Method and apparatus for blood pressure detection

Abstract

The application provides a blood pressure detection method and device, and relates to the technical field of wearable health detection. The blood pressure detection method comprises the following steps: at each sampling time in multiple sampling times, a plurality of beams of laser are used to irradiate a biological tissue to be detected respectively to collect a plurality of speckle images of the current sampling time, wherein the modulation parameters of the plurality of beams of laser are different; based on the plurality of speckle images, blood flow velocities at the current sampling time are fitted; based on the blood flow velocities at the multiple sampling times, a blood flow velocity sequence is obtained; and based on the blood flow velocity sequence, blood pressure detection is performed to obtain a blood pressure detection result.

Description

Technical Field

[0001] This application relates to the field of wearable health monitoring technology, and more specifically, to a blood pressure monitoring method and device. Background Technology

[0002] With the rapid growth in demand for telemedicine and home health monitoring, continuous blood pressure monitoring (CBHB) technology is increasingly being used in home health management scenarios. CBHB provides 24 / 7 dynamic blood pressure data support for the prevention, diagnosis, and management of chronic diseases such as hypertension and heart disease, playing an irreplaceable role in disease risk assessment, treatment plan optimization, and early warning of postoperative complications. For example, for hypertensive patients, CBHB can accurately capture the diurnal fluctuation pattern of blood pressure, helping doctors develop personalized medication plans; in the diagnosis of sleep apnea syndrome, CBHB data combined with physiological parameters such as blood oxygen saturation and respiratory rate can more comprehensively assess the extent of impact on the patient's cardiovascular system.

[0003] In related technologies, continuous blood pressure monitoring methods can be divided into two categories: traditional methods and non-invasive techniques. Traditional cuff-type blood pressure monitors are cumbersome to operate and have a low measurement frequency, making it impossible to achieve dynamic continuous monitoring and failing to meet the needs of refined clinical management. Among non-invasive techniques, methods based on photoplethysmography (PPG) have become a research hotspot due to their advantages such as strong real-time performance, small size, and low cost. These methods estimate blood pressure by detecting volume changes caused by arterial pulsation. However, PPG is easily affected by blood vessel diameter, interference from surrounding tissues, motion, and ambient light noise, resulting in a weak correlation with actual blood pressure and requiring improvement in stability. Piezoelectric sensors and MEMS (Micro-Electro-Mechanical System) technology utilize material deformation to sense blood pressure fluctuations. While they offer relatively better accuracy and stability, their high cost and close contact with the skin, coupled with poor long-term comfort, limit their widespread adoption in everyday wearable scenarios.

[0004] In recent years, with the integration of wearable devices and artificial intelligence technologies, continuous blood pressure monitoring technology has made some breakthroughs. Wearable devices such as smartwatches and wristbands have begun to integrate PPG sensors and use machine learning algorithms to model and predict blood pressure data. However, these methods lack adaptability to individual physiological differences, have limited algorithm generalization ability, and struggle to maintain stable accuracy across different populations. From an algorithmic perspective, while deep learning-based blood pressure prediction models can learn the nonlinear relationship between multiple physiological signals such as PPG, electrocardiogram (ECG), and heart rate variability (HRV) and blood pressure, they rely excessively on high-quality clinical training data and suffer from poor model interpretability, becoming a significant obstacle to their clinical translation.

[0005] Despite significant breakthroughs in continuous blood pressure monitoring (CBHB) technology in recent years, it still faces numerous challenges in terms of accuracy, stability, cost, and user-friendliness. First, blood pressure is influenced by a variety of factors, and a single physiological signal often fails to accurately reflect true blood pressure changes. Second, during long-term monitoring, data fluctuations are significant due to factors such as detection noise, making improving the robustness of the device a key research focus. Furthermore, cost is a critical obstacle to the widespread adoption of CBHB technology. Developing low-cost, high-performance sensors and algorithms is an important current research direction.

[0006] In related technologies, continuous blood pressure monitoring methods are mostly based on the PPG principle, which calculates diastolic and systolic blood pressure by modeling the volumetric pulse wave characteristics within the pulse cycle. However, the volumetric pulse wave is easily affected by vessel diameter and surrounding tissues, resulting in a poor correlation with blood pressure. According to Poiseuille's law, blood flow velocity has a higher correlation with blood pressure. Therefore, measuring the velocity changes within the cardiac cycle and calculating systolic and diastolic blood pressure based on the velocity pulse wave characteristics offers higher accuracy and shows promising application prospects in continuous blood pressure monitoring.

[0007] The continuous blood pressure monitoring method based on diffuse speckle can detect changes in blood flow within the pulsatile cycle based on diffuse light and interference speckle, and can also quantify blood flow velocity. Systolic and diastolic blood pressure can be calculated based on comprehensive blood flow and pulse blood flow characteristics, thus improving the accuracy of blood pressure detection. According to the speckle model and imaging principle, the speckle contrast value is easily affected by exposure time, sampling time, and noise, causing flow velocity measurement errors. The influence of exposure time is mainly manifested in that, within a certain exposure time, faster flow velocities result in more intense speckle movement, and longer exposure times lead to an averaging effect, causing the speckle contrast value to tend to be uniform. Conversely, at lower flow velocities, speckle fluctuations are slower, requiring a sufficiently long exposure time. However, human blood flow is complex; blood flow in arteries is faster and directional, while blood flow in microvessels is slower and mostly anisotropic diffuse flow. Using the same exposure time and other measurement parameters, the detection sensitivity and dynamic range differ for different flow velocities. Therefore, in order to improve the accuracy of blood flow velocity measurement within the pulsation cycle, it is necessary to improve the diffusion speckle imaging and acquisition method so that speckle changes can reflect flow velocity changes over a larger range.

[0008] For example, in blood flow detection methods based on speckle diffusion, speckle contrast is easily affected by exposure time, sampling time, and noise. The detection sensitivity and dynamic range differ significantly between rapid directional blood flow in arteries and slow diffuse blood flow in microvessels. Using fixed measurement parameters makes it difficult to cover a wide flow velocity range, leading to flow velocity measurement errors. Furthermore, blood pressure prediction models need to integrate blood flow velocity and pulse waveform characteristics. However, pulse waveforms are complex, and the characteristics corresponding to systolic and diastolic blood pressure differ significantly. Existing models lack the ability to fuse the correlation between these two factors, further affecting the accuracy of blood pressure calculation.

[0009] Non-invasive blood pressure monitoring based on the photoplethysmography (PPG) principle has become a major research direction in continuous blood pressure monitoring due to its advantages such as high real-time performance, small size, and low cost. Wearable devices such as smartwatches and wristbands have begun to integrate PPG sensors and use machine learning algorithms to model and predict blood pressure data. However, these methods lack adaptability to individual physiological differences, and the algorithm's generalization ability is limited, making it difficult to maintain stable accuracy across different populations. Therefore, there is an urgent need to develop highly accurate, widely adaptable, and low-cost continuous blood pressure monitoring technology to meet the pressing needs of the current wearable health monitoring field. Summary of the Invention

[0010] In order to at least partially solve the technical problems existing in the related art, this application provides a blood pressure detection method and device.

