonal signal is extracted to obtain the first time-domain features; The imaginary part of the target ultrasonic orthogonal signal is extracted to obtain the second time-domain features; The target ultrasound orthogonal signal is converted into a target ultrasound real signal, and feature extraction is performed to obtain frequency domain features.
4. The method according to claim 3, characterized in that, Converting the target ultrasound orthogonal signal into a target ultrasound real signal includes: The target ultrasonic orthogonal signal is subjected to Fourier transform to obtain the target ultrasonic frequency domain signal; The target ultrasonic frequency domain signal is subjected to a modulus extraction operation to generate a target ultrasonic real number signal.
5. The method according to claim 3, characterized in that, The process of fusing the time-domain features and frequency-domain features to obtain ultrasound fusion features includes: The first time-domain feature, the second time-domain feature, and the frequency-domain feature are concatenated to obtain the ultrasound fusion feature; The temperature prediction based on the ultrasound fusion features includes: The ultrasonic fusion features are mapped to temperature values for temperature prediction.
6. The method according to any one of claims 1 to 5, characterized in that, The step of performing target detection on the ultrasound image to obtain the target region of the area to be tested includes: The ultrasound image is subjected to target detection using a target detection model to obtain the target area of the region to be tested; the target detection model is pre-trained based on ultrasound sample images with the target area marked.
7. An ultrasonic temperature measuring device, characterized in that, The device includes: The acquisition module is used to acquire the ultrasonic orthogonal signals of the area to be tested; An image generation module is used to generate an ultrasound image based on the ultrasound orthogonal signal; The target detection module is used to perform target detection on the ultrasound image to obtain the target area of the region to be tested; The filtering module is used to filter the ultrasonic orthogonal signals based on the target area of the region to be tested, so as to obtain the target ultrasonic orthogonal signals; The temperature regression module is used to perform temperature regression processing on the target ultrasonic orthogonal signal in order to perform ultrasonic temperature measurement on the target area.
8. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the ultrasonic temperature measurement method according to any one of claims 1 to 6 by executing the computer instructions.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the ultrasonic temperature measurement method according to any one of claims 1 to 6.
10. A computer program product, characterized in that, Includes computer instructions for causing a computer to perform the ultrasonic temperature measurement method according to any one of claims 1 to 6.