[0011] One aspect of this application provides a blood pressure detection method, comprising: at each of multiple sampling times, irradiating the tissue of a biological subject with multiple laser beams to acquire multiple speckle images at the current sampling time, wherein the modulation parameters of each of the multiple laser beams are different; fitting the blood flow velocity at the current sampling time based on the multiple speckle images; obtaining a blood flow velocity sequence based on the blood flow velocities at the multiple sampling times; and performing blood pressure detection based on the blood flow velocity sequence to obtain a blood pressure detection result.

[0012] According to an embodiment of this application, the blood flow velocity at the current sampling time is obtained by fitting multiple speckle images, including: determining the speckle contrast ratio of each of the multiple speckle images; obtaining multiple speckle contrast ratio change rates based on the multiple speckle contrast ratio values ​​and the modulation parameters of each of the multiple laser beams; and fitting the blood flow velocity at the current sampling time based on the multiple speckle contrast ratio change rates.

[0013] According to an embodiment of this application, the blood flow velocity at the current sampling time is obtained by fitting multiple speckle contrast change rates, including: calculating the standard deviation and mean of the speckle contrast change rates based on multiple speckle contrast change rates; obtaining multiple candidate blood flow velocities based on multiple speckle contrast change rates, the standard deviation and the mean of the speckle contrast change rates; and selecting the minimum value from the multiple candidate blood flow velocities to obtain the blood flow velocity at the current sampling time.

[0014] According to embodiments of this application, multiple speckle contrast ratios are obtained based on multiple speckle contrast ratio values ​​and the modulation parameters of multiple laser beams, including: for each speckle image, determining the target speckle image corresponding to the speckle image among multiple next-frame speckle images acquired at the next time of the sampling time; determining the speckle correlation coefficient of the speckle image based on the speckle image and the target speckle image; inverting the blood flow characteristic time of the speckle image based on the diffusion imaging system parameters, the speckle contrast ratio value of the speckle image, the modulation parameters of the laser, and the speckle correlation coefficient of the speckle image; and for the first speckle image and the second speckle image among the multiple speckle images, obtaining the speckle contrast ratio between the first speckle image and the second speckle image based on the speckle contrast ratio value and the blood flow characteristic time of the first speckle image, and the speckle contrast ratio value and the blood flow characteristic time of the second speckle image.

[0015] According to an embodiment of this application, the blood pressure detection method further includes: performing a bionic test based on multiple preset blood flow velocities to determine the parameters of the diffusion imaging system.

[0016] According to an embodiment of this application, a phantom is tested based on multiple preset blood flow velocities to determine the parameters of a diffusion imaging system. This includes: irradiating the phantom with multiple laser beams while the blood flow velocity in the phantom is set to a preset velocity to acquire multiple test speckle images; calculating the test speckle contrast value and test speckle correlation coefficient for each test speckle image; determining the ideal speckle contrast value at each preset blood flow velocity based on the initial diffusion imaging system parameters and the test speckle correlation coefficient; and performing optimization calculations with the goal of minimizing the error between the ideal speckle contrast value and the test speckle contrast value to obtain the diffusion imaging system parameters.

[0017] According to an embodiment of this application, determining the speckle contrast value of each of the multiple speckle images based on multiple speckle images includes: determining the standard deviation of the intensity distribution and the spatial average value of the speckle intensity in the speckle image based on the light intensity value of each pixel in the speckle image; and obtaining the speckle contrast value of the speckle image based on the standard deviation of the intensity distribution and the spatial average value of the speckle intensity in the speckle image.

[0018] According to an embodiment of this application, the blood pressure detection method further includes: preprocessing a speckle image to obtain a preprocessed speckle image; wherein the preprocessing operation on the speckle image includes at least: segmentation and identification of the diffuse speckle region, background correction, intensity distribution correction, and noise correction; wherein, fitting the blood flow velocity at the current sampling time based on multiple speckle images includes: fitting the blood flow velocity at the current sampling time based on multiple preprocessed speckle images.

[0019] According to an embodiment of this application, blood pressure detection based on a blood flow velocity sequence to obtain a blood pressure detection result includes: dividing the blood flow velocity sequence into multiple first sub-sequences based on the pulse cycle; processing the first sub-sequences using a multi-head attention mechanism based on the row dimension of the first sub-sequences to obtain a first feature; processing the first sub-sequences using a multi-head attention mechanism based on the column dimension of the first sub-sequences to obtain a second feature; concatenating the first feature and the second feature to obtain a third feature; performing feature mapping on multiple third features to obtain multiple second sub-sequences; concatenating the multiple second sub-sequences to obtain a blood pressure sequence; and calculating systolic and diastolic blood pressure based on the blood pressure sequence to obtain a blood pressure detection result.

[0020] Another aspect of this application provides a blood pressure detection device, comprising: a sampling module for irradiating the tissue of a biological subject with multiple laser beams at each of multiple sampling times to acquire multiple speckle images at the current sampling time, wherein the modulation parameters of each of the multiple laser beams are different; a first processing module for fitting the blood flow velocity at the current sampling time based on the multiple speckle images; a second processing module for obtaining a blood flow velocity sequence based on the blood flow velocities at the multiple sampling times; and a detection module for detecting blood pressure based on the blood flow velocity sequence to obtain a blood pressure detection result.

[0021] Another aspect of this application provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the method as described above.

[0022] Another aspect of this application provides a computer-readable storage medium storing computer-executable instructions that, when executed, are used to implement the method described above.

[0023] Another aspect of this application provides a computer program product comprising computer-executable instructions which, when executed, are used to implement the method described above.

[0024] According to embodiments of this application, by irradiating the biological tissue under test with multiple laser beams of different modulation parameters at multiple sampling times, multiple speckle images are acquired and fitted to obtain the blood flow velocity at multiple sampling times, thereby forming a blood flow velocity sequence, and ultimately realizing blood pressure detection. Using multiple pulsed laser beams can increase the richness of the acquired blood flow information, thereby improving the measurement accuracy of blood flow velocity. Furthermore, the setting of multiple modulation parameters can construct pulsed lasers with multiple pulse widths, thus better addressing blood flow changes under different conditions and in different individuals when measuring various biological tissues under test. Finally, the blood flow velocity sequence obtained by fitting a large amount of speckle image data can more accurately reflect the dynamic changes in blood flow, providing a more comprehensive data foundation for blood pressure detection. Therefore, it can partially overcome the influence of exposure time, sampling time, and noise on speckle contrast values, making the blood pressure detection results more accurate. Moreover, using pulsed lasers to measure blood pressure can meet the needs of wearable health monitoring, achieving high-precision, wide-adaptability, and low-cost continuous blood pressure monitoring. Attached Figure Description

[0025] The above and other objects, features and advantages of this application will become clearer from the following description of embodiments of this application with reference to the accompanying drawings.

[0026] Figure 1 An exemplary system architecture for applying blood pressure detection methods according to embodiments of this application is shown.

[0027] Figure 2 A flowchart of a blood pressure detection method according to an embodiment of this application is shown.

[0028] Figure 3 A data flow diagram of blood pressure prediction by feature extraction according to an embodiment of this application is shown.

[0029] Figure 4 A block diagram of a blood pressure detection device according to an embodiment of this application is shown.

[0030] Figure 5 A block diagram of an electronic device suitable for implementing a blood pressure detection method according to an embodiment of this application is shown. Detailed Implementation

[0031] The embodiments of this application will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of this application. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of this application for ease of explanation. However, it will be apparent that one or more embodiments may be implemented without these specific details. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of this application.

[0032] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0033] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0034] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0035] In the embodiments of this application, the collection, updating, analysis, processing, use, transmission, provision, disclosure, and storage of data (e.g., including but not limited to user personal information) comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures have been taken to prevent unauthorized access to user personal information data and to safeguard user personal information security, network security, and national security.

[0036] In the embodiments of this application, the user's authorization or consent was obtained before obtaining or collecting the user's personal information.

[0037] The embodiments of this application, in order to at least partially address the problems of low flow velocity measurement accuracy, poor resolution of blood flow detection in blood vessels with different flow velocities and flow patterns, and inaccurate blood pressure prediction methods based on pulse wave characteristics in related technologies, provide a blood pressure detection method. This method includes: at each of multiple sampling times, irradiating the biological tissue to be tested with multiple laser beams to acquire multiple speckle images at the current sampling time, wherein each of the multiple laser beams has different modulation parameters; fitting the blood flow velocity at the current sampling time based on the multiple speckle images; obtaining a blood flow velocity sequence based on the blood flow velocities at the multiple sampling times; and performing blood pressure detection based on the blood flow velocity sequence to obtain a blood pressure detection result.

[0038] Figure 1 An exemplary system architecture 100 for applying a blood pressure detection method according to an embodiment of this application is shown. It should be noted that... Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this application, in order to help those skilled in the art understand the technical content of this application, but do not mean that the embodiments of this application cannot be used in other devices, systems, environments or scenarios.

[0039] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a laser driver 101, a laser 102, a camera 103, and a terminal device 104.

[0040] The laser driver 101 can be used to provide a TTL (Transistor-Transistor Logic) signal to the laser 102. The TTL signal can be composed of a level signal representing logic "1" and a level signal representing logic "0". The proportion of the level signal representing logic "1" in the overall TTL signal can be expressed as the duty cycle of the TTL signal.

[0041] The laser driver 101 can use a TTL signal to modulate the output frequency, pulse width, and phase encoding of the laser 102, so that the coherent laser emitted by the laser 102 is output in pulse form. Taking pulse width modulation as an example, when the laser 102 receives a level signal representing logic "1" in the TTL signal, it can output the coherent pulsed laser, and when it receives a level signal representing logic "0" in the TTL signal, it stops the laser output. Therefore, by modulating parameters such as the duty cycle and signal period duration of the TTL signal output by the laser driver 101, the pulse width of the coherent pulsed laser output by the laser 102 can be adjusted.

[0042] The laser output from laser 102 can be guided to the detection object 105 via a multimode fiber. The detection object 105 can be the surface of human tissue or a phantom of human tissue, without limitation.

[0043] When laser 102 outputs laser light to the object 105, a speckle pattern can be formed on the surface of the object 105. Camera 103 can be used to acquire the speckle pattern to obtain a speckle image and provide the speckle image to terminal device 104.

[0044] Based on the received multiple speckle images, the terminal device 104 can fit the blood flow velocity to obtain a blood flow waveform, and based on the blood flow waveform, it can perform blood pressure detection to obtain a blood pressure detection result.

[0045] It should be understood that Figure 1 The number of laser drivers, lasers, cameras, and terminal devices shown is merely illustrative. Any number of laser drivers, lasers, cameras, and terminal devices can be included depending on the implementation requirements.

[0046] Figure 2 A flowchart of a blood pressure detection method according to an embodiment of this application is shown.

[0047] like Figure 2 As shown, the method includes operations S201 to S204.

[0048] In operation S201, at each of the multiple sampling times, multiple laser beams are used to irradiate the biological tissue to be tested in order to acquire multiple speckle images at the current sampling time.

[0049] According to embodiments of this application, based on a preset sampling time interval, at each sampling time, the laser driver can be controlled to provide a TTL signal to the laser, so that the laser can irradiate the biological tissue to be tested with multiple laser beams at preset time intervals.

[0050] After the light emitted by the laser is scattered and absorbed by the biological tissue under test, it exits from the surface of the biological tissue. The resulting diffused light can be collected by a multimode optical fiber, and a speckle image can be formed on the fiber's exit surface. The diffused speckle image can be captured by a camera.

[0051] According to embodiments of this application, multiple laser beams each have different modulation parameters, which may include the modulation period and duty cycle of the laser. The modulation period of the laser refers to the time required for the laser modulation signal to repeat once; it determines the repetition frequency of the signal and can affect the system's temporal resolution and imaging speed. The duty cycle of the laser refers to the proportion of time the laser actually irradiates within one modulation period; it can affect signal strength, dynamic range, signal-to-noise ratio, and imaging contrast.

[0052] In operation S202, the blood flow velocity at the current sampling moment is obtained by fitting multiple speckle images.

[0053] Multiple speckle images can be obtained by irradiating with multiple laser beams. These speckle images can be used to obtain speckle contrast values. Since speckle contrast values ​​reflect the motion state of scattering particles by quantifying the blurring degree of the speckle pattern, they can be used to distinguish between dynamic and static regions, and thus fit the blood flow velocity at the current sampling moment.

[0054] In operation S203, a blood flow velocity sequence is obtained based on the blood flow velocity at multiple sampling times.

[0055] According to an embodiment of this application, the blood flow velocities at multiple sampling times obtained in operation S202 are sorted and spliced ​​based on a time series to obtain a blood flow velocity sequence.

[0056] In operation S204, blood pressure is detected based on blood flow velocity sequence to obtain blood pressure detection results.

[0057] Blood flow velocity sequences can be used as flow pulse waves. Further, these flow pulse waves can be mapped to blood pressure waveforms within a pulse cycle. Therefore, blood pressure waveforms of the organism being tested can be obtained based on blood flow velocity sequences, enabling the detection of systolic and diastolic blood pressure.

[0058] According to embodiments of this application, pulse-modulated laser illumination is used instead of traditional continuous-wave laser sources. Pulse-modulated lasers with various pulse widths can effectively improve the illumination efficiency of diffuse speckle signals, and synchronous and time-resolved image acquisition can be achieved through pulse interval control. By controlling the pulse width and duty cycle, diffuse speckle imaging with different exposure times can be achieved, further enhancing the contrast and dynamic response of the speckle image. Encoding the laser pulses can cover a wider average intensity range while avoiding the need for calibration of the nonlinear characteristics of continuous modulation. When the laser pulse frequency is sufficiently high and the laser pulse offset is sufficiently sharp, various modulation techniques such as pulse width, position, encoding, or delta modulation can also be adapted.

[0059] According to embodiments of this application, by irradiating the biological tissue under test with multiple laser beams of different modulation parameters at multiple sampling times, multiple speckle images are acquired and fitted to obtain the blood flow velocity at multiple sampling times, thereby forming a blood flow velocity sequence, and ultimately realizing blood pressure detection. Using multiple pulsed laser beams can increase the richness of the acquired blood flow information, thereby improving the measurement accuracy of blood flow velocity. Furthermore, the setting of multiple modulation parameters can construct pulsed lasers with multiple pulse widths, thus better addressing blood flow changes under different conditions and in different individuals when measuring various biological tissues under test. Finally, the blood flow velocity sequence obtained by fitting a large amount of speckle image data can more accurately reflect the dynamic changes in blood flow, providing a more comprehensive data foundation for blood pressure detection. Therefore, it can partially overcome the influence of exposure time, sampling time, and noise on speckle contrast values, making the blood pressure detection results more accurate. Moreover, using pulsed lasers to measure blood pressure can meet the needs of wearable health monitoring, achieving high-precision, wide-adaptability, and low-cost continuous blood pressure monitoring.

[0060] According to an embodiment of this application, the blood flow velocity at the current sampling time is obtained by fitting multiple speckle images, including: determining the speckle contrast ratio of each of the multiple speckle images; obtaining multiple speckle contrast ratio change rates based on the multiple speckle contrast ratio values ​​and the modulation parameters of each of the multiple laser beams; and fitting the blood flow velocity at the current sampling time based on the multiple speckle contrast ratio change rates.

[0061] According to an embodiment of this application, an exposure time can be set first. Within a sampling period, the laser signal is modulated according to two modulation parameters: modulation period and duty cycle. Specifically, a TTL signal with various pulse widths can be used to modulate the laser. Multiple laser beams are used to irradiate the biological tissue under test based on the aforementioned pulse widths. The speckle contrast value can be calculated based on the obtained speckle image. Since the pulse width is determined based on the modulation period and duty cycle, the rate of change of speckle contrast can be calculated based on the aforementioned two modulation parameters. The pulse width mentioned above can be... , Multiple of them.

[0062] According to embodiments of this application, multiple speckle contrast ratio change rates can be calculated using multiple laser beams with various pulse widths. Based on these multiple speckle contrast ratio change rates, a mapping relationship between the speckle contrast ratio change rates and the blood flow velocity at the current sampling time can be established, thereby establishing a mapping relationship between the speckle image and the blood flow velocity.

[0063] According to the embodiments of this application, multiple laser beams with various pulse widths are used to irradiate the biological tissue under test, which improves the overall stability of the results. It can eliminate individual differences between different biological tissues under test, making the above-mentioned fitted mapping relationship more reliable and stable, realizing highly sensitive blood flow signal capture, and making the final test results more accurate.

[0064] According to an embodiment of this application, determining the speckle contrast value of each of the multiple speckle images based on multiple speckle images includes: determining the standard deviation of the intensity distribution and the spatial average value of the speckle intensity in the speckle image based on the light intensity value of each pixel in the speckle image; and obtaining the speckle contrast value of the speckle image based on the standard deviation of the intensity distribution and the spatial average value of the speckle intensity in the speckle image.

[0065] According to embodiments of this application, the speckle contrast ratio (DSCA) can be calculated for each speckle image acquired by the camera. Specifically, the speckle contrast ratio (DSCA) is a parameter that describes the motion state of scattering particles by analyzing the statistical characteristics of the light intensity distribution in a speckle image. It can be obtained by calculating the ratio of the standard deviation of the light intensity to the average light intensity of the speckle image. The specific calculation method can be found in formula (1).

[0066] (1)

[0067] in, It can indicate the exposure time. The speckle contrast value under the given conditions It can represent the standard deviation of the light intensity distribution of pixels in a speckle image. It can represent the spatial average value of the light intensity distribution of pixels in a speckle image.

[0068] According to embodiments of this application, the speckle contrast value is negatively correlated with the velocity of the scattering particles. Therefore, the faster the object being measured moves, the smaller the contrast value; the slower the movement, the larger the contrast value. Under suitable imaging conditions, the speckle contrast value can be used to estimate the velocity of the scattering particles. The speckle contrast value is affected by exposure time. When the exposure time is longer, the speckle image becomes more blurred, and the speckle contrast value decreases; when the exposure time is shorter, the speckle image becomes clearer, and the speckle contrast value increases. Furthermore, this application uses multiple laser beams with various pulse widths, which allows for the acquisition of speckle patterns under various exposure times. This enables the final results to be used to predict blood pressure based on a large amount of data, further improving the accuracy of the prediction results.

[0069] According to embodiments of this application, multiple speckle contrast ratios are obtained based on multiple speckle contrast ratio values ​​and the modulation parameters of multiple laser beams, including: for each speckle image, determining the target speckle image corresponding to the speckle image among multiple next-frame speckle images acquired at the next time of the sampling time; determining the speckle correlation coefficient of the speckle image based on the speckle image and the target speckle image; inverting the blood flow characteristic time of the speckle image based on diffusion imaging system parameters, speckle contrast ratio values ​​of the speckle image, laser modulation parameters, and speckle correlation coefficients of the speckle image; for the first speckle image and the second speckle image among the multiple speckle images, obtaining the speckle contrast ratio change rate between the first speckle image and the second speckle image based on the speckle contrast ratio value and blood flow characteristic time of the first speckle image, and the speckle contrast ratio value and blood flow characteristic time of the second speckle image.

[0070] According to an embodiment of this application, for each speckle image, a target speckle image corresponding to the speckle image is determined from multiple next-frame speckle images acquired at the next time after the sampling time; based on the speckle image and the target speckle image, the speckle correlation coefficient of the speckle image is determined; then, based on the diffusion imaging system parameters, the speckle contrast value of the speckle image, the laser modulation parameters, and the speckle correlation coefficient of the speckle image, the speckle contrast value of the target speckle image previously obtained based on the speckle image is further fitted to obtain the speckle contrast value of the target speckle image, thereby obtaining the blood flow characteristic time. Then, based on the first speckle image and the second speckle image among multiple speckle images, using the speckle contrast value and blood flow characteristic time of the first speckle image, and the speckle contrast value and blood flow characteristic time of the second speckle image, the speckle contrast change rate between the first speckle image and the second speckle image can be obtained.

[0071] According to an embodiment of this application, specifically, the speckle contrast ratio value also has a mapping relationship with the modulation parameters, which can be shown in formula (2).

[0072] (2)

[0073] in, This represents the square of the speckle contrast value. It can represent the parameters of a diffusion imaging system. It can indicate the exposure time. It can represent the speckle correlation coefficient of a speckle image. It can represent the autocorrelation function of the optical field that can represent the dynamic scattered signals generated by blood flow at different velocities.

[0074] Furthermore, It can be expressed as formula (3).

[0075] (3)

[0076] in, This can represent the correlation coefficient with blood flow velocity, for blood flow in small arteries. The value of is generally 1, so formula (3) can be simplified to . It can represent the characteristic time of blood flow, which is the result that needs to be obtained through inversion.

[0077] Furthermore, according to the theory of diffuse speckle, it can be defined that... Blood flow velocity Therefore, the relationship between speckle contrast and blood flow velocity obtained from different exposure times can be expressed as formula (4).

[0078] (4)

[0079] According to the embodiments of this application, after the blood flow characteristic time is obtained by inversion using formula (4), the blood flow characteristic time of multiple corresponding speckle images can be used as a basis. The change rate of speckle contrast is obtained by combining the speckle contrast value with the speckle contrast ratio. .

[0080] According to the embodiments of this application, the method matches a speckle image with a corresponding target speckle image, uses the speckle contrast value obtained from the speckle image to invert the blood flow characteristic time, and establishes a mapping relationship between modulation parameters and blood flow characteristic time. This can improve the accuracy and stability of blood flow velocity measurement, provide more reliable data support for continuous blood pressure monitoring, and enhance the applicability and detection efficiency of the blood pressure monitoring method of this application.

[0081] According to an embodiment of this application, the blood pressure detection method further includes: performing phantom testing based on multiple preset blood flow velocities to determine diffusion imaging system parameters. Specifically: with the blood flow velocity in the phantom set to a preset blood flow velocity, multiple laser beams are used to irradiate the phantom to acquire multiple test speckle images; the test speckle contrast value and test speckle correlation coefficient are calculated for each test speckle image; based on the initial diffusion imaging system parameters and the test speckle correlation coefficient, an ideal speckle contrast value is determined for each preset blood flow velocity; optimization calculations are performed with the goal of minimizing the error between the ideal speckle contrast value and the test speckle contrast value to obtain the diffusion imaging system parameters.

[0082] According to an embodiment of this application, in order to obtain the parameters of the diffusion imaging system, data can be collected through a phantom experiment. First, the blood flow velocity in the phantom is set to a preset blood flow velocity, and then multiple laser beams are used to irradiate the phantom to acquire multiple test speckle images obtained through the phantom. The test speckle contrast value of each test speckle image is then calculated. Correlation coefficient with speckle test Based on initial diffusion imaging system parameters Correlation coefficient with speckle test Then, the ideal speckle contrast ratio at each preset blood flow velocity can be determined; and the initial diffusion imaging system parameters are continuously adjusted to perform optimization calculations with the optimization objective of minimizing the error between the ideal speckle contrast ratio and the test speckle contrast ratio, thereby obtaining the diffusion imaging system parameters. .

[0083] According to embodiments of this application, specifically, in the parameters of the diffusion imaging system... When performing fitting, blood flow can be defined. ,in It is the directional flow velocity of blood. This represents the blood flow diffusion velocity. For example, in the experiment, a tissue phantom was used, and the flow velocities were set to 1 mm / s-20 mm / s, with a step size of 1 mm / s. A total of 20 flow velocities could be obtained. Substituting the flow velocities into formula (4) yielded the ideal speckle contrast value. Then, the optimized parameters are obtained by calculating the minimum root mean square error using formula (5), and these parameters are used for flow velocity detection.

[0084] (5)

[0085] in, express The measured value at time, Indicates the total number of moments. This represents the root mean square error. This indicates the case where the minimum value is taken.

[0086] According to embodiments of this application, a large amount of data under preset conditions can be collected through phantom experiments. Based on this data, the initial diffusion imaging system parameters are continuously adjusted to obtain the final diffusion imaging system parameters. The parameters obtained through root mean square error fitting can improve the accuracy of blood flow velocity measurement and enhance the reliability of continuous blood pressure monitoring.

[0087] According to an embodiment of this application, the blood flow velocity at the current sampling time is obtained by fitting multiple speckle contrast change rates, including: calculating the standard deviation and mean of the speckle contrast change rates based on multiple speckle contrast change rates; obtaining multiple candidate blood flow velocities based on multiple speckle contrast change rates, the standard deviation and the mean of the speckle contrast change rates; and selecting the minimum value from the multiple candidate blood flow velocities to obtain the blood flow velocity at the current sampling time.

[0088] According to embodiments of this application, when fitting the blood flow velocity, the fitting is performed using various statistical patterns such as the speckle contrast ratio change rate and the standard deviation of the speckle contrast ratio change rate. Specifically, the mean of the speckle contrast ratio change rate can represent the average value of the data, reflecting the central tendency of the data; the standard deviation measures the dispersion of the data, reflecting the magnitude of the data fluctuation. The minimum value among the multiple blood flow velocities that can be fitted at the current time is selected and used as the blood flow velocity at the current sampling time.

[0089] According to an embodiment of this application, the blood flow velocity BFI can be fitted using the following formula (6).

[0090] (6)

[0091] in, It can represent The period of the laser modulation signal at any given moment. It can represent The duty cycle of the laser modulation signal at any given time. This can represent the rate of change of speckle contrast, where It can indicate the exposure time. It can represent the characteristic time of blood flow. It can be used to calculate the standard deviation. It can represent calculating the mean. It can represent the time interval between sampling moments. This can represent taking the minimum value.

[0092] According to embodiments of this application, using the mean and standard deviation of the speckle contrast variation rate can more accurately describe the characteristics of blood flow velocity fluctuations, providing multiple candidate blood flow velocities for subsequent screening. Then, selecting the minimum value from these candidate velocities reduces the interference of outliers, making the measurement results closer to the true blood flow velocity. In continuous blood pressure monitoring, this precise and stable blood flow velocity measurement improves monitoring accuracy and enhances the stability of blood pressure monitoring results.

[0093] According to an embodiment of this application, the blood pressure detection method further includes: preprocessing a speckle image to obtain a preprocessed speckle image; wherein the preprocessing operation on the speckle image includes at least: segmentation and identification of the diffuse speckle region, background correction, intensity distribution correction, and noise correction; wherein, fitting the blood flow velocity at the current sampling time based on multiple speckle images includes: fitting the blood flow velocity at the current sampling time based on multiple preprocessed speckle images.

[0094] According to embodiments of this application, the speckle image can first be smoothed using Gaussian filtering to reduce noise interference. Next, an appropriate threshold is set to segment the speckle regions related to blood flow in the image, ensuring that subsequent processing targets only these key regions. Then, a set of background images without blood flow can be acquired, and their average value can be calculated as a background reference. The background reference is subtracted from the preprocessed speckle image to eliminate background light interference and highlight the dynamic speckle signal. The segmented speckle regions can be normalized to unify the dynamic range of light intensity in the image, preventing excessively bright or dark areas from obscuring blood flow information. Histogram equalization and other methods can be used to enhance the overall contrast of the image.

[0095] According to embodiments of this application, during noise correction, the main noise sources can be categorized into shot noise and quantization noise. To improve measurement accuracy, denoising processing can also be performed, using the reciprocal of the square of the speckle contrast value after sequential adjustment through diffusion speckle region segmentation and identification, background correction, and intensity distribution correction. As a reference for blood flow velocity, This indicates an adjustment. The adjustment process is shown in formula (7).

[0096] (7)

[0097] in, It can represent the initial measurement value. It can represent shot noise. It can represent quantization noise. Shot noise can be calculated using formula (8).

[0098] (8)

[0099] in, It is the camera-related analog-to-digital conversion ratio, which depends on the camera's gain settings. and camera conversion factor , specific ; It can be the average light intensity of the camera, obtained by averaging the average light intensity of multiple images taken by the camera. Quantization noise can be calculated using formula (9).

[0100] (9)

[0101] According to embodiments of this application, segmentation and identification of diffuse speckle regions, background correction, intensity distribution correction, and noise correction during data preprocessing can improve data quality. Specific beneficial effects include: improved speckle contrast, leading to more accurate blood flow velocity calculations; enhanced temporal resolution of speckle correlation, resulting in clearer capture of dynamic changes in blood flow; and reduced analytical redundancy, alleviating computational burden. These improvements help to analyze and understand data more accurately, enhancing the reliability, accuracy, and efficiency of subsequent blood pressure prediction.

[0102] Figure 3 A data flow diagram of blood pressure prediction by feature extraction according to an embodiment of this application is shown.

[0103] According to an embodiment of this application, blood pressure detection based on a blood flow velocity sequence to obtain a blood pressure detection result includes: dividing the blood flow velocity sequence into multiple first sub-sequences based on the pulse cycle; processing the first sub-sequences using a multi-head attention mechanism based on the row dimension of the first sub-sequences to obtain a first feature; processing the first sub-sequences using a multi-head attention mechanism based on the column dimension of the first sub-sequences to obtain a second feature; concatenating the first feature and the second feature to obtain a third feature; performing feature mapping on multiple third features to obtain multiple second sub-sequences; concatenating the multiple second sub-sequences to obtain a blood pressure sequence; and calculating systolic and diastolic blood pressure based on the blood pressure sequence to obtain a blood pressure detection result.

[0104] According to embodiments of this application, after obtaining blood flow velocities at different sampling times, multiple blood flow velocities can be combined into a blood flow velocity sequence based on linear time flow. This blood flow velocity sequence can serve as a velocity-pulse wave. The velocity-pulse wave is a perturbation of blood flow velocity caused by the periodic contraction and ejection of blood by the heart, which propagates along the arteries in the form of a wave. End-to-end mapping can be performed based on the velocity-pulse wave to obtain the blood pressure waveform within the pulsation cycle, thereby enabling the detection of systolic and diastolic blood pressure.

[0105] Specifically, such as Figure 3As shown, the pulse wave signal is first truncated according to the same time window to obtain multiple first subsequences, each with a length of one cardiac cycle. Then, these multiple first subsequences are convolved through a first convolutional layer to obtain the row and column dimensions of the first subsequences. A multi-head attention layer in the row direction is used to process the row dimension data of the first subsequences to obtain the first feature. Similarly, a multi-head attention layer in the column direction is used to process the column dimension data features of the first subsequences to obtain the first feature. The multi-head attention layers in both the column and row directions can include multiple stacked or parallel encoders.

[0106] Then, the first and second features are concatenated to obtain the third feature. This third feature is then normalized using a normalization layer, followed by feature mapping using a second convolutional layer to obtain the second sub-sequence. These second sub-sequences are then concatenated to obtain the blood pressure sequence. Finally, the systolic and diastolic blood pressures can be calculated from the blood pressure sequence, completing the blood pressure detection.

[0107] According to embodiments of this application, during end-to-end mapping, the flow rate pulse wave time-series signal is divided into multiple sub-sequences using a fixed-length window. Each sub-sequence is one cardiac cycle long, introducing local information, reducing redundancy, facilitating attention mechanisms to focus on the sub-sequences, and improving feature extraction capabilities. Then, the high-precision features are mapped to the blood pressure sequence to complete blood pressure detection, enabling long-term, high-precision blood pressure monitoring.

[0108] Figure 4 A block diagram of a blood pressure detection device according to an embodiment of this application is shown.

[0109] like Figure 4 As shown, the blood pressure detection device 400 includes a sampling module 410, a first processing module 420, a second processing module 430, and a detection module 440.

[0110] The sampling module 410 is used to irradiate the biological tissue under test with multiple laser beams at each of the multiple sampling times to acquire multiple speckle images at the current sampling time, wherein the modulation parameters of each of the multiple laser beams are different.

[0111] The first processing module 420 is used to fit the blood flow velocity at the current sampling time based on multiple speckle images.

[0112] The second processing module 430 is used to obtain a blood flow velocity sequence based on the blood flow velocity at multiple sampling times.

[0113] The detection module 440 is used to detect blood pressure based on blood flow velocity sequence and obtain blood pressure detection results.

[0114] According to an embodiment of this application, the first processing module 420 may include a first processing submodule, a second processing submodule, and a third processing submodule.

[0115] The first processing submodule is used to determine the speckle contrast ratio of each speckle image based on multiple speckle images.

[0116] The second processing submodule is used to obtain multiple speckle contrast ratio change rates based on multiple speckle contrast ratio values ​​and the modulation parameters of each of the multiple laser beams.

[0117] The third processing submodule is used to fit the blood flow velocity at the current sampling moment based on multiple speckle contrast change rates.

[0118] According to embodiments of this application, the third processing submodule may include a first processing unit, a second processing unit, and a third processing unit.

[0119] The first processing unit is used to calculate the standard deviation and mean of the speckle contrast ratio based on multiple speckle contrast ratio change rates.

[0120] The second processing unit is used to obtain multiple candidate blood flow velocities based on multiple speckle contrast ratio changes, the standard deviation of speckle contrast ratio changes, and the mean of speckle contrast ratio changes.

[0121] The third processing unit is used to filter the minimum value from multiple candidate blood flow velocities to obtain the blood flow velocity at the current sampling time.

[0122] According to embodiments of this application, the second processing submodule may include a fourth processing unit, a fifth processing unit, a sixth processing unit, and a seventh processing unit.

[0123] The fourth processing unit is used to determine, for each speckle image, the target speckle image corresponding to the speckle image among the multiple next frame speckle images acquired at the next time of the sampling time.

[0124] The fifth processing unit is used to determine the speckle correlation coefficient of the speckle image based on the speckle image and the target speckle image.

[0125] The sixth processing unit is used to invert the blood flow characteristic time of the speckle image based on the parameters of the diffusion imaging system, the speckle contrast value of the speckle image, the modulation parameters of the laser, and the speckle correlation coefficient of the speckle image.

[0126] The seventh processing unit is used to obtain the speckle contrast change rate between the first speckle image and the second speckle image from multiple speckle images, based on the speckle contrast value and blood flow characteristic time of the first speckle image and the speckle contrast value and blood flow characteristic time of the second speckle image.

[0127] According to an embodiment of this application, the second processing submodule may further include an eighth processing unit.

[0128] The eighth processing unit is used to perform phantom testing based on multiple preset blood flow velocities and determine the parameters of the diffusion imaging system.

[0129] According to embodiments of this application, the eighth processing unit may include a first processing subunit, a second processing subunit, a third processing subunit, and a fourth processing subunit.

[0130] The first processing subunit is used to irradiate the phantom with multiple laser beams to acquire multiple test speckle images when the blood flow velocity in the phantom is set to a preset blood flow velocity.

[0131] The second processing subunit is used to calculate the test speckle contrast value and test speckle correlation coefficient for each test speckle image.

[0132] The third processing subunit is used to determine the ideal speckle contrast value at each preset blood flow velocity based on the initial diffusion imaging system parameters and the test speckle correlation coefficient.

[0133] The fourth processing subunit is used to perform optimization calculations with the goal of minimizing the error between the ideal speckle contrast value and the test speckle contrast value, so as to obtain the parameters of the diffusion imaging system.

[0134] According to embodiments of this application, the first processing module may include a ninth processing unit and a tenth processing unit.

[0135] The ninth processing unit is used to determine the standard deviation of the intensity distribution and the spatial average value of the speckle intensity in the speckle image based on the light intensity value of each pixel in the speckle image.

[0136] The tenth processing unit is used to obtain the speckle contrast value of the speckle image based on the standard deviation of the intensity distribution and the spatial average value of the speckle intensity in the speckle image.

[0137] According to embodiments of this application, the blood pressure detection device 400 may further include a preprocessing module.

[0138] The preprocessing module is used to preprocess the speckle image to obtain the preprocessed speckle image.

[0139] The first processing module 420 can also be used to fit the blood flow velocity at the current sampling time based on multiple preprocessed speckle images.

[0140] The first detection submodule is used to split the blood flow velocity sequence into multiple first subsequences based on the pulse cycle.

[0141] The second detection submodule is used to process the first subsequence based on the row dimension of the first subsequence using a multi-head attention mechanism to obtain the first feature.

[0142] The third detection submodule is used to process the first subsequence based on the column dimension of the first subsequence using a multi-head attention mechanism to obtain the second feature.

[0143] The fourth detection submodule is used to concatenate the first and second features to obtain the third feature.

[0144] The fifth detection submodule is used to perform feature mapping on multiple third features to obtain multiple second sub-sequences.

[0145] The sixth detection submodule is used to splice multiple second sub-sequences to obtain a blood pressure sequence.

[0146] The seventh detection submodule is used to calculate systolic and diastolic blood pressure based on the blood pressure sequence to obtain the blood pressure detection results.

[0147] Any one or more of the modules, submodules, units, and subunits according to the embodiments of this application, or at least part of the functions of any one or more of them, can be implemented in one module. Any one or more of the modules, submodules, units, and subunits according to the embodiments of this application can be implemented by dividing them into multiple modules. Any one or more of the modules, submodules, units, and subunits according to the embodiments of this application can be at least partially implemented as hardware circuits, such as field-programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems-on-a-chip, systems-on-a-substrate, systems-on-package, application-specific integrated circuits (ASICs), or implemented by hardware or firmware in any other reasonable manner by integrating or packaging circuits, or implemented in any one of software, hardware, and firmware, or in a suitable combination of any of these. Alternatively, one or more of the modules, submodules, units, and subunits according to the embodiments of this application can be at least partially implemented as computer program modules, which, when run, can perform corresponding functions.

[0148] For example, any plurality of the sampling module 410, the first processing module 420, the second processing module 430, and the detection module 440 can be combined into one module / unit / subunit, or any one of these modules / units / subunits can be split into multiple modules / units / subunits. Alternatively, at least part of the functionality of one or more of these modules / units / subunits can be combined with at least part of the functionality of other modules / units / subunits and implemented in one module / unit / subunit. According to embodiments of this application, at least one of the sampling module 410, the first processing module 420, the second processing module 430, and the detection module 440 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging the circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, at least one of the sampling module 410, the first processing module 420, the second processing module 430, and the detection module 440 may be implemented at least partially as a computer program module, which can perform corresponding functions when the computer program module is run.

[0149] It should be noted that the blood pressure detection device part in the embodiments of this application corresponds to the blood pressure detection device part in the embodiments of this application. For a detailed description of the blood pressure detection device part, please refer to the blood pressure detection device part, which will not be repeated here.

[0150] Figure 5 A block diagram of an electronic device suitable for implementing a blood pressure detection method according to an embodiment of this application is shown. Figure 5 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0151] like Figure 5 As shown, an electronic device 500 according to an embodiment of this application includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage portion 508 into a random access memory (RAM) 503. The processor 501 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 501 may also include onboard memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this application.

[0152] RAM 503 stores various programs and data required for the operation of electronic device 500. Processor 501, ROM 502, and RAM 503 are interconnected via bus 504. Processor 501 executes various operations of the method flow according to embodiments of this application by executing programs in ROM 502 and / or RAM 503. It should be noted that the programs may also be stored in one or more memories other than ROM 502 and RAM 503. Processor 501 may also execute various operations of the method flow according to embodiments of this application by executing programs stored in said one or more memories.

[0153] According to embodiments of this application, the electronic device 500 may further include an input / output (I / O) interface 505, which is also connected to a bus 504. The electronic device 500 may also include one or more of the following components connected to the input / output (I / O) interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output (I / O) interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 510 as needed so that computer programs read from it can be installed into the storage section 508 as needed.

[0154] According to embodiments of this application, the method flow according to embodiments of this application can be implemented as a computer software program. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by processor 501, it performs the functions defined in the system of embodiments of this application. According to embodiments of this application, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0155] This application also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0156] According to embodiments of this application, the computer-readable storage medium can be a non-volatile computer-readable storage medium. Examples include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0157] For example, according to embodiments of this application, a computer-readable storage medium may include the ROM 502 and / or RAM 503 described above and / or one or more memories other than ROM 502 and RAM 503.

[0158] Embodiments of this application also include a computer program product comprising a computer program containing program code for performing the methods provided in the embodiments of this application. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the blood pressure detection method provided in the embodiments of this application.

[0159] When the computer program is executed by the processor 501, it performs the functions defined in the system / apparatus of this application embodiment. According to the embodiments of this application, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0160] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 509, and / or installed from a removable medium 511. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0161] According to embodiments of this application, program code for executing the computer programs provided in the embodiments of this application can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0162] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features described in the various embodiments of this application can be combined and / or combined in various ways, even if such combinations are not explicitly described in this application. In particular, without departing from the spirit and teachings of this application, the features described in the various embodiments of this application can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of this application.

[0163] The embodiments of this application have been described above. However, these embodiments are merely illustrative and not intended to limit the scope of this application. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Without departing from the scope of this application, those skilled in the art can make various substitutions and modifications, all of which should fall within the scope of this application.

Claims

1. A method for detecting blood pressure, characterized in that, The method includes: At each of the multiple sampling times, the biological tissue to be tested is irradiated with multiple laser beams to acquire multiple speckle images at the current sampling time, wherein the modulation parameters of each of the multiple laser beams are different; Based on multiple speckle images, the blood flow velocity at the current sampling time is obtained by fitting. Based on the blood flow velocity at each of the multiple sampling times, a blood flow velocity sequence is obtained; and Blood pressure is detected based on the blood flow velocity sequence to obtain blood pressure detection results; The step of fitting the blood flow velocity at the current sampling time based on multiple speckle images includes: Based on the multiple speckle images, determine the speckle contrast value of each of the multiple speckle images; Based on the multiple speckle contrast ratio values ​​and the modulation parameters of the multiple laser beams, multiple speckle contrast ratio change rates are obtained; Based on the multiple speckle contrast ratio change rates, the standard deviation and mean of the speckle contrast ratio change rates were calculated. Based on multiple speckle contrast ratio changes, the standard deviation of the speckle contrast ratio changes, and the mean of the speckle contrast ratio changes, multiple candidate blood flow velocities are obtained; and The minimum value is selected from multiple candidate blood flow velocities to obtain the blood flow velocity at the current sampling time.

2. The method according to claim 1, characterized in that, The process of obtaining multiple speckle contrast ratio changes based on multiple speckle contrast ratio values ​​and the modulation parameters of each of the multiple laser beams includes: For each speckle image, determine the target speckle image corresponding to the speckle image among multiple next-frame speckle images acquired at the next time after the sampling time; Based on the speckle image and the target speckle image, determine the speckle correlation coefficient of the speckle image; Based on the diffusion imaging system parameters, the speckle contrast ratio of the speckle image, the modulation parameters of the laser, and the speckle correlation coefficient of the speckle image, the blood flow characteristic time of the speckle image is inverted; and For a first speckle image and a second speckle image among the multiple speckle images, the speckle contrast change rate between the first speckle image and the second speckle image is obtained based on the speckle contrast value and blood flow characteristic time of the first speckle image, and the speckle contrast value and blood flow characteristic time of the second speckle image.

3. The method according to claim 2, characterized in that, The method further includes: The parameters of the diffusion imaging system were determined by conducting phantom tests based on multiple preset blood flow velocities.

4. The method according to claim 3, characterized in that, The process of determining the parameters of the diffusion imaging system by performing phantom testing based on multiple preset blood flow velocities includes: With the blood flow velocity in the phantom set to the preset blood flow velocity, the phantom is irradiated with multiple laser beams to acquire multiple test speckle images. Calculate the test speckle contrast value and test speckle correlation coefficient for each test speckle image; Based on the initial diffusion imaging system parameters and the test speckle correlation coefficient, determine the ideal speckle contrast value at each preset blood flow velocity; and The optimization calculation is performed with the goal of minimizing the error between the ideal speckle contrast value and the test speckle contrast value to obtain the parameters of the diffusion imaging system.

5. The method according to claim 1, characterized in that, The step of determining the speckle contrast value of each of the multiple speckle images includes: Based on the light intensity values ​​of each pixel in the speckle image, determine the standard deviation of the intensity distribution and the spatial average value of the speckle intensity in the speckle image; and Based on the standard deviation of the intensity distribution and the spatial average value of the speckle intensity in the speckle image, the speckle contrast value of the speckle image is obtained.

6. The method according to claim 1, characterized in that, The method further includes: The speckle image is preprocessed to obtain a preprocessed speckle image; The preprocessing operations performed on the speckle image include at least the following: Segmentation and identification of diffuse speckle regions, background correction, intensity distribution correction, and noise correction; The step of fitting the blood flow velocity at the current sampling time based on multiple speckle images includes: Based on multiple preprocessed speckle images, the blood flow velocity at the current sampling time is obtained by fitting.

7. The method according to claim 1, characterized in that, The blood pressure detection based on the blood flow velocity sequence, to obtain the blood pressure detection result, includes: Based on the pulse cycle, the blood flow velocity sequence is divided into multiple first sub-sequences; Based on the row dimension of the first subsequence, the first subsequence is processed using a multi-head attention mechanism to obtain the first feature; Based on the column dimension of the first subsequence, a multi-head attention mechanism is used to process the first subsequence to obtain the second feature; The first feature and the second feature are concatenated to obtain the third feature; Multiple third features are respectively subjected to feature mapping to obtain multiple second sub-sequences; The blood pressure sequence is obtained by splicing together multiple second sub-sequences; and The systolic and diastolic blood pressures are calculated based on the blood pressure sequence to obtain the blood pressure test results.

8. A blood pressure detection device, characterized in that, The device includes: The sampling module is used to irradiate the biological tissue under test with multiple laser beams at each of the multiple sampling times to acquire multiple speckle images at the current sampling time, wherein the modulation parameters of each of the multiple laser beams are different; The first processing module is used to fit the blood flow velocity at the current sampling time based on multiple speckle images; The second processing module is used to obtain a blood flow velocity sequence based on the blood flow velocities at each of the multiple sampling times; and The detection module is used to detect blood pressure based on the blood flow velocity sequence and obtain the blood pressure detection result; Specifically, the first processing module is used for: Based on the multiple speckle images, determine the speckle contrast value of each of the multiple speckle images; Based on the multiple speckle contrast ratio values ​​and the modulation parameters of the multiple laser beams, multiple speckle contrast ratio change rates are obtained; Based on the multiple speckle contrast ratio change rates, the standard deviation and mean of the speckle contrast ratio change rates were calculated. Based on multiple speckle contrast ratio changes, the standard deviation of the speckle contrast ratio changes, and the mean of the speckle contrast ratio changes, multiple candidate blood flow velocities are obtained; and The minimum value is selected from multiple candidate blood flow velocities to obtain the blood flow velocity at the current sampling time.

Images